{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T11:12:24Z","timestamp":1767611544070,"version":"3.41.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T00:00:00Z","timestamp":1713744000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T00:00:00Z","timestamp":1713744000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1007\/s11432-022-3666-2","type":"journal-article","created":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T05:02:01Z","timestamp":1713934921000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Perception field based imitation learning for unlabeled multi-agent pathfinding"],"prefix":"10.1007","volume":"67","author":[{"given":"Wenjie","family":"Chu","sequence":"first","affiliation":[]},{"given":"Ailun","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Haiyan","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Zhi","family":"Jin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,4,22]]},"reference":[{"key":"3666_CR1","unstructured":"Ma H, Koenig S. Optimal target assignment and path finding for teams of agents. In: Proceedings of the International Conference on Autonomous Agents & Multiagent Systems, Singapore, 2016. 1144\u20131152"},{"key":"3666_CR2","series-title":"Dissertation for Ph.D. Degree","volume-title":"Target assignment and path planning for navigation tasks with teams of agents","author":"H Ma","year":"2020","unstructured":"Ma H. Target assignment and path planning for navigation tasks with teams of agents. Dissertation for Ph.D. Degree. Los Angeles: University of Southern California, 2020"},{"key":"3666_CR3","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1109\/TRO.2020.2967656","volume":"36","author":"H L Wang","year":"2020","unstructured":"Wang H L, Rubenstein M. Shape formation in homogeneous swarms using local task swapping. IEEE Trans Robot, 2020, 36: 597\u2013612","journal-title":"IEEE Trans Robot"},{"key":"3666_CR4","unstructured":"Li J Y, Tinka A, Kiesel S, et al. Lifelong multi-agent path finding in large-scale warehouses. In: Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems, Richland, 2020. 1898\u20131900"},{"key":"3666_CR5","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1142\/S2301385018500036","volume":"6","author":"K Z Y Ang","year":"2018","unstructured":"Ang K Z Y, Dong X, Liu W, et al. High-precision multi-UAV teaming for the first outdoor night show in Singapore. Unman Sys, 2018, 6: 39\u201365","journal-title":"Unman Sys"},{"key":"3666_CR6","doi-asserted-by":"publisher","first-page":"e1006523","DOI":"10.1371\/journal.pcbi.1006523","volume":"14","author":"D Str\u00f6mbom","year":"2018","unstructured":"Str\u00f6mbom D, Dussutour A. Self-organized traffic via priority rules in leaf-cutting ants. PLoS Comput Biol, 2018, 14: e1006523","journal-title":"PLoS Comput Biol"},{"key":"3666_CR7","doi-asserted-by":"crossref","unstructured":"Yu J J, LaValle S M. Multi-agent path planning and network flow. In: Proceedings of the Algorithmic Foundations of Robotics X, 2013","DOI":"10.1007\/978-3-642-36279-8_10"},{"key":"3666_CR8","unstructured":"Okumura K, Defago X. Solving simultaneous target assignment and path planning efficiently with time-independent execution. 2021. ArXiv:2109.04264"},{"key":"3666_CR9","doi-asserted-by":"crossref","unstructured":"Yu J J, LaValle S M. Shortest path set induced vertex ordering and its application to distributed distance optimal formation path planning and control on graphs. In: Proceedings of the 52nd IEEE Conference on Decision and Control, 2013. 2775\u20132780","DOI":"10.1109\/CDC.2013.6760303"},{"key":"3666_CR10","unstructured":"H\u00f6nig W, Kiesel S, Tinka A, et al. Conflict-based search with optimal task assignment. In: Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, 2018"},{"key":"3666_CR11","unstructured":"Nguyen V, Obermeier P, Son T C, et al. Generalized target assignment and path finding using answer set programming. In: Proceedings of the 12th Annual Symposium on Combinatorial Search, 2019"},{"key":"3666_CR12","doi-asserted-by":"crossref","unstructured":"Ma Z Y, Luo Y D, Ma H. Distributed heuristic multi-agent path finding with communication. 2021. ArXiv:2106.11365","DOI":"10.1109\/ICRA48506.2021.9560748"},{"key":"3666_CR13","doi-asserted-by":"publisher","first-page":"2666","DOI":"10.1109\/LRA.2021.3062803","volume":"6","author":"M Damani","year":"2021","unstructured":"Damani M, Luo Z Y, Wenzel E, et al. PRIMAL2: pathfinding via reinforcement and imitation multi-agent learning-lifelong. IEEE Robot Autom Lett, 2021, 6: 2666\u20132673","journal-title":"IEEE Robot Autom Lett"},{"key":"3666_CR14","doi-asserted-by":"crossref","unstructured":"Li Q B, Gama F, Ribeiro A, et al. Graph neural networks for decentralized multi-robot path planning. In: Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020. 11785\u201311792","DOI":"10.1109\/IROS45743.2020.9341668"},{"key":"3666_CR15","doi-asserted-by":"publisher","first-page":"5533","DOI":"10.1109\/LRA.2021.3077863","volume":"6","author":"Q B Li","year":"2021","unstructured":"Li Q B, Lin W Z, Liu Z, et al. Message-aware graph attention networks for large-scale multi-robot path planning. IEEE Robot Autom Lett, 2021, 6: 5533\u20135540","journal-title":"IEEE Robot Autom Lett"},{"key":"3666_CR16","first-page":"21","volume":"50","author":"A Hussein","year":"2017","unstructured":"Hussein A, Gaber M M, Elyan E, et al. Imitation learning: a survey of learning methods. ACM Comput Surv, 2017, 50: 21","journal-title":"ACM Comput Surv"},{"key":"3666_CR17","unstructured":"Duan Y, Andrychowicz M, Stadie B C, et al. One-shot imitation learning. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017"},{"key":"3666_CR18","volume-title":"Behavioral Cloning","author":"C Sammut","year":"2010","unstructured":"Sammut C. Behavioral Cloning. Berlin: Springer, 2010"},{"key":"3666_CR19","doi-asserted-by":"publisher","first-page":"4249","DOI":"10.1109\/LRA.2020.2994035","volume":"5","author":"B Riviere","year":"2020","unstructured":"Riviere B, Honig W, Yue Y, et al. GLAS: global-to-local safe autonomy synthesis for multi-robot motion planning with end-to-end learning. IEEE Robot Autom Lett, 2020, 5: 4249\u20134256","journal-title":"IEEE Robot Autom Lett"},{"key":"3666_CR20","doi-asserted-by":"crossref","unstructured":"Surynek P, Felner A, Stern R, et al. Efficient sat approach to multi-agent path finding under the sum of costs objective. In: Proceedings of the 22nd European Conference on Artificial Intelligence, 2016. 810\u2013818","DOI":"10.3233\/978-1-61499-672-9-810"},{"key":"3666_CR21","doi-asserted-by":"crossref","unstructured":"Yu J J, LaValle S M. Planning optimal paths for multiple robots on graphs. In: Proceedings of the IEEE International Conference on Robotics and Automation, Karlsruhe, 2013. 3612\u20133617","DOI":"10.1109\/ICRA.2013.6631084"},{"key":"3666_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.artint.2014.11.001","volume":"219","author":"G Wagner","year":"2015","unstructured":"Wagner G, Choset H. Subdimensional expansion for multirobot path planning. Artif Intell, 2015, 219: 1\u201324","journal-title":"Artif Intell"},{"key":"3666_CR23","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1016\/j.artint.2014.11.006","volume":"219","author":"G Sharon","year":"2015","unstructured":"Sharon G, Stern R, Felner A, et al. Conflict-based search for optimal multi-agent pathfinding. Artif Intell, 2015, 219: 40\u201366","journal-title":"Artif Intell"},{"key":"3666_CR24","doi-asserted-by":"crossref","unstructured":"Felner A, Li J Y, Boyarski E, et al. Adding heuristics to conflict-based search for multi-agent path finding. In: Proceedings of the International Conference on Automated Planning and Scheduling, 2018","DOI":"10.1609\/icaps.v28i1.13883"},{"key":"3666_CR25","doi-asserted-by":"crossref","unstructured":"C\u00e1p M, Nov\u00e1k P, Selecky M, et al. Asynchronous decentralized prioritized planning for coordination in multi-robot system. In: Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems, 2013. 3822\u20133829","DOI":"10.1109\/IROS.2013.6696903"},{"key":"3666_CR26","doi-asserted-by":"crossref","unstructured":"Berg J V D, Guy S J, Lin M C, et al. Reciprocal n-body collision avoidance. In: Proceedings of the Robotics Research, 2011. 3\u201319","DOI":"10.1007\/978-3-642-19457-3_1"},{"key":"3666_CR27","doi-asserted-by":"publisher","first-page":"2378","DOI":"10.1109\/LRA.2019.2903261","volume":"4","author":"G Sartoretti","year":"2019","unstructured":"Sartoretti G, Kerr J, Shi Y, et al. PRIMAL: pathfinding via reinforcement and imitation multi-agent learning. IEEE Robot Autom Lett, 2019, 4: 2378\u20132385","journal-title":"IEEE Robot Autom Lett"},{"key":"3666_CR28","unstructured":"Mnih V, Badia A P, Mirza M, et al. Asynchronous methods for deep reinforcement learning. In: Proceedings of the 33rd International Conference on International Conference on Machine Learning, 2016. 1928\u20131937"},{"key":"3666_CR29","doi-asserted-by":"publisher","first-page":"1745","DOI":"10.1109\/TASE.2022.3185537","volume":"20","author":"W J Chu","year":"2023","unstructured":"Chu W J, Zhang W, Zhao H Y, et al. Massive shape formation in grid environments. IEEE Trans Autom Sci Eng, 2023, 20: 1745\u20131759","journal-title":"IEEE Trans Autom Sci Eng"},{"key":"3666_CR30","unstructured":"Rashid T, Samvelyan M, Schroeder C, et al. QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning. In: Proceedings of the International Conference on Machine Learning, 2018. 4295\u20134304"},{"key":"3666_CR31","doi-asserted-by":"crossref","unstructured":"Foerster J, Farquhar G, Afouras T, et al. Counterfactual multi-agent policy gradients. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2018","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"3666_CR32","unstructured":"Inala J P, Yang Y C, Paulos J, et al. Neurosymbolic transformers for multi-agent communication. In: Proceedings of the Advances in Neural Information Processing Systems, 2020. 13597\u201313608"},{"key":"3666_CR33","unstructured":"Ma H, Li J Y, Kumar T K S, et al. Lifelong multi-agent path finding for online pickup and delivery tasks. 2017. ArXiv:1705.10868"},{"key":"3666_CR34","unstructured":"Liu M H, Ma H, Li J Y, et al. Task and path planning for multi-agent pickup and delivery. In: Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2019"},{"key":"3666_CR35","doi-asserted-by":"crossref","unstructured":"Kou N M, Peng C, Ma H, et al. Idle time optimization for target assignment and path finding in sortation centers. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2020. 9925\u20139932","DOI":"10.1609\/aaai.v34i06.6547"},{"key":"3666_CR36","unstructured":"Ma Y, Hao X T, Hao J Y, et al. A hierarchical reinforcement learning based optimization framework for large-scale dynamic pickup and delivery problems. In: Proceedings of the Advances in Neural Information Processing Systems, 2021. 23609\u201323620"},{"key":"3666_CR37","unstructured":"Devlin J, Chang M W, Lee K, et al. BERT: pre-training of deep bidirectional transformers for language understanding. 2018. ArXiv:1810.04805"},{"key":"3666_CR38","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16\u00d716 words: transformers for image recognition at scale. 2020. ArXiv:2010.11929"},{"key":"3666_CR39","doi-asserted-by":"crossref","unstructured":"Chen C F R, Fan Q, Panda R. CrossViT: cross-attention multi-scale vision transformer for image classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), 2021. 357\u2013366","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"3666_CR40","unstructured":"Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. In: Proceedings of the Advances in Neural Information Processing Systems, 2017. 5998\u20136008"},{"key":"3666_CR41","unstructured":"Boyarski E, Felner A, Stern R, et al. ICBS: improved conflict-based search algorithm for multi-agent pathfinding. In: Proceedings of the 24th International Joint Conference on Artificial Intelligence, 2015"},{"key":"3666_CR42","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"R S Sutton","year":"1999","unstructured":"Sutton R S, Precup D, Singh S. Between MDPs and semi-MDPs: a framework for temporal abstraction in reinforcement learning. Artif Intell, 1999, 112: 181\u2013211","journal-title":"Artif Intell"},{"key":"3666_CR43","unstructured":"Kulkarni T D, Narasimhan K, Saeedi A, et al. Hierarchical deep reinforcement learning: integrating temporal abstraction and intrinsic motivation. In: Proceedings of the Advances in Neural Information Processing Systems, 2016"},{"key":"3666_CR44","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1022140919877","volume":"13","author":"A G Barto","year":"2003","unstructured":"Barto A G, Mahadevan S. Recent advances in hierarchical reinforcement learning. Discrete Event Dyn Syst, 2003, 13: 41\u201377","journal-title":"Discrete Event Dyn Syst"},{"key":"3666_CR45","unstructured":"Le H, Jiang N, Agarwal A, et al. Hierarchical imitation and reinforcement learning. In: Proceedings of the International Conference on Machine Learning, 2018. 2917\u20132926"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-022-3666-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-022-3666-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-022-3666-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T19:52:38Z","timestamp":1750362758000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-022-3666-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,22]]},"references-count":45,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,5]]}},"alternative-id":["3666"],"URL":"https:\/\/doi.org\/10.1007\/s11432-022-3666-2","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"type":"print","value":"1674-733X"},{"type":"electronic","value":"1869-1919"}],"subject":[],"published":{"date-parts":[[2024,4,22]]},"assertion":[{"value":"5 April 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 July 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 October 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 April 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"152107"}}