{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T12:56:31Z","timestamp":1753880191400,"version":"3.41.2"},"reference-count":28,"publisher":"ASME International","issue":"8","license":[{"start":{"date-parts":[[2024,4,16]],"date-time":"2024-04-16T00:00:00Z","timestamp":1713225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.asme.org\/publications-submissions\/publishing-information\/legal-policies"}],"funder":[{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of the People's Republic of China","doi-asserted-by":"publisher","award":["2022YFB4702400"],"award-info":[{"award-number":["2022YFB4702400"]}],"id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["asmedigitalcollection.asme.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Multi-agent path planning (MAPP) is crucial for large-scale mobile robot systems to work safely and properly in complex environments. Existing learning-based decentralized MAPP approaches allow each agent to gather information from nearby agents, leading to more efficient coordination among agents. However, these approaches often struggle with reasonably handling local information inputs for each agent, and their communication mechanisms between agents need to be further refined to treat those congested traffic scenarios effectively. To address these issues, we propose a decentralized MAPP approach based on imitation learning and selective communication. Our approach adopts an imitation learning architecture that enables agents to rapidly learn complex behaviors from expert planning experience. The information extraction layer is integrated with convolutional neural network (CNN) and gated recurrent unit (GRU) for capturing features from local field-of-view observations. A two-stage selective communication process based on graph attention neural network (GAT) is developed to reduce the required neighbor agents in inter-agent communication. In addition, an adaptive strategy switching mechanism utilizing local expert-planned paths is designed to support robots to escape from local traps. The effectiveness of our proposed approach is evaluated in simulated grid environments with varying map sizes, obstacle densities, and numbers of agents. Experimental results show that our approach outperforms other decentralized path planning methods in success rate while maintaining the lowest flowtime variation and communication frequency. Furthermore, our approach is computationally efficient and scalable, making it suitable for real-world applications.<\/jats:p>","DOI":"10.1115\/1.4065167","type":"journal-article","created":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T15:46:16Z","timestamp":1711467976000},"update-policy":"https:\/\/doi.org\/10.1115\/crossmarkpolicy-asme","source":"Crossref","is-referenced-by-count":1,"title":["A Decentralized Multi-Agent Path Planning Approach Based on Imitation Learning and Selective Communication"],"prefix":"10.1115","volume":"24","author":[{"given":"Bohan","family":"Feng","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University University of Michigan\u2014Shanghai Jiao Tong University Joint Institute, , 800 Dongchuan Road, Minhang District, Shanghai 200240 , China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youyi","family":"Bi","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University University of Michigan\u2014Shanghai Jiao Tong University Joint Institute, , 800 Dongchuan Road, Minhang District, Shanghai 200240 , China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mian","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University Global Institute of Future Technology, , 800 Dongchuan Road, Minhang District, Shanghai 200240 , China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liyong","family":"Lin","sequence":"additional","affiliation":[{"name":"Contemporary Amperex Technology Co., Limited , 2 Xingang Road, Zhangwan Town, Jiaocheng District, Ningde, Fujian 352100 , China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"33","published-online":{"date-parts":[[2024,4,16]]},"reference":[{"key":"2024041619290484100_CIT0001","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1016\/j.jmsy.2019.12.002","article-title":"Automated Guided Vehicle Systems, State-of-the-Art Control Algorithms and Techniques","volume":"54","author":"De Ryck","year":"2020","journal-title":"J. Manuf. Syst."},{"issue":"4","key":"2024041619290484100_CIT0002","doi-asserted-by":"publisher","DOI":"10.1115\/1.4045143","article-title":"A Heuristic Scaling Strategy for Multi-Robot Cooperative Three-Dimensional Printing","volume":"20","author":"Poudel","year":"2020","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"5","key":"2024041619290484100_CIT0003","doi-asserted-by":"publisher","first-page":"051003","DOI":"10.1115\/1.4046587","article-title":"An Extended Bayesian Optimization Approach to Decentralized Swarm Robotic Search","volume":"20","author":"Ghassemi","year":"2020","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"key":"2024041619290484100_CIT0004","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1016\/j.artint.2014.11.006","article-title":"Conflict-Based Search for Optimal Multi-agent Pathfinding","volume":"219","author":"Sharon","year":"2015","journal-title":"Artif. Intell."},{"key":"2024041619290484100_CIT0005","first-page":"3260","article-title":"M*: A Complete Multirobot Path Planning Algorithm With Performance Bounds","author":"Wagner","year":"2011"},{"issue":"1","key":"2024041619290484100_CIT0006","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1609\/socs.v10i1.18510","article-title":"Multi-Agent Pathfinding: Definitions, Variants, and Benchmarks","volume":"10","author":"Stern","year":"2021","journal-title":"Proc. Int. Symp. Comb. Search"},{"issue":"3","key":"2024041619290484100_CIT0007","doi-asserted-by":"publisher","first-page":"2378","DOI":"10.1109\/LRA.2019.2903261","article-title":"PRIMAL: Pathfinding Via Reinforcement and Imitation Multi-agent Learning","volume":"4","author":"Sartoretti","year":"2019","journal-title":"IEEE Rob. Autom. Lett."},{"key":"2024041619290484100_CIT0008","first-page":"11785","article-title":"Graph Neural Networks for Decentralized Multi-robot Path Planning","author":"Li","year":"2020"},{"issue":"1","key":"2024041619290484100_CIT0009","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1609\/socs.v5i1.18315","article-title":"Suboptimal Variants of the Conflict-Based Search Algorithm for the Multi-agent Pathfinding Problem","volume":"5","author":"Barer","year":"2021","journal-title":"Proc. Int. Symp. Comb. Search"},{"key":"2024041619290484100_CIT0010","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-642-19457-3_1","article-title":"Reciprocal n-Body Collision Avoidance","author":"van den Berg","year":"2009"},{"article-title":"The Holy Grail of Multi-Robot Planning: Learning to Generate Online-Scalable Solutions From Offline-Optimal Experts","year":"2022","author":"Prorok","key":"2024041619290484100_CIT0011"},{"issue":"9","key":"2024041619290484100_CIT0012","doi-asserted-by":"publisher","first-page":"773","DOI":"10.3390\/machines10090773","article-title":"A Review of Path-Planning Approaches for Multiple Mobile Robots","volume":"10","author":"Lin","year":"2022","journal-title":"Machines"},{"issue":"3","key":"2024041619290484100_CIT0013","doi-asserted-by":"publisher","first-page":"5533","DOI":"10.1109\/LRA.2021.3077863","article-title":"Message-Aware Graph Attention Networks for Large-Scale Multi-Robot Path Planning","volume":"6","author":"Li","year":"2021","journal-title":"IEEE Rob. Autom. Lett."},{"article-title":"Attention, Learn to Solve Routing Problems!","year":"2019","author":"Kool","key":"2024041619290484100_CIT0014"},{"key":"2024041619290484100_CIT0015","first-page":"8815","article-title":"Learning Scalable Policies Over Graphs for Multi-Robot Task Allocation Using Capsule Attention Networks","author":"Paul","year":"2022"},{"issue":"1","key":"2024041619290484100_CIT0016","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1007\/s10514-021-09997-2","article-title":"Heterogeneous Graph Attention Networks for Scalable Multi-Robot Scheduling With Temporospatial Constraints","volume":"46","author":"Wang","year":"2022","journal-title":"Auton. Rob."},{"key":"2024041619290484100_CIT0017","first-page":"5779","article-title":"Efficient Planning of Multi-Robot Collective Transport Using Graph Reinforcement Learning With Higher Order Topological Abstraction","author":"Paul","year":"2023"},{"key":"2024041619290484100_CIT0018","first-page":"8699","article-title":"Distributed Heuristic Multi-agent Path Finding With Communication","author":"Ma","year":"2021"},{"article-title":"Succinct and Robust Multi-agent Communication With Temporal Message Control","year":"2020","author":"Zhang","key":"2024041619290484100_CIT0019"},{"key":"2024041619290484100_CIT0020","first-page":"22069","article-title":"Learning Individually Inferred Communication for Multi-Agent Cooperation","author":"Ding","year":"2020"},{"issue":"2","key":"2024041619290484100_CIT0021","doi-asserted-by":"publisher","first-page":"1455","DOI":"10.1109\/LRA.2021.3139145","article-title":"Learning Selective Communication for Multi-Agent Path Finding","volume":"7","author":"Ma","year":"2022","journal-title":"IEEE Rob. Autom. Lett."},{"issue":"2","key":"2024041619290484100_CIT0022","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1007\/s10458-022-09580-8","article-title":"Learning Structured Communication for Multi-agent Reinforcement Learning","volume":"36","author":"Sheng","year":"2022","journal-title":"Auton. Agent Multi-Agent Syst."},{"issue":"10","key":"2024041619290484100_CIT0023","doi-asserted-by":"crossref","first-page":"10233","DOI":"10.1109\/TII.2023.3240585","article-title":"Transformer-Based Imitative Reinforcement Learning for Multi-robot Path Planning","volume":"19","author":"Chen","year":"2023","journal-title":"IEEE Trans. Ind. Inform."},{"article-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","year":"2015","author":"Simonyan","key":"2024041619290484100_CIT0024"},{"article-title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","year":"2014","author":"Chung","key":"2024041619290484100_CIT0025"},{"article-title":"Graph Attention Networks","year":"2018","author":"Veli\u010dkovi\u0107","key":"2024041619290484100_CIT0026"},{"key":"2024041619290484100_CIT0027","first-page":"6000","article-title":"Attention Is All You Need","author":"Vaswani","year":"2017"},{"key":"2024041619290484100_CIT0028","first-page":"4693","article-title":"End-to-End Driving Via Conditional Imitation Learning","author":"Codevilla","year":"2018"}],"container-title":["Journal of Computing and Information Science in Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/24\/8\/084501\/7328652\/jcise_24_8_084501.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/24\/8\/084501\/7328652\/jcise_24_8_084501.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,16]],"date-time":"2024-04-16T19:29:17Z","timestamp":1713295757000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article\/24\/8\/084501\/1198899\/A-Decentralized-Multi-Agent-Path-Planning-Approach"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,16]]},"references-count":28,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,8,1]]}},"URL":"https:\/\/doi.org\/10.1115\/1.4065167","relation":{},"ISSN":["1530-9827","1944-7078"],"issn-type":[{"type":"print","value":"1530-9827"},{"type":"electronic","value":"1944-7078"}],"subject":[],"published":{"date-parts":[[2024,4,16]]},"article-number":"084501"}}