基于改进灰狼优化算法的移动机器人路径规划方法

Path planning method of mobile robot based on improved grey wolf optimization algorithm

提出基于改进灰狼优化(IGWO)算法的移动机器人路径规划方法。首先,将均匀分布空间与伪反向学习策略相结合,进行灰狼种群初始化;其次提出非线性收敛因子改进策略,使算法的前段搜索和后段寻优过程更容易得到平衡;接着,融合布谷鸟搜索(CS)算法搜索机制,更新灰狼个体位置,提高算法的全局寻优能力;最后,选用4个标准测试函数进行改进前后的测试对比实验,以及在栅格地图上进行路径规划仿真对比实验。实验结果表明,IGWO算法在测试函数上表现能更快收敛性、寻优结果更精确;路径规划仿真实验结果表明,IGWO算法的最短路径长度、平均路径长度、路径长度标准差均优于传统GWO算法。

A mobile robot path planning method based on improved GWO(IGWO)algorithm is proposed.Firstly,the uniform distribution space is combined with the pseudo reverse learning strategy to initialize the gray wolf population.Secondly,an improved strategy of nonlinear convergence factor is proposed,which makes it easier to balance the front-end searching and back-end optimizing process of the algorithm.Then,the cuckoo search(CS)algorithm search mechanism is fused to update the individual position of the gray wolf and improve the global optimizing ability of the algorithm.Finally,four standard test functions are selected to carry out the test comparison experiment before and after the improvement,and the path planning simulation comparison experiment is carried out on the grid map.The experimental results show that the IGWO algorithm performs faster convergence and more accurate optimizing results on the test function.The simulation results of path planning show that the shortest path length,average path length and path length standard deviation of IGWO algorithm are superior to those of traditional GWO algorithm.