基于导向强化Q学习的无人机路径规划

Path planning of UAV using guided enhancement Q-learning algorithm

随着无人机的广泛应用,其飞行能耗和计算能力面临着瓶颈问题,因此无人机路径规划研究越来越重要。很多情况下,无人机并不能提前获得目标点的确切位置和环境信息,往往无法规划出一条有效的飞行路径。针对这一问题,提出了基于导向强化Q学习的无人机路径规划方法,该方法利用接收信号强度定义回报值,并通过Q学习算法不断优化路径;提出"导向强化"的原则,加快了学习算法的收敛速度。仿真结果表明,该方法能够实现无人机的自主导航和快速路径规划,与传统算法相比,大大减少了迭代次数,能够获得更短的规划路径。

With the increasing application of the Unmanned Aerial Vehicle(UAV)technology,the energy consumption and computing capacity of UAV are faced with bottleneck problems,so path planning of UAV is becoming increasingly important.In many cases,the UAV cannot obtain the exact location of the target point and environmental information in advance,and thus is difficult to plan an effective flight path.To solve this problem,this paper proposes a path planning method for UAV using the guided enhancement Q-learning algorithm.This method uses Receiving Signal Strength(RSS)to define the reward value,and continuously optimizes the path by using the Q-learning algorithm.The principle of“guided reinforcement”is proposed to accelerate the convergence speed of the Qlearning algorithm.The simulation results show that the method proposed can realize autonomous navigation and fast path planning for UAV.Compared with the traditional algorithm,it can greatly reduce the number of iterations and obtain a shorter planned path.