http://www.lcad.inf.ufes.br/wiki/api.php?action=feedcontributions&user=Raphael+Carneiro&feedformat=atomLCAD - Contribuições do(a) usuário(a) [pt-br]2024-03-29T10:39:39ZContribuições do(a) usuário(a)MediaWiki 1.30.0http://www.lcad.inf.ufes.br/wiki/index.php?title=Instala%C3%A7%C3%A3o_Carmen_para_Ubuntu_14.04&diff=81415Instalação Carmen para Ubuntu 14.042018-06-28T20:43:36Z<p>Raphael Carneiro: Novo roteiro Ubuntu 16</p>
<hr />
<div>[[category:Carmen]]<br />
<br />
'''Atenção: Os novos roteiros de instalação do Carmen encontram-se nas seguintes páginas do GitHub:'''<br />
<br />
Ubuntu 14: https://github.com/LCAD-UFES/carmen_lcad/wiki/Installing-Carmen-LCAD-on-Ubuntu-14<br />
<br />
Ubuntu 16: https://github.com/LCAD-UFES/carmen_lcad/wiki/Installing-Carmen-LCAD-on-Ubuntu-16<br />
<br />
O roteiro de instalação abaixo está mantido apenas como histórico.<br />
<br />
'''(OBSOLETO) ROTEIRO DE INSTALAÇÃO DO CARMEN NO UBUNTU 14.04.5'''<br />
<br />
Essa instalação é completa, mas é necessário testar todos os módulos (Se for usar CUDA, a versão atual utilizada é a 7.5). <br />
<br />
= Preparação para a instalação do Carmen = <br />
<br />
Atualizar o apt:<br />
sudo apt-get update<br />
<br />
Instalar o git, gimp, meld e vim:<br />
sudo apt-get install gimp meld vim git<br />
<br />
Baixar o Carmen pelo git (faça o download enquanto segue os próximos passos):<br />
git clone https://github.com/LCAD-UFES/carmen_lcad.git<br />
<br />
Baixe a MAE via git:<br />
git clone https://github.com/LCAD-UFES/MAE.git<br />
<br />
Instalar os pacotes para o carmem no 14.04<br />
<br />
sudo apt-get install swig \<br />
libgtk2.0-dev \<br />
qt-sdk \<br />
libimlib2 libimlib2-dev \<br />
imagemagick libmagick++-dev \<br />
libwrap0 libwrap0-dev tcpd \<br />
libncurses5 libncurses5-dev \<br />
libgsl0-dev libgsl0ldbl \<br />
libdc1394-22 libdc1394-22-dev libdc1394-utils \<br />
cmake \<br />
libgtkglext1 libgtkglext1-dev \<br />
libgtkglextmm-x11-1.2-0 libgtkglextmm-x11-1.2-dev \<br />
libglade2-0 libglade2-dev \<br />
freeglut3 freeglut3-dev \<br />
libcurl3 libcurl3-nss libcurl4-nss-dev \<br />
libglew1.5 libglew1.5-dev libglewmx1.5 libglewmx1.5-dev libglew-dev \<br />
libkml0 libkml-dev \<br />
liburiparser1 liburiparser-dev \<br />
libusb-1.0-0 libusb-1.0-0-dev libusb-dev \<br />
libxi-dev libxi6 \<br />
libxmu-dev libxmu6 \<br />
build-essential libforms-dev \<br />
byacc \<br />
flex \<br />
doxygen \<br />
libespeak-dev libfftw3-dev<br />
<br />
<br />
caso de erro em libcheese-gtk23 instale os pacotes abaixo antes dos anteriores (Solucão nao confirmada):<br />
sudo apt-get install libglew-dev libcheese7 libcheese-gtk23 libclutter-gst-2.0-0 libcogl15 libclutter-gtk-1.0-0 libclutter-1.0-0<br />
<br />
Instalar o Java:<br />
<br />
sudo add-apt-repository ppa:webupd8team/java<br />
sudo apt-get update<br />
sudo apt-get install oracle-java8-installer<br />
update-alternatives --display java<br />
<br />
Edite o arquivo /etc/environment:<br />
sudo gedit /etc/environment<br />
<br />
Adicione no final do arquivo:<br />
JAVA_HOME=/usr/lib/jvm/java-8-oracle<br />
<br />
Instalar o eclipse:<br />
<br />
Baixe o eclipse de:<br />
https://www.eclipse.org/downloads/eclipse-packages/<br />
<br />
Descompacte o ecplise<br />
cd Downloads/<br />
sudo mv eclipse-...tar.gz /opt<br />
cd /opt/<br />
sudo tar -xvf eclipse-...tar.gz <br />
<br />
Crie um arquivo desktop e edite ele em /usr/share/applications:<br />
sudo gedit /usr/share/applications/eclipse.desktop<br />
<br />
Coloque o seguinte conteudo:<br />
[Desktop Entry]<br />
Name=Eclipse<br />
Type=Application<br />
Exec=/opt/eclipse/eclipse<br />
Terminal=false<br />
Icon=/opt/eclipse/icon.xpm<br />
Comment=Integrated Development Environment<br />
NoDisplay=false<br />
Categories=Development;IDE<br />
Name[en]=Eclipse<br />
<br />
Instale as deps da PCL:<br />
sudo apt-get install libeigen3-dev libboost-all-dev libflann-dev libvtk5-dev cmake-qt-gui<br />
<br />
Install OpenCV 3.1:<br />
<br />
Start installing the dependencies:<br />
sudo apt-get install build-essential cmake git libgtk2.0-dev pkg-config libavcodec-dev libavformat-dev libswscale-dev \<br />
python-dev python-numpy libtbb2 libtbb-dev libjpeg-dev libpng-dev libtiff-dev libjasper-dev libdc1394-22-dev<br />
<br />
Download and select the correct version:<br />
<br />
sudo mkdir /opt/opencv3.1.0/<br />
cd /opt/opencv3.1.0/<br />
sudo git clone https://github.com/Itseez/opencv.git<br />
sudo git clone https://github.com/Itseez/opencv_contrib.git<br />
cd opencv<br />
sudo git checkout 3.1.0<br />
cd /opt/opencv3.1.0/opencv_contrib<br />
sudo git checkout 3.1.0<br />
cd /opt/opencv3.1.0/opencv<br />
<br />
Build it:<br />
<br />
sudo mkdir build<br />
cd build<br />
sudo cmake -D -DWITH_IPP=ON -D WITH_CUDA=OFF -D CMAKE_BUILD_TYPE=RELEASE -D CMAKE_INSTALL_PREFIX=/usr/local \<br />
-D OPENCV_EXTRA_MODULES_PATH=/opt/opencv3.1.0/opencv_contrib/modules /opt/opencv3.1.0/opencv/ ..<br />
sudo make -j8<br />
sudo make install<br />
<br />
It is common to have problems with -lippicv using this version of OpenCV. To fix it:<br />
Edit `/usr/local/lib/pkgconfig/opencv.pc`<br />
Add `libdir3rd=${exec_prefix}/share/OpenCV/3rdparty/lib` after libdir<br />
Add `-L${libdir3rd}` at Libs <br />
<br />
Baixar os arquivos:<br />
sudo su<br />
cd /usr/local/<br />
wget https://storage.googleapis.com/google-code-archive-downloads/v2/code.google.com/bullet/bullet-2.78-r2387.tgz<br />
wget http://downloads.sourceforge.net/project/fann/fann/2.2.0/FANN-2.2.0-Source.tar.gz<br />
wget http://www.kvaser.com/software/7330130980754/V5_3_0/linuxcan.tar.gz<br />
tar -xvf bullet-2.78-r2387.tgz<br />
tar -xvf linuxcan.tar.gz<br />
tar -xvf FANN-2.2.0-Source.tar.gz<br />
mv bullet-2.78 bullet<br />
cd bullet<br />
./configure<br />
make<br />
make install<br />
cd ..<br />
cd linuxcan<br />
make<br />
make install<br />
cd ..<br />
cd FANN-2.2.0-Source<br />
mkdir build<br />
cd build<br />
cmake ..<br />
make<br />
make install<br />
<br />
Edite o arquivo /etc/ld.so.conf.d/opencv.conf<br />
gedit /etc/ld.so.conf.d/opencv.conf<br />
<br />
Adicione ao final dele:<br />
/usr/local/lib<br />
<br />
Execute: <br />
ldconfig<br />
<br />
Edite o arquivo /etc/bash.bashrc:<br />
gedit /etc/bash.bashrc<br />
<br />
Adicione no final do arquivo:<br />
PKG_CONFIG_PATH=$PKG_CONFIG_PATH:/usr/local/lib/pkgconfig<br />
export PKG_CONFIG_PATH<br />
<br />
sair do rooot<br />
exit<br />
<br />
Coloque no .bashrc:<br />
#CARMEN<br />
export PKG_CONFIG_PATH=$PKG_CONFIG_PATH:/usr/local/lib/pkgconfig<br />
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/lib:/usr/lib/x86_64-linux-gnu:/usr/lib/i386-linux-gnu/:/usr/lib/libkml<br />
export CARMEN_HOME=~/carmen_lcad<br />
#OpenJaus<br />
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$CARMEN_HOME/sharedlib/OpenJAUS/libopenJaus/lib:$CARMEN_HOME/sharedlib/OpenJAUS/libjaus/lib:$CARMEN_HOME/sharedlib/OpenJAUS/ojTorc/lib:$CARMEN_HOME/sharedlib/OpenJAUS/ojIARASim/lib<br />
<br />
<br />
#MAE<br />
export MAEHOME=~/MAE<br />
export PATH=$PATH:$MAEHOME/bin<br />
<br />
# Darknet<br />
export DARKNET_HOME=$CARMEN_HOME/sharedlib/darknet<br />
export LD_LIBRARY_PATH=$DARKNET_HOME/lib:$LD_LIBRARY_PATH<br />
<br />
Instale os pacotes imlib e flycapture:<br />
cd $CARMEN_HOME/ubuntu_packages/<br />
sudo dpkg -i imlib_1.9.15-20_amd64.deb <br />
sudo dpkg -i imlib-devel_1.9.15-20_amd64.deb<br />
tar -xvf flycapture2-2.5.3.4-amd64-pkg.tgz<br />
cd flycapture2-2.5.3.4-amd64/<br />
sudo apt-get install libglademm-2.4-1c2a<br />
sudo apt-get install libglademm-2.4-dev<br />
sudo apt-get install libgtkmm-2.4-dev<br />
sudo sh install_flycapture.sh<br />
<br />
Faça os links:<br />
sudo ln -s /usr/lib64/libgdk_imlib.so.1.9.15 /usr/lib64/libgdk_imlib.a<br />
sudo ln -s /usr/src/linux-headers-3.8.0-30/ /usr/src/linux<br />
<br />
Instale a PCL:<br />
sudo add-apt-repository ppa:v-launchpad-jochen-sprickerhof-de/pcl<br />
sudo apt-get update<br />
sudo apt-get install libpcl-all<br />
<br />
Instale a câmera Kinect:<br />
sudo su<br />
cd /usr/local<br />
wget http://sourceforge.net/projects/libusb/files/libusb-1.0/libusb-1.0.19/libusb-1.0.19.tar.bz2<br />
tar xvf libusb-1.0.19.tar.bz2<br />
cd libusb-1.0.19<br />
./configure<br />
make<br />
make install<br />
<br />
se der erro na instalacao acima tente instalar a udev-dev antes:<br />
sudo apt-get install libudev-dev<br />
<br />
mkdir /usr/local/tplib<br />
cd /usr/local/tplib<br />
git clone git://github.com/OpenKinect/libfreenect.git<br />
cd libfreenect<br />
mkdir build<br />
cd build<br />
cmake ..<br />
cp src/libfreenect.pc /usr/local/tplib/<br />
make<br />
cp ../src/libfreenect.pc.in src/libfreenect.pc <br />
cp ../fakenect/fakenect.sh.in fakenect/fakenect.sh<br />
make install<br />
ldconfig /usr/local/lib64/<br />
exit<br />
<br />
Execute:<br />
glview<br />
<br />
Caso dê erro, tente:<br />
freenect-glview<br />
<br />
Se der erro execute:<br />
sudo ldconfig /usr/local/lib64/<br />
<br />
Instalação da biblioteca G2O 14.04:<br />
sudo apt-get install cmake libsuitesparse-dev libqt4-dev qt4-qmake<br />
cd /usr/local/<br />
sudo svn co https://svn.openslam.org/data/svn/g2o<br />
cd /usr/local/g2o/trunk/build/<br />
sudo cmake ../ -DBUILD_CSPARSE=ON -DG2O_BUILD_DEPRECATED_TYPES=ON -DG2O_BUILD_LINKED_APPS=ON<br />
sudo make<br />
sudo make install<br />
<br />
----<br />
<blockquote><br />
'''ATENCAO: Caso esteja usando o UBUNTU 14.04.3 é necessario instalar a zlib:'''<br />
<pre><br />
Para verificar sua versão, veja no campo Description, na saída do comando abaixo:<br />
lsb_release -a<br />
Caso seja o 14.04.3 faca: <br />
cd $CARMEN_HOME/ubuntu_packages<br />
sudo dpkg -i zlib1g_1.2.3.4.dfsg-3ubuntu4_amd64.deb <br />
sudo dpkg -i zlib1g-dev_1.2.3.4.dfsg-3ubuntu4_amd64.deb<br />
</pre><br />
</blockquote><br />
----<br />
<br />
Faça o link da boost:<br />
sudo ln -s /usr/lib/x86_64-linux-gnu/libboost_thread.so /usr/lib/x86_64-linux-gnu/libboost_thread-mt.so<br />
<br />
<br />
Instale as bibliotecas da MAE:<br />
sudo apt-get install make g++ freeglut3-dev byacc libforms-dev libtiff4-dev libXi-dev libXmu-dev doxygen tcsh flex libdc1394-22-dev<br />
<br />
# Compilar a MAE:<br />
## Pré-requisito: as variáveis de ambiente MAEHOME e PATH devem estar ajustadas;<br />
## Entrar no diretório da MAE: "cd $MAEHOME";<br />
## Compilar a MAE: "make".<br />
## Verificar se a biblioteca da MAE libnet_conn.a foi gerado em MAEHOME/lib;<br />
## Verificar se o compilador da MAE netcomp foi gerado em MAEHOME/bin.<br />
<br />
Mais informações sobre a MAE: http://www.lcad.inf.ufes.br/wiki/index.php/M%C3%A1quina_Associadora_de_Eventos_-_MAE#Compilando_a_MAE<br />
<br />
Instalação da dlib:<br />
cd /usr/local<br />
sudo su<br />
git clone https://github.com/davisking/dlib.git<br />
cd dlib/<br />
mkdir build<br />
cd build/<br />
cmake .. {Vai reclamar de coisas CUDA. Mas pode compilar sem suporte a CUDA}<br />
make<br />
make install<br />
<br />
Instalação da libwnn:<br />
cd /usr/local<br />
git clone http://github.com/filipemtz/libwnn<br />
cd libwnn<br />
mkdir build<br />
cd build<br />
cmake ..<br />
make -j 4<br />
sudo make install<br />
<br />
Atenção: em caso de problema com o opencv, faça:<br />
cd build<br />
rm -rf *<br />
cmake -DOpenCV_DIR=/usr/local/opencv-2.4.9/build/ ..<br />
make -j 4<br />
sudo make install<br />
<br />
----<br />
Se for usar a ZED stereo Câmera:<br />
Faça o download do SDK ZED 1.0<br />
https://www.stereolabs.com/developers/release/1.0.0/<br />
<br />
Instale a ZED (Lembre-se essa versão usa CUDA 7.5! e Opencv3.1)<br />
sudo chmod +x ZED....<br />
./ZED....<br />
Se houver erro com libodbc.so.1: cannot open shared object file: No such file or directory<br />
sudo apt-get install libodbc1 <br />
---- <br />
<br />
Feche todos os terminais e faça:<br />
cd $CARMEN_HOME/src<br />
./configure --nojava --nocuda --nozlib<br />
Should the C++ tools be installed for CARMEN: [Y/n] Y<br />
Should Python Bindings be installed: [y/N] N<br />
Searching for Python2.4... Should the old laser server be used instead of the new one: [y/N] N<br />
Install path [/usr/local/]: <br />
Robot numbers [*]: 1,2<br />
<br />
Antes de compilar o CARMEN, precisamos que o módulo tracker seja compilado separadamente para que o navigator_spline funcione:<br />
cd $CARMEN_HOME/src/tracker<br />
make<br />
<br />
Vai dar um erro de compilação, mas está tudo ok.<br />
<br />
Para compilar o carmen rode:<br />
cd $CARMEN_HOME/src<br />
make<br />
<br />
Caso dê erro por causa da libusb.h vá no arquivo:<br />
sudo vim /usr/local/include/libfreenect.hpp<br />
E altere #include <libusb.h> para<br />
#include <libusb-1.0/libusb.h><br />
<br />
Caso dê erro na compilacão no global por causa do z_stream tente<br />
cd $CARMEN_HOME/src<br />
make clean<br />
./configure --nojava --nocuda<br />
Should the C++ tools be installed for CARMEN: [Y/n] Y<br />
Should Python Bindings be installed: [y/N] N<br />
Searching for Python2.4... Should the old laser server be used instead of the new one: [y/N] N<br />
Install path [/usr/local/]: <br />
Robot numbers [*]: 1,2<br />
make<br />
<br />
= Ajustes para a IARA = <br />
'''(seções abaixo apenas para serem feitas na IARA)'''<br />
<br />
Para configurar o OpenJAUS siga o tutorial em : <br />
<br />
$CARMEN_HOME/sharedlib/OpenJAUS/README_ALBERTO.txt<br />
<br />
Para que o GPS e o XSENS sejam configurados automaticamente ao serem conectados às portas USB, copie o seguinte arquivo do diretório data do Carmen para sua máquina:<br />
<br />
cd $CARMEN_HOME/data<br />
sudo cp 99-usb-serial.rules /etc/udev/rules.d/<br />
<br />
== Ajustes na rede para o GPS Trimble ==<br />
<br />
Para conectar o novo GPS Trimble é necessário uma conexão com a Internet dentro da IARA. Optamos por usar um iPhone com conexão 3G.<br />
<br />
Para o iPhone funcionar no Ubuntu 12.04 é necessário um tanto de coisas... Perdemos o histórico mas dá para achar na Internet (Google iPhone 4S ubuntu 12.04 mount). Precisa instalar uns pacotes (apt-get install ...). Se você tiver sucesso, vai ser possível usar o iPhone como Personal Hotspot, ou seja, usar a Internet de dentro da IARA.<br />
<br />
Feito isso, é necessário criar um Gateway da máquina que tem acesso a Internet (car01) para uma subrede da IARA (192.168.0.0 - a subrede de Carro Network). Para isso (ver página de referência em https://help.ubuntu.com/community/Internet/ConnectionSharing (Gateway set up)), considerando o iPhone em eth2 e a subrede da IARA em eth1:<br />
sudo iptables -A FORWARD -o eth2 -i eth1 -s 192.168.0.0/24 -m conntrack --ctstate NEW -j ACCEPT<br />
sudo iptables -A FORWARD -m conntrack --ctstate ESTABLISHED,RELATED -j ACCEPT<br />
sudo iptables -t nat -F POSTROUTING<br />
sudo iptables -t nat -A POSTROUTING -o eth2 -j MASQUERADE<br />
sudo iptables-save | sudo tee /etc/iptables.sav<br />
<br />
Os comandos acima criam um NAT do iPhone para a subrede da IARA. Em seguida, é necessário editar o /etc/rc.local e adicionar a linha abaixo antes de "exit 0":<br />
iptables-restore < /etc/iptables.sav<br />
<br />
É necessário ainda:<br />
sudo sh -c "echo 1 > /proc/sys/net/ipv4/ip_forward"<br />
<br />
Para tornar isso permanente, inclua as linhas abaixo em /etc/sysctl.conf:<br />
net.ipv4.ip_forward=1<br />
net.ipv4.conf.default.forwarding=1<br />
net.ipv4.conf.all.forwarding=1<br />
<br />
No Network Manager, tem que setar "Use this connection only for resources on its network" (Network Manager->IPv4 Settings->Routes) em todas as redes cabeadas exceto a do iPhone.<br />
<br />
Pronto!<br />
<br />
== Ajustes para o Raspberry do volante ==<br />
<br />
'''Prevenir que entre em modo de espera, proteção de tela ou desabilite o monitor'''<br />
<br />
Fonte: https://raspberrypi.stackexchange.com/questions/752/how-do-i-prevent-the-screen-from-going-blank<br />
<br />
Testado no Raspbian jessey<br />
<br />
Only if the files don't exist install (It was not necessary):<br />
<br />
apt-get install x11-xserver-utils<br />
<br />
Edit the files:<br />
<br />
/etc/xdg/lxsession/LXDE/autostart<br />
/etc/xdg/lxsession/LXDE-pi/autostart<br />
~/.config/lxprofile/LXDE-pi/autostart<br />
<br />
Append these lines:<br />
<br />
@xset s noblank<br />
@xset s off<br />
@xset -dpms<br />
<br />
Possibly also comment out the line that says @xscreensaver -no-splash, so the complete file should look something like this:<br />
<br />
@lxpanel --profile LXDE<br />
@pcmanfm --desktop --profile LXDE<br />
# @xscreensaver -no-splash<br />
<br />
@xset s noblank<br />
@xset s off<br />
@xset -dpms<br />
<br />
Maybe also exist the line @point-rpi, DONT DELETE and DONT ADD in the others files!<br />
<br />
Also edit /etc/kbd/config and make sure these values are set as follows (however I believe this is only for when the lightweight desktop (LXDE) is not running (i.e. the pi is still in text / terminal mode):<br />
<br />
BLANK_TIME=0<br />
BLANK_DPMS=off<br />
POWERDOWN_TIME=0<br />
<br />
I believe that the /etc/xdg/lxsession/LXDE/autostart may be the sort of system-wide version of ~/.xinitrc but someone else probably knows the nuances better.</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=Nvidia-352.41-rt.patch&diff=81381Nvidia-352.41-rt.patch2017-11-30T03:20:28Z<p>Raphael Carneiro: </p>
<hr />
<div>Copy the following lines to a blank text file and name it: '''nvidia-352.41-rt.patch'''<br />
<br />
41a42,43<br />
> #define CONFIG_PREEMPT_RT_FULL 1<br />
> <br />
340,343c342,352<br />
< #if defined(CONFIG_PREEMPT_RT) || defined(CONFIG_PREEMPT_RT_FULL)<br />
< #define NV_CONFIG_PREEMPT_RT 1<br />
< #endif<br />
< <br />
---<br />
> #if defined(CONFIG_PREEMPT_RT_FULL)<br />
> typedef raw_spinlock_t nv_spinlock_t;<br />
> #define NV_SPIN_LOCK_INIT(lock) raw_spin_lock_init(lock)<br />
> #define NV_SPIN_LOCK_IRQ(lock) raw_spin_lock_irq(lock)<br />
> #define NV_SPIN_UNLOCK_IRQ(lock) raw_spin_unlock_irq(lock)<br />
> #define NV_SPIN_LOCK_IRQSAVE(lock,flags) raw_spin_lock_irqsave(lock,flags)<br />
> #define NV_SPIN_UNLOCK_IRQRESTORE(lock,flags) raw_spin_unlock_irqrestore(lock,flags)<br />
> #define NV_SPIN_LOCK(lock) raw_spin_lock(lock)<br />
> #define NV_SPIN_UNLOCK(lock) raw_spin_unlock(lock)<br />
> #define NV_SPIN_UNLOCK_WAIT(lock) raw_spin_unlock_wait(lock)<br />
> #else<br />
352a362<br />
> #endif<br />
905c915<br />
< #if defined(NV_CONFIG_PREEMPT_RT)<br />
---<br />
> #if defined(CONFIG_PREEMPT_RT_FULL)</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=Criando_Kernel_RT_Ubuntu_14.04&diff=81380Criando Kernel RT Ubuntu 14.042017-11-30T03:18:22Z<p>Raphael Carneiro: </p>
<hr />
<div>Todas as informacoes aqui foram retiradas de: http://linuxaudioproduction.blogspot.com.br/2015/09/patching-compiling-and-installing.html<br />
<br />
'''Testado com o Ubuntu 14.04.1'''<br />
<br />
This guide is a condensed reference on how to patch, compile and install the 4.1.5. kernel.<br />
<br />
Download kernel and patch:<br />
https://www.kernel.org/pub/linux/kernel/v4.x/linux-4.1.5.tar.xz<br />
https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patch-4.1.5-rt5.patch.xz<br />
<br />
use sudo mode:<br />
sudo su<br />
Extract kernel archive and patch file:<br />
tar -Jxf linux-4.1.5.tar.xz<br />
tar -Jxf patch-4.1.5-rt5.patch.xz<br />
Put the patch file one directory level above the kernel source.<br />
cp linux-4.1.5 /usr/src<br />
cp patch-4.1.5-rt5.patch /usr/src<br />
<br />
Change directory to the newly created kernel source directory<br />
cd /usr/src/linux-4.1.5<br />
<br />
Apply the patch to the kernel.<br />
<br />
less ../patch-4.1.5-rt5.patch | patch -p1<br />
<br />
Get the latest configuration of new kernel<br />
make oldconfig<br />
<br />
The make will ask some questions, answer with the default option, '''EXCEPT''' the options about real time and debug mode. When asked for:<br />
<br />
* "Preemption Model"<br />
** Choose "5. Fully Preemptible Kernel (RT) (PREEMPT_RT_FULL) (NEW)"<br />
<br />
* "Debug preemptible kernel (DEBUG_PREEMPT)"<br />
** Choose "n"<br />
<br />
Open up the kernel configuration tool:<br />
make menuconfig<br />
<br />
To configure the IP_TABLES NAT support:<br />
<pre><br />
On the Kernel Configuration go to:<br />
Networking support > Networking Options > Network packet filtering framework (Netfilter) > IP: Netfilter Configuration<br />
Find the options listed below and mark with <M><br />
<M>iptables NAT support'' <br />
Other options will apear:<br />
<M> MASQUERADE target support<br />
<M> NETMAP tarrget support<br />
<M> REDIRECT target support<br />
save and exit<br />
</pre><br />
Build and install the kernel:<br />
<br />
make<br />
make modules<br />
make INSTALL_MOD_STRIP=1 modules_install<br />
make install<br />
<br />
Update the bootloader (probably grub) if not done automatically.<br />
<br />
restart the computer.<br />
<br />
<br />
Check if the iptables_nat is working:<br />
<br />
iptables -t nat -L<br />
<pre><br />
If shows the following error:<br />
iptables v1.4.21: can't initialize iptables table `nat': Table does not exist (do you need to insmod?)<br />
Perhaps iptables or your kernel needs to be upgraded.<br />
Back to the step of menu configuration tool:make menuconfig and check the iptables options. If is ok, try the solution:<br />
cd /usr/src/linux-4.1.5<br />
sudo make menuconfig<br />
Go to menu Networking Support > Networking Options > Network packet filtering framework (Netfilter)<br />
and press spacebar to mark with star<br />
Entry in this menu and go to Core Netfilter Configuration. Fill all options with M EXCEPT the options <br />
below that should be filled with star :<br />
"Netfilter connection tracking support", <br />
"Connection tracking flow accounting", <br />
"Connection mark tracking support", <br />
"Connection tracking security mark support", <br />
"Connection tracking events" and <br />
"Netfilter Xtables support (required for ip_tables)"<br />
And the option "Enable obsolete /proc/net/ipt_recent" doesn't should be filled.<br />
Save changes and exit. <br />
BACK TO THE '''Build and install the kernel''' STEP in this tutorial.<br />
</pre><br />
<br />
If you are using RAID and partition isn't recognized, install the package and reboot:<br />
sudo apt-get install dmraid<br />
<br />
<br />
=== Install Nvidia Graphics Driver (352.41) for the Realtime Kernel ===<br />
<br />
<pre>After installing the realtime kernel as described above, Nvidia graphics card owners will probably want<br />
to install the official graphics driver from Nvidia (if you're using Ardour you're going to need this driver <br />
to get smooth GUI performance). Unfortunately, the installer will just complain about the realtime kernel and<br />
quit. With some tweaks it is possible to install it nevertheless. This article describes the installation of the<br />
Nvidia driver version 352.41. For different versions you will need a different patch file or perform the patch manually.<br />
<br />
Warning: I found that the driver sometimes locks itself up on my system, leading to a frozen image.<br />
If 100% stability is a requirement for you, you should not install it. During the installation you will <br />
need to stop your desktop session so consider printing this guide or open it up on a different device.<br />
</pre><br />
<br />
Go ahead if you're ready:<br />
<br />
Download the driver package from your local nvidia page:<br />
http://www.nvidia.com/content/global/global.php<br />
Make a patch file as follows: <br />
[[nvidia-352.41-rt.patch]]<br />
Open a console and change directory to the folder where you downloaded the driver package to.<br />
<br />
Make the driver package executable:<br />
chmod +x NVIDIA-Linux-x86_64-352.41.run<br />
<br />
Extract the driver source:<br />
./NVIDIA-Linux-x86_64-352.41.run --extract-only<br />
<br />
Apply the patch file:<br />
less nvidia-352.41-rt.patch | patch NVIDIA-Linux-x86_64-352.41/kernel/nv-linux.h<br />
<br />
Press Ctrl+Alt+F1 to open up a terminal session and login as root<br />
Stop your desktop manager. If you're using XFCE (UbuntuStudio) this is LightDM. Beware that this kills all programs running in the GUI session, including the browser you might be reading this article in:<br />
/etc/init.d/lightdm stop<br />
<br />
Set this environment variable to disable the a check for the realtime kernel patch in the installer:<br />
export IGNORE_PREEMPT_RT_PRESENCE=1<br />
<br />
Change directory to the folder where the nvidia driver source was extracted to. <br />
Run the installer just like you normally would:<br />
./nvidia-installer<br />
Restart your desktop manager:<br />
/etc/init.d/lightdm start<br />
<br />
Check if the driver was install correctly, deve mostrar as informações da placa de video<br />
$ nvidia-settings<br />
<br />
Your system should now use the freshly installed driver!<br />
<br />
<pre>If you want to adapt this process for a different driver version, you will need to take a look what the patch actually<br />
does and make those changes to the nv-linux.h file manually. If you do so, it would be very nice of you to create a new patch <br />
file and post it here in the comments. Of course, there's no guarantee that this will work for newer driver versions.<br />
</pre><br />
<br />
Para instalar o cuda siga as instruções do Getting_Started: http://developer.download.nvidia.com/compute/cuda/6_5/rel/docs/CUDA_Getting_Started_Linux.pdf<br />
<br />
Use o instador .run<br />
<br />
Na instalação vai aparecer algumas perguntas, Siga essas respostas.<br />
<br />
Install NVIDIA Accelerated Graphics Driver for Linux-x86_64 340.29? ((y)es/(n)o/(q)uit): n<br />
Install the CUDA 6.5 Toolkit? ((y)es/(n)o/(q)uit): y<br />
Enter Toolkit Location [ default is /usr/local/cuda-6.5 ]: <br />
Do you want to install a symbolic link at /usr/local/cuda? ((y)es/(n)o/(q)uit): y<br />
Install the CUDA 6.5 Samples? ((y)es/(n)o/(q)uit): y<br />
Enter CUDA Samples Location [ default is /home/car01 ]: <br />
<br />
References:<br />
http://linuxaudioproduction.blogspot.com.br/2015/09/how-to-patching-and-compiling-nvidia.html<br />
<br />
https://devtalk.nvidia.com/default/topic/572468/nvidia-325-15-linux-rt-old-amp-amp-new-nvidia-rt-patch-methods-questions-about-nvidia-installer/<br />
<br />
<br />
== Possíveis problemas ==<br />
<br />
Error NVRM/VGA com o driver da nvidia:<br />
<br />
use o comando:<br />
sudo dmesg | tail<br />
Se ocorrer os seguintes erros:<br />
<pre><br />
[ 15.458823] NVRM: Your system is not currently configured to drive a VGA console<br />
[ 15.458830] NVRM: on the primary VGA device. The NVIDIA Linux graphics driver<br />
[ 15.458834] NVRM: requires the use of a text-mode VGA console. Use of other console<br />
[ 15.458838] NVRM: drivers including, but not limited to, vesafb, may result in<br />
[ 15.458841] NVRM: corruption and stability problems, and is not supported.<br />
</pre><br />
<br />
Adicione a seguinte linha no arquivo /boot/grub/grub.cfg ao fim da linha do kernel<br />
<br />
video=vesa:off vga=normal<br />
<br />
e.g.<br />
<br />
menuentry 'Ubuntu' --class ubuntu...<br />
<br />
(...)<br />
<br />
linux /boot/vmlinuz-4.1.5-rt5 root=UUID=f5a99a1a-15a4-4a83-a3fb-2adbee7f8311 ro quiet splash $vt_handoff '''video=vesa:off vga=normal'''<br />
<br />
(..)<br />
<br />
verificar nesse link<br />
https://bbs.archlinux.org/viewtopic.php?id=143569<br />
<br />
Erro na resolução do monitor.<br />
Entre na configurações da nvidia como super usuário<br />
<br />
$ sudo nvidia-settings <br />
<br />
Em X Server Display Configuration, restaure a configuração do X server clicando no botão de "Reset". Após isso reinicie a maquina.<br />
<br />
Feito isso, volte na mesma aba da nvidia-settings. Verifique no campo "Selection" se o aparece o seu monitor. Depois mude a resolução do monitor para uma configuração maior e salve a configuração em "Save to X Configuration File".</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=Criando_Kernel_RT_Ubuntu_14.04&diff=81379Criando Kernel RT Ubuntu 14.042017-11-30T03:15:23Z<p>Raphael Carneiro: </p>
<hr />
<div>Todas as informacoes aqui foram retiradas de: http://linuxaudioproduction.blogspot.com.br/2015/09/patching-compiling-and-installing.html<br />
<br />
'''Testado com o Ubuntu 14.04.1'''<br />
<br />
This guide is a condensed reference on how to patch, compile and install the 4.1.5. kernel.<br />
<br />
Download kernel and patch:<br />
https://www.kernel.org/pub/linux/kernel/v4.x/linux-4.1.5.tar.xz<br />
https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patch-4.1.5-rt5.patch.xz<br />
<br />
use sudo mode:<br />
sudo su<br />
Extract kernel archive and patch file:<br />
tar -Jxf linux-4.1.5.tar.xz<br />
tar -Jxf patch-4.1.5-rt5.patch.xz<br />
Put the patch file one directory level above the kernel source.<br />
cp linux-4.1.5 /usr/src<br />
cp patch-4.1.5-rt5.patch /usr/src<br />
<br />
Change directory to the newly created kernel source directory<br />
cd /usr/src/linux-4.1.5<br />
<br />
Apply the patch to the kernel.<br />
<br />
less ../patch-4.1.5-rt5.patch | patch -p1<br />
<br />
Get the latest configuration of new kernel<br />
make oldconfig<br />
<br />
The make will ask some questions, answer with the default option, '''EXCEPT''' the options about real time and debug mode. When asked for:<br />
<br />
* "Preemption Model"<br />
** Choose "5. Fully Preemptible Kernel (RT) (PREEMPT_RT_FULL) (NEW)"<br />
<br />
* "Debug preemptible kernel (DEBUG_PREEMPT)"<br />
** Choose "n"<br />
<br />
Open up the kernel configuration tool:<br />
make menuconfig<br />
<br />
To configure the IP_TABLES NAT support:<br />
<pre><br />
On the Kernel Configuration go to:<br />
Networking support > Networking Options > Network packet filtering framework (Netfilter) > IP: Netfilter Configuration<br />
Find the options listed below and mark with <M><br />
<M>iptables NAT support'' <br />
Other options will apear:<br />
<M> MASQUERADE target support<br />
<M> NETMAP tarrget support<br />
<M> REDIRECT target support<br />
save and exit<br />
</pre><br />
Build and install the kernel:<br />
<br />
make<br />
make modules<br />
make INSTALL_MOD_STRIP=1 modules_install<br />
make install<br />
<br />
Update the bootloader (probably grub) if not done automatically.<br />
<br />
restart the computer.<br />
<br />
<br />
Check if the iptables_nat is working:<br />
<br />
iptables -t nat -L<br />
<pre><br />
If shows the following error:<br />
iptables v1.4.21: can't initialize iptables table `nat': Table does not exist (do you need to insmod?)<br />
Perhaps iptables or your kernel needs to be upgraded.<br />
Back to the step of menu configuration tool:make menuconfig and check the iptables options. If is ok, try the solution:<br />
cd /usr/src/linux-4.1.5<br />
sudo make menuconfig<br />
Go to menu Networking Support > Networking Options > Network packet filtering framework (Netfilter)<br />
and press spacebar to mark with star<br />
Entry in this menu and go to Core Netfilter Configuration. Fill all options with M EXCEPT the options <br />
below that should be filled with star :<br />
"Netfilter connection tracking support", <br />
"Connection tracking flow accounting", <br />
"Connection mark tracking support", <br />
"Connection tracking security mark support", <br />
"Connection tracking events" and <br />
"Netfilter Xtables support (required for ip_tables)"<br />
And the option "Enable obsolete /proc/net/ipt_recent" doesn't should be filled.<br />
Save changes and exit. <br />
BACK TO THE '''Build and install the kernel''' STEP in this tutorial.<br />
</pre><br />
<br />
If you are using RAID and partition isn't recognized, install the package and reboot:<br />
sudo apt-get install dmraid<br />
<br />
<br />
=== Install Nvidia Graphics Driver (352.41) for the Realtime Kernel ===<br />
<br />
<pre>After installing the realtime kernel as described above, Nvidia graphics card owners will probably want<br />
to install the official graphics driver from Nvidia (if you're using Ardour you're going to need this driver <br />
to get smooth GUI performance). Unfortunately, the installer will just complain about the realtime kernel and<br />
quit. With some tweaks it is possible to install it nevertheless. This article describes the installation of the<br />
Nvidia driver version 352.41. For different versions you will need a different patch file or perform the patch manually.<br />
<br />
Warning: I found that the driver sometimes locks itself up on my system, leading to a frozen image.<br />
If 100% stability is a requirement for you, you should not install it. During the installation you will <br />
need to stop your desktop session so consider printing this guide or open it up on a different device.<br />
</pre><br />
<br />
Go ahead if you're ready:<br />
<br />
Download the driver package from your local nvidia page:<br />
http://www.nvidia.com/content/global/global.php<br />
Download the patch file to the same directory: <br />
[[nvidia-352.41-rt.patch]]<br />
Open a console and change directory to the folder where you downloaded the driver package to.<br />
<br />
Make the driver package executable:<br />
chmod +x NVIDIA-Linux-x86_64-352.41.run<br />
<br />
Extract the driver source:<br />
./NVIDIA-Linux-x86_64-352.41.run --extract-only<br />
<br />
Apply the patch file:<br />
less nvidia-352.41-rt.patch | patch NVIDIA-Linux-x86_64-352.41/kernel/nv-linux.h<br />
<br />
Press Ctrl+Alt+F1 to open up a terminal session and login as root<br />
Stop your desktop manager. If you're using XFCE (UbuntuStudio) this is LightDM. Beware that this kills all programs running in the GUI session, including the browser you might be reading this article in:<br />
/etc/init.d/lightdm stop<br />
<br />
Set this environment variable to disable the a check for the realtime kernel patch in the installer:<br />
export IGNORE_PREEMPT_RT_PRESENCE=1<br />
<br />
Change directory to the folder where the nvidia driver source was extracted to. <br />
Run the installer just like you normally would:<br />
./nvidia-installer<br />
Restart your desktop manager:<br />
/etc/init.d/lightdm start<br />
<br />
Check if the driver was install correctly, deve mostrar as informações da placa de video<br />
$ nvidia-settings<br />
<br />
Your system should now use the freshly installed driver!<br />
<br />
<pre>If you want to adapt this process for a different driver version, you will need to take a look what the patch actually<br />
does and make those changes to the nv-linux.h file manually. If you do so, it would be very nice of you to create a new patch <br />
file and post it here in the comments. Of course, there's no guarantee that this will work for newer driver versions.<br />
</pre><br />
<br />
Para instalar o cuda siga as instruções do Getting_Started: http://developer.download.nvidia.com/compute/cuda/6_5/rel/docs/CUDA_Getting_Started_Linux.pdf<br />
<br />
Use o instador .run<br />
<br />
Na instalação vai aparecer algumas perguntas, Siga essas respostas.<br />
<br />
Install NVIDIA Accelerated Graphics Driver for Linux-x86_64 340.29? ((y)es/(n)o/(q)uit): n<br />
Install the CUDA 6.5 Toolkit? ((y)es/(n)o/(q)uit): y<br />
Enter Toolkit Location [ default is /usr/local/cuda-6.5 ]: <br />
Do you want to install a symbolic link at /usr/local/cuda? ((y)es/(n)o/(q)uit): y<br />
Install the CUDA 6.5 Samples? ((y)es/(n)o/(q)uit): y<br />
Enter CUDA Samples Location [ default is /home/car01 ]: <br />
<br />
References:<br />
http://linuxaudioproduction.blogspot.com.br/2015/09/how-to-patching-and-compiling-nvidia.html<br />
<br />
https://devtalk.nvidia.com/default/topic/572468/nvidia-325-15-linux-rt-old-amp-amp-new-nvidia-rt-patch-methods-questions-about-nvidia-installer/<br />
<br />
<br />
== Possíveis problemas ==<br />
<br />
Error NVRM/VGA com o driver da nvidia:<br />
<br />
use o comando:<br />
sudo dmesg | tail<br />
Se ocorrer os seguintes erros:<br />
<pre><br />
[ 15.458823] NVRM: Your system is not currently configured to drive a VGA console<br />
[ 15.458830] NVRM: on the primary VGA device. The NVIDIA Linux graphics driver<br />
[ 15.458834] NVRM: requires the use of a text-mode VGA console. Use of other console<br />
[ 15.458838] NVRM: drivers including, but not limited to, vesafb, may result in<br />
[ 15.458841] NVRM: corruption and stability problems, and is not supported.<br />
</pre><br />
<br />
Adicione a seguinte linha no arquivo /boot/grub/grub.cfg ao fim da linha do kernel<br />
<br />
video=vesa:off vga=normal<br />
<br />
e.g.<br />
<br />
menuentry 'Ubuntu' --class ubuntu...<br />
<br />
(...)<br />
<br />
linux /boot/vmlinuz-4.1.5-rt5 root=UUID=f5a99a1a-15a4-4a83-a3fb-2adbee7f8311 ro quiet splash $vt_handoff '''video=vesa:off vga=normal'''<br />
<br />
(..)<br />
<br />
verificar nesse link<br />
https://bbs.archlinux.org/viewtopic.php?id=143569<br />
<br />
Erro na resolução do monitor.<br />
Entre na configurações da nvidia como super usuário<br />
<br />
$ sudo nvidia-settings <br />
<br />
Em X Server Display Configuration, restaure a configuração do X server clicando no botão de "Reset". Após isso reinicie a maquina.<br />
<br />
Feito isso, volte na mesma aba da nvidia-settings. Verifique no campo "Selection" se o aparece o seu monitor. Depois mude a resolução do monitor para uma configuração maior e salve a configuração em "Save to X Configuration File".</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=Nvidia-352.41-rt.patch&diff=81378Nvidia-352.41-rt.patch2017-11-30T03:12:58Z<p>Raphael Carneiro: Criou página com 'Copie as linhas abaixo e salve num arquivo de texto com nome: '''nvidia-352.41-rt.patch''' 41a42,43 > #define CONFIG_PREEMPT_RT_FULL 1 > 340,343c342,352 < #if defined(C...'</p>
<hr />
<div>Copie as linhas abaixo e salve num arquivo de texto com nome: '''nvidia-352.41-rt.patch'''<br />
<br />
41a42,43<br />
> #define CONFIG_PREEMPT_RT_FULL 1<br />
> <br />
340,343c342,352<br />
< #if defined(CONFIG_PREEMPT_RT) || defined(CONFIG_PREEMPT_RT_FULL)<br />
< #define NV_CONFIG_PREEMPT_RT 1<br />
< #endif<br />
< <br />
---<br />
> #if defined(CONFIG_PREEMPT_RT_FULL)<br />
> typedef raw_spinlock_t nv_spinlock_t;<br />
> #define NV_SPIN_LOCK_INIT(lock) raw_spin_lock_init(lock)<br />
> #define NV_SPIN_LOCK_IRQ(lock) raw_spin_lock_irq(lock)<br />
> #define NV_SPIN_UNLOCK_IRQ(lock) raw_spin_unlock_irq(lock)<br />
> #define NV_SPIN_LOCK_IRQSAVE(lock,flags) raw_spin_lock_irqsave(lock,flags)<br />
> #define NV_SPIN_UNLOCK_IRQRESTORE(lock,flags) raw_spin_unlock_irqrestore(lock,flags)<br />
> #define NV_SPIN_LOCK(lock) raw_spin_lock(lock)<br />
> #define NV_SPIN_UNLOCK(lock) raw_spin_unlock(lock)<br />
> #define NV_SPIN_UNLOCK_WAIT(lock) raw_spin_unlock_wait(lock)<br />
> #else<br />
352a362<br />
> #endif<br />
905c915<br />
< #if defined(NV_CONFIG_PREEMPT_RT)<br />
---<br />
> #if defined(CONFIG_PREEMPT_RT_FULL)</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=IARA&diff=81310IARA2017-08-03T19:27:03Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''Intelligent Autonomous Robotic Automobile - IARA'''</big></big></big><br />
<br />
__TOC__<br />
<br />
== '''Latest News!''' ==<br />
High-Performance Computing Lab (LCAD) at Federal University of Espirito Santo (UFES) developed an autonomous car called IARA: Intelligent Autonomous Robotic Automobile. On May 12th, 2017 it achieved a 74-kilometer autonomous journey from Vitoria to Guarapari, Brazil, travelling through city avenues and country highways, dealing with semaphores, bumps, tolls, bridges and all the traffic matters. Television and press media widely reported the fact.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:globo_iara.jpg|border|center|546px|TV Globo: Autonomous car traveled 74 km from Vitoria to Guarapari, ES]]<br />
| align="center" | [[imagem:iara_guarapari_plus_drone_view.jpg|border|center|394px|YouTube videos of IARA]]<br />
|-<br />
| align="center" | TV Globo: Autonomous car traveled 74 km from Vitoria to Guarapari, ES [http://g1.globo.com/jornal-nacional/videos/t/edicoes/v/carro-autonomo-viaja-74-quilometros-de-vitoria-a-guarapari-no-es/6009111/]<br />
| align="center" | YouTube videos of IARA [https://www.youtube.com/user/lcadufes]<br />
|}<br />
<br />
<br />
== '''About IARA''' ==<br />
A team of students and researchers of the Laboratório de Computação de Alto Desempenho (High-Performance Computing Laboratory) of Universidade Federal do Espírito Santo (Federal University of Espírito Santo), leaded by Professor Alberto F. De Souza, designed and built one of the first autonomous cars of Brazil. Christened IARA (Intelligent Autonomous Robotic Automobile), this autonomous car was able to run autonomously for tens of kilometers at speeds of up to of 30 Km/h in urban roads surrounding the main campus of UFES (See video at [http://youtu.be/LBM--2dAvyI?list=UUsQuY9t5ss3jwHBiRaEEFFg]).<br />
<br />
<br />
== '''IARA's Specifications''' ==<br />
IARA is an experimental robotic platform, based on a Ford Escape Hybrid (Fig. 5(a)). It has several high-end sensors, including: two Point Grey Bumblebee XB3 stereo cameras and two Point Grey Bumblebee 2 stereo cameras, one Light Detection and Ranging (LIDAR) Velodyne HDL 32-E, and one GPS-aided Attitude and Heading Reference System (AHRS/GPS) Xsens MTiG (Fig. 5(b)). To process the data coming from the sensors, the platform can hold up to four Dell Precision R5500 (2 Intel Xeon 2.13 GHZ, 12 GB RAM, 2 HDs SSD of 120GB on RAID0 and GPU cards Tesla C2050) (two installed in the configuration shown in Fig. 5(b)). We implemented many software modules for IARA that currently allows for its autonomous operation, such as modules for mapping, localization, behavior selection, path following, control, and motion planning (that is the focus of this paper). We also implemented a software module for autonomous vehicle simulation to help in the development and testing of all the other IARA’s modules (that was used to evaluate the performance of the motion planner presented in this paper). See video of IARA autonomous operation at [https://www.youtube.com/watch?v=zE7np6tgCHc&list=UUsQuY9t5ss3jwHBiRaEEFFg] and videos about other IARA’s software modules at [http://www.youtube.com/user/lcadufes].<br />
<br />
{| border=0<br />
| align="center" | [[imagem:iara.jpg|border|center|500px|Intelligent Autonomous Robotic Automobile - IARA]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|440px|Inside IARA's cockpit]]<br />
|-<br />
| align="center" | Intelligent Autonomous Robotic Automobile - IARA<br />
| align="center" | Inside IARA's cockpit<br />
|}<br />
<br />
<br />
== '''Our team''' ==<br />
Our team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. To learn more about our team [[Equipe|see '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|950px|LCAD/UFES team and IARA autonomous vehicle]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
|}</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=Arquivo:Iara_guarapari_plus_drone_view.jpg&diff=81309Arquivo:Iara guarapari plus drone view.jpg2017-08-03T19:22:04Z<p>Raphael Carneiro: Viagem da IARA a Guarapari e vista de um drone.</p>
<hr />
<div>Viagem da IARA a Guarapari e vista de um drone.</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=Arquivo:Iara_guarapari.jpg&diff=81308Arquivo:Iara guarapari.jpg2017-08-03T19:08:53Z<p>Raphael Carneiro: Viagem da IARA a Guarapari</p>
<hr />
<div>Viagem da IARA a Guarapari</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=Arquivo:Iara_guarapari.png&diff=81307Arquivo:Iara guarapari.png2017-08-03T19:00:17Z<p>Raphael Carneiro: IARA journey to Guarapari</p>
<hr />
<div>IARA journey to Guarapari</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=Arquivo:Globo_iara.jpg&diff=81306Arquivo:Globo iara.jpg2017-08-03T18:33:42Z<p>Raphael Carneiro: Reportagem da TV Globo sobre a viagem da IARA a Guarapari em maio de 2017.</p>
<hr />
<div>Reportagem da TV Globo sobre a viagem da IARA a Guarapari em maio de 2017.</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=IARA&diff=81304IARA2017-08-03T16:40:33Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''Intelligent Autonomous Robotic Automobile - IARA'''</big></big></big><br />
<br />
== '''About IARA''' ==<br />
A team of students and researchers of the Laboratório de Computação de Alto Desempenho (High-Performance Computing Laboratory) of Universidade Federal do Espírito Santo (Federal University of Espírito Santo), leaded by Professor Alberto F. De Souza, designed and built one of the first autonomous cars of Brazil. Christened IARA (Intelligent Autonomous Robotic Automobile), this autonomous car was able to run autonomously for tens of kilometers at speeds of up to of 30 Km/h in urban roads surrounding the main campus of UFES (See video at [http://youtu.be/LBM--2dAvyI?list=UUsQuY9t5ss3jwHBiRaEEFFg]).<br />
<br />
== '''IARA's Specifications''' ==<br />
IARA is an experimental robotic platform, based on a Ford Escape Hybrid (Fig. 5(a)). It has several high-end sensors, including: two Point Grey Bumblebee XB3 stereo cameras and two Point Grey Bumblebee 2 stereo cameras, one Light Detection and Ranging (LIDAR) Velodyne HDL 32-E, and one GPS-aided Attitude and Heading Reference System (AHRS/GPS) Xsens MTiG (Fig. 5(b)). To process the data coming from the sensors, the platform can hold up to four Dell Precision R5500 (2 Intel Xeon 2.13 GHZ, 12 GB RAM, 2 HDs SSD of 120GB on RAID0 and GPU cards Tesla C2050) (two installed in the configuration shown in Fig. 5(b)). We implemented many software modules for IARA that currently allows for its autonomous operation, such as modules for mapping, localization, behavior selection, path following, control, and motion planning (that is the focus of this paper). We also implemented a software module for autonomous vehicle simulation to help in the development and testing of all the other IARA’s modules (that was used to evaluate the performance of the motion planner presented in this paper). See video of IARA autonomous operation at [https://www.youtube.com/watch?v=zE7np6tgCHc&list=UUsQuY9t5ss3jwHBiRaEEFFg] and videos about other IARA’s software modules at [http://www.youtube.com/user/lcadufes].<br />
<br />
{| border=0<br />
| align="center" | [[imagem:iara.jpg|border|center|500px|Intelligent Autonomous Robotic Automobile - IARA]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|440px|Inside IARA's cockpit]]<br />
|-<br />
| align="center" | Intelligent Autonomous Robotic Automobile - IARA<br />
| align="center" | Inside IARA's cockpit<br />
|}<br />
<br />
== '''Our team''' ==<br />
Our team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. To learn more about our team [[Equipe|see '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|950px|LCAD/UFES team and IARA autonomous vehicle]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
|}</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80743DARPA2013-07-05T17:23:27Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to belong to this two-digit-score club by the following tale. The U.S. Government invited 10 top-class teams from USA and one from Israel, funding $375,000 each to develop robotic software and compete in the DARPA VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying test. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). <br />
<br />
Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying test, telling how narrow was that funnel. These Track C teams came from universities and research organizations located in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks, the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score during the three days. The '''Br Robotics Team''' is glad to be able to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind of only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
{| border=1<br />
|+ '''DARPA Virtual Robotics Challenge's Top Performers'''<br />
|- bgcolor="#DFDFDF" | <br />
! Ranking<br />
! Team Name<br />
! Track<br />
! Score<br />
! Country<br />
! Organization<br />
! Location<br />
|-<br />
! 1<br />
| Team IHMC<br />
| align="center" | B<br />
| align="center" | 52<br />
| align="center" | USA<br />
| IHMC - Florida Institute for Human & Machine Cognition<br />
| Pensacola, Florida<br />
|-<br />
! 2<br />
| WRECS<br />
| align="center" | C<br />
| align="center" | 39<br />
| align="center" | USA<br />
| WPI - Worcester Polytechnic Institute<br />
| Worcester, Massachusetts<br />
|-<br />
! 3<br />
| MIT<br />
| align="center" | B<br />
| align="center" | 34<br />
| align="center" | USA<br />
| MIT - Massachusetts Institute of Technology<br />
| Cambridge, Massachusetts<br />
|-<br />
! 4<br />
| Team TRACLabs<br />
| align="center" | B<br />
| align="center" | 30<br />
| align="center" | USA<br />
| TRACLabs, Inc.<br />
| Webster, Texas<br />
|-<br />
! 5<br />
| JPL / UCSB / Caltech<br />
| align="center" | B<br />
| align="center" | 29<br />
| align="center" | USA<br />
| NASA JPL - Jet Propulsion Laboratory (et al.)<br />
| Pasadena, California<br />
|-<br />
! 6<br />
| TORC / TU Darmstadt / Virginia Tech<br />
| align="center" | B<br />
| align="center" | 27<br />
| align="center" | USA<br />
| TORC Robotics, LLC (et al.)<br />
| Blacksburg, Virginia<br />
|-<br />
! 7<br />
| Team K<br />
| align="center" | C<br />
| align="center" | 25<br />
| align="center" | Japan<br />
| <br />
| <br />
|-<br />
! 8<br />
| TROOPER<br />
| align="center" | B<br />
| align="center" | 24<br />
| align="center" | USA<br />
| Lockheed Martin Corp.<br />
| Cherry Hill, New Jersey<br />
<br />
|-<br />
! 9<br />
| Team Case<br />
| align="center" | C<br />
| align="center" | 23<br />
| align="center" | USA<br />
| CWRU - Case Western Reserve University<br />
<br />
| Cleveland, Ohio<br />
|-<br />
! 10<br />
| Team Steel<br />
| align="center" | B<br />
| align="center" | 22<br />
| align="center" | USA<br />
<br />
| CMU - Carnegie Mellon University<br />
| Pittsburg, Pennsylvania<br />
|-<br />
! 11<br />
| Team ELEX<br />
| align="center" | C<br />
| align="center" | 21<br />
| align="center" | Japan<br />
| <br />
| <br />
|- <br />
! 12<br />
| '''Br Robotics Team'''<br />
| align="center" | C<br />
| align="center" | 16<br />
| align="center" | Brazil<br />
| '''UFES - Federal University of Espirito Santo''' (et al.)<br />
| Vitoria, Espirito Santo<br />
|}<br />
<br />
<br />
After all, what's the big deal about making a robot walk, drive and grasp things? Well, we've spent a few weeks to make it happen, while a baby carbon-based unit takes more than a year!<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80742DARPA2013-07-05T17:21:06Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to belong to this two-digit-score club by the following tale. The U.S. Government invited 10 top-class teams from USA and one from Israel, funding $375,000 each to develop robotic software and compete in the DARPA VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying test. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). <br />
<br />
Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying test, telling how narrow was that funnel. These Track C teams came from universities and research organizations located in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score during the three days. The '''Br Robotics Team''' is glad to be able to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind of only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
{| border=1<br />
|+ '''DARPA Virtual Robotics Challenge's Top Performers'''<br />
|- bgcolor="#DFDFDF" | <br />
! Ranking<br />
! Team Name<br />
! Track<br />
! Score<br />
! Country<br />
! Organization<br />
! Location<br />
|-<br />
! 1<br />
| Team IHMC<br />
| align="center" | B<br />
| align="center" | 52<br />
| align="center" | USA<br />
| IHMC - Florida Institute for Human & Machine Cognition<br />
| Pensacola, Florida<br />
|-<br />
! 2<br />
| WRECS<br />
| align="center" | C<br />
| align="center" | 39<br />
| align="center" | USA<br />
| WPI - Worcester Polytechnic Institute<br />
| Worcester, Massachusetts<br />
|-<br />
! 3<br />
| MIT<br />
| align="center" | B<br />
| align="center" | 34<br />
| align="center" | USA<br />
| MIT - Massachusetts Institute of Technology<br />
| Cambridge, Massachusetts<br />
|-<br />
! 4<br />
| Team TRACLabs<br />
| align="center" | B<br />
| align="center" | 30<br />
| align="center" | USA<br />
| TRACLabs, Inc.<br />
| Webster, Texas<br />
|-<br />
! 5<br />
| JPL / UCSB / Caltech<br />
| align="center" | B<br />
| align="center" | 29<br />
| align="center" | USA<br />
| NASA JPL - Jet Propulsion Laboratory (et al.)<br />
| Pasadena, California<br />
|-<br />
! 6<br />
| TORC / TU Darmstadt / Virginia Tech<br />
| align="center" | B<br />
| align="center" | 27<br />
| align="center" | USA<br />
| TORC Robotics, LLC (et al.)<br />
| Blacksburg, Virginia<br />
|-<br />
! 7<br />
| Team K<br />
| align="center" | C<br />
| align="center" | 25<br />
| align="center" | Japan<br />
| <br />
| <br />
|-<br />
! 8<br />
| TROOPER<br />
| align="center" | B<br />
| align="center" | 24<br />
| align="center" | USA<br />
| Lockheed Martin Corp.<br />
| Cherry Hill, New Jersey<br />
<br />
|-<br />
! 9<br />
| Team Case<br />
| align="center" | C<br />
| align="center" | 23<br />
| align="center" | USA<br />
| CWRU - Case Western Reserve University<br />
<br />
| Cleveland, Ohio<br />
|-<br />
! 10<br />
| Team Steel<br />
| align="center" | B<br />
| align="center" | 22<br />
| align="center" | USA<br />
<br />
| CMU - Carnegie Mellon University<br />
| Pittsburg, Pennsylvania<br />
|-<br />
! 11<br />
| Team ELEX<br />
| align="center" | C<br />
| align="center" | 21<br />
| align="center" | Japan<br />
| <br />
| <br />
|- <br />
! 12<br />
| '''Br Robotics Team'''<br />
| align="center" | C<br />
| align="center" | 16<br />
| align="center" | Brazil<br />
| '''UFES - Federal University of Espirito Santo''' (et al.)<br />
| Vitoria, Espirito Santo<br />
|}<br />
<br />
<br />
After all, what's the big deal about making a robot walk, drive and grasp things? Well, we've done it in few weeks, while a baby carbon-based unit takes more than a year!<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80741DARPA2013-07-05T17:17:48Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to belong to this two-digit-score club by the following tale. The U.S. Government invited 10 top-class teams from USA and one from Israel, and funded $375,000 each to develop robotic software and compete in the DARPA VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying test. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). <br />
<br />
Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying test, telling how narrow was that funnel. These Track C teams came from universities and research organizations located in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score during the three days. The '''Br Robotics Team''' is glad to be able to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind of only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
{| border=1<br />
|+ '''DARPA Virtual Robotics Challenge's Top Performers'''<br />
|- bgcolor="#DFDFDF" | <br />
! Ranking<br />
! Team Name<br />
! Track<br />
! Score<br />
! Country<br />
! Organization<br />
! Location<br />
|-<br />
! 1<br />
| Team IHMC<br />
| align="center" | B<br />
| align="center" | 52<br />
| align="center" | USA<br />
| IHMC - Florida Institute for Human & Machine Cognition<br />
| Pensacola, Florida<br />
|-<br />
! 2<br />
| WRECS<br />
| align="center" | C<br />
| align="center" | 39<br />
| align="center" | USA<br />
| WPI - Worcester Polytechnic Institute<br />
| Worcester, Massachusetts<br />
|-<br />
! 3<br />
| MIT<br />
| align="center" | B<br />
| align="center" | 34<br />
| align="center" | USA<br />
| MIT - Massachusetts Institute of Technology<br />
| Cambridge, Massachusetts<br />
|-<br />
! 4<br />
| Team TRACLabs<br />
| align="center" | B<br />
| align="center" | 30<br />
| align="center" | USA<br />
| TRACLabs, Inc.<br />
| Webster, Texas<br />
|-<br />
! 5<br />
| JPL / UCSB / Caltech<br />
| align="center" | B<br />
| align="center" | 29<br />
| align="center" | USA<br />
| NASA JPL - Jet Propulsion Laboratory (et al.)<br />
| Pasadena, California<br />
|-<br />
! 6<br />
| TORC / TU Darmstadt / Virginia Tech<br />
| align="center" | B<br />
| align="center" | 27<br />
| align="center" | USA<br />
| TORC Robotics, LLC (et al.)<br />
| Blacksburg, Virginia<br />
|-<br />
! 7<br />
| Team K<br />
| align="center" | C<br />
| align="center" | 25<br />
| align="center" | Japan<br />
| <br />
| <br />
|-<br />
! 8<br />
| TROOPER<br />
| align="center" | B<br />
| align="center" | 24<br />
| align="center" | USA<br />
| Lockheed Martin Corp.<br />
| Cherry Hill, New Jersey<br />
<br />
|-<br />
! 9<br />
| Team Case<br />
| align="center" | C<br />
| align="center" | 23<br />
| align="center" | USA<br />
| CWRU - Case Western Reserve University<br />
<br />
| Cleveland, Ohio<br />
|-<br />
! 10<br />
| Team Steel<br />
| align="center" | B<br />
| align="center" | 22<br />
| align="center" | USA<br />
<br />
| CMU - Carnegie Mellon University<br />
| Pittsburg, Pennsylvania<br />
|-<br />
! 11<br />
| Team ELEX<br />
| align="center" | C<br />
| align="center" | 21<br />
| align="center" | Japan<br />
| <br />
| <br />
|- <br />
! 12<br />
| '''Br Robotics Team'''<br />
| align="center" | C<br />
| align="center" | 16<br />
| align="center" | Brazil<br />
| '''UFES - Federal University of Espirito Santo''' (et al.)<br />
| Vitoria, Espirito Santo<br />
|}<br />
<br />
<br />
After all, what's the big deal about making a robot walk, drive and grasp things? Well, we've done it in few weeks, while a baby carbon-based unit takes more than a year!<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80740DARPA2013-07-05T07:52:19Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to belong to this two-digit-score club by reading the following tale. The U.S. Government invited 10 top-class teams from USA e one from Israel, and funded $375,000 each to develop robotic software and compete in the DARPA VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying test. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). <br />
<br />
Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying test, telling how narrow was that funnel. These Track C teams came from universities and research organizations located in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score during the three days. The '''Br Robotics Team''' is glad to be able to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind of only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
{| border=1<br />
|+ '''DARPA Virtual Robotics Challenge's Top Performers'''<br />
|- bgcolor="#DFDFDF" | <br />
! Ranking<br />
! Team Name<br />
! Track<br />
! Score<br />
! Country<br />
! Organization<br />
! Location<br />
|-<br />
! 1<br />
| Team IHMC<br />
| align="center" | B<br />
| align="center" | 52<br />
| align="center" | USA<br />
| IHMC - Florida Institute for Human & Machine Cognition<br />
| Pensacola, Florida<br />
|-<br />
! 2<br />
| WRECS<br />
| align="center" | C<br />
| align="center" | 39<br />
| align="center" | USA<br />
| WPI - Worcester Polytechnic Institute<br />
| Worcester, Massachusetts<br />
|-<br />
! 3<br />
| MIT<br />
| align="center" | B<br />
| align="center" | 34<br />
| align="center" | USA<br />
| MIT - Massachusetts Institute of Technology<br />
| Cambridge, Massachusetts<br />
|-<br />
! 4<br />
| Team TRACLabs<br />
| align="center" | B<br />
| align="center" | 30<br />
| align="center" | USA<br />
| TRACLabs, Inc.<br />
| Webster, Texas<br />
|-<br />
! 5<br />
| JPL / UCSB / Caltech<br />
| align="center" | B<br />
| align="center" | 29<br />
| align="center" | USA<br />
| NASA JPL - Jet Propulsion Laboratory (et al.)<br />
| Pasadena, California<br />
|-<br />
! 6<br />
| TORC / TU Darmstadt / Virginia Tech<br />
| align="center" | B<br />
| align="center" | 27<br />
| align="center" | USA<br />
| TORC Robotics, LLC (et al.)<br />
| Blacksburg, Virginia<br />
|-<br />
! 7<br />
| Team K<br />
| align="center" | C<br />
| align="center" | 25<br />
| align="center" | Japan<br />
| <br />
| <br />
|-<br />
! 8<br />
| TROOPER<br />
| align="center" | B<br />
| align="center" | 24<br />
| align="center" | USA<br />
| Lockheed Martin Corp.<br />
| Cherry Hill, New Jersey<br />
<br />
|-<br />
! 9<br />
| Team Case<br />
| align="center" | C<br />
| align="center" | 23<br />
| align="center" | USA<br />
| CWRU - Case Western Reserve University<br />
<br />
| Cleveland, Ohio<br />
|-<br />
! 10<br />
| Team Steel<br />
| align="center" | B<br />
| align="center" | 22<br />
| align="center" | USA<br />
<br />
| CMU - Carnegie Mellon University<br />
| Pittsburg, Pennsylvania<br />
|-<br />
! 11<br />
| Team ELEX<br />
| align="center" | C<br />
| align="center" | 21<br />
| align="center" | Japan<br />
| <br />
| <br />
|- <br />
! 12<br />
| '''Br Robotics Team'''<br />
| align="center" | C<br />
| align="center" | 16<br />
| align="center" | Brazil<br />
| '''UFES - Federal University of Espirito Santo''' (et al.)<br />
| Vitoria, Espirito Santo<br />
|}<br />
<br />
<br />
After all, what's the big deal about making a robot walk, drive and grasp things? Well, we've done it in few weeks, while a baby carbon-based unit takes more than a year!<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80739DARPA2013-07-05T07:50:19Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to belong to this two-digit-score club by reading the following tale. The U.S. Government invited 10 top-class teams from USA e one from Israel, and funded $375,000 each to develop robotic software and compete in the DARPA VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying test. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). <br />
<br />
Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying test, telling how narrow was that funnel. These Track C teams came from universities and research organizations located in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score during the three days. The '''Br Robotics Team''' is glad to be able to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind of only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
{| border=1<br />
|+ '''DARPA Virtual Robotics Challenge's Top Performers'''<br />
|- bgcolor="#DFDFDF" | <br />
! Ranking<br />
! Team Name<br />
! Track<br />
! Score<br />
! Country<br />
! Organization<br />
! Location<br />
|-<br />
! 1<br />
| Team IHMC<br />
| align="center" | B<br />
| align="center" | 52<br />
| align="center" | USA<br />
| IHMC - Florida Institute for Human & Machine Cognition<br />
| Pensacola, Florida<br />
|-<br />
! 2<br />
| WRECS<br />
| align="center" | C<br />
| align="center" | 39<br />
| align="center" | USA<br />
| WPI - Worcester Polytechnic Institute<br />
| Worcester, Massachusetts<br />
|-<br />
! 3<br />
| MIT<br />
| align="center" | B<br />
| align="center" | 34<br />
| align="center" | USA<br />
| MIT - Massachusetts Institute of Technology<br />
| Cambridge, Massachusetts<br />
|-<br />
! 4<br />
| Team TRACLabs<br />
| align="center" | B<br />
| align="center" | 30<br />
| align="center" | USA<br />
| TRACLabs, Inc.<br />
| Webster, Texas<br />
|-<br />
! 5<br />
| JPL / UCSB / Caltech<br />
| align="center" | B<br />
| align="center" | 29<br />
| align="center" | USA<br />
| NASA JPL - Jet Propulsion Laboratory (et al.)<br />
| Pasadena, California<br />
|-<br />
! 6<br />
| TORC / TU Darmstadt / Virginia Tech<br />
| align="center" | B<br />
| align="center" | 27<br />
| align="center" | USA<br />
| TORC Robotics, LLC (et al.)<br />
| Blacksburg, Virginia<br />
|-<br />
! 7<br />
| Team K<br />
| align="center" | C<br />
| align="center" | 25<br />
| align="center" | Japan<br />
| <br />
| <br />
|-<br />
! 8<br />
| TROOPER<br />
| align="center" | B<br />
| align="center" | 24<br />
| align="center" | USA<br />
| Lockheed Martin Corp.<br />
| Cherry Hill, New Jersey<br />
<br />
|-<br />
! 9<br />
| Team Case<br />
| align="center" | C<br />
| align="center" | 23<br />
| align="center" | USA<br />
| CWRU - Case Western Reserve University<br />
<br />
| Cleveland, Ohio<br />
|-<br />
! 10<br />
| Team Steel<br />
| align="center" | B<br />
| align="center" | 22<br />
| align="center" | USA<br />
<br />
| CMU - Carnegie Mellon University<br />
| Pittsburg, Pennsylvania<br />
|-<br />
! 11<br />
| Team ELEX<br />
| align="center" | C<br />
| align="center" | 21<br />
| align="center" | Japan<br />
| <br />
| <br />
|- <br />
! 12<br />
| '''Br Robotics Team'''<br />
| align="center" | C<br />
| align="center" | 16<br />
| align="center" | Brazil<br />
| '''UFES - Federal University of Espirito Santo''' (et al.)<br />
| Vitoria, Espirito Santo<br />
|}<br />
<br />
<br />
After all, what's the big deal about making a robot walk, drive and grasp things? Well, we've done it in few weeks, while a baby carbon-based unit takes a year or more!<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80738DARPA2013-07-05T07:45:25Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to belong to this two-digit-score club by reading the following tale. The U.S. Government invited 10 top-class teams from USA e one from Israel, and funded $375,000 each to develop robotic software and compete in the DARPA VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying test. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). <br />
<br />
Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying test, telling how narrow was that funnel. These Track C teams came from universities and research organizations located in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score during the three days. The '''Br Robotics Team''' is glad to be able to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind of only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
{| border=1<br />
|+ '''DARPA Virtual Robotics Challenge's Top Performers'''<br />
|- bgcolor="#DFDFDF" | <br />
! Ranking<br />
! Team Name<br />
! Track<br />
! Score<br />
! Country<br />
! Organization<br />
! Location<br />
|-<br />
! 1<br />
| Team IHMC<br />
| align="center" | B<br />
| align="center" | 52<br />
| align="center" | USA<br />
| IHMC - Florida Institute for Human & Machine Cognition<br />
| Pensacola, Florida<br />
|-<br />
! 2<br />
| WRECS<br />
| align="center" | C<br />
| align="center" | 39<br />
| align="center" | USA<br />
| WPI - Worcester Polytechnic Institute<br />
| Worcester, Massachusetts<br />
|-<br />
! 3<br />
| MIT<br />
| align="center" | B<br />
| align="center" | 34<br />
| align="center" | USA<br />
| MIT - Massachusetts Institute of Technology<br />
| Cambridge, Massachusetts<br />
|-<br />
! 4<br />
| Team TRACLabs<br />
| align="center" | B<br />
| align="center" | 30<br />
| align="center" | USA<br />
| TRACLabs, Inc.<br />
| Webster, Texas<br />
|-<br />
! 5<br />
| JPL / UCSB / Caltech<br />
| align="center" | B<br />
| align="center" | 29<br />
| align="center" | USA<br />
| NASA JPL - Jet Propulsion Laboratory (et al.)<br />
| Pasadena, California<br />
|-<br />
! 6<br />
| TORC / TU Darmstadt / Virginia Tech<br />
| align="center" | B<br />
| align="center" | 27<br />
| align="center" | USA<br />
| TORC Robotics, LLC (et al.)<br />
| Blacksburg, Virginia<br />
|-<br />
! 7<br />
| Team K<br />
| align="center" | C<br />
| align="center" | 25<br />
| align="center" | Japan<br />
| <br />
| <br />
|-<br />
! 8<br />
| TROOPER<br />
| align="center" | B<br />
| align="center" | 24<br />
| align="center" | USA<br />
| Lockheed Martin Corp.<br />
| Cherry Hill, New Jersey<br />
<br />
|-<br />
! 9<br />
| Team Case<br />
| align="center" | C<br />
| align="center" | 23<br />
| align="center" | USA<br />
| CWRU - Case Western Reserve University<br />
<br />
| Cleveland, Ohio<br />
|-<br />
! 10<br />
| Team Steel<br />
| align="center" | B<br />
| align="center" | 22<br />
| align="center" | USA<br />
<br />
| CMU - Carnegie Mellon University<br />
| Pittsburg, Pennsylvania<br />
|-<br />
! 11<br />
| Team ELEX<br />
| align="center" | C<br />
| align="center" | 21<br />
| align="center" | Japan<br />
| <br />
| <br />
|- <br />
! 12<br />
| '''Br Robotics Team'''<br />
| align="center" | C<br />
| align="center" | 16<br />
| align="center" | Brazil<br />
| '''UFES - Federal University of Espirito Santo''' (et al.)<br />
| Vitoria, Espirito Santo<br />
|}<br />
<br />
<br />
After all, what's the big deal about making a robot walk, drive and grasp things? Let's pick this iron man and give it another try!<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80737DARPA2013-07-05T07:42:09Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to belong to this two-digit-score club by reading the following tale. The U.S. Government invited 10 top-class teams from USA e one from Israel, and funded $375,000 each to develop robotic software and compete in the DARPA VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying test. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). <br />
<br />
Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying test, telling how narrow was that funnel. These Track C teams came from universities and research organizations located in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score at least once during the three days. The '''Br Robotics Team''' is glad to be able to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind of only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
{| border=1<br />
|+ '''DARPA Virtual Robotics Challenge's Top Performers'''<br />
|- bgcolor="#DFDFDF" | <br />
! Ranking<br />
! Team Name<br />
! Track<br />
! Score<br />
! Country<br />
! Organization<br />
! Location<br />
|-<br />
! 1<br />
| Team IHMC<br />
| align="center" | B<br />
| align="center" | 52<br />
| align="center" | USA<br />
| IHMC - Florida Institute for Human & Machine Cognition<br />
| Pensacola, Florida<br />
|-<br />
! 2<br />
| WRECS<br />
| align="center" | C<br />
| align="center" | 39<br />
| align="center" | USA<br />
| WPI - Worcester Polytechnic Institute<br />
| Worcester, Massachusetts<br />
|-<br />
! 3<br />
| MIT<br />
| align="center" | B<br />
| align="center" | 34<br />
| align="center" | USA<br />
| MIT - Massachusetts Institute of Technology<br />
| Cambridge, Massachusetts<br />
|-<br />
! 4<br />
| Team TRACLabs<br />
| align="center" | B<br />
| align="center" | 30<br />
| align="center" | USA<br />
| TRACLabs, Inc.<br />
| Webster, Texas<br />
|-<br />
! 5<br />
| JPL / UCSB / Caltech<br />
| align="center" | B<br />
| align="center" | 29<br />
| align="center" | USA<br />
| NASA JPL - Jet Propulsion Laboratory (et al.)<br />
| Pasadena, California<br />
|-<br />
! 6<br />
| TORC / TU Darmstadt / Virginia Tech<br />
| align="center" | B<br />
| align="center" | 27<br />
| align="center" | USA<br />
| TORC Robotics, LLC (et al.)<br />
| Blacksburg, Virginia<br />
|-<br />
! 7<br />
| Team K<br />
| align="center" | C<br />
| align="center" | 25<br />
| align="center" | Japan<br />
| <br />
| <br />
|-<br />
! 8<br />
| TROOPER<br />
| align="center" | B<br />
| align="center" | 24<br />
| align="center" | USA<br />
| Lockheed Martin Corp.<br />
| Cherry Hill, New Jersey<br />
<br />
|-<br />
! 9<br />
| Team Case<br />
| align="center" | C<br />
| align="center" | 23<br />
| align="center" | USA<br />
| CWRU - Case Western Reserve University<br />
<br />
| Cleveland, Ohio<br />
|-<br />
! 10<br />
| Team Steel<br />
| align="center" | B<br />
| align="center" | 22<br />
| align="center" | USA<br />
<br />
| CMU - Carnegie Mellon University<br />
| Pittsburg, Pennsylvania<br />
|-<br />
! 11<br />
| Team ELEX<br />
| align="center" | C<br />
| align="center" | 21<br />
| align="center" | Japan<br />
| <br />
| <br />
|- <br />
! 12<br />
| '''Br Robotics Team'''<br />
| align="center" | C<br />
| align="center" | 16<br />
| align="center" | Brazil<br />
| '''UFES - Federal University of Espirito Santo''' (et al.)<br />
| Vitoria, Espirito Santo<br />
|}<br />
<br />
<br />
After all, what's the big deal about making a robot walk, drive and grasp things? Let's pick this iron man and give it another try!<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80736DARPA2013-07-05T07:29:49Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to belong to this two-digit-score club by reading the following tale. The U.S. Government invited 10 top-class teams from USA e one from Israel, and funded $375,000 each to develop robotic software and compete in the DARPA VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying test. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). <br />
<br />
Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying test, telling how narrow was that funnel. These Track C teams came from universities and research organizations located in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score at least once during the three days. The '''Br Robotics Team''' is glad to be able to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind of only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
{| border=1<br />
|+ '''DARPA Virtual Robotics Challenge Top Performers'''<br />
|- bgcolor="#DFDFDF" | <br />
! Ranking<br />
! Team Name<br />
! Track<br />
! Score<br />
! Country<br />
! Organization<br />
! Location<br />
|-<br />
! 1<br />
| Team IHMC<br />
| align="center" | B<br />
| align="center" | 52<br />
| align="center" | USA<br />
| IHMC - Florida Institute for Human & Machine Cognition<br />
| Pensacola, Florida<br />
|-<br />
! 2<br />
| WRECS<br />
| align="center" | C<br />
| align="center" | 39<br />
| align="center" | USA<br />
| WPI - Worcester Polytechnic Institute<br />
| Worcester, Massachusetts<br />
|-<br />
! 3<br />
| MIT<br />
| align="center" | B<br />
| align="center" | 34<br />
| align="center" | USA<br />
| MIT - Massachusetts Institute of Technology<br />
| Cambridge, Massachusetts<br />
|-<br />
! 4<br />
| Team TRACLabs<br />
| align="center" | B<br />
| align="center" | 30<br />
| align="center" | USA<br />
| TRACLabs, Inc.<br />
| Webster, Texas<br />
|-<br />
! 5<br />
| JPL / UCSB / Caltech<br />
| align="center" | B<br />
| align="center" | 29<br />
| align="center" | USA<br />
| NASA JPL - Jet Propulsion Laboratory (et al.)<br />
| Pasadena, California<br />
|-<br />
! 6<br />
| TORC / TU Darmstadt / Virginia Tech<br />
| align="center" | B<br />
| align="center" | 27<br />
| align="center" | USA<br />
| TORC Robotics, LLC (et al.)<br />
| Blacksburg, Virginia<br />
|-<br />
! 7<br />
| Team K<br />
| align="center" | C<br />
| align="center" | 25<br />
| align="center" | Japan<br />
| <br />
| <br />
|-<br />
! 8<br />
| TROOPER<br />
| align="center" | B<br />
| align="center" | 24<br />
| align="center" | USA<br />
| Lockheed Martin Corp.<br />
| Cherry Hill, New Jersey<br />
<br />
|-<br />
! 9<br />
| Team Case<br />
| align="center" | C<br />
| align="center" | 23<br />
| align="center" | USA<br />
| CWRU - Case Western Reserve University<br />
<br />
| Cleveland, Ohio<br />
|-<br />
! 10<br />
| Team Steel<br />
| align="center" | B<br />
| align="center" | 22<br />
| align="center" | USA<br />
<br />
| CMU - Carnegie Mellon University<br />
| Pittsburg, Pennsylvania<br />
|-<br />
! 11<br />
| Team ELEX<br />
| align="center" | C<br />
| align="center" | 21<br />
| align="center" | Japan<br />
| <br />
| <br />
|- <br />
! 12<br />
| '''Br Robotics Team'''<br />
| align="center" | C<br />
| align="center" | 16<br />
| align="center" | Brazil<br />
| '''UFES - Federal University of Espirito Santo''' (et al.)<br />
| Vitoria, Espirito Santo<br />
|}<br />
<br />
<br />
After all, what's the big deal about making a robot walk, drive and grasp things? Let's pick this iron man and give it another try!<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80735DARPA2013-07-05T07:26:55Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to belong to this two-digit-score club by reading the following tale. The U.S. Government invited 10 top-class teams from USA e one from Israel, and funded $375,000 each to develop robotic software and compete in the DARPA VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying test. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). <br />
<br />
Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying test, telling how narrow was that funnel. These Track C teams came from universities and research organizations located in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score at least once during the three days. The '''Br Robotics Team''' is glad to be skilled enough to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind of only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
{| border=1<br />
|+ '''DARPA Virtual Robotics Challenge Top Performers'''<br />
|- bgcolor="#DFDFDF" | <br />
! Ranking<br />
! Team Name<br />
! Track<br />
! Score<br />
! Country<br />
! Organization<br />
! Location<br />
|-<br />
! 1<br />
| Team IHMC<br />
| align="center" | B<br />
| align="center" | 52<br />
| align="center" | USA<br />
| IHMC - Florida Institute for Human & Machine Cognition<br />
| Pensacola, Florida<br />
|-<br />
! 2<br />
| WRECS<br />
| align="center" | C<br />
| align="center" | 39<br />
| align="center" | USA<br />
| WPI - Worcester Polytechnic Institute<br />
| Worcester, Massachusetts<br />
|-<br />
! 3<br />
| MIT<br />
| align="center" | B<br />
| align="center" | 34<br />
| align="center" | USA<br />
| MIT - Massachusetts Institute of Technology<br />
| Cambridge, Massachusetts<br />
|-<br />
! 4<br />
| Team TRACLabs<br />
| align="center" | B<br />
| align="center" | 30<br />
| align="center" | USA<br />
| TRACLabs, Inc.<br />
| Webster, Texas<br />
|-<br />
! 5<br />
| JPL / UCSB / Caltech<br />
| align="center" | B<br />
| align="center" | 29<br />
| align="center" | USA<br />
| NASA JPL - Jet Propulsion Laboratory (et al.)<br />
| Pasadena, California<br />
|-<br />
! 6<br />
| TORC / TU Darmstadt / Virginia Tech<br />
| align="center" | B<br />
| align="center" | 27<br />
| align="center" | USA<br />
| TORC Robotics, LLC (et al.)<br />
| Blacksburg, Virginia<br />
|-<br />
! 7<br />
| Team K<br />
| align="center" | C<br />
| align="center" | 25<br />
| align="center" | Japan<br />
| <br />
| <br />
|-<br />
! 8<br />
| TROOPER<br />
| align="center" | B<br />
| align="center" | 24<br />
| align="center" | USA<br />
| Lockheed Martin Corp.<br />
| Cherry Hill, New Jersey<br />
<br />
|-<br />
! 9<br />
| Team Case<br />
| align="center" | C<br />
| align="center" | 23<br />
| align="center" | USA<br />
| CWRU - Case Western Reserve University<br />
<br />
| Cleveland, Ohio<br />
|-<br />
! 10<br />
| Team Steel<br />
| align="center" | B<br />
| align="center" | 22<br />
| align="center" | USA<br />
<br />
| CMU - Carnegie Mellon University<br />
| Pittsburg, Pennsylvania<br />
|-<br />
! 11<br />
| Team ELEX<br />
| align="center" | C<br />
| align="center" | 21<br />
| align="center" | Japan<br />
| <br />
| <br />
|- <br />
! 12<br />
| '''Br Robotics Team'''<br />
| align="center" | C<br />
| align="center" | 16<br />
| align="center" | Brazil<br />
| '''UFES - Federal University of Espirito Santo''' (et al.)<br />
| Vitoria, Espirito Santo<br />
|}<br />
<br />
<br />
After all, what's the big deal about making a robot walk, drive and grasp things? Let's pick this iron man and give it another try!<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80734DARPA2013-07-05T07:17:40Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to belong to this two-digit-score club by reading the following tale. The U.S. Government invited 10 top-class teams from USA e one from Israel, and funded $375,000 each to develop robotic software and compete in the DARPA VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying process. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). <br />
<br />
Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying process, telling how narrow was that funnel. These Track C teams came from universities and research organizations located in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score at least once during the three days. The '''Br Robotics Team''' is glad to be skilled enough to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind of only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
{| border=1<br />
|+ '''DARPA Virtual Robotics Challenge Top Performers'''<br />
|- bgcolor="#DFDFDF" | <br />
! Ranking<br />
! Team Name<br />
! Track<br />
! Score<br />
! Country<br />
! Organization<br />
! Location<br />
|-<br />
! 1<br />
| Team IHMC<br />
| align="center" | B<br />
| align="center" | 52<br />
| align="center" | USA<br />
| IHMC - Florida Institute for Human & Machine Cognition<br />
| Pensacola, Florida<br />
|-<br />
! 2<br />
| WRECS<br />
| align="center" | C<br />
| align="center" | 39<br />
| align="center" | USA<br />
| WPI - Worcester Polytechnic Institute<br />
| Worcester, Massachusetts<br />
|-<br />
! 3<br />
| MIT<br />
| align="center" | B<br />
| align="center" | 34<br />
| align="center" | USA<br />
| MIT - Massachusetts Institute of Technology<br />
| Cambridge, Massachusetts<br />
|-<br />
! 4<br />
| Team TRACLabs<br />
| align="center" | B<br />
| align="center" | 30<br />
| align="center" | USA<br />
| TRACLabs, Inc.<br />
| Webster, Texas<br />
|-<br />
! 5<br />
| JPL / UCSB / Caltech<br />
| align="center" | B<br />
| align="center" | 29<br />
| align="center" | USA<br />
| NASA JPL - Jet Propulsion Laboratory (et al.)<br />
| Pasadena, California<br />
|-<br />
! 6<br />
| TORC / TU Darmstadt / Virginia Tech<br />
| align="center" | B<br />
| align="center" | 27<br />
| align="center" | USA<br />
| TORC Robotics, LLC (et al.)<br />
| Blacksburg, Virginia<br />
|-<br />
! 7<br />
| Team K<br />
| align="center" | C<br />
| align="center" | 25<br />
| align="center" | Japan<br />
| <br />
| <br />
|-<br />
! 8<br />
| TROOPER<br />
| align="center" | B<br />
| align="center" | 24<br />
| align="center" | USA<br />
| Lockheed Martin Corp.<br />
| Cherry Hill, New Jersey<br />
<br />
|-<br />
! 9<br />
| Team Case<br />
| align="center" | C<br />
| align="center" | 23<br />
| align="center" | USA<br />
| CWRU - Case Western Reserve University<br />
<br />
| Cleveland, Ohio<br />
|-<br />
! 10<br />
| Team Steel<br />
| align="center" | B<br />
| align="center" | 22<br />
| align="center" | USA<br />
<br />
| CMU - Carnegie Mellon University<br />
| Pittsburg, Pennsylvania<br />
|-<br />
! 11<br />
| Team ELEX<br />
| align="center" | C<br />
| align="center" | 21<br />
| align="center" | Japan<br />
| <br />
| <br />
|- <br />
! 12<br />
| '''Br Robotics Team'''<br />
| align="center" | C<br />
| align="center" | 16<br />
| align="center" | Brazil<br />
| '''UFES - Federal University of Espirito Santo''' (et al.)<br />
| Vitoria, Espirito Santo<br />
|}<br />
<br />
<br />
After all, what's the big deal about making a robot walk, drive and grasp things? Let's pick this iron man and give it another try!<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80733DARPA2013-07-05T07:16:26Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to belong to this two-digit-score club by reading the following tale. The U.S. Government invited 10 top-class teams from USA e one from Israel, and funded $375,000 each to develop robotic software and compete in the DARPA VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying process. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). <br />
<br />
Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying process, telling how narrow was that funnel. These Track C teams came from universities and research organizations located in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score at least once during the three days. The '''Br Robotics Team''' is glad to be skilled enough to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind of only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
{| border=1<br />
|+ '''DARPA Virtual Robotics Challenge Top Performers'''<br />
|- bgcolor="#DFDFDF" | <br />
! Ranking<br />
! Team Name<br />
! Track<br />
! Score<br />
! Country<br />
! Organization<br />
! Location<br />
|-<br />
! 1<br />
| Team IHMC<br />
| align="center" | B<br />
| align="center" | 52<br />
| align="center" | USA<br />
| IHMC - Florida Institute for Human & Machine Cognition<br />
| Pensacola, Florida<br />
|-<br />
! 2<br />
| WRECS<br />
| align="center" | C<br />
| align="center" | 39<br />
| align="center" | USA<br />
| WPI - Worcester Polytechnic Institute<br />
| Worcester, Massachusetts<br />
|-<br />
! 3<br />
| MIT<br />
| align="center" | B<br />
| align="center" | 34<br />
| align="center" | USA<br />
| MIT - Massachusetts Institute of Technology<br />
| Cambridge, Massachusetts<br />
|-<br />
! 4<br />
| Team TRACLabs<br />
| align="center" | B<br />
| align="center" | 30<br />
| align="center" | USA<br />
| TRACLabs, Inc.<br />
| Webster, Texas<br />
|-<br />
! 5<br />
| JPL / UCSB / Caltech<br />
| align="center" | B<br />
| align="center" | 29<br />
| align="center" | USA<br />
| NASA JPL - Jet Propulsion Laboratory (et al.)<br />
| Pasadena, California<br />
|-<br />
! 6<br />
| TORC / TU Darmstadt / Virginia Tech<br />
| align="center" | B<br />
| align="center" | 27<br />
| align="center" | USA<br />
| TORC Robotics, LLC (et al.)<br />
| Blacksburg, Virginia<br />
|-<br />
! 7<br />
| Team K<br />
| align="center" | C<br />
| align="center" | 25<br />
| align="center" | Japan<br />
| <br />
| <br />
|-<br />
! 8<br />
| TROOPER<br />
| align="center" | B<br />
| align="center" | 24<br />
| align="center" | USA<br />
| Lockheed Martin Corp.<br />
| Cherry Hill, New Jersey<br />
<br />
|-<br />
! 9<br />
| Team Case<br />
| align="center" | C<br />
| align="center" | 23<br />
| align="center" | USA<br />
| CWRU - Case Western Reserve University<br />
<br />
| Cleveland, Ohio<br />
|-<br />
! 10<br />
| Team Steel<br />
| align="center" | B<br />
| align="center" | 22<br />
| align="center" | USA<br />
<br />
| CMU - Carnegie Mellon University<br />
| Pittsburg, Pennsylvania<br />
|-<br />
! 11<br />
| Team ELEX<br />
| align="center" | C<br />
| align="center" | 21<br />
| align="center" | Japan<br />
| <br />
| <br />
|- <br />
! 12<br />
| '''Br Robotics Team'''<br />
| align="center" | C<br />
| align="center" | 16<br />
| align="center" | Brazil<br />
| '''UFES - Federal University of Espirito Santo''' (et al.)<br />
| Vitoria, Espirito Santo<br />
|}<br />
<br />
<br />
After all, what's the big deal about making a robot walk, drive and grasp things? Let's pick this big guy and give it another try!<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80732DARPA2013-07-05T07:04:58Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to belong to this two-digit-score club by reading the following tale. The U.S. Government invited 10 top-class teams from USA e one from Israel, and funded $375,000 each to develop robotic software and compete in the DARPA VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying process. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). <br />
<br />
Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying process, telling how narrow was that funnel. These Track C teams came from universities and research organizations located in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score at least once during the three days. The '''Br Robotics Team''' is glad to be skilled enough to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind of only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
{| border=1<br />
|+ '''DARPA VRC Top Performers'''<br />
|-<br />
! Ranking<br />
! Team Name<br />
! Track<br />
! Score<br />
! Country<br />
! Organization<br />
! Location<br />
|-<br />
! 1<br />
| Team IHMC<br />
| align="center" | B<br />
| align="center" | 52<br />
| align="center" | USA<br />
| IHMC - Florida Institute for Human & Machine Cognition<br />
| Pensacola, Florida<br />
|-<br />
! 2<br />
| WRECS<br />
| align="center" | C<br />
| align="center" | 39<br />
| align="center" | USA<br />
| WPI - Worcester Polytechnic Institute<br />
| Worcester, Massachusetts<br />
|-<br />
! 3<br />
| MIT<br />
| align="center" | B<br />
| align="center" | 34<br />
| align="center" | USA<br />
| MIT - Massachusetts Institute of Technology<br />
| Cambridge, Massachusetts<br />
|-<br />
! 4<br />
| Team TRACLabs<br />
| align="center" | B<br />
| align="center" | 30<br />
| align="center" | USA<br />
| TRACLabs, Inc.<br />
| Webster, Texas<br />
|-<br />
! 5<br />
| JPL / UCSB / Caltech<br />
| align="center" | B<br />
| align="center" | 29<br />
| align="center" | USA<br />
| NASA JPL - Jet Propulsion Laboratory (et al.)<br />
| Pasadena, California<br />
|-<br />
! 6<br />
| TORC / TU Darmstadt / Virginia Tech<br />
| align="center" | B<br />
| align="center" | 27<br />
| align="center" | USA<br />
| TORC Robotics, LLC (et al.)<br />
| Blacksburg, Virginia<br />
|-<br />
! 7<br />
| Team K<br />
| align="center" | C<br />
| align="center" | 25<br />
| align="center" | Japan<br />
| <br />
| <br />
|-<br />
! 8<br />
| TROOPER<br />
| align="center" | B<br />
| align="center" | 24<br />
| align="center" | USA<br />
| Lockheed Martin Corp.<br />
| Cherry Hill, New Jersey<br />
<br />
|-<br />
! 9<br />
| Team Case<br />
| align="center" | C<br />
| align="center" | 23<br />
| align="center" | USA<br />
| CWRU - Case Western Reserve University<br />
<br />
| Cleveland, Ohio<br />
|-<br />
! 10<br />
| Team Steel<br />
| align="center" | B<br />
| align="center" | 22<br />
| align="center" | USA<br />
<br />
| CMU - Carnegie Mellon University<br />
| Pittsburg, Pennsylvania<br />
|-<br />
! 11<br />
| Team ELEX<br />
| align="center" | C<br />
| align="center" | 21<br />
| align="center" | Japan<br />
| <br />
| <br />
|-<br />
! 12<br />
| Br Robotics Team<br />
| align="center" | C<br />
| align="center" | 16<br />
| align="center" | Brazil<br />
| bgcolor="#C0C0C0" | UFES - Federal University of Espirito Santo (et al.)<br />
| Vitoria, Espirito Santo<br />
|}<br />
<br />
After all, what's the big deal about making a robot walk, drive and grasp things? Let's pick this big guy and give it another try!<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80731DARPA2013-07-05T07:02:54Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to belong to this two-digit-score club by reading the following tale. The U.S. Government invited 10 top-class teams from USA e one from Israel, and funded $375,000 each to develop robotic software and compete in the DARPA VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying process. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). <br />
<br />
Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying process, telling how narrow was that funnel. These Track C teams came from universities and research organizations located in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score at least once during the three days. The '''Br Robotics Team''' is glad to be skilled enough to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind of only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
{| border=1<br />
|+ DARPA VRC Top Performers<br />
|-<br />
! Ranking<br />
! Team Name<br />
! Track<br />
! Score<br />
! Country<br />
! Organization<br />
! Location<br />
|-<br />
! 1<br />
| Team IHMC<br />
| align="center" | B<br />
| align="center" | 52<br />
| align="center" | USA<br />
| IHMC - Florida Institute for Human & Machine Cognition<br />
| Pensacola, Florida<br />
|-<br />
! 2<br />
| WRECS<br />
| align="center" | C<br />
| align="center" | 39<br />
| align="center" | USA<br />
| WPI - Worcester Polytechnic Institute<br />
| Worcester, Massachusetts<br />
|-<br />
! 3<br />
| MIT<br />
| align="center" | B<br />
| align="center" | 34<br />
| align="center" | USA<br />
| MIT - Massachusetts Institute of Technology<br />
| Cambridge, Massachusetts<br />
|-<br />
! 4<br />
| Team TRACLabs<br />
| align="center" | B<br />
| align="center" | 30<br />
| align="center" | USA<br />
| TRACLabs, Inc.<br />
| Webster, Texas<br />
|-<br />
! 5<br />
| JPL / UCSB / Caltech<br />
| align="center" | B<br />
| align="center" | 29<br />
| align="center" | USA<br />
| NASA JPL - Jet Propulsion Laboratory (et al.)<br />
| Pasadena, California<br />
|-<br />
! 6<br />
| TORC / TU Darmstadt / Virginia Tech<br />
| align="center" | B<br />
| align="center" | 27<br />
| align="center" | USA<br />
| TORC Robotics, LLC (et al.)<br />
| Blacksburg, Virginia<br />
|-<br />
! 7<br />
| Team K<br />
| align="center" | C<br />
| align="center" | 25<br />
| align="center" | Japan<br />
| <br />
| <br />
|-<br />
! 8<br />
| TROOPER<br />
| align="center" | B<br />
| align="center" | 24<br />
| align="center" | USA<br />
| Lockheed Martin Corp.<br />
| Cherry Hill, New Jersey<br />
<br />
|-<br />
! 9<br />
| Team Case<br />
| align="center" | C<br />
| align="center" | 23<br />
| align="center" | USA<br />
| CWRU - Case Western Reserve University<br />
<br />
| Cleveland, Ohio<br />
|-<br />
! 10<br />
| Team Steel<br />
| align="center" | B<br />
| align="center" | 22<br />
| align="center" | USA<br />
<br />
| CMU - Carnegie Mellon University<br />
| Pittsburg, Pennsylvania<br />
|-<br />
! 11<br />
| Team ELEX<br />
| align="center" | C<br />
| align="center" | 21<br />
| align="center" | Japan<br />
| <br />
| <br />
|-<br />
! 12<br />
| Br Robotics Team<br />
| align="center" | C<br />
| align="center" | 16<br />
| align="center" | Brazil<br />
| UFES - Federal University of Espirito Santo (et al.)<br />
| Vitoria, Espirito Santo<br />
|+ '''DARPA VRC Top Performers'''<br />
|}<br />
<br />
After all, what's the big deal about making a robot walk, drive and grasp things? Let's pick this big guy and give it another try!<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80730DARPA2013-07-05T06:57:01Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to belong to this two-digit-score club by reading the following tale. The U.S. Government invited 10 top-class teams from USA e one from Israel, and funded $375,000 each to develop robotic software and compete in the DARPA VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying process. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). <br />
<br />
Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying process, telling how narrow was that funnel. These Track C teams came from universities and research organizations located in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score at least once during the three days. The '''Br Robotics Team''' is glad to be skilled enough to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind of only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
{| border=1<br />
|+ DARPA VRC Top Performers<br />
|-<br />
! Ranking<br />
! Team Name<br />
! Track<br />
! Score<br />
! Country<br />
! Organization<br />
! Location<br />
|-<br />
! 1<br />
| Team IHMC<br />
| align="center" | B<br />
| align="center" | 52<br />
| align="center" | USA<br />
| IHMC - Florida Institute for Human & Machine Cognition<br />
| Pensacola, Florida<br />
|-<br />
! 2<br />
| WRECS<br />
| C<br />
| align="center" | 39<br />
| align="center" | USA<br />
| align="center" | WPI - Worcester Polytechnic Institute<br />
| Worcester, Massachusetts<br />
|-<br />
! 3<br />
| MIT<br />
| B<br />
| align="center" | 34<br />
| align="center" | USA<br />
| align="center" | MIT - Massachusetts Institute of Technology<br />
| Cambridge, Massachusetts<br />
|-<br />
! 4<br />
| Team TRACLabs<br />
| B<br />
| align="center" | 30<br />
| align="center" | USA<br />
| align="center" | TRACLabs, Inc.<br />
| Webster, Texas<br />
|-<br />
! 5<br />
| JPL / UCSB / Caltech<br />
| B<br />
| align="center" | 29<br />
| align="center" | USA<br />
| align="center" | NASA JPL - Jet Propulsion Laboratory (et al.)<br />
| Pasadena, California<br />
|-<br />
! 6<br />
| TORC / TU Darmstadt / Virginia Tech<br />
| B<br />
| align="center" | 27<br />
| align="center" | USA<br />
| align="center" | TORC Robotics, LLC (et al.)<br />
| Blacksburg, Virginia<br />
|-<br />
! 7<br />
| Team K<br />
| C<br />
| align="center" | 25<br />
| align="center" | Japan<br />
| align="center" | <br />
| <br />
|-<br />
! 8<br />
| TROOPER<br />
| align="center" | B<br />
| align="center" | 24<br />
| align="center" | USA<br />
| Lockheed Martin Corp.<br />
| Cherry Hill, New Jersey<br />
<br />
|-<br />
! 9<br />
| Team Case<br />
| align="center" | C<br />
| align="center" | 23<br />
| align="center" | USA<br />
| CWRU - Case Western Reserve University<br />
<br />
| Cleveland, Ohio<br />
|-<br />
! 10<br />
| Team Steel<br />
| align="center" | B<br />
| align="center" | 22<br />
| align="center" | USA<br />
<br />
| CMU - Carnegie Mellon University<br />
| Pittsburg, Pennsylvania<br />
|-<br />
! 11<br />
| Team ELEX<br />
| align="center" | C<br />
| align="center" | 21<br />
| align="center" | Japan<br />
| <br />
| <br />
|-<br />
! 12<br />
| Br Robotics Team<br />
| align="center" | C<br />
| align="center" | 16<br />
| align="center" | Brazil<br />
| UFES - Federal University of Espirito Santo (et al.)<br />
| Vitoria, Espirito Santo<br />
|}<br />
<br />
After all, what's the big deal about making a robot walk, drive and grasp things? Let's pick this big guy and give it another try!<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80729DARPA2013-07-05T06:55:08Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to belong to this two-digit-score club by reading the following tale. The U.S. Government invited 10 top-class teams from USA e one from Israel, and funded $375,000 each to develop robotic software and compete in the DARPA VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying process. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). <br />
<br />
Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying process, telling how narrow was that funnel. These Track C teams came from universities and research organizations located in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score at least once during the three days. The '''Br Robotics Team''' is glad to be skilled enough to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind of only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
{| border=1<br />
|+ DARPA VRC Top Performers<br />
|-<br />
! Ranking<br />
! Team Name<br />
! Track<br />
! Score<br />
! Country<br />
! Organization<br />
! Location<br />
|-<br />
! 1<br />
| Team IHMC<br />
| align="center" | B<br />
| align="center" | 52<br />
| align="center" | USA<br />
| IHMC - Florida Institute for Human & Machine Cognition<br />
| Pensacola, Florida<br />
|-<br />
! 2<br />
| WRECS<br />
| C<br />
| align="center" | 39<br />
| align="center" | USA<br />
| align="center" | WPI - Worcester Polytechnic Institute<br />
| Worcester, Massachusetts<br />
|-<br />
! 3<br />
| MIT<br />
| B<br />
| align="center" | 34<br />
| align="center" | USA<br />
| align="center" | MIT - Massachusetts Institute of Technology<br />
| Cambridge, Massachusetts<br />
|-<br />
! 4<br />
| Team TRACLabs<br />
| B<br />
| align="center" | 30<br />
| align="center" | USA<br />
| align="center" | TRACLabs, Inc.<br />
| Webster, Texas<br />
|-<br />
! 5<br />
| JPL / UCSB / Caltech<br />
| B<br />
| align="center" | 29<br />
| align="center" | USA<br />
| align="center" | NASA JPL - Jet Propulsion Laboratory (et al.)<br />
| Pasadena, California<br />
|-<br />
! 6<br />
| TORC / TU Darmstadt / Virginia Tech<br />
| B<br />
| align="center" | 27<br />
| align="center" | USA<br />
| align="center" | TORC Robotics, LLC (et al.)<br />
| Blacksburg, Virginia<br />
|-<br />
! 7<br />
| Team K<br />
| C<br />
| align="center" | 25<br />
| align="center" | Japan<br />
| align="center" | <br />
| <br />
|-<br />
! 8<br />
| TROOPER<br />
| align="center" | B<br />
| align="center" | 24<br />
| align="center" | USA<br />
| Lockheed Martin Corp.<br />
| Cherry Hill, New Jersey<br />
<br />
|-<br />
! 9<br />
| Team Case<br />
| align="center" | C<br />
| align="center" | 23<br />
| align="center" | USA<br />
| CWRU - Case Western Reserve University<br />
<br />
| Cleveland, Ohio<br />
|-<br />
! 10<br />
| Team Steel<br />
| align="center" | B<br />
| align="center" | 22<br />
| align="center" | USA<br />
<br />
| CMU - Carnegie Mellon University<br />
| Pittsburg, Pennsylvania<br />
|-<br />
! 11<br />
| Team ELEX<br />
| align="center" | C<br />
| align="center" | 21<br />
| align="center" | Japan<br />
| <br />
| <br />
|-<br />
! 12<br />
| Br Robotics Team<br />
| align="center" | C<br />
| align="center" | 16<br />
| align="center" | Brazil<br />
| UFES - Federal University of Espirito Santo (et al.)<br />
| Vitoria, Espirito Santo<br />
|}<br />
<br />
What's the big deal about making a robot walk, drive and grasp things, anyway? Let's pick this guy and give it another try!<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80728DARPA2013-07-05T06:53:42Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to belong to this two-digit-score club by reading the following tale. The U.S. Government invited 10 top-class teams from USA e one from Israel, and funded $375,000 each to develop robotic software and compete in the DARPA VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying process. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). <br />
<br />
Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying process, telling how narrow was that funnel. These Track C teams came from universities and research organizations located in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score at least once during the three days. The '''Br Robotics Team''' is glad to be skilled enough to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind of only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
{| border=1<br />
|+ DARPA VRC Top Performers<br />
|-<br />
! Ranking<br />
! Team Name<br />
! Track<br />
! Score<br />
! Country<br />
! Organization<br />
! Location<br />
|-<br />
! 1<br />
| Team IHMC<br />
| align="center" | B<br />
| align="center" | 52<br />
| align="center" | USA<br />
| IHMC - Florida Institute for Human & Machine Cognition<br />
| Pensacola, Florida<br />
|-<br />
! 2<br />
| WRECS<br />
| C<br />
| align="center" | 39<br />
| align="center" | USA<br />
| align="center" | WPI - Worcester Polytechnic Institute<br />
| Worcester, Massachusetts<br />
|-<br />
! 3<br />
| MIT<br />
| B<br />
| align="center" | 34<br />
| align="center" | USA<br />
| align="center" | MIT - Massachusetts Institute of Technology<br />
| Cambridge, Massachusetts<br />
|-<br />
! 4<br />
| Team TRACLabs<br />
| B<br />
| align="center" | 30<br />
| align="center" | USA<br />
| align="center" | TRACLabs, Inc.<br />
| Webster, Texas<br />
|-<br />
! 5<br />
| JPL / UCSB / Caltech<br />
| B<br />
| align="center" | 29<br />
| align="center" | USA<br />
| align="center" | NASA JPL - Jet Propulsion Laboratory (et al.)<br />
| Pasadena, California<br />
|-<br />
! 6<br />
| TORC / TU Darmstadt / Virginia Tech<br />
| B<br />
| align="center" | 27<br />
| align="center" | USA<br />
| align="center" | TORC Robotics, LLC (et al.)<br />
| Blacksburg, Virginia<br />
|-<br />
! 7<br />
| Team K<br />
| C<br />
| align="center" | 25<br />
| align="center" | Japan<br />
| align="center" | <br />
| <br />
! 8<br />
| TROOPER<br />
| align="center" | B<br />
| align="center" | 24<br />
| align="center" | USA<br />
| Lockheed Martin Corp.<br />
| Cherry Hill, New Jersey<br />
<br />
|-<br />
! 9<br />
| Team Case<br />
| align="center" | C<br />
| align="center" | 23<br />
| align="center" | USA<br />
| CWRU - Case Western Reserve University<br />
<br />
| Cleveland, Ohio<br />
|-<br />
! 10<br />
| Team Steel<br />
| align="center" | B<br />
| align="center" | 22<br />
| align="center" | USA<br />
<br />
| CMU - Carnegie Mellon University<br />
| Pittsburg, Pennsylvania<br />
|-<br />
! 11<br />
| Team ELEX<br />
| align="center" | C<br />
| align="center" | 21<br />
| align="center" | Japan<br />
| <br />
| <br />
|-<br />
! 12<br />
| Br Robotics Team<br />
| align="center" | C<br />
| align="center" | 16<br />
| align="center" | Brazil<br />
| UFES - Federal University of Espirito Santo (et al.)<br />
| Vitoria, Espirito Santo<br />
|}<br />
<br />
What's the big deal about making a robot walk, drive and grasp things, anyway? Let's pick this guy and give it another try!<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80727DARPA2013-07-05T06:29:44Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to belong to this two-digit-score club by reading the following tale. The U.S. Government invited 10 top-class teams from USA e one from Israel, and funded $375,000 each to develop robotic software and compete in the DARPA VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying process. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). <br />
<br />
Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying process, telling how narrow was that funnel. These Track C teams came from universities and research organizations located in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score at least once during the three days. The '''Br Robotics Team''' is glad to be skilled enough to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind of only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
{| border=1<br />
|+ DARPA VRC Top Performers<br />
<br />
|}<br />
<br />
What's the big deal about making a robot walk, drive and grasp things, anyway? Let's pick this guy and give it another try!<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80726DARPA2013-07-05T06:28:51Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to belong to this two-digit-score club by reading the following tale. The U.S. Government invited 10 top-class teams from USA e one from Israel, and funded $375,000 each to develop robotic software and compete in the DARPA VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying process. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). <br />
<br />
Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying process, telling how narrow was that funnel. These Track C teams came from universities and research organizations located in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score at least once during the three days. The '''Br Robotics Team''' is glad to be skilled enough to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind of only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
{| border=1<br />
|+ DARPA VRC Top Performers<br />
<br />
|}<br />
<br />
What's the big deal about making a robot walk, drive and grasp things, anyway? Let's pick this guy and give it a try!<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80725DARPA2013-07-05T06:27:23Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to belong to this two-digit-score club by reading the following tale. The U.S. Government invited 10 top-class teams from USA e one from Israel, and funded $375,000 each to develop robotic software and compete in the DARPA VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying process. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). <br />
<br />
Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying process, telling how narrow was that funnel. These Track C teams came from universities and research organizations located in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score at least once during the three days. The '''Br Robotics Team''' is glad to be skilled enough to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind of only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
{| border=1<br />
|+ DARPA VRC Top Performers<br />
<br />
|}<br />
<br />
What's the big deal about making a robot walk, drive and grasp things, anyway? Why don't you pick this guy and give a try?<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80724DARPA2013-07-05T06:15:44Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to belong to this two-digit-score club by reading the following tale. The U.S. Government invited 10 top-class teams from USA e one from Israel, and funded $375,000 each to develop robotic software and compete in DARPA's VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying process. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). <br />
<br />
Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying process, telling how narrow was that funnel. These Track C teams came from universities and research organizations located in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score at least once during the three days. The '''Br Robotics Team''' is glad to be skilled enough to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind of only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80723DARPA2013-07-05T05:19:29Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to belong to this two-digit-score club by reading the following tale. The U.S. Government invited 10 top-class teams from USA e one from Israel, and funded $375,000 each to develop robotic software and compete in DARPA's VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying process. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). <br />
<br />
Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying process, telling how narrow was that funnel. These Track C teams came from universities and research organizations located in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score at least once during the three days. The '''Br Robotics Team''' is glad to be skilled enough to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80722DARPA2013-07-05T05:14:59Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to join this smart club by reading the following tale. The U.S. Government invited 10 top-class teams from USA e one from Israel, and funded $375,000 each to develop robotic software and compete in DARPA's VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying process. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). <br />
<br />
Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying process, telling how narrow was that funnel. These Track C teams came from universities and research organizations located in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score at least once during the three days. The '''Br Robotics Team''' is glad to be skilled enough to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80721DARPA2013-07-05T05:09:31Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to join this smart club by reading the following tale. The U.S. Government invited 10 top-class teams from USA e one from Israel, and funded $375,000 each to develop robotic software and compete in DARPA's VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying process. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying process, telling how narrow was that funnel. These Track C teams came from universities and research organizations located in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score at least once during the three days. The '''Br Robotics Team''' is glad to be skilled enough to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80720DARPA2013-07-05T05:08:54Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to join this smart club by reading the following tale. The U.S. Government invited 10 top-class teams from USA e one from Israel, and funded $375,000 each to develop robotic software and compete in DARPA's VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying process. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying process, telling how narrow was that funnel. These Track C teams came from universities and research organizations in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score at least once during the three days. The '''Br Robotics Team''' is glad to be skilled enough to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80719DARPA2013-07-05T05:05:49Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to join this smart club by reading the following tale. The U.S. Government invited 10 top-class teams from USA e one from Israel, and funded $375,000 each to develop robotic software and compete in DARPA's VRC. They were tagged Track B teams. Eventually only 10 Track B teams were successful in the qualifying process. These teams came from high-tech companies (Lockheed Martin, TRAC Labs, TORC Robotics, RE2), top-class universities (MIT, Carnegie Mellon, Washington, Ben-Gurion) and advanced research centers (NASA JPL, Florida IHMC). Over 100 non-funded teams had applied for the VRC competition, and they were tagged Track C teams. Only 16 Track C teams were successful in the qualifying process, and this tells how narrow was the funnel. These Track C teams came from universities and research organizations in USA and six other countries: Japan, UK, Spain, Poland, Brazil and Mexico. After a few weeks the 26 teams met at the VRC three-day competition, and tested their skills in simulated robotic locomotion and dexterity. The tasks were so hard that 4 out of the 26 qualified teams were unable to score at least once during the three days. The '''Br Robotics Team''' is glad to be skilled enough to score 16 times. Another remarkable achievement of our team is to overmatch the performance of 3 Track B funded teams. We ranked #5 out of the 16 Track C teams, standing behind only a couple of teams from USA and Japan. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80718DARPA2013-07-05T04:44:28Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to join this smart club by reading the tale: <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80717DARPA2013-07-05T04:44:01Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to join this smart club by reading the tale: <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC final scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the VRC Press Release])<br />
<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80716DARPA2013-07-05T03:14:30Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to join this smart club by reading the tale: <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC final scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See DARPA's media release])<br />
<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80715DARPA2013-07-05T03:06:40Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition! The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. One can tell how tough is to get in this selected group by reading the tale: <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC final scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See DARPA's media release])<br />
<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80714DARPA2013-07-05T02:59:51Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition. The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC final scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See DARPA's media release])<br />
<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80713DARPA2013-07-05T02:59:03Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition. The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See DARPA's media release])<br />
<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80712DARPA2013-07-05T02:56:08Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition. The '''Br Robotics Team''' ranked #12 out of the 26 qualifiers. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the DRC Trials announcement])<br />
<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80711DARPA2013-07-05T02:55:06Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) ran from June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
The guys from Brazil did great in the VRC competition. The '''Br Robotics Team''' ranked <br />
<br />
#12 out of the 26 qualifiers. <br />
<br />
([http://www.theroboticschallenge.com/local/documents/Scoreboard%20Final.pdf See the VRC <br />
<br />
Final Scoreboard])<br />
<br />
([http://www.darpa.mil/NewsEvents/Releases/2013/06/27.aspx See the DRC Trials <br />
<br />
announcement])<br />
<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80710DARPA2013-07-05T01:04:38Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) was run on June 18-20, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final).<br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80709DARPA2013-07-05T00:24:28Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) is scheduled for June 17-28, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final). <br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing a VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing a VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
<br />
== '''Our achievements''' ==<br />
<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80708DARPA2013-07-05T00:21:50Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) is scheduled for June 17-28, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final). <br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
[[imagem:atlas.jpg|80px|]]<br />
<br />
<br />
== '''Our achievements''' ==</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=DARPA&diff=80695DARPA2013-06-15T03:07:19Z<p>Raphael Carneiro: </p>
<hr />
<div><br />
<big><big><big>'''DARPA Robotics Challenge'''</big></big></big><br />
<br />
== '''What is DARPA?''' ==<br />
The Defense Advanced Research Projects Agency [http://www.darpa.mil (DARPA)] is the U.S. Department of Defense [http://www.defense.gov (DoD)] 's primary innovation engine. The Agency undertakes projects and scientific investigations aiming to create innovative technologies that address current practical problems. One of the focus areas of DARPA's Tactical Technology Office [http://www.darpa.mil/our_work/TTO (TTO)] is the development of [http://www.darpa.mil/Our_Work/TTO/Focus_Areas/AdvancedPlatforms.aspx unmanned systems] to improve navigation in dynamic conditions, extend range and endurance, and increase adaptive autonomous operations. The DARPA Robotics Challenge [http://www.darpa.mil/Our_Work/TTO/Programs/DARPA_Robotics_Challenge.aspx (DRC)] is all about that.<br />
<br />
<br />
== '''What is the DARPA Robotics Challenge?''' ==<br />
Some natural or man-made disasters, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great for timely and effective human response. The DARPA Robotics Challenge (DRC) intends to extend humanitarian aid to victims of disasters by promoting innovation in robotic technology for disaster-response operations.<br />
<br />
The primary technical goal of the DRC is to develop ground robots capable of executing complex tasks in dangerous, degraded, human-engineered environments. Competitors in the DRC are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.<br />
<br />
{| border=0<br />
| align="center" | [[imagem:atlas_robot.jpg|border|center|250px|Boston Dynamics Atlas robot]]<br />
| align="center" | [[imagem:drc_tasks.jpg|border|center|650px|Robots performing some DRC tasks]]<br />
|-<br />
| align="center" | Boston Dynamics Atlas robot<br />
| align="center" | Robots performing some DRC tasks<br />
|}<br />
<br />
The robot competitions will comprise eight tasks:<br />
# Enter an utility vehicle, drive it on a road, and exit the vehicle.<br />
# Travel dismounted across a terrain ranging from smooth and level, to rough with some loose rocks.<br />
# Remove objects blocking an entryway.<br />
# Open a door and enter a building.<br />
# Climb industrial ladder or stairs or walkway.<br />
# Use a power tool to break through a wall.<br />
# Locate and close a valve.<br />
# Connect a cable or hose.<br />
<br />
<br />
The DRC kicked off on October 24, 2012, and has three planned competitions: one virtual followed by two live. The first competition, the Virtual Robotics Challenge (VRC) is scheduled for June 17-28, 2013. The real robot competitions are planned for December 2013 (DRC Trials) and December 2014 (DRC Final). <br />
<br />
{| border=0<br />
| align="center" | [[imagem:vrc_tasks.jpg|border|center|570px|Robot performing VRC task in Gazebo simulator]]<br />
|-<br />
| align="center" | Robot performing VRC task in Gazebo simulator<br />
|}<br />
<br />
The VRC competition will comprise three tasks using [http://gazebosim.org Gazebo] robot simulator:<br />
# Walk a short distance, climb into a utility vehicle, drive along a roadway, climb out of the utility vehicle, and walk to the finish area. <br />
# Walk across progressively more difficult terrain. Some perception and footstep planning are expected. <br />
# Connect a hose to a spigot and open the spigot by way of turning a valve.<br />
<br />
<br />
The top 6 performers in the VRC competition will be funded by DARPA up to US$750,000 each and will receive a [http://www.bostondynamics.com/robot_Atlas.html Boston Dynamics Atlas] robot for the DRC competitions. The top 8 performers in 2013 DRC Trials will be funded by DARPA up to one million dollars each. The 2014 DRC Final winner will be awarded a two million dollar prize.<br />
<br />
([http://www.theroboticschallenge.com See the DARPA Robotics Challenge details])<br />
<br />
<br />
== '''Our team''' ==<br />
The '''Br Robotics Team''' is very proud to be one of the 26 teams in the world who were qualified for the VRC competition. Our competitors could not have better reputation: NASA, MIT, Carnegie Mellon... [http://www.theroboticschallenge.com/meet.aspx#vrcteams (see the qualifier list)]. The team is lead by [http://www.lcad.inf.ufes.br/team/index.php/Dr._Alberto_Ferreira_De_Souza Dr. Alberto Ferreira De Souza] from the High Performance Computing Laboratory [http://www.lcad.inf.ufes.br (LCAD)] of the Federal University of Espirito Santo [http://www.ufes.br (UFES)]. The LCAD/UFES lab is located in the [http://en.wikipedia.org/wiki/Vit%C3%B3ria,_Esp%C3%ADrito_Santo city of Vitoria], Brazil, and congregates several professors and students working on artificial vision, face recognition, autonomous vehicles and humanoid robot researches. The Br Robotics Team unites experts from multiple Brazilian universities: [http://www.ufes.br UFES], [http://www.poli.usp.br EPUSP], [http://www.icmc.usp.br ICMC/USP], [http://www.eesc.usp.br/portaleesc/en EESC/USP], [http://www.ufmg.br/english UFMG], [http://portal.fei.edu.br/en-US FEI] and the innovation and technology company [http://www.mogai.com.br/en MOGAI].<br />
<br />
([[Br_Robotics_Team|See '''Br Robotics Team''' member list]])<br />
<br />
([[Equipe|See '''LCAD/UFES''' member list]])<br />
<br />
{| border=0<br />
| align="center" | [[imagem:lcad_team.jpg|border|center|500px|LCAD/UFES team and IARA autonomous vehicle]]<br />
| align="center" | [[imagem:autonomous_vehicle_iara.jpg|border|center|441px|IARA autonomously driving around UFES campus]]<br />
|-<br />
| align="center" | LCAD/UFES team and IARA autonomous vehicle<br />
| align="center" | IARA autonomously driving around UFES campus<br />
|}<br />
<br />
<br />
== '''Our approach''' ==<br />
{| border=0<br />
| align="center" | [[imagem:drc_sra.jpg|border|center|750px|SRA - Autonomous Robotic System]]<br />
|-<br />
| align="center" | SRA - Autonomous Robotic System<br />
|}<br />
<br />
The above figure shows the Autonomous Robotic System (SRA) architecture with two computer systems: the Remote Robot Operation System (CSR) and the Robot User System (CUR). The CSR is a high-performance computing system running the code responsible for the robot supervision. The CUR is part of the robot and performs basic control and sensor reading. SRA has the following subsystems:<br />
# Human-Machine Interface Subsystem - responsible for translating CSR’s internal representation of the surrounding environment to something manageable by a non-expert human operator, and translating high-level commands from the operator back to CSR’s Control Subsystem.<br />
# High-Level Robot Control & Predictive State Subsystem - responsible for creating the CSR’s internal representation of the surrounding environment, and predicting the effects to the robot and to its surrounding world, caused by the human operator commands.<br />
# Robot Sensing Subsystem - responsible for providing a high-level interface with the given robot sensor drivers.<br />
# Robot Control Subsystem - responsible for providing a high-level interface with the given robot control system.<br />
<br />
<br />
Since we aim to develop robotic supervised autonomy, our approach mixes some artificial neural networks and some 100-billion-neuron "carbon-based units"... [http://www.imdb.com/title/tt0079945/synopsis (quoting Star Trek)] Hopefully our "Br" carbon-based units will not "infest" the robotic system! :-)<br />
<br />
[[imagem:atlas.jpg|80px|]]</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=Equipe&diff=80694Equipe2013-06-14T22:08:03Z<p>Raphael Carneiro: </p>
<hr />
<div>__TOC__<br />
<br />
==Researchers==<br />
<br />
* Dr. Alberto Ferreira De Souza (Coordinator)<br />
* Dr. Andrea Maria Pedrosa Valli<br />
* Dr. Claudine Badue<br />
* Dr. Edilson de Aguiar<br />
* Dr. Elias Oliveira<br />
* Dr. Fabio Daros Freitas <br />
* Dr. Lucia Catabriga<br />
* Dr. Maria Claudia Silva Boeres<br />
* Dr. Maria Cristina Rangel<br />
* Dr. Thiago Oliveira dos Santos <br />
<br />
==Phd Students==<br />
<br />
* Avelino Forechi<br />
* Lucas de Paula Veronese<br />
* Mariella Berger<br />
<br />
==Masters Students==<br />
<br />
* Cayo Fontana<br />
* Filipe Wall Mutz<br />
* Lauro Jose Lyrio Junior<br />
* Michael André Goncalves<br />
* Romulo Ramos Radaelli<br />
* [http://www.lcad.inf.ufes.br/~toliveira Tiago Alves de Oliveira]<br />
* Vitor Barbirato<br />
<br />
==Graduate Students==<br />
<br />
* Lucas Catabriga<br />
* Ranick Guidolini</div>Raphael Carneirohttp://www.lcad.inf.ufes.br/wiki/index.php?title=Equipe&diff=80693Equipe2013-06-14T22:07:20Z<p>Raphael Carneiro: </p>
<hr />
<div>__TOC__<br />
<br />
==Researchers==<br />
<br />
* Dr. Alberto Ferreira De Souza (Coordinator)<br />
* Dr. Andrea Maria Pedrosa Valli<br />
* Dr. Claudine Badue<br />
* Dr. Edilson de Aguiar<br />
* Dr. Elias Oliveira<br />
* Dr. Fabio Daros Freitas <br />
* Dr. Lucia Catabriga<br />
* Dr. Maria Cristina Rangel<br />
* Dr. Maria Claudia Silva Boeres<br />
* Dr. Thiago Oliveira dos Santos <br />
<br />
==Phd Students==<br />
<br />
* Avelino Forechi<br />
* Lucas de Paula Veronese<br />
* Mariella Berger<br />
<br />
==Masters Students==<br />
<br />
* Cayo Fontana<br />
* Filipe Wall Mutz<br />
* Lauro Jose Lyrio Junior<br />
* Michael André Goncalves<br />
* Romulo Ramos Radaelli<br />
* [http://www.lcad.inf.ufes.br/~toliveira Tiago Alves de Oliveira]<br />
* Vitor Barbirato<br />
<br />
==Graduate Students==<br />
<br />
* Lucas Catabriga<br />
* Ranick Guidolini</div>Raphael Carneiro