{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:26:58Z","timestamp":1772119618126,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T00:00:00Z","timestamp":1673827200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T00:00:00Z","timestamp":1673827200000},"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":["Geoinformatica"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s10707-023-00486-5","type":"journal-article","created":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T06:05:09Z","timestamp":1673849109000},"page":"709-736","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Optimizing pedestrian simulation based on expert trajectory guidance and deep reinforcement learning"],"prefix":"10.1007","volume":"27","author":[{"given":"Senlin","family":"Mu","sequence":"first","affiliation":[]},{"given":"Xiao","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Moyang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Di","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Dong","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Xiang","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,1,16]]},"reference":[{"key":"486_CR1","doi-asserted-by":"publisher","DOI":"10.27149\/d.cnki.ghdsu.2021.000427","author":"D Xu","year":"2021","unstructured":"Xu D (2021) Study on micro-scale pedestrian simulation using reinforcement learning [D]. East China Normal University. https:\/\/doi.org\/10.27149\/d.cnki.ghdsu.2021.000427","journal-title":"East China Normal University"},{"key":"486_CR2","doi-asserted-by":"publisher","unstructured":"Du J (2020) Research on emergency evacuation modeling and path planning based on artificial bee colony algorithm [D]. Hubei University of Technology. https:\/\/doi.org\/10.27131\/d.cnki.ghugc.2020.000042","DOI":"10.27131\/d.cnki.ghugc.2020.000042"},{"key":"486_CR3","unstructured":"Helbing D, Farkas IJ, Molnar P et al (2002) Simulation of pedestrian crowds in normal and evacuation situations[J]. Pedestr Evacuation Dyn 21(2):21\u201358"},{"key":"486_CR4","first-page":"173","volume":"173","author":"J Dijkstra","year":"2001","unstructured":"Dijkstra J, Jessurun J, Timmermans HJP (2001) A multi-agent cellular automata model of pedestrian movement[J]. Pedestr Evacuation Dyn 173:173\u2013180","journal-title":"Pedestr Evacuation Dyn"},{"key":"486_CR5","unstructured":"Helbing D (1998) A fluid dynamic model for the movement of pedestrians[J]. arXiv preprint cond-mat\/9805213"},{"issue":"11","key":"486_CR6","first-page":"108","volume":"22","author":"Z Wu","year":"2012","unstructured":"Wu Z, Liu D, Cheng Y, Sun Y (2012) Three-dimensional crowd simulation of agent-based method[J]. Comput Technol Dev 22(11):108\u2013112","journal-title":"Comput Technol Dev"},{"key":"486_CR7","doi-asserted-by":"publisher","unstructured":"Zhao L, Guo M, Tang S, Tang J (2022) Adaptive crowd evacuation simulation model based on bounded rationality constraints [J\/OL]. J Syst Simul: 1\u20139. https:\/\/doi.org\/10.16182\/j.issn1004731x.joss.21-0472","DOI":"10.16182\/j.issn1004731x.joss.21-0472"},{"issue":"3","key":"486_CR8","first-page":"205","volume":"2","author":"Y Shen","year":"2020","unstructured":"Shen Y, Han J, Li L et al (2020) AI in game intelligence\u2014from multi-role game to parallel game[J]. Chin J Intell Sci Technol 2(3):205\u2013213","journal-title":"Chin J Intell Sci Technol"},{"key":"486_CR9","unstructured":"Hu Y, Mottaghi R, Kolve E et al (2017) Target-driven visual navigation in indoor scenes using deep reinforcement learning[C].\u00a02017 IEEE international conference on robotics and automation (ICRA). Piscataway: IEEE Press, pp 3357\u20133364"},{"key":"486_CR10","unstructured":"Shani G, Heckerman D, Brafman RI et al (2005) An MDP-based recommender system[J]. J Mach Learn Res 6(9):1265\u20131295"},{"key":"486_CR11","doi-asserted-by":"publisher","unstructured":"Yao Z (2020) Research on simulation method of crowd evacuation based on reinforcement learning and deep residual network learning [D]. Shandong Normal University. https:\/\/doi.org\/10.27280\/d.cnki.gsdsu.2020.001531","DOI":"10.27280\/d.cnki.gsdsu.2020.001531"},{"issue":"3","key":"486_CR12","doi-asserted-by":"publisher","first-page":"756","DOI":"10.1111\/tgis.12620","volume":"24","author":"D Xu","year":"2020","unstructured":"Xu D, Huang X, Li Z et al (2020) Local motion simulation using deep reinforcement learning[J]. Trans GIS 24(3):756\u2013779","journal-title":"Trans GIS"},{"key":"486_CR13","doi-asserted-by":"publisher","unstructured":"Lowe R, Wu Y I, Tamar A, et al (2017) Multi-agent actor-critic for mixed cooperative-competitive environments[J]. Advances in Neural Information Processing systems.\u00a0https:\/\/doi.org\/10.48550\/arXiv.1706.02275","DOI":"10.48550\/arXiv.1706.02275"},{"key":"486_CR14","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1016\/j.neucom.2020.05.097","volume":"411","author":"F Zhang","year":"2020","unstructured":"Zhang F, Li J, Li ZA (2020) TD3-based multi-agent deep reinforcement learning method in mixed cooperation-competition environment[J]. Neurocomputing 411:206\u2013215","journal-title":"Neurocomputing"},{"key":"486_CR15","unstructured":"Zhelo O, Zhang J, Tai L et al (2018) Curiosity-driven exploration for mapless navigation with deep reinforcement learning[J], arXiv: 1804.00456"},{"key":"486_CR16","doi-asserted-by":"publisher","unstructured":"Yang Y (2019) Study on crowd evacuation simulation models for semi-submersible accommodation platform [D]. Shanghai Jiao Tong University. https:\/\/doi.org\/10.27307\/d.cnki.gsjtu.2019.001894","DOI":"10.27307\/d.cnki.gsjtu.2019.001894"},{"key":"486_CR17","doi-asserted-by":"crossref","unstructured":"Bounini F, Gingras D, Pollart H et al (2017) Modified artificial potential field method for online path planning applications[C].\u00a02017 IEEE Intelligent Vehicles Symposium (IV). IEEE, pp 180\u2013185","DOI":"10.1109\/IVS.2017.7995717"},{"key":"486_CR18","unstructured":"Wu H (2017) Evacuation Simulation of indoor pedestrian [D]. University of Electronic Science and Technology of China"},{"issue":"03","key":"486_CR19","first-page":"63","volume":"38","author":"S Ma","year":"2021","unstructured":"Ma S, Zhang R, Qi Z, Hao J (2021) Research on improvement of social force model of opposite avoidance and contact behavior [J]. Comput Simul 38(03):63\u201367","journal-title":"Comput Simul"},{"issue":"3","key":"486_CR20","doi-asserted-by":"publisher","first-page":"4520","DOI":"10.1109\/LRA.2021.3067851","volume":"6","author":"K Guo","year":"2021","unstructured":"Guo K, Wang D, Fan T et al (2021) VR-ORCA: variable responsibility optimal reciprocal collision Avoidance[J]. IEEE Rob Autom Lett 6(3):4520\u20134527","journal-title":"IEEE Rob Autom Lett"},{"issue":"03","key":"486_CR21","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1360\/N112017-00253","volume":"48","author":"G He","year":"2018","unstructured":"He G, Jiang D, Jin Y, Chen Q, Lu X, Xu M (2018) Crowd behavior simulation based on shadow obstacle and ORCA models [J]. Sci Sin Informationis 48(03):233\u2013247","journal-title":"Sci Sin Informationis"},{"issue":"7587","key":"486_CR22","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver D, Huang A, Maddison CJ et al (2016) Mastering the game of go with deep neural networks and tree search[J]. Nature 529(7587):484\u2013489","journal-title":"Nature"},{"issue":"7540","key":"486_CR23","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D et al (2015) Human-level control through deep reinforcement learning[J]. Nature 518(7540):529\u2013533","journal-title":"Nature"},{"key":"486_CR24","doi-asserted-by":"crossref","unstructured":"Van Hasselt H, Guez A, Silver D (2016) Deep reinforcement learning with double q-learning[C]. Proceedings of the AAAI conference on artificial intelligence, 30(1)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"486_CR25","unstructured":"Wang Z, Schaul T, Hessel M et al (2016) Dueling network architectures for deep reinforcement learning[C]. International conference on machine learning. PMLR, pp\u00a01995\u20132003"},{"key":"486_CR26","unstructured":"Schaul T, Quan J, Antonoglou I et al (2015) Prioritized experience replay[J]. arXiv preprint arXiv:1511.05952"},{"issue":"3","key":"486_CR27","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams RJ (1992) Simple statistical gradient-following algorithms for connectionist reinforcement learning[J]. Mach Learn 8(3):229\u2013256","journal-title":"Mach Learn"},{"key":"486_CR28","unstructured":"Schulman J, Levine S, Abbeel P et al (2015) Trust region policy optimization[C]. International conference on machine learning. PMLR, pp\u00a01889\u20131897"},{"key":"486_CR29","unstructured":"Schulman J, Wolski F, Dhariwal P et al (2017) Proximal policy optimization algorithms[J]. arXiv preprint arXiv:1707.06347"},{"key":"486_CR30","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A et al (2015) Continuous control with deep reinforcement learning[J]. arXiv preprint arXiv:1509.02971"},{"key":"486_CR31","unstructured":"Fujimoto S, Hoof H, Meger D (2018) Addressing function approximation error in actor-critic methods[C]. International conference on machine learning. PMLR, pp 1587\u20131596"},{"key":"486_CR32","unstructured":"Haarnoja T, Zhou A, Abbeel P et al (2018) Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor[C]. International conference on machine learning. PMLR, pp\u00a01861\u20131870"},{"key":"486_CR33","doi-asserted-by":"crossref","unstructured":"Lee J, Won J, Lee J (2018) Crowd simulation by deep reinforcement learning[C]. Proceedings of the 11th Annual International Conference on Motion, Interaction, and Games. pp 1\u20137","DOI":"10.1145\/3274247.3274510"},{"issue":"12","key":"486_CR34","doi-asserted-by":"publisher","first-page":"7363","DOI":"10.1109\/TSMC.2020.2967936","volume":"51","author":"J Sharma","year":"2020","unstructured":"Sharma J, Andersen PA, Granmo OC et al (2020) Deep q-learning with q-matrix transfer learning for novel fire evacuation environment[J]. IEEE Trans Syst Man Cybernet Syst 51(12):7363\u20137381","journal-title":"IEEE Trans Syst Man Cybernet Syst"},{"key":"486_CR35","doi-asserted-by":"publisher","unstructured":"Lu G (2021) Regularized maximum entropy imitation learning based on prior reward of trajectory [D].\u00a0East China Normal University.\u00a0https:\/\/doi.org\/10.27149\/d.cnki.ghdsu.2021.000029","DOI":"10.27149\/d.cnki.ghdsu.2021.000029"},{"key":"486_CR36","unstructured":"Levine S, Kumar A, Tucker G et al (2020) Offline reinforcement learning: Tutorial, review, and perspectives on open problems[J]. arXiv preprint arXiv:2005.01643"},{"key":"486_CR37","doi-asserted-by":"crossref","unstructured":"Berg J, Guy SJ, Lin M et al (2011) Reciprocal n-body collision avoidance[M]. Robotics research. Springer, Berlin, Heidelberg, pp 3\u201319","DOI":"10.1007\/978-3-642-19457-3_1"},{"key":"486_CR38","unstructured":"Fortunato M, Azar MG, Piot B et al (2017) Noisy networks for exploration[J]. arXiv preprint arXiv:1706.10295"},{"key":"486_CR39","first-page":"2115","volume-title":"Employing the hydraulic model in assessing emergency movement[M]. SFPE handbook of fire protection engineering","author":"S Gwynne","year":"2016","unstructured":"Gwynne S, Rosenbaum ER (2016) Employing the hydraulic model in assessing emergency movement[M]. SFPE handbook of fire protection engineering. Springer, New York, pp 2115\u20132151"},{"key":"486_CR40","volume-title":"Pathfinder technical reference","author":"Thunderhead Engineering","year":"2011","unstructured":"Thunderhead Engineering (2011) Pathfinder technical reference. Thunderhead Engineering Consultants, Inc, Manhattan"}],"container-title":["GeoInformatica"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10707-023-00486-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10707-023-00486-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10707-023-00486-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T03:10:39Z","timestamp":1695265839000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10707-023-00486-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,16]]},"references-count":40,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["486"],"URL":"https:\/\/doi.org\/10.1007\/s10707-023-00486-5","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-1798752\/v1","asserted-by":"object"}]},"ISSN":["1384-6175","1573-7624"],"issn-type":[{"value":"1384-6175","type":"print"},{"value":"1573-7624","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,16]]},"assertion":[{"value":"27 June 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 December 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 January 2023","order":4,"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":"Ethics approval and consent to participate"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}