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.
关键词
灰狼优化算法/移动机器人/路径规划/非线性收敛因子
Key words
grey wolf optimization(GWO)algorithm/mobile robot/path planning/nonlinear convergence factor
维普
万方数据