{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T14:25:03Z","timestamp":1762266303726,"version":"build-2065373602"},"reference-count":39,"publisher":"Association for Computing Machinery (ACM)","issue":"4","funder":[{"name":"National Science Foundation","award":["1952011"],"award-info":[{"award-number":["1952011"]}]},{"name":"Federal Transit Administration COVID-19 Research","award":["TN-2021-015-00"],"award-info":[{"award-number":["TN-2021-015-00"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Cyber-Phys. Syst."],"published-print":{"date-parts":[[2025,10,31]]},"abstract":"<jats:p>Public bus transit systems provide critical transportation services for large sections of modern communities. On-time performance and maintaining the reliable quality of service is therefore very important. Unfortunately, disruptions caused by overcrowding, vehicular failures, and road accidents often lead to service performance degradation. Though transit agencies keep a limited number of vehicles in reserve and dispatch them to relieve the affected routes during disruptions, the procedure is often ad-hoc and has to rely on human experience and intuition to allocate resources (vehicles) to affected trips under uncertainty. In this article, we describe a principled approach using non-myopic sequential decision procedures to solve the problem and decide (a) if it is advantageous to anticipate problems and proactively station transit buses near areas with high-likelihood of disruptions and (b) decide if and which vehicle to dispatch to a particular problem. Our approach was developed in partnership WeGo Public Transit, a public transportation agency based in Nashville, Tennessee and models the system as a semi-Markov decision problem (solved as a Monte-Carlo tree search procedure) and shows that it is possible to obtain an answer to these two coupled decision problems in a way that maximizes the overall reward (number of people served). We sample many possible futures from generative models; each is assigned to a tree and processed using root parallelization. We validate our approach with both real-world and scaled-up data from two agencies in Tennessee. Our experiments show that the proposed framework serves 2% more passengers while reducing deadhead miles by 40%. Finally, we introduce Vectura, a dashboard providing transit dispatchers a complete view of the transit system at a glance along with access to our developed tools.<\/jats:p>","DOI":"10.1145\/3754454","type":"journal-article","created":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T12:10:45Z","timestamp":1753791045000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["An End-to-End Solution for Public Transit Stationing and Dispatch Problem"],"prefix":"10.1145","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0921-182X","authenticated-orcid":false,"given":"Jose Paolo","family":"Talusan","sequence":"first","affiliation":[{"name":"Vanderbilt University, Nashville, Tennessee, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5275-7142","authenticated-orcid":false,"given":"Chaeeun","family":"Han","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University, University Park, Pennsylvania, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8207-4638","authenticated-orcid":false,"given":"David","family":"Rogers","sequence":"additional","affiliation":[{"name":"Vanderbilt University, Nashville, Tennessee, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8355-0950","authenticated-orcid":false,"given":"Ayan","family":"Mukhopadhyay","sequence":"additional","affiliation":[{"name":"Vanderbilt University, Nashville, Tennessee, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7400-2357","authenticated-orcid":false,"given":"Aron","family":"Laszka","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University, University Park, Pennsylvania, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3465-9527","authenticated-orcid":false,"given":"Dan","family":"Freudberg","sequence":"additional","affiliation":[{"name":"WeGo Public Transit, Nashville, Tennessee, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0168-4948","authenticated-orcid":false,"given":"Abhishek","family":"Dubey","sequence":"additional","affiliation":[{"name":"Vanderbilt University, Nashville, Tennessee, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,11,4]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611675114"},{"key":"e_1_3_1_3_2","unstructured":"American Public Transportation Association. 2022. Public Transportation Ridership Report. Retrieved from https:\/\/www.apta.com\/wp-content\/uploads\/2022-Q2-Ridership-APTA.pdf"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(94)00011-O"},{"key":"e_1_3_1_5_2","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1109\/SMARTCOMP58114.2023.00020","volume-title":"2023 IEEE International Conference on Smart Computing (SMARTCOMP)","author":"Zulqarnain Ammar Bin","year":"2023","unstructured":"Ammar Bin Zulqarnain, Samir Gupta, Jose Paolo Talusan, Dan Freudberg, Philip Pugliese, Ayan Mukhopadhyay, and Abhishek Dubey. 2023. Addressing APC data sparsity in predicting occupancy and delay of transit buses: A multitask learning approach. In 2023 IEEE International Conference on Smart Computing (SMARTCOMP). IEEE Computer Society, 17\u201324."},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.1060.0161"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","unstructured":"Cameron B. Browne Edward Powley Daniel Whitehouse Simon M. Lucas Peter I. Cowling Philipp Rohlfshagen Stephen Tavener Diego Perez Spyridon Samothrakis and Simon Colton. 2012. A survey of Monte Carlo tree search methods. IEEE Transactions on Computational Intelligence and AI in Games 4 1 (March 2012) 1\u201343. DOI: 10.1109\/TCIAIG.2012.2186810","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"e_1_3_1_8_2","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1007\/978-3-540-87608-3_6","volume-title":"Computers and Games","author":"Chaslot Guillaume M. J. B.","year":"2008","unstructured":"Guillaume M. J. B. Chaslot, Mark H. M. Winands, and H. Jaap van den Herik. 2008. Parallel Monte-Carlo tree search. In Computers and Games. H. Jaap van den Herik, Xinhe Xu, Zongmin Ma, and Mark H. M. Winands (Eds.), Springer Berlin, 60\u201371."},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.5555\/3091125.3091198"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2009.04.002"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2010.06.005"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.35.1.1.10143"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.3141\/1857-06"},{"issue":"1","key":"e_1_3_1_15_2","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1177\/0361198105193400112","article-title":"Prediction of arrival profiles and queue lengths along signalized arterials by using a Markov decision process","volume":"1934","author":"Geroliminis Nikolaos","year":"2005","unstructured":"Nikolaos Geroliminis and Alexander Skabardonis. 2005. Prediction of arrival profiles and queue lengths along signalized arterials by using a Markov decision process. Transportation Research Record 1934, 1 (2005), 116\u2013124.","journal-title":"Transportation Research Record"},{"issue":"3","key":"e_1_3_1_16_2","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1080\/01441647.2020.1857886","article-title":"Public transport planning adaption under the COVID-19 pandemic crisis: Literature review of research needs and directions","volume":"41","author":"Gkiotsalitis Konstantinos","year":"2021","unstructured":"Konstantinos Gkiotsalitis and Oded Cats. 2021. Public transport planning adaption under the COVID-19 pandemic crisis: Literature review of research needs and directions. Transport Reviews 41, 3 (2021), 374\u2013392.","journal-title":"Transport Reviews"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/SMARTCOMP61445.2024.00024"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.5555\/3635637.3662933"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.5555\/3635637.3662933"},{"key":"e_1_3_1_20_2","first-page":"219","volume-title":"2020 USENIX Annual Technical Conference (USENIX ATC \u201920)","author":"Keahey Kate","year":"2020","unstructured":"Kate Keahey, Jason Anderson, Zhuo Zhen, Pierre Riteau, Paul Ruth, Dan Stanzione, Mert Cevik, Jacob Colleran, Haryadi S. Gunawi, Cody Hammock, et al. 2020. Lessons learned from the chameleon testbed. In 2020 USENIX Annual Technical Conference (USENIX ATC \u201920). USENIX Association, 219\u2013233. Retrieved from https:\/\/www.usenix.org\/conference\/atc20\/presentation\/keahey"},{"key":"e_1_3_1_21_2","first-page":"282","volume-title":"Machine Learning (ECML \u201906)","author":"Kocsis Levente","year":"2006","unstructured":"Levente Kocsis and Csaba Szepesv\u00e1ri. 2006. Bandit based Monte-Carlo planning. In Machine Learning (ECML \u201906). Johannes F\u00fcrnkranz, Tobias Scheffer, and Myra Spiliopoulou (Eds.), Springer Berlin, 282\u2013293."},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219993"},{"issue":"1","key":"e_1_3_1_23_2","doi-asserted-by":"crossref","first-page":"73","DOI":"10.3390\/su14010073","article-title":"Robust optimization model for single line dynamic bus dispatching","volume":"14","author":"Liu Yingxin","year":"2021","unstructured":"Yingxin Liu, Xinggang Luo, Xu Wei, Yang Yu, and Jiafu Tang. 2021. Robust optimization model for single line dynamic bus dispatching. Sustainability 14, 1 (2021), 73.","journal-title":"Sustainability"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2013.07.010"},{"key":"e_1_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Ayan Mukhopadhyay Geoffrey Pettet Chinmaya Samal Abhishek Dubey and Yevgeniy Vorobeychik. 2019. An online decision-theoretic pipeline for responder dispatch. arXiv:1902.08274. Retrieved from http:\/\/arxiv.org\/abs\/1902.08274","DOI":"10.1145\/3302509.3311055"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3502869"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00291-011-0251-6"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"issue":"1","key":"e_1_3_1_29_2","first-page":"181","article-title":"Between MDPs and Semi-MDPs: Learning, planning, and representing knowledge at multiple temporal scales","volume":"112","author":"Sutton Richard S.","year":"1998","unstructured":"Richard S. Sutton, Doina Precup, and Satinder Singh. 1998. Between MDPs and Semi-MDPs: Learning, planning, and representing knowledge at multiple temporal scales. Artificial Intelligence 112, 1\u20132 (1998), 181\u2013211.","journal-title":"Artificial Intelligence"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData55660.2022.10020390"},{"key":"e_1_3_1_31_2","unstructured":"Xiaocheng Tang Fan Zhang Zhiwei Qin Yansheng Wang Dingyuan Shi Bingchen Song Yongxin Tong Hongtu Zhu and Jieping Ye. 2021. Value function is all you need: A unified learning framework for ride hailing platforms. arXiv:2105.08791. Retrieved from https:\/\/arxiv.org\/abs\/2105.08791"},{"key":"e_1_3_1_32_2","unstructured":"Federal Highway Administration U.S. Department of Transportation. 2003. Status of the nation\u2019s highways bridges and transit: 2002 conditions and performance report to congress. Retrieved from https:\/\/www.apta.com\/wp-content\/uploads\/2022-Q2-Ridership-APTA.pdf"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-015-7744-1_2"},{"issue":"4","key":"e_1_3_1_34_2","doi-asserted-by":"crossref","first-page":"2404","DOI":"10.1109\/TITS.2020.3028415","article-title":"A proactive real-time control strategy based on data-driven transit demand prediction","volume":"22","author":"Wang Wensi","year":"2020","unstructured":"Wensi Wang, Fang Zong, and Baozhen Yao. 2020. A proactive real-time control strategy based on data-driven transit demand prediction. IEEE Transactions on Intelligent Transportation Systems 22, 4 (2020), 2404\u20132416.","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"2","key":"e_1_3_1_35_2","doi-asserted-by":"crossref","first-page":"1185","DOI":"10.1109\/TITS.2020.2964012","article-title":"Pareto-optimal transit route planning with multi-objective Monte-Carlo tree search","volume":"22","author":"Weng Di","year":"2020","unstructured":"Di Weng, Ran Chen, Jianhui Zhang, Jie Bao, Yu Zheng, and Yingcai Wu. 2020. Pareto-optimal transit route planning with multi-objective Monte-Carlo tree search. IEEE Transactions on Intelligent Transportation Systems 22, 2 (2020), 1185\u20131195.","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1057\/jors.1993.181"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS54341.2022.00020"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2016.07.009"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2018.12.013"},{"issue":"3","key":"e_1_3_1_40_2","doi-asserted-by":"crossref","first-page":"2497","DOI":"10.1007\/s10462-022-10228-y","article-title":"Monte Carlo tree search: A review of recent modifications and applications","volume":"56","author":"\u015awiechowski Maciej","year":"2022","unstructured":"Maciej \u015awiechowski, Konrad Godlewski, Bartosz Sawicki, and Jacek Ma\u0144dziuk. 2022. Monte Carlo tree search: A review of recent modifications and applications. Artificial Intelligence Review 56, 3 (July 2022), 2497\u20132562.","journal-title":"Artificial Intelligence Review"}],"container-title":["ACM Transactions on Cyber-Physical Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3754454","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T14:21:54Z","timestamp":1762266114000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3754454"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,31]]},"references-count":39,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,10,31]]}},"alternative-id":["10.1145\/3754454"],"URL":"https:\/\/doi.org\/10.1145\/3754454","relation":{},"ISSN":["2378-962X","2378-9638"],"issn-type":[{"type":"print","value":"2378-962X"},{"type":"electronic","value":"2378-9638"}],"subject":[],"published":{"date-parts":[[2025,10,31]]},"assertion":[{"value":"2024-09-04","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-02","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}