QuadCtrl/quad-ctrl
Quadcopter Controller with Deep Reinforcement Learning
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.
Stars
34
Forks
6
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
LucasAlegre/sumo-rl
Reinforcement Learning environments for Traffic Signal Control with SUMO. Compatible with...
hilo-mpc/hilo-mpc
HILO-MPC is a Python toolbox for easy, flexible and fast development of...
reiniscimurs/DRL-robot-navigation
Deep Reinforcement Learning for mobile robot navigation in ROS Gazebo simulator. Using Twin...
kyegomez/RoboCAT
Implementation of Deepmind's RoboCat: "Self-Improving Foundation Agent for Robotic Manipulation"...
OpenQuadruped/spot_mini_mini
Dynamics and Domain Randomized Gait Modulation with Bezier Curves for Sim-to-Real Legged Locomotion.