Safety reinforcement learning quadrotor control system and method based on control barrier function

The invention discloses a safety reinforcement learning four-rotor control system based on a control barrier function, which comprises a simulation platform and a controller, and is characterized in that the controller is used for receiving a state quantity output by a simulation model and outputting a control instruction to an unmanned aerial vehicle or the simulation model, and the controller comprises a reinforcement learning sub-controller and a control barrier function sub-controller; through the combination of the control barrier function and the near-end strategy optimization method, the problem of low safety of a reinforcement learning controller is solved, and the stability of the system is improved. 本发明公开了一种基于控制障碍函数的安全强化学习四旋翼控制系统，包括仿真平台和控制器，所述接收仿真模型输出的状态量，向无人机或仿真模型输出控制指令，所述控制器包括强化学习子控制器和控制障碍函数子控制器，通过控制障碍函数与近端策略优化法结合的方式，解决了强化学习类的控制器安全性低的问题，提高了系统的稳定性。