QuadCtrl/quad-ctrl

Quadcopter Controller with Deep Reinforcement Learning

38
/ 100
Emerging

This project explores using deep reinforcement learning to train quadcopter drones for two key tasks: maintaining a stable hover and moving to a specific target position. It takes simulated drone flight data and reward functions, then outputs a neural network model that controls the drone or tunes a traditional PID controller. Drone engineers, robotics researchers, and control system designers would find this useful for developing autonomous flight systems.

No commits in the last 6 months.

Use this if you are a drone engineer or robotics researcher looking to apply deep reinforcement learning to control quadcopters for hovering or precise movement tasks without extensive control theory expertise.

Not ideal if you need to control physical drones in real-time with guarantees on performance under strong, persistent disturbances, as the full DRL approach showed limitations compared to PID in such scenarios.

drone-control robotics autonomous-systems quadcopter-flight reinforcement-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

34

Forks

6

Language

Python

License

MIT

Last pushed

Mar 17, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/QuadCtrl/quad-ctrl"

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