RPZ Planning (RA-L 2022 with ICRA option)

Demo

This is a quick-start section, which describes how to use the rpz_planner as a stand-alone package without installation of the entire exploration pipeline. If you would like to explore, how the trajectory optimization works using a prerecorded data (as a ROS bag-file), please, follow the instructions in docs/demo.md.

Prerequisites

• Singularity
• DARPA Subt simulator
• Exloration pipeline

Exploration with trajectory optimization

Start the simulator using the simgularity image cloudsim.simg:

cd ~/subt_virtual/scripts/
SUBT_USE_SINGULARITY=1 SUBT_ROBOT_TEAM=x1x2 ./run_sim worldName:=simple_cave_01

Run the ROS-bridge to the simulator:

cd ~/subt_virtual/scripts/
SUBT_USE_SINGULARITY=1 SUBT_ROBOT_TEAM=x1x2 ./run_bridge_all worldName:=simple_cave_01

Run exploration pipeline (naex) with local trajectory optimization:

roslaunch rpz_planning naex.launch follow_opt_path:=true

Reference

Trajectory Optimization using Learned Robot-Terrain Interaction Model in Exploration of Large Subterranean Environments

@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}
}