[!TIP]
For research work with symbolic dynamics and constraints, also try safe-control-gym

For GPU-accelerated, differentiable, JAX-based simulation, also try crazyflow

For production-grade deployment of ROS2 + PX4/ArduPilot + YOLO/LiDAR, use aerial-autonomy-stack

gym-pybullet-drones

This is a minimalist refactoring of the original gym-pybullet-drones repository, designed for compatibility with gymnasium, stable-baselines3 2.0, and betaflight/crazyflie-firmware SITL.

NEWS: gym-pybullet-drones was featured in GitHub's Maintainer Spotlight 2026

NOTE: if you want to access the original codebase, presented at IROS in 2021, please git checkout [paper|master]

<img src="gym_pybullet_drones/assets/helix.gif" alt="formation flight" width="325"> <img src="gym_pybullet_drones/assets/helix.png" alt="control info" width="425">

Installation

Tested on Intel x64/Ubuntu 22.04 and Apple Silicon/macOS 26.2.

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

conda create -n drones python=3.10
conda activate drones

pip3 install -e . # if needed, `sudo apt install build-essential` to install `gcc` and build `pybullet`

# check installed packages with `conda list`, deactivate with `conda deactivate`, remove with `conda remove -n drones --all`

Use

PID control examples

shCopy
cd gym_pybullet_drones/examples/
python3 pid.py # position and velocity reference
python3 pid_velocity.py # desired velocity reference

Downwash effect example

shCopy
cd gym_pybullet_drones/examples/
python3 downwash.py

Reinforcement learning examples (SB3's PPO)

shCopy
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

LATEST_MODEL=$(ls -t results | head -n 1) && python play.py --model_path "results/${LATEST_MODEL}/best_model.zip" # play and visualize the most recent learned policy after training

<img src="gym_pybullet_drones/assets/rl.gif" alt="rl example" width="375"> <img src="gym_pybullet_drones/assets/marl.gif" alt="marl example" width="375">

Run all tests

shCopy
# from the repo's top folder
cd gym-pybullet-drones/
pytest tests/

Betaflight SITL example (Ubuntu only)

shCopy
git clone https://github.com/betaflight/betaflight 
cd betaflight/
git checkout cafe727 # `master` branch head at the time of writing (future release 4.5)
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

shCopy
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

pycffirmware Python Bindings example (multiplatform, single-drone)

First, install pycffirmware for Ubuntu, macOS, or Windows, then

shCopy
cd gym_pybullet_drones/examples/
python3 cf.py

Citation

If you wish, please cite our IROS 2021 paper (and original codebase) as

bibtexCopy
@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

• Erwin Coumans and Yunfei Bai (2023) PyBullet Quickstart Guide
• Carlos Luis and Jeroome Le Ny (2016) Design of a Trajectory Tracking Controller for a Nanoquadcopter
• 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
• 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
• 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

---

UTIAS / Learning Systems and Robotics Lab / Vector Institute / University of Cambridge's Prorok Lab

<!-- ## WIP/Desired Contributions/PRs - [ ] Multi-drone `crazyflie-firmware` SITL support - [ ] Use SITL services with steppable simulation - [ ] Add motor delay, advanced ESC modeling by implementing a buffer in `BaseAviary._dynamics()` - [ ] Replace `rpy` with quaternions (and `ang_vel` with body rates) by editing `BaseAviary._updateAndStoreKinematicInformation()`, `BaseAviary._getDroneStateVector()`, and the `.computeObs()` methods of relevant subclasses ## 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. -->