RobinGas Mission Gazebo

GPS-IMU navigation pipeline with Traversability Estimation and OSM data usage for Path Planning tested in Gazebo simulator.

RobinGas pipeline in Gazebo simulator, video, currently including:

• Husky robot gazebo model with sensors (including Ouster LiDAR Gazebo Plugin with GPU ray),
• Fused localization,
• Traversability estimation,
• Path planner,
• Path follower,
• Obstacle avoidance (virtual bumper).

Installation

The navigation pipeline is currently tested in simulator with Husky robot only.

• Install ROS navigation stack and Husky related packages:

  sudo apt-get install ros-$ROS_DISTRO-navigation

  Install husky simulation, reference:

  sudo apt-get install ros-$ROS_DISTRO-husky-*
  echo "export HUSKY_GAZEBO_DESCRIPTION=$(rospack find husky_gazebo)/urdf/description.gazebo.xacro" >> ~/.bashrc
  source ~/.bashrc

• Configure ROS workspace. Download the package and its dependencies and build individual packages listed above.

  ws=~/catkin_ws/
  mkdir -p "${ws}/src"
  cd "${ws}/src"
  
  git clone https://github.com/ctu-vras/husky_nav -b robingas
  
  wstool init
  wstool merge husky_nav/dependencies.rosinstall
  wstool up -j 4
  
  cd "${ws}"
  catkin init
  catkin config --extend /opt/ros/$ROS_DISTRO/
  catkin config --cmake-args -DCMAKE_BUILD_TYPE=Release
  catkin build -c

• Download relevant Gazebo models used in the virtual worlds and place them to $HOME/.gazebo/models/ folder.

RobinGas Navigation Pipeline

Start Gazebo simulator with Husky robot spawned:

roslaunch husky_nav husky_gazebo.launch

Launch navigation pipeline:

roslaunch husky_nav navigation.launch rviz:=true

Citation

The traversability estimation method is described in the following paper:

@ARTICLE{9699042,
  author={Agishev, Ruslan and Petříček, Tomáš and Zimmermann, Karel},
  journal={IEEE Robotics and Automation Letters},
  title={Trajectory Optimization Using Learned Robot-Terrain Interaction Model in Exploration of Large Subterranean Environments},
  year={2022},
  volume={7},
  number={2},
  pages={3365-3371},
  doi={10.1109/LRA.2022.3147332}
}