基于改进遗传算法的自动导引小车动态路径规划及其实现  

AGV dynamic path planning based on improved genetic algorithm and its implementation

作　　者：刘二辉[1] 姚锡凡[1] 蓝宏宇 金鸿 LIUErhui;YAO Xi fan;LAN Hongyu;JIN Hong(School of Mechanical and Automobile Engineering, South China University of Technology, Guangzhou 510640, China;College of Engineering, South China Agricultural University, Guangzhou 510642, China)

机构地区：[1]华南理工大学机械与汽车工程学院,广东广州510640 [2]华南农业大学工程学院,广东广州510642

出　　处：《计算机集成制造系统》2018年第6期1455-1467,共13页Computer Integrated Manufacturing Systems

基　　金：国家自然科学基金资助项目(51675186;51175187);广东省科技计划资助项目(2017A030223002);广州市南沙区科技计划资助项目(2015CX005)~~

摘　　要：针对传统遗传算法求解自动导引小车动态路径规划易早熟的缺点,提出一种改进遗传算法的自动导引小车动态路径规划算法,针对传统变异算子缺少启发式规则导致变异产生优质解的概率较低和算法早熟的缺陷,基于相连的路径片段组成的三角形建立使路径缩短的启发式变异规则,并提出路径微调算法;为了提高路径的光滑程度便于自动导引小车行驶,提出路径光滑处理算法;为了增加改进遗传算法的局部寻优能力,对每一代的最优解进行模拟退火操作;并且基于MATLAB GUI开发工具开发出自动导引小车动态路径规划仿真平台,以证明所改进遗传算法求解自动导引小车动态路径规划问题的有效性。Aiming at the premature in traditional genetic algorithm for solving Automated Guided Vehicle（AGV）dynamic path planning problem,an Improved Genetic Algorithm（IGA）for AGV dynamic path planning was proposed,in which fine-tuning path algorithm was proposed based on heuristic rule to shorten path by setting up of a triangle consisted of connected path segments to aim at the drawbacks such as low probability of producing high quality solutions and premature resulted from the lack of heuristic rules in traditional mutation operators.To improve the path smoothness for facilitating the running of AGV,the path smoothing algorithm was proposed;to enhance the IGA exploitation performance,the simulated annealing operation was performed for the optimal solution in each generation.An AGV dynamic path planning platform developed based on MATLAB GUI tools so as to verify the proposed IGA for solving AGV dynamic path planning problems.

关 键 词：启发式规则 路径微调算法 路径光滑处理算法 动态路径规划 

分 类 号：TH16[机械工程—机械制造及自动化] TP24[自动化与计算机技术—检测技术与自动化装置]