China Mechanical Engineering ›› 2026, Vol. 37 ›› Issue (8): 2017-2028.DOI: 10.3969/j.issn.1004-132X.2026.08.021

Previous Articles    

Anti-conflict Path Planning for AGVs in the Automated Container Terminals Based on Proximal Policy Optimization Algorithm

XIAO Shichang1(), LIN Xuan1, ZHENG Peng1(), WANG Jinfeng2   

  1. 1.Logistics Engineering College,Shanghai Maritime University,Shanghai,201306
    2.China Institute of FTZ Supply Chain,Shanghai Maritime University,Shanghai,201306
  • Received:2025-08-07 Online:2026-08-25 Published:2026-09-17
  • Contact: ZHENG Peng

基于近端策略优化算法的自动化集装箱码头自动导引车防冲突路径规划

肖世昌1(), 林轩1, 郑鹏1(), 王金凤2   

  1. 1.上海海事大学物流工程学院, 上海, 201306
    2.上海海事大学中国(上海)自贸区供应链研究院, 上海, 201306
  • 通讯作者: 郑鹏
  • 作者简介:肖世昌,男,1987年生,副教授、博士。研究方向为港口调度优化/智能制造系统建模与调度优化。E-mail: scxiao@shmtu.edu.cn

Abstract:

To enhance the operational efficiency and intelligent decision making capability of automated container terminals, this study addresses the collision free path planning problem for multiple AGVs operating bidirectionally in the horizontal transport area. Considering the layout characteristics of the terminal’s horizontal transport zone, a grid-based map is constructed, and the AGV collision-free path planning problem is formulated as a mathematical programming model with the objective of minimizing the makespan (i.e., the maximum completion time) of all tasks. A PPO algorithm is then designed. A simulation environment tailored for bidirectional guideway systems is developed, incorporating specifically designed action and state spaces for multi-AGV operations. An anti-detour heuristic is introduced to improve the search efficiency of the algorithm. The proposed algorithm is benchmarked against the commercial solver Gurobi, the A* algorithm, and a genetic algorithm. Simulation results demonstrate that the proposed algorithm exhibits superior solution stability and stronger convergence capability, particularly for large-scale problem instances.

Key words: automated container terminal(ACT), automated guided vehicle(AGV) path planning, proximal policy optimization(PPO) algorithm, detour prevention strategy

摘要:

为了提高自动化集装箱码头的运营效率和智能决策能力,针对水平运输区域中双向行驶的多自动导引车(AGV)防冲突路径规划问题展开研究。首先针对码头水平运输区域特征构建网格地图,并将AGV防冲突路径规划问题建模为以最小化所有任务最大完工时间为目标的数学规划模型。随后设计了近端策略优化(PPO)算法,搭建了面向双向引导车道的工作环境模型,设计了多AGV作业的动作空间和状态空间,通过引入防绕远策略提高算法搜索能力。最后将所提算法与商业求解器Gurobi、A*算法及遗传算法进行性能对比,仿真实验结果表明,所提算法针对大规模问题具有更强的性能稳定性和收敛能力。

关键词: 自动化集装箱码头, 自动导引车路径规划, 近端策略优化算法, 防绕远策略

CLC Number: