基于改进粒子群算法的自动引导小车路径规划

曲靖师范学院学报 ›› 2024, Vol. 43 ›› Issue (6): 74-81.

基于改进粒子群算法的自动引导小车路径规划

罗子灿^1,2, 黄宇轩^1,2, 何广^1,2

1.湖南工业大学商学院,湖南株洲 412007;
2.湖南省包装经济研究基地,湖南株洲 412007

收稿日期:2024-04-26 出版日期:2024-12-17 发布日期:2024-12-17
作者简介:罗子灿,湖南工业大学商学院讲师,博士,主要从事运营管理和营销管理研究.
基金资助:
湖南省包装经济研究基地项目“考虑政府补贴的包装生态标签认证策略研究”(2022BZJG08)、 “EPR制度下BYOC行为对包装生产策略影响研究”(23JD035);湖南工业大学商学院“跨境电商”专项研究项目“面向跨境电商仓储的搬运机器人路径规划研究”(2023KJDS14).

Path Planning of Automatic Guided Vehicle Based on Improved Particle Swarm Optimization Algorithm

LUO Zican^1,2, HUANG Yuxuan^1,2, HE Guang^1,2

1. School of Business,Hunan University of Technology , Zhuzhou Hunan 412007;
2. Hunan Provincial Packaging Economy Research Base,Zhuzhou Hunan 412007,China

Received:2024-04-26 Published:2024-12-17 Online:2024-12-17

摘要/Abstract

摘要： 针对传统粒子群算法易收敛到局部最优、搜索效率低等问题,提出一种改进算法并将其运用于自动引导小车(Automated Guided Vehicle,AGV)的路径规划问题中. 首先,引入非线性递减惯性权重,调节不同时期粒子自身对寻优的影响. 然后,对两个学习因子进行自适应改进,增强算法的局部和全局搜索能力. 最后,提出考虑路径长度和平滑度的适应度函数,并通过干扰粒子速度来摆脱局部最优区域,提高搜寻路径的质量. 在地图规模和障碍复杂度均不同的四种环境中进行多次实验,仿真结果表明,改进后算法相较于原算法,搜寻的平均路径缩短7.9%,平均迭代次数减少了20.2%,体现出更优越的路径规划能力.

关键词: 路径规划, 粒子群算法, 惯性权重, 学习因子

Abstract: Aiming at the problems of traditional particle swarm optimization algorithms easily converging to local optima and low search efficiency, an improved algorithm is proposed and applied to the path planning problem of Automated Guided Vehicle (AGV). Firstly, non-linear decreasing inertia weights are introduced to adjust the influence of particles themselves on optimization at different stages. Then, adaptive improvements are made to the two learning factors to enhance the algorithm's local and global search capabilities. Finally, a fitness function considering path length and smoothness is proposed, and local optimal regions are eliminated by interfering with particle velocity to improve the quality of the search path. Multiple experiments were conducted in four environments with different map sizes and obstacle complexity. Simulation results showed that the improved algorithm reduced the average search path by 7.9% and the average iteration times by 20.2% compared to the original algorithm, demonstrating superior path planning capabilities.

Key words: path planning, particle swarm optimization algorithm, inertial weight, learning factors

中图分类号:

TP242
TP18

罗子灿, 黄宇轩, 何广. 基于改进粒子群算法的自动引导小车路径规划[J]. 曲靖师范学院学报, 2024, 43(6): 74-81.

LUO Zican, HUANG Yuxuan, HE Guang. Path Planning of Automatic Guided Vehicle Based on Improved Particle Swarm Optimization Algorithm[J]. Journal of Qujing Normal University, 2024, 43(6): 74-81.

参考文献

[1] 雷斌,金彦彤,王致诚,等.仓储物流机器人技术现状与发展[J].现代制造工程,2021(12):143-153.
[2] 赵学健,叶昊,贾伟,等.AGV路径规划及避障算法研究综述[J].小型微型计算机系统,2024,45(3):529-541.
[3] 邵琪,时维国.基于改进蚁群算法的机器人路径规划研究[J].现代制造工程,2023(6):46-51.
[4] 孙波,姜平,周根荣,等.基于改进遗传算法的AGV路径规划[J].计算机工程与设计,2020,41(2):550-556.
[5] 巫光福,万路萍.粒子群算法优化机器人路径规划的研究[J].机械科学与技术,2022,41(11):1759-1764.
[6] 姜辰凯,李智,盘书宝,等.基于改进Dijkstra算法的AGVs无碰撞路径规划[J].计算机科学,2020,47(8):272-277.
[7] 王洪斌,尹鹏衡,郑维,等.基于改进的A~*算法与动态窗口法的移动机器人路径规划[J].机器人,2020,42(3):346-353.
[8] 牛秦玉,李美凡,赵勇.改进人工势场法的AGV路径规划算法研究[J].机床与液压,2022,50(17):19-24.
[9] 林韩熙,向丹,欧阳剑,等.移动机器人路径规划算法的研究综述[J].计算机工程与应用,2021,57(18):38-48.
[10] 胡章芳,冯淳一,罗元.改进粒子群优化算法的移动机器人路径规划[J].计算机应用研究,2021,38(10):3089-3092.
[11] 白晓兰,周文全,张振朋,等.基于启发式粒子群算法的机器人平滑路径规划[J].组合机床与自动化加工技术,2022(8):44-47+52.
[12] 郝琨,邓晁硕,赵璐,等.基于区域搜索粒子群算法的机器人路径规划[J].电子测量与仪器学报,2022,36(12):126-135.
[13] 赵迪,何克勤,赵祖高.基于改进粒子群优化算法的移动机器人路径规划[J].传感器与微系统,2023,42(6):150-153.
[14] 陈旭东,杨光永,徐天奇,等.基于多策略融合改进粒子群算法的路径规划研究[J].组合机床与自动化加工技术,2024(2):44-50.