{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:34:53Z","timestamp":1783438493351,"version":"3.54.6"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62003218"],"award-info":[{"award-number":["62003218"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Projects for Shenzhen Higher Education Institutions","award":["20220717223051001"],"award-info":[{"award-number":["20220717223051001"]}]},{"name":"Guangdong Provincial Engineering Technology Research Center for Materials for Advanced MEMS Sensor Chip","award":["2022GCZX005"],"award-info":[{"award-number":["2022GCZX005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Inf."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tii.2025.3545083","type":"journal-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:52:17Z","timestamp":1741801937000},"page":"4672-4682","source":"Crossref","is-referenced-by-count":18,"title":["Multiagent Formation Control and Dynamic Obstacle Avoidance Based on Deep Reinforcement Learning"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6269-3236","authenticated-orcid":false,"given":"Zike","family":"Yuan","sequence":"first","affiliation":[{"name":"Sino-German College of Intelligent Manufacturing, Shenzhen Technology University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenhao","family":"Yao","sequence":"additional","affiliation":[{"name":"Sino-German College of Intelligent Manufacturing, Shenzhen Technology University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8268-7077","authenticated-orcid":false,"given":"Xiaoxu","family":"Liu","sequence":"additional","affiliation":[{"name":"Sino-German College of Intelligent Manufacturing, Shenzhen Technology University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5464-3288","authenticated-orcid":false,"given":"Zhiwei","family":"Gao","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Physics and Electrical Engineering, Northumbria University, Newcastle upon Tyne, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5663-5790","authenticated-orcid":false,"given":"Wenwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Sino-German College of Intelligent Manufacturing, Shenzhen Technology University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3236945"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2582745"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3034280"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SSRR.2012.6523905"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2015.12.010"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2983646"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfranklin.2016.12.021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfranklin.2023.02.033"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2024.3373027"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2012.2183831"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2839739"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2023.3240223"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980408"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543489"},{"key":"ref15","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"Puterman","year":"2014"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3050338"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3178791"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3068762"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3004893"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812263"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3240585"},{"key":"ref23","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Yu","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2944160"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3020400"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.10.022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3301295"},{"key":"ref28","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver","year":"2014"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref30","article-title":"A new framework for multi-agent reinforcement learningcentralized training and exploration with decentralized execution via policy distillation","author":"Chen","year":"2019"},{"key":"ref31","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"John Schulman","year":"2015"},{"issue":"181","key":"ref32","first-page":"1","article-title":"Curriculum learning for reinforcement learning domains: A framework and survey","volume":"21","author":"Narvekar","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2017.2782245"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2021.110016"}],"container-title":["IEEE Transactions on Industrial Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9424\/11014248\/10924305.pdf?arnumber=10924305","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T04:50:28Z","timestamp":1748062228000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10924305\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":34,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tii.2025.3545083","relation":{},"ISSN":["1551-3203","1941-0050"],"issn-type":[{"value":"1551-3203","type":"print"},{"value":"1941-0050","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}