基于改进DQN算法的自动化码头AGV调度问题研究  

AGV Scheduling Problem at Automated Terminals Based on Improved DQN Algorithm

作　　者：梁承姬 张石东 王钰 鲁斌 Liang Chengji;Zhang Shidong;Wang Yu;Lu Bin(Institute of Logistics Science and Engineering,Shanghai Maritime University,Shanghai 201306,China;Shanghai Municipal Engineering Design Institute Co.,Ltd.,Shanghai 200092,China)

机构地区：[1]上海海事大学,物流科学与工程研究院,上海201306 [2]上海市政工程设计研究总院有限公司,上海200092

出　　处：《系统仿真学报》2024年第11期2592-2603,共12页Journal of System Simulation

基　　金：国家自然科学基金(71972128);上海市青年科技英才扬帆计划(21YF1416400);上海市青年科技启明星计划(21QB1404800)。

摘　　要：针对自动化码头AGV(automated guided vehicle)调度问题,提出了一种考虑未来任务的深度Q网络(future tasks considering deep Q-network,F-DQN)算法指导AGV进行实时调度。对系统状态进行了改进,结合实时调度和静态调度的优点,在做出实时决策时考虑了静态的未来任务信息,以获得更优的调度方案。以洋山四期自动化码头的真实布局和设备情况为参考,使用仿真软件Plant Simulation进行了一系列仿真实验。实验结果表明:F-DQN算法可以有效解决自动化码头AGV实时调度问题,且F-DQN算法相比于传统DQN算法,能够显著缩短岸桥的等待时间。A future tasks considering deep Q-network(F-DQN)algorithm was proposed to output realtime scheduling results of automated guided vehicles(AGVs)at automated terminals.This algorithm combined the advantages of real-time scheduling and static scheduling,improving the system status by considering static future task information when making real-time decisions,so as to obtain a better scheduling solution.In this study,the actual layout and equipment conditions of the Yangshan phase IV automated terminal were considered,and a series of simulation experiments were conducted using the Plant Simulation software.The experimental results show that the F-DQN algorithm can effectively solve the real-time scheduling problem of AGVs at automated terminals.Furthermore,the F-DQN algorithm significantly reduces the waiting time of quay cranes compared to the traditional DQN algorithm.

关 键 词：自动化码头 AGV调度 DQN MDP 仿真模型 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术] TP181[自动化与计算机技术—计算机科学与技术]