utiasDSL/gym-pybullet-drones

PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control

64
/ 100
Established

This project offers a simulated environment for developing and testing control algorithms for single and multi-agent quadcopters. It takes in control commands or reinforcement learning policies and outputs realistic drone behavior, allowing researchers and roboticists to experiment with flight dynamics, formation flying, and autonomous navigation.

1,885 stars. Actively maintained with 2 commits in the last 30 days.

Use this if you are a robotics researcher or control engineer developing and evaluating drone control strategies using simulated environments like PyBullet and Gymnasium.

Not ideal if you need a GPU-accelerated, differentiable JAX-based simulation, symbolic dynamics with constraints, or a production-grade ROS2 deployment with real-world sensors.

drone-control robotics-simulation reinforcement-learning multi-agent-systems quadcopter-autonomy
No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

1,885

Forks

524

Language

Python

License

MIT

Last pushed

Feb 15, 2026

Commits (30d)

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/utiasDSL/gym-pybullet-drones"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.