Robust Reinforcement Learning Control for a Quadrotor with Disturbance Compensation
Yu‐Dong Cai, Tao Huang, Yefeng Yang · 2024
The control of quadrotors holds paramount importance in the field of robotics. This paper introduces a novel reinforcement learning (RL)-based robust controller with disturbance compensation for a quadrotor unmanned aerial vehicle (UAV). Specifically, the translational subsystem is stabilized using a Proximal Policy Optimization (PPO) controller, while the rotational subsystem is fine-tuned by a fast non-singular terminal sliding mode controller (FNTSMC). Additionally, a robust compensator is introduced to mitigate the impact of external disturbances on the system. A comprehensive set of comparative simulations is conducted to validate the effectiveness and superiority of the proposed control framework.