{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:51:29Z","timestamp":1772121089948,"version":"3.50.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Dean's Prize of University College London Faculty of Engineering Sciences"},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/Y000862\/1"],"award-info":[{"award-number":["EP\/Y000862\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000288","name":"Royal Society","doi-asserted-by":"publisher","award":["RGS\\R2\\212343"],"award-info":[{"award-number":["RGS\\R2\\212343"]}],"id":[{"id":"10.13039\/501100000288","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000288","name":"Royal Society","doi-asserted-by":"publisher","award":["IEC\\NSFC\\191633"],"award-info":[{"award-number":["IEC\\NSFC\\191633"]}],"id":[{"id":"10.13039\/501100000288","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2024.3367237","type":"journal-article","created":{"date-parts":[[2024,2,21]],"date-time":"2024-02-21T14:02:33Z","timestamp":1708524153000},"page":"1519-1533","source":"Crossref","is-referenced-by-count":21,"title":["An End-to-End Deep Reinforcement Learning Based Modular Task Allocation Framework for Autonomous Mobile Systems"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4820-4857","authenticated-orcid":false,"given":"Song","family":"Ma","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, University College London, London, U.K"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4857-9053","authenticated-orcid":false,"given":"Jingqing","family":"Ruan","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Yali","family":"Du","sequence":"additional","affiliation":[{"name":"Department of Informatics, King's College London, London, U.K"}]},{"given":"Richard","family":"Bucknall","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, University College London, London, U.K"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9306-297X","authenticated-orcid":false,"given":"Yuanchang","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, University College London, London, U.K"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Shakey the robot","author":"Nilsson","year":"1984"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1985.1087002"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3061435"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3303848"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.2478\/jaiscr-2019-0008"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.048"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3349801.3349814"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01488"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-021-00363-w"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2849833"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICAC55051.2022.9911160"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-4412-5_5"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2020.3041573"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISMCR47492.2019.8955663"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561955"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460661"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981822"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/RCAR.2018.8621801"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197283"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1016\/j.robot.2019.04.012","article-title":"A distributed method for dynamic multi-robot task allocation problems with critical time constraints","volume":"118","author":"Chen","year":"2019","journal-title":"Robot. Auton. Syst."},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2020.113437","article-title":"Assessing a swarm-GAP based solution for the task allocation problem in dynamic scenarios","volume":"152","author":"Amorim","year":"2020","journal-title":"Exp. Syst. Appl."},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2831228"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-7080-4"},{"issue":"1","key":"ref24","doi-asserted-by":"crossref","first-page":"272","DOI":"10.3390\/app12010272","article-title":"Cooperative multi-robot task allocation with reinforcement learning","volume":"12","author":"Park","year":"2021","journal-title":"Appl. Sci."},{"key":"ref25","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1016\/j.future.2018.11.014","article-title":"Application of reinforcement learning in UAV cluster task scheduling","volume":"95","author":"Yang","year":"2019","journal-title":"Future Gener. Comput. Syst."},{"key":"ref26","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1016\/j.asoc.2014.11.005","article-title":"A survey of genetic algorithms for solving multi depot vehicle routing problem","volume":"27","author":"Karakati\u010d","year":"2015","journal-title":"Appl. Soft Comput."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-016-2279-7"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1016\/j.neucom.2020.09.031","article-title":"Unsupervised learning based coordinated multi-task allocation for unmanned surface vehicles","volume":"420","author":"Ma","year":"2021","journal-title":"Neurocomputing"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3165198"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2828499"},{"issue":"1","key":"ref31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/0167-6377(87)90002-2","article-title":"Optimization of a 532-city symmetric traveling salesman problem by branch and cut","volume":"6","author":"Padberg","year":"1987","journal-title":"Oper. Res. Lett."},{"issue":"1","key":"ref32","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/0377-2217(94)00299-1","article-title":"A restricted dynamic programming heuristic algorithm for the time dependent traveling salesman problem","volume":"90","author":"Malandraki","year":"1996","journal-title":"Eur. J. Oper. Res."},{"issue":"4","key":"ref33","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1016\/0893-6080(88)90002-0","article-title":"Self-organizing feature maps and the travelling salesman problem","volume":"1","author":"Ang\u00e9niol","year":"1988","journal-title":"Neural Netw."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3089179"},{"key":"ref35","article-title":"Neural combinatorial optimization with reinforcement learning","author":"Bello","year":"2017","journal-title":"arXiv:1611.09940"},{"key":"ref36","volume-title":"The Traveling Salesman Problem: A Computational Study","author":"Applegate","year":"2007"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/nnsp.1994.366050"},{"key":"ref39","article-title":"A mixture of experts classifier with learning based on both labelled and unlabelled data","volume":"9","author":"Miller","year":"1996","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref40","first-page":"1","article-title":"Attention, learn to solve routing problems!","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kool"},{"issue":"1","key":"ref41","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. 31st Int. Conf. Mach. Learn.","volume":"32","author":"Silver"},{"issue":"9","key":"ref42","first-page":"1","article-title":"Variance reduction techniques for gradient estimates in reinforcement learning","volume":"5","author":"Greensmith","year":"2004","journal-title":"J. Mach. Learn. Res."},{"key":"ref43","article-title":"Spectral clustering with graph neural networks for graph pooling","author":"Bianchi","year":"2019","journal-title":"arXiv:1907.00481"},{"key":"ref44","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref45","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref46","article-title":"PCG: A family of simple fast space-efficient statistically good algorithms for random number generation","author":"O\u2019Neill","year":"2014"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2649-2"},{"key":"ref48","volume-title":"Offshore Oil and Gas Activity","year":"2018"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1080\/03155986.1989.11732113"},{"issue":"1","key":"ref50","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1016\/j.ejor.2002.11.003","article-title":"Heuristic algorithms for single and multiple depot vehicle routing problems with pickups and deliveries","volume":"162","author":"Nagy","year":"2005","journal-title":"Eur. J. Oper. Res."},{"issue":"5","key":"ref51","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1016\/S0305-0548(02)00051-5","article-title":"A genetic algorithm for the vehicle routing problem","volume":"30","author":"Baker","year":"2003","journal-title":"Comput. Oper. Res."},{"key":"ref52","doi-asserted-by":"crossref","first-page":"564","DOI":"10.1016\/j.asoc.2017.12.031","article-title":"A comparative study of improved GA and PSO in solving multiple traveling salesmen problem","volume":"64","author":"Zhou","year":"2018","journal-title":"Appl. Soft Comput."},{"key":"ref53","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1016\/j.chemolab.2015.08.020","article-title":"Particle swarm optimization (PSO). A tutorial","volume":"149","author":"Marini","year":"2015","journal-title":"Chemometric Intell. Lab. Syst."},{"key":"ref54","doi-asserted-by":"crossref","DOI":"10.1016\/j.cor.2020.105192","article-title":"Modeling and optimization of multiple traveling salesmen problems: An evolution strategy approach","volume":"129","author":"Karabulut","year":"2021","journal-title":"Comput. Oper. Res."},{"key":"ref55","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.asoc.2014.09.029","article-title":"Two metaheuristic approaches for the multiple traveling salesperson problem","volume":"26","author":"Venkatesh","year":"2015","journal-title":"Appl. Soft Comput."},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2972894"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI50451.2021.9659963"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCNT49239.2020.9225622"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iay008"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abm6074"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ieeestd.2017.7907155"},{"key":"ref62","first-page":"1","volume-title":"IEEE Standard for Information Technology\u2013Telecommunications and Information Exchange Between Systems\u2014Local and Metropolitan Area Networks\u2013Specific Requirements\u2014Part 11: Wireless LAN Medium Access Control (MAC) and Physical Layer (PHY) Specifications","year":"2021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341207"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1999.772544"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2003.1242022"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/100.580977"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8856\/10839176\/10443430.pdf?arnumber=10443430","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T17:27:06Z","timestamp":1761154026000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10443430\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/tase.2024.3367237","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}