{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T03:10:39Z","timestamp":1778037039407,"version":"3.51.4"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T00:00:00Z","timestamp":1766102400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T00:00:00Z","timestamp":1766102400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62303357"],"award-info":[{"award-number":["62303357"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["2023AFB109"],"award-info":[{"award-number":["2023AFB109"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hubei Provincial Advantaged Characteristic Disciplines (Groups) Project of Wuhan University of Science and Technology","award":["2023D031"],"award-info":[{"award-number":["2023D031"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Intel Serv Robotics"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s11370-025-00664-4","type":"journal-article","created":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T03:53:09Z","timestamp":1766116389000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Offline spatial\u2013temporal actor-critic learning for robot crowd navigation without behavior regularization"],"prefix":"10.1007","volume":"19","author":[{"given":"Shuai","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6456-3839","authenticated-orcid":false,"given":"Hao","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haodong","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zixin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,12,19]]},"reference":[{"key":"664_CR1","doi-asserted-by":"crossref","unstructured":"Daun K, Von\u00a0Stryk O (2023) Requirements and challenges for autonomy and assistance functions for ground rescue robots in reconnaissance missions. In: 2023 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), pp 83\u201390 IEEE","DOI":"10.1109\/SSRR59696.2023.10499930"},{"issue":"4","key":"664_CR2","doi-asserted-by":"publisher","first-page":"2624","DOI":"10.1109\/TSMC.2019.2916932","volume":"51","author":"W Yuan","year":"2019","unstructured":"Yuan W, Li Z, Su C-Y (2019) Multisensor-based navigation and control of a mobile service robot. IEEE Trans Syst Man Cybern Syst 51(4):2624\u20132634","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"664_CR3","doi-asserted-by":"publisher","first-page":"13155","DOI":"10.1007\/s00521-020-04764-3","volume":"32","author":"M-K Ng","year":"2020","unstructured":"Ng M-K, Chong Y-W, Ko K-M, Park Y-H, Leau Y-B (2020) Adaptive path finding algorithm in dynamic environment for warehouse robot. Neural Comput Appl 32:13155\u201313171","journal-title":"Neural Comput Appl"},{"key":"664_CR4","doi-asserted-by":"crossref","unstructured":"Ferrer G, Garrell A, Sanfeliu A (2013) Robot companion: a social-force based approach with human awareness-navigation in crowded environments. In: 2013 IEEE\/RSJ international conference on intelligent robots and systems, pp 1688\u20131694 IEEE","DOI":"10.1109\/IROS.2013.6696576"},{"issue":"5","key":"664_CR5","doi-asserted-by":"publisher","first-page":"4282","DOI":"10.1103\/PhysRevE.51.4282","volume":"51","author":"D Helbing","year":"1995","unstructured":"Helbing D, Molnar P (1995) Social force model for pedestrian dynamics. Phys Rev E 51(5):4282","journal-title":"Phys Rev E"},{"key":"664_CR6","doi-asserted-by":"crossref","unstructured":"Van Den\u00a0Berg J, Guy SJ, Lin M, Manocha D (2011) Reciprocal n-body collision avoidance. In: Robotics research: the 14th international symposium ISRR, pp 3\u201319 Springer","DOI":"10.1007\/978-3-642-19457-3_1"},{"issue":"11","key":"664_CR7","doi-asserted-by":"publisher","first-page":"1289","DOI":"10.1177\/0278364915619772","volume":"35","author":"H Kretzschmar","year":"2016","unstructured":"Kretzschmar H, Spies M, Sprunk C, Burgard W (2016) Socially compliant mobile robot navigation via inverse reinforcement learning. Int J Robot Res 35(11):1289\u20131307","journal-title":"Int J Robot Res"},{"key":"664_CR8","doi-asserted-by":"crossref","unstructured":"Trautman P, Ma J, Murray RM, Krause A (2013) Robot navigation in dense human crowds: the case for cooperation. In: 2013 IEEE international conference on robotics and automation, pp 2153\u20132160 IEEE","DOI":"10.1109\/ICRA.2013.6630866"},{"key":"664_CR9","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1007\/s11370-021-00387-2","volume":"14","author":"J Choi","year":"2021","unstructured":"Choi J, Lee G, Lee C (2021) Reinforcement learning-based dynamic obstacle avoidance and integration of path planning. Intel Serv Robot 14:663\u2013677","journal-title":"Intel Serv Robot"},{"key":"664_CR10","doi-asserted-by":"crossref","unstructured":"Long P, Fan T, Liao X, Liu W, Zhang H, Pan J (2018) Towards optimally decentralized multi-robot collision avoidance via deep reinforcement learning. In: 2018 IEEE international conference on robotics and automation (ICRA), pp 6252\u20136259 IEEE","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"664_CR11","doi-asserted-by":"crossref","unstructured":"Xue J, Zhang S, Lu Y, Yan X, Zheng Y (2024) Bidirectional obstacle avoidance enhancement-deep deterministic policy gradient: a novel algorithm for mobile-robot path planning in unknown dynamic environments. Adv Intell Syst 2300444","DOI":"10.1002\/aisy.202300444"},{"key":"664_CR12","doi-asserted-by":"crossref","unstructured":"Sathyamoorthy AJ, Liang J, Patel U, Guan T, Chandra R, Manocha D (2020) Densecavoid: Real-time navigation in dense crowds using anticipatory behaviors. In: 2020 IEEE international conference on robotics and automation (ICRA), pp 11345\u201311352 IEEE","DOI":"10.1109\/ICRA40945.2020.9197379"},{"key":"664_CR13","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1016\/j.neucom.2020.07.091","volume":"421","author":"Y Lu","year":"2021","unstructured":"Lu Y, Chen Y, Zhao D, Li D (2021) Mgrl: Graph neural network based inference in a markov network with reinforcement learning for visual navigation. Neurocomputing 421:140\u2013150","journal-title":"Neurocomputing"},{"key":"664_CR14","doi-asserted-by":"crossref","unstructured":"Chen YF, Liu M, Everett M, How JP (2017) Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning. In: 2017 IEEE international conference on robotics and automation (ICRA), pp 285\u2013292 IEEE","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"664_CR15","doi-asserted-by":"crossref","unstructured":"Chen YF, Everett M, Liu M, How JP (2017) Socially aware motion planning with deep reinforcement learning. In: 2017 IEEE\/RSJ international conference on intelligent robots and systems (IROS), pp 1343\u20131350 IEEE","DOI":"10.1109\/IROS.2017.8202312"},{"key":"664_CR16","unstructured":"Levine S, Kumar A, Tucker G, Fu J (2020) Offline reinforcement learning: Tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643"},{"key":"664_CR17","doi-asserted-by":"crossref","unstructured":"Everett M, Chen YF, How JP (2018) Motion planning among dynamic, decision-making agents with deep reinforcement learning. In: 2018 IEEE\/RSJ international conference on intelligent robots and systems (IROS), pp 3052\u20133059 IEEE","DOI":"10.1109\/IROS.2018.8593871"},{"key":"664_CR18","doi-asserted-by":"crossref","unstructured":"Chen C, Liu Y, Kreiss S, Alahi A (2019) Crowd-robot interaction: Crowd-aware robot navigation with attention-based deep reinforcement learning. In: 2019 international conference on robotics and automation (ICRA), pp 6015\u20136022 IEEE","DOI":"10.1109\/ICRA.2019.8794134"},{"key":"664_CR19","doi-asserted-by":"crossref","unstructured":"Liu S, Chang P, Liang W, Chakraborty N, Driggs-Campbell K (2021) Decentralized structural-rnn for robot crowd navigation with deep reinforcement learning. In: 2021 IEEE international conference on robotics and automation (ICRA), pp 3517\u20133524 IEEE","DOI":"10.1109\/ICRA48506.2021.9561595"},{"key":"664_CR20","doi-asserted-by":"crossref","unstructured":"Yang Y, Jiang J, Zhang J, Huang J, Gao M (2023) St$$^{2}$$: Spatial-temporal state transformer for crowd-aware autonomous navigation. IEEE Robot Autom Lett 8(2):912\u2013919","DOI":"10.1109\/LRA.2023.3234815"},{"key":"664_CR21","doi-asserted-by":"crossref","unstructured":"Berg J, Lin M, Manocha D (2008) Reciprocal velocity obstacles for real-time multi-agent navigation. In: 2008 IEEE international conference on robotics and automation, pp 1928\u20131935 IEEE","DOI":"10.1109\/ROBOT.2008.4543489"},{"key":"664_CR22","doi-asserted-by":"crossref","unstructured":"Trautman P, Krause A (2010) Unfreezing the robot: navigation in dense, interacting crowds. In 2010 IEEE RSJ international conference on intelligent robots and systems, pp 797\u2013803 IEEE","DOI":"10.1109\/IROS.2010.5654369"},{"issue":"4","key":"664_CR23","doi-asserted-by":"publisher","first-page":"2289","DOI":"10.1109\/TSMC.2020.3048964","volume":"52","author":"Y Chen","year":"2021","unstructured":"Chen Y, Zhao F, Lou Y (2021) Interactive model predictive control for robot navigation in dense crowds. IEEE Trans Syst Man Cybern Syst 52(4):2289\u20132301","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"664_CR24","doi-asserted-by":"crossref","unstructured":"Eiffert S, Kong H, Pirmarzdashti N, Sukkarieh S (2020) Path planning in dynamic environments using generative rnns and monte carlo tree search. In: 2020 IEEE international conference on robotics and automation (ICRA), pp 10263\u201310269 IEEE","DOI":"10.1109\/ICRA40945.2020.9196631"},{"issue":"12","key":"664_CR25","doi-asserted-by":"publisher","first-page":"3461","DOI":"10.1109\/TITS.2017.2715836","volume":"18","author":"K Driggs-Campbell","year":"2017","unstructured":"Driggs-Campbell K, Govindarajan V, Bajcsy R (2017) Integrating intuitive driver models in autonomous planning for interactive maneuvers. IEEE Trans Intell Transp Syst 18(12):3461\u20133472","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"3","key":"664_CR26","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1109\/TIV.2018.2843125","volume":"3","author":"K Driggs-Campbell","year":"2018","unstructured":"Driggs-Campbell K, Dong R, Bajcsy R (2018) Robust, informative human-in-the-loop predictions via empirical reachable sets. IEEE Trans Intell Vehicl 3(3):300\u2013309","journal-title":"IEEE Trans Intell Vehicl"},{"issue":"2","key":"664_CR27","doi-asserted-by":"publisher","first-page":"656","DOI":"10.1109\/LRA.2017.2651371","volume":"2","author":"P Long","year":"2017","unstructured":"Long P, Liu W, Pan J (2017) Deep-learned collision avoidance policy for distributed multiagent navigation. IEEE Robot Autom Lett 2(2):656\u2013663","journal-title":"IEEE Robot Autom Lett"},{"issue":"4","key":"664_CR28","doi-asserted-by":"publisher","first-page":"2393","DOI":"10.1109\/TII.2019.2936167","volume":"16","author":"H Shi","year":"2019","unstructured":"Shi H, Shi L, Xu M, Hwang K-S (2019) End-to-end navigation strategy with deep reinforcement learning for mobile robots. IEEE Trans Ind Inf 16(4):2393\u20132402","journal-title":"IEEE Trans Ind Inf"},{"key":"664_CR29","doi-asserted-by":"crossref","unstructured":"Lu X, Faragasso A, Wang Y, Yamashita A, Asama H (2025) Group-aware robot navigation in crowds using spatio-temporal graph attention network with deep reinforcement learning. IEEE Robot Autom Lett","DOI":"10.1109\/LRA.2025.3549663"},{"key":"664_CR30","doi-asserted-by":"crossref","unstructured":"Zhou Y, Garcke J (2024) Learning crowd behaviors in navigation with attention-based spatial-temporal graphs. In: 2024 IEEE international conference on robotics and automation (ICRA), pp 5485\u20135491 IEEE","DOI":"10.1109\/ICRA57147.2024.10610279"},{"key":"664_CR31","unstructured":"Liu S, Xia H, Pouria FC, Hong K, Chakraborty N, Driggs-Campbell K (2024) Height: Heterogeneous interaction graph transformer for robot navigation in crowded and constrained environments. arXiv preprint arXiv:2411.12150"},{"key":"664_CR32","unstructured":"Kostrikov I, Nair A, Levine S (2021) Offline reinforcement learning with implicit q-learning. arXiv preprint arXiv:2110.06169"},{"key":"664_CR33","doi-asserted-by":"publisher","first-page":"2835","DOI":"10.1038\/s41467-025-58192-9","volume":"16","author":"Y Wang","year":"2025","unstructured":"Wang Y, Wu J, He H, Wei Z, Sun F (2025) Data-driven energy management for electric vehicles using offline reinforcement learning. Nat Commun 16:2835","journal-title":"Nat Commun"},{"issue":"1","key":"664_CR34","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1109\/TII.2024.3423440","volume":"21","author":"Z Yuan","year":"2025","unstructured":"Yuan Z, Zhang Z, Li X, Cui Y, Li M, Ban X (2025) Controlling partially observed industrial system based on offline reinforcement learning\u2014a case study of paste thickener. IEEE Trans Ind Inf 21(1):49\u201359","journal-title":"IEEE Trans Ind Inf"},{"issue":"10","key":"664_CR35","doi-asserted-by":"publisher","first-page":"12703","DOI":"10.1109\/TWC.2024.3395624","volume":"23","author":"K Yang","year":"2024","unstructured":"Yang K, Shi C, Shen C, Yang J, Yeh S-P, Sydir JJ (2024) Offline reinforcement learning for wireless network optimization with mixture datasets. IEEE Trans Wireless Commun 23(10):12703\u201312716","journal-title":"IEEE Trans Wireless Commun"},{"key":"664_CR36","unstructured":"Peng XB, Kumar A, Zhang G, Levine S (2019) Advantage-weighted regression: Simple and scalable off-policy reinforcement learning. arXiv preprint arXiv:1910.00177"},{"key":"664_CR37","doi-asserted-by":"crossref","unstructured":"Leigh A, Pineau J, Olmedo N, Zhang H (2015) Person tracking and following with 2d laser scanners. In: 2015 IEEE international conference on robotics and automation (ICRA), pp 726\u2013733","DOI":"10.1109\/ICRA.2015.7139259"},{"key":"664_CR38","unstructured":"Fu J, Kumar A, Nachum O, Tucker G, Levine S (2020) D4rl: Datasets for deep data-driven reinforcement learning. arXiv preprint arXiv:2004.07219"},{"key":"664_CR39","unstructured":"Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980"}],"container-title":["Intelligent Service Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11370-025-00664-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11370-025-00664-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11370-025-00664-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T02:16:08Z","timestamp":1778033768000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11370-025-00664-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,19]]},"references-count":39,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["664"],"URL":"https:\/\/doi.org\/10.1007\/s11370-025-00664-4","relation":{},"ISSN":["1861-2776","1861-2784"],"issn-type":[{"value":"1861-2776","type":"print"},{"value":"1861-2784","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,19]]},"assertion":[{"value":"1 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not Applicable","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"The authors have no conflict of interest to declare that are relevant to the content of this article.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"6"}}