一种基于改进PSO-PIO算法的AGV路径规划方法  

A Path Planning Method for AGV Based on Improved PSO-PIO Algorithm

作　　者：秦昌礼 张华强[1] 刘林 陈雨 苏庆华[3] QIN Chang-li;ZHANG Hua-qiang;LIU Lin;CHEN Yu;SU Qing-hua(School of Mechanical Engineering, Shandong University of Technology, Zibo 255049, China;Military Representative Office of Rocket Army in 211 Factory, Beijing 100076, China;School of Information Engineering, Beijing Wuzi University, Beijing 101149, China)

机构地区：[1]山东理工大学机械工程学院,山东淄博255049 [2]北京航天发射技术研究所,北京100076 [3]北京物资学院信息学院,北京101149

出　　处：《哈尔滨理工大学学报》2022年第3期82-89,共8页Journal of Harbin University of Science and Technology

基　　金：国家自然科学基金青年基金(61803035).

摘　　要：针对粒子群优化算法在全局路径规划时存在容易陷入局部最优的问题,依据粒子群算法和鸽群算法的相关理论,分析了导致粒子群算法陷入局部最优的影响因素,根据AGV小车的最小转向半径确定二维栅格地图中单元格的大小,改进粒子群算法并结合鸽群算法的快速收敛能力进行全局路径规划,给出了一种融合改进粒子群与鸽群算法的二阶段混合优化算法。对比传统的粒子群算法,新方法能有效防止算法陷入局部最优,规划的全局最优路径长度比传统的粒子群算法缩短了约3.8%并减少了路径规划时长。In order to solve the problem of particle swarm optimization algorithm easily falling into local optimum in global path planning,according to the related theories of particle swarm optimization algorithm and pigeon-inspired optimization algorithm,the influencing factors that lead to particle swarm optimization algorithm falling into local optimum are analyzed,and the size of raster in two-dimensional raster map is determined according to the minimum turning radius of automatic guided vehicle.The particle swarm optimization is improved and combined with the fast convergence ability of pigeon-inspired optimization algorithm,and a two-stage hybrid optimization algorithm based on improved particle swarm optimization and pigeon-inspired optimization algorithm is proposed for global path planning.Compared with the traditional particle swarm optimization algorithm,the new method can effectively avoid falling into local optimum.The global optimal path length is shortened by about 3.8%and the path planning time is reduced.

关 键 词：路径规划 改进粒子群算法 鸽群算法 二维栅格地图 AGV小车 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]