{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T09:41:14Z","timestamp":1787823674447,"version":"build-2784847793"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Project of New Generation Artificial Intelligence of China","award":["2018AAA0102504"],"award-info":[{"award-number":["2018AAA0102504"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62103236"],"award-info":[{"award-number":["62103236"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007128","name":"Natural Science Foundation of Shaanxi Province","doi-asserted-by":"publisher","award":["2023-JC-QN-0778"],"award-info":[{"award-number":["2023-JC-QN-0778"]}],"id":[{"id":"10.13039\/501100007128","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tits.2023.3333409","type":"journal-article","created":{"date-parts":[[2024,1,2]],"date-time":"2024-01-02T21:26:05Z","timestamp":1704230765000},"page":"5022-5033","source":"Crossref","is-referenced-by-count":34,"title":["Multi-Robot Environmental Coverage With a Two-Stage Coordination Strategy via Deep Reinforcement Learning"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4522-7976","authenticated-orcid":false,"given":"Lina","family":"Zhu","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8063-2547","authenticated-orcid":false,"given":"Jiyu","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1393-3670","authenticated-orcid":false,"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4960-3190","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuehu","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916688103"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146912"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341657"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635898"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9510-8"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2003.1242260"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460661"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967793"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10472-009-9120-2"},{"key":"ref10","article-title":"Nowhere to go: Benchmarking multi-robot collaboration in target trapping environment","author":"Zhang","year":"2023","journal-title":"arXiv:2308.08862"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636675"},{"key":"ref12","first-page":"1538","article-title":"TarMAC: Targeted multi-agent communication","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Das"},{"key":"ref13","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Sukhbaatar"},{"key":"ref14","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017","journal-title":"arXiv:1706.05296"},{"key":"ref15","first-page":"7613","article-title":"MAVEN: Multi-agent variational exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Mahajan"},{"key":"ref16","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Kulkarni"},{"key":"ref17","first-page":"3303","article-title":"Data-efficient hierarchical reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Nachum"},{"key":"ref18","article-title":"Learning multi-level hierarchies with hindsight","author":"Levy","year":"2017","journal-title":"arXiv:1712.00948"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref21","first-page":"1146","article-title":"Macro-action-based deep multi-agent reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Xiao"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2848264"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/sym13061057"},{"key":"ref24","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3200906"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3205250"},{"key":"ref27","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"Plappert","year":"2018","journal-title":"arXiv:1802.09464"},{"key":"ref28","first-page":"8532","article-title":"PlanGAN: Model-based planning with sparse rewards and multiple goals","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Charlesworth"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.06.022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919882082"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206000"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008958800904"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139032"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3034800"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989732"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.02.007"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01442"},{"key":"ref39","volume-title":"Hungarian Maximum Matching Algorithm","author":"Weisstein","year":"2011"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.proeng.2014.12.098"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3026638"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.3016143"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2103.01955"},{"key":"ref45","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref46","first-page":"1394","article-title":"The emergence of adversarial communication in multi-agent reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Blumenkamp"},{"key":"ref47","article-title":"Learning efficient multi-agent cooperative visual exploration","author":"Yu","year":"2021","journal-title":"arXiv:2110.05734"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/10543072\/10379517.pdf?arnumber=10379517","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T02:42:01Z","timestamp":1733884921000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10379517\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":47,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tits.2023.3333409","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}