{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T22:05:44Z","timestamp":1785189944323,"version":"3.55.0"},"reference-count":168,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"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":["62273135"],"award-info":[{"award-number":["62273135"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Hubei Province in China","award":["2021CFB460"],"award-info":[{"award-number":["2021CFB460"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62103139"],"award-info":[{"award-number":["62103139"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"2022 Opening Foundation of State Key Laboratory of Management and Control for Complex Systems","award":["E2S9021119"],"award-info":[{"award-number":["E2S9021119"]}]},{"name":"Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science"},{"name":"BNU-HKBU United International College","award":["2022B1212010006"],"award-info":[{"award-number":["2022B1212010006"]}]},{"name":"Guangdong Higher Education Upgrading Plan with UIC Research","award":["R0400001-22"],"award-info":[{"award-number":["R0400001-22"]}]},{"name":"Guangdong Higher Education Upgrading Plan with UIC Research","award":["R201902"],"award-info":[{"award-number":["R201902"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Veh."],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/tiv.2023.3274536","type":"journal-article","created":{"date-parts":[[2023,5,11]],"date-time":"2023-05-11T00:02:49Z","timestamp":1683763369000},"page":"3692-3711","source":"Crossref","is-referenced-by-count":561,"title":["Motion Planning for Autonomous Driving: The State of the Art and Future Perspectives"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6860-9547","authenticated-orcid":false,"given":"Siyu","family":"Teng","sequence":"first","affiliation":[{"name":"BNU-HKBU United International College, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3918-8461","authenticated-orcid":false,"given":"Xuemin","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hubei University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hubei University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8966-8992","authenticated-orcid":false,"given":"Bai","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Changsha"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6732-323X","authenticated-orcid":false,"given":"Yuchen","family":"Li","sequence":"additional","affiliation":[{"name":"BNU-HKBU United International College, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2673-1368","authenticated-orcid":false,"given":"Yunfeng","family":"Ai","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7935-7605","authenticated-orcid":false,"given":"Dongsheng","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Public Management\/Emergency Management, Jinan University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5192-492X","authenticated-orcid":false,"given":"Lingxi","family":"Li","sequence":"additional","affiliation":[{"name":"Purdue School of Engineering and Technology, Indiana University-Purdue University Indianapolis, Indianapolis, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6070-9658","authenticated-orcid":false,"given":"Zhe","family":"Xuanyuan","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Lab of IRADS, BNU-HKBU United International College, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2886-6968","authenticated-orcid":false,"given":"Fenghua","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4925-0572","authenticated-orcid":false,"given":"Long","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11755"},{"key":"ref56","first-page":"1","article-title":"Nonlinear inverse reinforcement learning with Gaussian processes","volume":"24","author":"levine","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref59","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"8","author":"ziebart","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2022.3203761"},{"key":"ref52","article-title":"Query-efficient imitation learning for end-to-end autonomous driving","author":"zhang","year":"2016"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01131"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2022.3197950"},{"key":"ref54","article-title":"Oil: Observational imitation learning","author":"li","year":"2018"},{"key":"ref51","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"0","journal-title":"Proc 14th Int Conf Artif Intell Statist JMLR Workshop Conf Proc"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_25"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref45","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016"},{"key":"ref48","first-page":"237","article-title":"Conditional affordance learning for driving in urban environments","author":"sauer","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.312"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2021.3065867"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980223"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3229682"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3214777"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00886"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2498841"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2913998"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3032227"},{"key":"ref4","first-page":"801","article-title":"Parallel driving os: A ubiquitous cyber-physical-socialsystem-based operating system for autonomous driving","volume":"7","author":"chen","year":"0","journal-title":"IEEE Trans Intell Veh"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/9781638281290"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3189511"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3221767"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3047129"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197132"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2008.2012116"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3052816"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.2140\/pjm.1990.145.367"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3141881"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2017.07.019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3168130"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref30","article-title":"Baidu Apollo EM motion planner","author":"fan","year":"2018"},{"key":"ref149","first-page":"2636","article-title":"BDD100 K: A diverse driving dataset for heterogeneous multitask learning","author":"yu","year":"0","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2016.11.007"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2756099"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00141"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3163335"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3178061"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.14722\/autosec.2022.23032"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3150906"},{"key":"ref153","article-title":"Soda10M: A large-scale 2 d self\/semi-supervised object detection dataset for autonomous driving","author":"han","year":"2021"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9922031"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02062"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00957"},{"key":"ref150","article-title":"A2d2: Audi autonomous driving dataset","author":"geyer","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2020.103447"},{"key":"ref23","first-page":"18","article-title":"Practical search techniques in path planning for autonomous driving","volume":"1001","author":"dolgov","year":"2008","journal-title":"Ann Arbor"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139219"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2015.2493980"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3109011"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS.2018.00035"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907209"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3244948"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/0278364909359210"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-6142-6_7"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1002\/oca.2123"},{"key":"ref27","article-title":"DESPOT: Online POMDP planning with regularization","volume":"26","author":"somani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3145389"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2952735"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2857566"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67361-5_40"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3228963"},{"key":"ref162","first-page":"3461","article-title":"Metadrive: Composing diverse driving scenarios for generalizable reinforcement learning","volume":"45","author":"li","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294422"},{"key":"ref160","first-page":"1","article-title":"CARLA: An open urban driving simulator","author":"dosovitskiy","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref161","first-page":"2","article-title":"Torcs, the open racing car simulator","volume":"4","author":"wymann","year":"2000","journal-title":"Software"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIA.2021.3091418"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1287\/opre.14.5.914"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21236\/ADA459660"},{"key":"ref128","first-page":"1","article-title":"Parallel learning a new framework for machine learning","volume":"43","author":"li","year":"2017","journal-title":"ACTA Automatica Sinica"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1968.300136"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-017-9569-z"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3061627"},{"key":"ref126","first-page":"485","article-title":"Parallel system methods for management and control of complex systems","volume":"19","author":"wang","year":"2004","journal-title":"Control Decis"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3238656"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2022.3196592"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BF01386390"},{"key":"ref99","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811626"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2578706"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref125","first-page":"10784","article-title":"Learning to simulate self-driven particles system with coordinated policy optimization","volume":"34","author":"peng","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2019.2898599"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3156429"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593579"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2018.2821767"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103452"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.106097"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635925"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2022.3202825"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(85)90011-9"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2018.2884515"},{"key":"ref94","article-title":"Lyapunov-based safe policy optimization for continuous control","author":"chow","year":"2019"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aaw4106"},{"key":"ref130","first-page":"485","article-title":"Research on digital quadruplets in cyber-physical-social space-based parallel driving","volume":"1","author":"teng","year":"2019","journal-title":"Chin J Intell Sci Technol"},{"key":"ref91","article-title":"Benchmarking safe exploration in deep reinforcement learning","author":"ray","year":"2019"},{"key":"ref90","first-page":"22","article-title":"Constrained policy optimization","author":"achiam","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICRAS.2019.8808950"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2934991"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389727"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3164977"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995727"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.106094"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917192"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1016\/j.trit.2016.11.005"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3025671"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2010.2060218"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.105950"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916679498"},{"key":"ref81","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.534"},{"key":"ref84","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref143","article-title":"Learning a driving simulator","author":"santana","year":"2016"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3073429"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2017.7510598"},{"key":"ref80","first-page":"1279","article-title":"Co-gail: Learning diverse strategies for human-robot collaboration","author":"wang","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref79","article-title":"Directed-info gail: Learning hierarchical policies from unsegmented demonstrations using directed information","author":"sharma","year":"2018"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3142822"},{"key":"ref78","first-page":"1","article-title":"Infogail: Interpretable imitation learning from visual demonstrations","volume":"30","author":"li","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3177685"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_36"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3055899"},{"key":"ref75","first-page":"420","article-title":"Preference learning in assistive robotics: Observational repeated inverse reinforcement learning","author":"woodworth","year":"0","journal-title":"Proc Mach Learn Healthcare Conf"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3026111"},{"key":"ref74","first-page":"131","article-title":"Semi-supervised apprenticeship learning","author":"valko","year":"0","journal-title":"Proc of European Workshop on Reinforcement Learning"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3116063"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759328"},{"key":"ref102","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref76","first-page":"2586","article-title":"Bayesian inverse reinforcement learning","volume":"7","author":"ramachandran","year":"0","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304668"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3223131"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3043505"},{"key":"ref71","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","volume":"1","author":"ng","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref111","first-page":"1","article-title":"Attention-based hierarchical deep reinforcement learning for lane change behaviors in autonomous driving","author":"chen","year":"0","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit Workshops"},{"key":"ref70","article-title":"Thriftydagger: Budget-aware novelty and risk gating for interactive imitation learning","author":"hoque","year":"2021"},{"key":"ref112","article-title":"Driving decision and control for autonomous lane change based on deep reinforcement learning","author":"shi","year":"2019"},{"key":"ref73","first-page":"1","article-title":"A game-theoretic approach to apprenticeship learning","volume":"20","author":"syed","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.106049"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3004984"},{"key":"ref119","article-title":"Model-agnostic multi-agent perception framework","author":"xu","year":"2022"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3225340"},{"key":"ref117","article-title":"Bridging the domain gap for multi-agent perception","author":"xu","year":"2022"},{"key":"ref69","first-page":"1","article-title":"Imitation learning by coaching","volume":"25","author":"he","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123087"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3256972"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3034225"},{"key":"ref63","article-title":"Global overview of imitation learning","author":"attia","year":"2018"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982041"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197027"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561195"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2921918"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2019.0317"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146635"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1007\/s43684-022-00023-5"},{"key":"ref123","article-title":"Deep multi-agent reinforcement learning for highway on-ramp merging in mixed traffic","author":"chen","year":"2021"},{"key":"ref62","article-title":"Driving in real life with inverse reinforcement learning","author":"phan-minh","year":"2022"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1145\/3352593.3352625"},{"key":"ref61","first-page":"1","article-title":"Generative adversarial imitation learning","volume":"29","author":"ho","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref121","first-page":"1","article-title":"Multi-agent graph reinforcement learning for connected automated driving","author":"wang","year":"0","journal-title":"Proc 37th Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Intelligent Vehicles"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274857\/10187697\/10122127.pdf?arnumber=10122127","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T18:27:56Z","timestamp":1691432876000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10122127\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":168,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tiv.2023.3274536","relation":{},"ISSN":["2379-8904","2379-8858"],"issn-type":[{"value":"2379-8904","type":"electronic"},{"value":"2379-8858","type":"print"}],"subject":[],"published":{"date-parts":[[2023,6]]}}}