Daniele1209 / Swarm-Behavior-in-Multi-Agent-Drone-Systems

Using Multiagent Reinforcement Learning in PyBullet Gym environments for Drone Swarm behavior

gym-pybullet-drones

This is a (minimalist) refactoring of the original gym-pybullet-drones repository, designed for compatibility with gymnasium and stable-baselines3 2.0.

Installation

git clone https://github.com/utiasDSL/gym-pybullet-drones.git
cd gym-pybullet-drones/

conda create -n drones python=3.10
conda activate drones

pip3 install --upgrade pip
pip3 install -e .

At the time of writing, stable-baselines3 2.0's alpha can be installed from PyPI

pip3 install "sb3_contrib>=2.0.0a1" --upgrade
pip3 install "stable_baselines3>=2.0.0a1" --upgrade

Use

PID position control example

cd gym_pybullet_drones/examples/
python3 pid.py

PPO RL example

cd gym_pybullet_drones/examples/
python3 learn.py

Betaflight SITL example

In one terminal, run the Betaflight SITL binary

git clone  https://github.com/betaflight/betaflight
cd betaflight/
make TARGET=SITL # comment out this line: https://github.com/betaflight/betaflight/blob/c41b458e5891205da50465caeec0c1aa83beeb0c/src/main/main.c#L52
betaflight/obj/main/betaflight_SITL.elf

In another terminal, run the example

cd gym_pybullet_drones/examples/
python3 beta.py

Troubleshooting

• On Ubuntu, with an NVIDIA card, if you receive a "Failed to create and OpenGL context" message, launch nvidia-settings and under "PRIME Profiles" select "NVIDIA (Performance Mode)", reboot and try again.

Citation

If you wish, please cite our IROS 2021 paper as

@INPROCEEDINGS{panerati2021learning,
      title={Learning to Fly---a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Control}, 
      author={Jacopo Panerati and Hehui Zheng and SiQi Zhou and James Xu and Amanda Prorok and Angela P. Schoellig},
      booktitle={2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
      year={2021},
      volume={},
      number={},
      pages={7512-7519},
      doi={10.1109/IROS51168.2021.9635857}
}

References

• Nathan Michael, Daniel Mellinger, Quentin Lindsey, Vijay Kumar (2010) The GRASP Multiple Micro UAV Testbed
• Benoit Landry (2014) Planning and Control for Quadrotor Flight through Cluttered Environments
• Julian Forster (2015) System Identification of the Crazyflie 2.0 Nano Quadrocopter
• Carlos Luis and Jeroome Le Ny (2016) Design of a Trajectory Tracking Controller for a Nanoquadcopter
• Shital Shah, Debadeepta Dey, Chris Lovett, and Ashish Kapoor (2017) AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles
• Eric Liang, Richard Liaw, Philipp Moritz, Robert Nishihara, Roy Fox, Ken Goldberg, Joseph E. Gonzalez, Michael I. Jordan, and Ion Stoica (2018) RLlib: Abstractions for Distributed Reinforcement Learning
• Antonin Raffin, Ashley Hill, Maximilian Ernestus, Adam Gleave, Anssi Kanervisto, and Noah Dormann (2019) Stable Baselines3
• Guanya Shi, Xichen Shi, Michael O’Connell, Rose Yu, Kamyar Azizzadenesheli, Animashree Anandkumar, Yisong Yue, and Soon-Jo Chung (2019) Neural Lander: Stable Drone Landing Control Using Learned Dynamics
• Mikayel Samvelyan, Tabish Rashid, Christian Schroeder de Witt, Gregory Farquhar, Nantas Nardelli, Tim G. J. Rudner, Chia-Man Hung, Philip H. S. Torr, Jakob Foerster, and Shimon Whiteson (2019) The StarCraft Multi-Agent Challenge
• C. Karen Liu and Dan Negrut (2020) The Role of Physics-Based Simulators in Robotics
• Yunlong Song, Selim Naji, Elia Kaufmann, Antonio Loquercio, and Davide Scaramuzza (2020) Flightmare: A Flexible Quadrotor Simulator

TODO

• IMU transforms in Betaflight SITL example
• Flatten dict observations/action into np.arrays (with wrapper?)
• Replace aggregate_phy_steps with simulation and control frequencies
• Add motor delay
• Replace rpy with quaternions and ang_vel with body rates
• Replace BaseSingleAgentAviary and BaseMultiAgentAviary with RLAviary
• Add pointer in README.md to the original master branch
• Add yaml configuration files
• Add stable-baselines3 2.0 support/examples
• Add pytests/GitHub Action for learning examples
• Add cffirmware SITL support

---

University of Toronto's Dynamic Systems Lab / Vector Institute / University of Cambridge's Prorok Lab