基于改进融合蚁群算法的AGV路径规划
AGV Path Planning Based on Improved Fusion Ant Colony Algorithm
周振 1耿晨晨 1崔若庚 1肖金壮1
作者信息
- 1. 河北大学电子信息工程学院,河北 保定 071000
- 折叠
摘要
针对传统蚁群算法在AGV 寻路时存在收敛速度慢、转角次数多且不够平滑等问题,在蚁群系统算法(Ant Colony System,ACS)的基础上,提出一种改进融合蚁群算法.首先通过势场引力函数来改进蚁群系统的启发函数;其次,采用一种改进自适应伪随机转移策略,在信息素更新中引入自适应挥发因子;然后,采用三次B样条曲线平滑策略进行优化;最后,在栅格地图中进行仿真,结果表明,改进算法达到缩短路径长度和减少转角次数的目的,同时提高算法的收敛性和路径平滑性,相较于传统蚁群算法能明显提升寻路效率.
Abstract
Aiming at the problems of the traditional Ant Colony algorithm in AGV pathfinding,such as slow con-vergence speed,too many corners and not smooth enough,this paper proposes an improved fusion Ant Colony algorithm based on Ant Colony System(ACS)algorithm.Firstly,the heuristic function of ant colony system was im-proved by the potential field target attraction function.Secondly,an improved adaptive pseudo-random transfer strategy was used to introduce adaptive volatile factors into pheromone update.Then,a cubic B-spline curve smoot-hing strategy was used for optimization.Finally,the simulation experiment was carried out in raster map.The experi-mental results show that the improved algorithm can shorten the path length and reduce the number of corners,and improve the convergence and path smoothness of the algorithm.Compared with the traditional ant colony algorithm,it can significantly improve the pathfinding efficiency.
关键词
蚁群算法/路径规划/人工势场法Key words
Ant colony algorithm/Path planning/Artificial potential field method引用本文复制引用
基金项目
国家自然科学基金(62103127)
河北省自然科学基金(F2020201048)
河北省高等学校科学技术研究项目(521000981366)
出版年
2024
NETL
NSTL
万方数据