Baxter Pick and Place using GR-ConvNet. IROS 2020.
This repository contains the implementation of the control module from the paper:
Sulabh Kumra, Shirin Joshi, Ferat Sahin
If you use this project in your research or wish to refer to the baseline results published in the paper, please use the following BibTeX entry:
@article{kumra2019antipodal,
title={Antipodal Robotic Grasping using Generative Residual Convolutional Neural Network},
author={Kumra, Sulabh and Joshi, Shirin and Sahin, Ferat},
journal={arXiv preprint arXiv:1909.04810},
year={2019}
}
$ sudo apt-get install python-wstool python-rosdep
$ mkdir -p ~/ros_ws/src
$ cd ~/ros_ws/src
$ wstool init .
$ wstool merge https://raw.github.com/RethinkRobotics/baxter/master/baxter_sdk.rosinstall
$ wstool update
$ cd ..
This pulls down the development branches from all of our repositories into your source directory.
For Baxter Gazebo simulation, checkout the baxter_simulator repository:
$ cd ~/ros_ws/src
$ git clone https://github.com/RethinkRobotics/baxter_simulator.git
$ cd ~/ros_ws/src
$ git clone https://github.com/skumra/baxter-pnp.git
$ source /opt/ros/kinetic/setup.bash
$ cd ~/ros_ws
$ catkin_make
$ catkin_make install
$ cp src/baxter/baxter.sh .
$ cd ~/ros_ws
$ ./baxter.sh sim
$ roslaunch baxter_gazebo baxter_world.launch
$ cd ~/ros_ws
$ source devel/setup.bash
$ rosrun baxter-pnp run_pnp.py
$ cd ~/ros_ws
$ ./baxter.sh
$ cd ~/ros_ws
$ source devel/setup.bash
$ rosrun baxter-pnp run_pnp.py