摘要
为解决水下机器人的路径规划问题,针对传统的蚁群算法存在算法收敛较慢、寻优路径较差等问题,提出了一种PSO融合蚁群算法。其利用PSO算法对蚁群算法的参数进行了各方面的优化。首先是将蚁群算法中各个参数代入到PSO算法进行寻优,设计出适应度函数,让各个参数向评价指数高的方向进行收敛,得出全局最优极值,最后再把每个参数代入蚁群算法,计算出路径及迭代次数。仿真结果对比表明,PSO融合蚁群算法在解决路径规划问题中具有更高的快速性和准确性。
In order to solve the path planning problems of the underwater vehicle,a PSO fusion ant colony algorithm is proposed to solve the problems of slow convergence and poor path optimization of the ant colony algorithm,which uses the PSO to optimize the parameters of the ant colony algorithm in all aspects.Each parameter in the ant colony algorithm is substituted into the particle swarm optimization algorithm for optimization,and the fitness function is designed to make each parameter converge to the direction of high evaluation indexes,and the global optimal extremum is obtained.Then,each parameter is substituted into the ant colony algorithm to calculate the path and the number of iterations.Through the comparison of the simulation results,the PSO fusion ant colony algorithm has higher rapidity and accuracy in solving the path planing problems.
作者
陈永康
蒲德奎
何小丽
CHEN Yongkang;PU Dekui;HE Xiaoli(Chongqing Vocational College of Light Industry,Chongqing 400065,P.R.China;Chongqing University of Science and Technology,Chongqing 401331,P.R.China)
出处
《重庆电力高等专科学校学报》
2024年第6期20-24,共5页
Journal of Chongqing Electric Power College
基金
重庆市教育委员会科学技术研究项目(KJQN202404518,KJQN202001531)。
关键词
水下机器人
路径规划
蚁群算法
PSO算法
underwater vehicle
path planning
ant colony algorithm
PSO algorithm
作者简介
陈永康(1990-),研究方向为智能控制、智慧农业。
