wil3/gymfc
A flight control tuning framework that synthesizes neuro-flight controllers using reinforcement learning for UAV attitude control.

Velocity · 7d
+0.1
★ / day
Trend
→steady
star history
GymFC is a modular framework for tuning flight control systems using reinforcement learning. It synthesizes neural network-based attitude controllers that exceed traditional PID controller performance. The project integrates with Gazebo simulator and OpenAI Gym environments for training RL agents that control quadcopters, and powers the Neuroflight neural network flight control firmware.