基于事件驱动的无人机强化学习避障研究

Research on obstacle avoidance for UAV using reinforcement learning based on event driven

强化学习方法在避障研究中应用广泛,针对其需要消耗大量的计算资源问题,本文提出一种基于事件驱动的无人机强化学习避障算法.通过在强化学习中加入事件驱动的触发机制,减少无人机的动作决策的同时找到最优路径,既可以保证性能,又可以降低系统的通信频率.实验的仿真结果表明,该算法可以在学习过程中减少对计算资源的消耗,并且完成避障任务的同时可以明显加快收敛速度.

The reinforcement learning method is widely used in the research of obstacle avoidance,and it needs to consume a large amount of computing resources.This paper proposes an event-driven drone reinforcement learning obstacle avoidance algorithm.By adding event-driven triggering mechanism to reinforcement learning,the optimal path can be found while the UAV action decision is reduced,which can ensure the performance and reduce the communication frequency of the system.The simulation results show that the algorithm can reduce the consumption of computing resources in the learning process and achieve obstacle avoidance tasks while significantly accelerating the convergence rate.