基于变体马尔可夫博弈的自动引导车任务协同处理  

Cooperative Processing of Tasks for Automatic Guided Vehicles Based on Variant Markov Game

作　　者：赵鹏瑞 任建伟[1] 王青 冯晨曦 ZHAO Pengrui;REN Jianwei;WANG Qing;FENG Chenxi(Institute of Transportation,Inner Mongolia University,Hohhot O1oo70,China)

机构地区：[1]内蒙古大学交通学院,呼和浩特010070

出　　处：《内蒙古大学学报（自然科学版）》2024年第3期308-316,共9页Journal of Inner Mongolia University：Natural Science Edition

基　　金：国家自然科学基金项目(71862026);内蒙古高等学校“青年科技英才支持计划”项目(NJYT22095)。

摘　　要：为了提高转运仓库的转运效率,提出了一种基于变体马尔可夫博弈的自动引导车任务协同处理(VMG-AGV任务协同处理)方法。在利用FlexSim构建转运仓库模型的基础上对ProcessFlow、全局表、任务分配器、AGV等组件或实体进行参数、脚本设计,将VMG-AGV任务协同处理方法与传统的“一车带一物”拣选方法进行对比实验。仿真结果表明:新方法与传统方法相比,4辆AGV的平均利用率提高了11%,在制品平均运输量提高了40%,4台出库合成器平均每小时增加出库4.5单。In order to improve the transfer efficiency of the transfer warehouse,a method of automatic guided vehicle task cooperative processing(VMG-AGV task cooperative processing)based on variant Markov game is proposed.Based on FlexSim,parameters and scripts of Process-Flow,global table,task distributor,AGV and other components or entities are designed,and the VMG-AGV task collaborative processing method is compared with the traditional"one cart with one object"picking method.The simulation results show that compared with the traditional method,the average utilization rate of four AGVs is increased by l1%,the average delivery rate of four synthesizers is increased by 4.5 per hour,and the average transport volume of products in process is increased by 40%.

关 键 词：物流工程 任务协同处理 FLEXSIM AGV系统 多智能体 仿真模拟 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]