基于无冲突路径算法的多目标智能仓储路径规划

doi:10.11896/jsjkx.250200035

计算机科学 ›› 2026, Vol. 53 ›› Issue (4): 88-100.doi: 10.11896/jsjkx.250200035

• 人工智能与理论计算机科学交叉融合 • 上一篇下一篇

基于无冲突路径算法的多目标智能仓储路径规划

宫婧^1,2, 杨玉发³, 郑一帆³, 孙知信^1,2

1 南京邮电大学江苏省邮政大数据技术与应用工程研究中心南京 210003
2 南京邮电大学国家邮政局邮政行业技术研发中心(物联网技术) 南京 210003
3 南京邮电大学现代邮政学院南京 210003

收稿日期:2025-02-10 修回日期:2025-06-05 出版日期:2026-04-15 发布日期:2026-04-08
通讯作者: 孙知信(sunzx@njupt.edu.cn)
作者简介:(gongj@njupt.edu.cn)
基金资助:
国家自然科学基金(62272239);江苏省农业科技自主创新项目(CX(22)1007);贵州省科技支撑项目([2023]一般272)

Multi-objective Intelligent Warehousing Path Planning Based on Conflict Free Path Algorithm

GONG Jing^1,2, YANG Yufa³, ZHENG Yifan³, SUN Zhixin^1,2

1 Engineering Research Center of Post Big Data Technology and Application of Jiangsu Province, Nanjing University of Posts and Telecommunications, Nanjing 210003, China
2 Research and Development Center of Post Industry Technology of the State Posts Bureau(Internet of Things Technology), Nanjing University of Posts and Telecommunications, Nanjing 210003, China
3 Modern Postal College, Nanjing University of Posts and Telecommunications, Nanjing 210003, China

Received:2025-02-10 Revised:2025-06-05 Published:2026-04-15 Online:2026-04-08
About author:GONG Jing,born in 1977,Ph.D,associate professor.Her main research in-terests include data network security technology,data mining technology and modern logistics technology.
SUN Zhixin,born in 1964,Ph.D,professor,doctoral supervisor.His main research interests include the theory and technology of network communication,computer network and security.
Supported by:
National Natural Science Foundation of China(62272239),Jiangsu Agriculture Science and Technology Innovation Fund(CX(22)1007) and Guizhou Provincial Key Technology R & D Program([2023]272).

摘要/Abstract

摘要： 研究仓储路径规划对智能仓储具有重要意义,合理的路径规划能够有效避免仓储路径冲突,提升仓库内货物运输效率。针对当前仓储布局较为简单、缺乏针对复杂仓储布局的路径冲突策略问题,提出基于AGV坐标保留表和冲突分类的多目标AGV路径规划算法。首先,构建基于网格法的智能仓储鱼骨布局方案,并根据分区机制,给出存储节点间的距离计算模型,构成单一单向的仓储路径网络有向图。其次,建立AGV坐标保留表方法和路径冲突分类方法,制定路径冲突解决策略和算法。然后,建立以最小化总运输距离、最小化最大运输距离、最小化冲突解决等待时间为目标的多目标智能仓储路径规划模型。最后,结合所提路径冲突解决算法,设计基于进化遗传搜索算法的突变操作,在基于学习的多目标组合优化求解算法P-MOCO的基础上,通过构建偏好条件随机策略,借助多目标降维和强化学习方法,提出改进P-MOCO的无冲突多目标智能仓储路径优化算法CF-MOWVRP,求解无冲突的多目标规划模型的近似帕累托解。实验结果表明,所提算法具备更快的收敛速度和更优的解,能够解决路径冲突,给出无冲突的路径规划方案。

关键词: 路径规划, 智能仓储, 路径冲突, 多目标优化, 强化学习, AGV

Abstract: The research on warehouse path planning plays a crucial role in intelligent warehousing,as reasonable path planning can effectively avoid AGV path conflicts and improve in-warehouse transportation efficiency.To address the limitations of simplistic warehouse layouts and the lack of effective path conflict resolution strategies for complex environments,this paper proposes a multi-objective AGV path planning algorithm based on a coordinate reservation table and conflict classification.Firstly,a grid-based fish-bone layout scheme for intelligent warehousing is constructed.A distance calculation model between storage nodes is developed using a partition mechanism,forming a unidirectional directed graph representing the storage path network.Next,an AGV coordinate reservation table and a path conflict classification method are established,followed by the formulation of a hierarchical conflict resolution strategy.Then,a multi-objective intelligent warehouse path planning model is constructed with the goals of minimizing the total transportation distance,minimizing the maximum single transportation distance,and minimizing the waiting time for conflict resolution.Based on the proposed conflict resolution mechanism,a set of mutation operators and crossover operations is designed under an evolutionary genetic search framework.On top of the preference-guided multi-objective combinatorial optimization(P-MOCO) algorithm,an enhanced algorithm named CF-MOWVRP is proposed.This algorithm integrates preference-driven stochastic strategies,multi-objective dimensionality reduction,and reinforcement learning to obtain approximate Pareto-optimal solutions to the conflict-free multi-objective path planning model.Experimental results demonstrate that the proposed algorithm achieves faster convergence and better solution quality,successfully resolves AGV path conflicts,and provides feasible conflict-free path planning solutions.

Key words: Path planning, Intelligent warehousing, Path conflict, Multi objective optimization, Reinforcement learning, AGV

中图分类号:

TP242

宫婧, 杨玉发, 郑一帆, 孙知信. 基于无冲突路径算法的多目标智能仓储路径规划[J]. 计算机科学, 2026, 53(4): 88-100. https://doi.org/10.11896/jsjkx.250200035

GONG Jing, YANG Yufa, ZHENG Yifan, SUN Zhixin. Multi-objective Intelligent Warehousing Path Planning Based on Conflict Free Path Algorithm[J]. Computer Science, 2026, 53(4): 88-100. https://doi.org/10.11896/jsjkx.250200035

参考文献

[1]ZHANG Z,CHEN J,GUO Q.Application of Automated Guided Vehicles in Smart Automated Warehouse Systems:A Survey[J].Computer Modeling in Engineering & Sciences,2023,134(3):1529-1563.
[2]WAN Y,WANG S,HU Y,et al.Multiobjective Optimization of the Storage Location Allocation of a Retail E-commerce Picking Zone in a Picker-to-parts Warehouse[J].Engineering Letters,2023,31(2):481-493.
[3]CHEN Y,WU J,HE C,et al.Intelligent warehouse robot path planning based on improved ant colony algorithm[J].IEEE Access,2023,11:12360-12367.
[4]WU Z S,CHANG D F,GAI Y H.Optimization of Storage Location Allocation in Four Directional Shuttle Dense Warehousing System Based on Two Stage Hybrid Algorithm[J].Journal of System Simulation,2025,37(5):1234-1245.
[5]WANG Y F,CAO X H,GUO X.Warehouse AGV path planning method based on improved A^* algorithm and short-term system state prediction[J].Computer Integrated Manufacturing Systems,2023,29(11):3897-3908.
[6]KAWABE T,NISHI T,LIU Z.Flexible Route Planning forMultiple Mobile Robots by Combining Q-Learning and Graph Search Algorithm[J].Applied Sciences,2023,13(3):1879.
[7]CAO X H,ZHU M.Optimization of Collision Avoidance Deci-sion for Multi Automatic Guided Vehicles Based on Conflict Prediction[J].Computer Integrated Manufacturing System,2020,26(8):2092-2098.
[8]YAN X Y,MAO J L,WANG N,et al.CBS Multi Robot Path Planning Based on Conflict Avoidance Strategy[J].Small Microcomputer System,2025,46(4):841-846.
[9]LI T,DING P P,LIU J F.Multi stage and Multi AGV PathPlanning for Goods to Person Picking System[J].Journal of System Simulation,2022,34(7):1512-1523.
[10]JIANG C K,LI Z,PAN S B,et al.AGVs collision free pathplanning based on improved Dijkstra algorithm[J].Computer Science,2020,47(8):272-277.
[11]ZHANG Z,GUO Q,CHEN J,et al.Collision-Free Route Planning for Multiple AGVs in an Automated Warehouse Based on Collision Classification[J].IEEE Access,2018,6:26022-26035.
[12]ZHAO X J,YE H,LI H,et al.Multi AGV path planning algorithm based on improved DDPG[J].Computer Science,2025,52(6):306-315.
[13]LIN X,YANG Z,ZHANG Q.Pareto Set Learning for NeuralMulti-Objective Combinatorial Optimization[C]//10th International Conference on Learning Representations(ICLR 2022).2022.
[14]WANG J,WENG T,ZHANG Q.A Two-Stage MultiobjectiveEvolutionary Algorithm for Multiobjective Multidepot Vehicle Routing Problem With Time Windows[J].IEEE Transactions on Cybernetics,2019,49(7):2467-2478.
[15]VASWANI A,SHAZEER N,PARMAR N,et al.Attention Is All You Need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.2017:6000-6010.
[16]ELGHARABLY N,EASA S,NASSEF A,et al.Stochasticmulti-objective vehicle routing model in green environment with customer satisfaction[J].IEEE Transactions on Intelligent Transportation Systems,2022,24(1):1337-1355.
[17]WANG L L,ZHANG M Z,WU F,et al.High dimensional objective evolutionary algorithm under dynamic penalty decomposition strategy[J].Small and Micro Computer Systems,2018,39(10):2154-2161.
[18]KWON Y D,CHOO J,KIM B,et al.POMO:Policy Optimization with Multiple Optima for Reinforcement Learning[C]//Proceedings of the 34th Conference on Neural Information Processing Systems.2020:21188-21198.

相关文章 15

[1]	李伯尧, 赵斌斌, 陶明杰, 陈露. 基于Maklink图与Boustrophedon路径的移动机器人二维全覆盖路径规划算法 Mobile Robot Two-dimensional Full Coverage Path Planning Algorithm Based on MaklinkDiagram and Boustrophedon Path 计算机科学, 2026, 53(4): 78-87. https://doi.org/10.11896/jsjkx.250700190
[2]	柳家起, 汪玉杰, 相国督, 俞奎, 曹付元. 基于深度强化学习的长期因果效应估计 Long-term Causal Effect Estimation Based on Deep Reinforcement Learning 计算机科学, 2026, 53(4): 235-244. https://doi.org/10.11896/jsjkx.250600043
[3]	潘嘉豪, 冯翔, 虞慧群. 基于多任务强化学习的优先级加权软模块化方法:SM-PHT SM-PHT:Robust,Scalable,and Efficient Method for Multi-task Reinforcement Learning 计算机科学, 2026, 53(4): 366-376. https://doi.org/10.11896/jsjkx.250700198
[4]	郑诚, 班晴晴. 知识辅助和强化句法驱动的方面级情感分析 Knowledge-assisted and Reinforced Syntax-driven for Aspect-based Sentiment Analysis 计算机科学, 2026, 53(4): 406-414. https://doi.org/10.11896/jsjkx.250600117
[5]	杨昌好, 秦进, 王豪. 基于目标相似性驱动与双端变量引导搜索的大规模多目标进化算法 Large-scale Multi-objective Evolutionary Algorithm Based on Objective Similarity and Dual-EndVariable Guided Search 计算机科学, 2026, 53(3): 351-365. https://doi.org/10.11896/jsjkx.250200091
[6]	林兵, 姜海鸥, 檀啸, 陈星, 郑裕恒. 数据空间中基于纠删码的数据布局策略 Data Placement Strategy Based on Erasure Code in Data Space 计算机科学, 2026, 53(2): 196-206. https://doi.org/10.11896/jsjkx.241200199
[7]	文佳, 吴舒霞, 于正欣, 苗旺, 陈哲毅. 基于多目标优化的大规模Hadoop集群虚拟机放置 Multi-objective Optimization for Virtual Machine Placement in Large-scale Hadoop Cluster 计算机科学, 2026, 53(2): 387-395. https://doi.org/10.11896/jsjkx.241200020
[8]	李芳, 袁宝淳, 沈航, 王天荆, 白光伟. 低轨卫星网络中基于深度强化学习的航空器任务卸载策略 Deep Reinforcement Learning-based Aircraft Task Offloading in Low Earth Orbit Satellite Networks 计算机科学, 2026, 53(2): 406-415. https://doi.org/10.11896/jsjkx.250200092
[9]	翟洁, 李艳豪, 陈乐旋, 郭卫斌. 基于轻量级教育大模型的个性化实践学习资料动态推荐 Dynamic Recommendation of Personalized Hands-on Learning Materials Based on LightweightEducational LLMs 计算机科学, 2026, 53(2): 48-56. https://doi.org/10.11896/jsjkx.250800002
[10]	王皓焱, 李崇寿, 李天瑞. 基于双层注意力网络的强化学习方法求解柔性作业车间调度问题 Reinforcement Learning Method for Solving Flexible Job Shop Scheduling Problem Based onDouble Layer Attention Network 计算机科学, 2026, 53(1): 231-240. https://doi.org/10.11896/jsjkx.250100088
[11]	段鹏婷, 温超, 王保平, 王珍妮. 基于协作语义融合的多智能体行为决策方法 Collaborative Semantics Fusion for Multi-agent Behavior Decision-making 计算机科学, 2026, 53(1): 252-261. https://doi.org/10.11896/jsjkx.250300145
[12]	周德强, 季新生, 游伟, 邱航, 杨杰. 攻击图辅助下基于深度强化学习的服务功能链攻击恢复方法 Attack Graph-assisted Deep Reinforcement Learning-based Service Function Chain AttackRecovery Method 计算机科学, 2026, 53(1): 371-381. https://doi.org/10.11896/jsjkx.250300076
[13]	万盛华, 徐兴业, 甘乐, 詹德川. 基于多模态大模型辅助视频动作生成的预训练世界模型 Pre-training World Models from Videos with Generated Actions by Multi-modal Large Models 计算机科学, 2026, 53(1): 51-57. https://doi.org/10.11896/jsjkx.250800033
[14]	朱士昊, 彭可兴, 马廷淮. 基于图注意力的分组多智能体强化学习方法 Graph Attention-based Grouped Multi-agent Reinforcement Learning Method 计算机科学, 2025, 52(9): 330-336. https://doi.org/10.11896/jsjkx.240700107
[15]	陈锦韬, 林兵, 林崧, 陈静, 陈星. 基于多智能体深度强化学习的光储充电站动态定价及能源调度策略 Dynamic Pricing and Energy Scheduling Strategy for Photovoltaic Storage Charging Stations Based on Multi-agent Deep Reinforcement Learning 计算机科学, 2025, 52(9): 337-345. https://doi.org/10.11896/jsjkx.240700197

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于无冲突路径算法的多目标智能仓储路径规划

Multi-objective Intelligent Warehousing Path Planning Based on Conflict Free Path Algorithm

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0