本文已被：浏览 2255次 下载 692次
Received:August 20, 2021
Received:August 20, 2021
中文摘要: 自动化分拣仓储包含大量的分拣任务, 需要多个自动导引车(AGV)来辅助人工完成快速分拣任务。为了提高效率, 在保障AGV电量的前提下, 以AGV完成任务的空载时间与AGV的空置率为优化目标, 对多AGV的碰撞进行了冲突分析, 并通过改进的Q-learning算法来生成AGV的无冲突搬运路径; 为了完成多AGV路径和调度综合优化, 提出了一种改进遗传算法, 算法采用精英保留和轮盘赌的方式选择个体, 运用自适应的交叉和变异算子来进行进化操作。最后, 通过仿真验证了算法的有效性。
中文关键词: 多AGV 路径规划与任务调度 Q-learning算法 改进遗传算法
Abstract:Automated sorting warehousing involves a large number of sorting tasks and requires multiple automated guided vehicles (AGVs) to assist manually in completing quick sorting tasks.In order to improve efficiency, under the premise of guaranteeing AGV power, the empty load time of AGV task and AGV's vacancy rate are optimized, the collision of multi-AGV is analyzed, and the conflict-free handling path of AGV is generated by the improved Q-learning algorithm.Finally, the validity of the algorithm is verified by simulation.
keywords: multi-automated guided vehicle path planning and task scheduling Q-learning algorithm improved genetic algorithm
文章编号：20221014 中图分类号：TP301.6;TP23 文献标志码：
基金项目:国家重点研发计划(2020YFB1711001)
Reference text: