# learnsyslab/gym-pybullet-drones

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

Repository: https://github.com/learnsyslab/gym-pybullet-drones
Canonical: https://ross.abutalabs.com/products/gym-pybullet-drones
Homepage: https://arxiv.org/pdf/2103.02142
Language: Python
License: MIT
License Family: permissive
Topics: pybullet, crazyflie, robotics, reinforcement-learning, quadrotor, control, uav, quadcopter, multi-agent, gym, gymnasium, stable-baselines3, betaflight, sitl
Last push: 2026-08-23T01:16:29+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 8, longevity 100
- inputs: {"age_days": 2214, "days_push": 11, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2116, forks 557 (observed 2026-08-28T04:06:16.148488+00:00)

## What it is
A Python library providing PyBullet-based Gymnasium environments for simulating quadcopter control in single- and multi-agent reinforcement learning settings. It integrates with stable-baselines3 and supports Betaflight SITL for realistic flight controller simulation.

## Use cases
- train RL agents to hover a quadcopter
- simulate multi-drone formation flight
- research multi-agent reinforcement learning for UAV control
- test drone controllers like PID against a physics simulator
- integrate Betaflight SITL with a physics simulation
- study downwash effects between drones

## When to avoid
- you need GPU-accelerated or differentiable simulation (consider crazyflow)
- you need symbolic dynamics and safety constraints (consider safe-control-gym)
- you need full real-world deployment stacks with ROS2

## Facets
- artifact type: library
- maturity: active
- function: simulation, machine-learning, reinforcement-learning, robotics
- domain: robotics, reinforcement-learning, simulation, machine-learning
- platform: python, cross-platform
- tags: pybullet, quadcopter, uav, multi-agent, gymnasium, stable-baselines3, crazyflie, betaflight-sitl, drone-simulation, linux, macos

## Member repositories
- learnsyslab/gym-pybullet-drones (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:16.148488+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:53:19.849762+00:00, confidence not recorded.
  - readme: https://github.com/learnsyslab/gym-pybullet-drones (fetched 2026-08-28T04:06:16.148488+00:00, sha 84482a94a5f9)
- Data as of 2026-08-30T08:39:29.467469+00:00.