Research on motor speed control algorithm of UAV Based on Reinforcement Learning

Abstract Aiming at the hovering control problem of four-rotor UAVs, this paper proposes to use the reinforcement learning method to control the motor speed of UAVs to improve the intellectual control level of four-rotor UAVs. Firstly, two reinforcement learning algorithm models of DDPG (deep deterministic policy gradient) and PPO (proximal policy optimization) are built using the PARL framework, and the super parameters of the algorithm model are set. Secondly, the algorithms are trained and optimized to obtain scores in the RLSchool simulation environment. Finally, the performance differences between the two algorithm models in the same simulation environment are analyzed. The test and analysis results show that the two algorithms can realize the four-axis aircraft suspension control in the simulation environment. Between them, the PPO algorithm features high scores, simple and convenient parameter adjustment, stable control, and good performance.