PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
MIT License
This is a minimalist refactoring of the original gym-pybullet-drones
repository, designed for compatibility with gymnasium
, stable-baselines3
2.0, and SITL betaflight
/crazyflie-firmware
.
NOTE: if you prefer to access the original codebase, presented at IROS in 2021, please
git checkout [paper|master]
after cloning the repo, and refer to the correspondingREADME.md
's.
Tested on Intel x64/Ubuntu 22.04 and Apple Silicon/macOS 14.1.
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 . # if needed, `sudo apt install build-essential` to install `gcc` and build `pybullet`
cd gym_pybullet_drones/examples/
python3 pid.py # position and velocity reference
python3 pid_velocity.py # desired velocity reference
cd gym_pybullet_drones/examples/
python3 downwash.py
cd gym_pybullet_drones/examples/
python learn.py # task: single drone hover at z == 1.0
python learn.py --multiagent true # task: 2-drone hover at z == 1.2 and 0.7
pycffirmware
Python Bindings example (multiplatform, single-drone)Install pycffirmware
for Ubuntu, macOS, or Windows
cd gym_pybullet_drones/examples/
python3 cff-dsl.py
git clone https://github.com/betaflight/betaflight # use the `master` branch at the time of writing (future release 4.5)
cd betaflight/
make arm_sdk_install # if needed, `apt install curl``
make TARGET=SITL # comment out line: https://github.com/betaflight/betaflight/blob/master/src/main/main.c#L52
cp ~/gym-pybullet-drones/gym_pybullet_drones/assets/eeprom.bin ~/betaflight/ # assuming both gym-pybullet-drones/ and betaflight/ were cloned in ~/
betaflight/obj/main/betaflight_SITL.elf
In another terminal, run the example
conda activate drones
cd gym_pybullet_drones/examples/
python3 beta.py --num_drones 1 # check the steps in the file's docstrings to use multiple drones
If you wish, please cite our IROS 2021 paper (and original codebase) 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}
}
crazyflie-firmware
SITL support (@spencerteetaert, @JacopoPan)BaseAviary._dynamics()
rpy
with quaternions (and ang_vel
with body rates) by editing BaseAviary._updateAndStoreKinematicInformation()
, BaseAviary._getDroneStateVector()
, and the .computeObs()
methods of relevant subclassesnvidia-settings
and under "PRIME Profiles" select "NVIDIA (Performance Mode)", reboot and try again.Run all tests from the top folder with
pytest tests/
University of Toronto's Dynamic Systems Lab / Vector Institute / University of Cambridge's Prorok Lab