Design of Speed Compensator for Tandem Unmanned Helicopter Based on Reinforcement Learning

In this paper, a tandem unmanned helicopter is taken as the research object, and the problem of altitude control of unmanned helicopter in strong interference environment is studied. To solve the problem of poor performance of traditional constant speed height control method under strong airflow disturbance, a tandem UAV variable speed compensation method based on reinforcement learning is proposed. The depth deterministic strategy gradient algorithm is adopted to ensure the continuity and stability of the output, and the precise control of the UAV variable speed is realized. Compared with the traditional constant speed altitude control method, the simulation results show that the depth deterministic strategy gradient speed compensation controller can significantly improve the altitude tracking performance and anti-disturbance ability under strong interference environment, and the altitude and speed change are smoother.