{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T15:54:13Z","timestamp":1776182053365,"version":"3.50.1"},"reference-count":131,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100015269","name":"Magyarorsz\u00e1g Korm\u00e1nya","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100015269","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011019","name":"European Social Fund through the project \u201cTalent management in autonomous vehicle control technologies\u201d","doi-asserted-by":"publisher","award":["EFOP-3.6.3-VEKOP-16-2017-00001"],"award-info":[{"award-number":["EFOP-3.6.3-VEKOP-16-2017-00001"]}],"id":[{"id":"10.13039\/501100011019","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2022,2]]},"DOI":"10.1109\/tits.2020.3024655","type":"journal-article","created":{"date-parts":[[2020,9,30]],"date-time":"2020-09-30T20:26:12Z","timestamp":1601497572000},"page":"740-759","source":"Crossref","is-referenced-by-count":527,"title":["Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehicles"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6811-2584","authenticated-orcid":false,"given":"Szilard","family":"Aradi","sequence":"first","affiliation":[]}],"member":"263","reference":[{"key":"ref1","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2578706"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49487-6_2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2014.6957722"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2012.6232277"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/AIM.2016.7576883"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1979.10"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CINTI.2018.8928220"},{"key":"ref10","article-title":"Driving in dense traffic with model-free reinforcement learning","author":"Mauria Saxena","year":"2019","journal-title":"arXiv:1909.06710"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5220\/0007955504220429"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref13","volume-title":"Dynamic Programming","author":"Bellman","year":"1957"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref15","article-title":"Dueling network architectures for deep reinforcement learning","author":"Wang","year":"2015","journal-title":"arXiv:1511.06581"},{"key":"ref16","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. 31st Int. Conf. Mach. Learn. (ICML)","author":"Silver"},{"key":"ref17","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500603"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8916924"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500718"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569635"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500450"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21236\/ada333248"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09421-1"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref28","first-page":"4190","article-title":"A unified game-theoretic approach to multiagent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lanctot"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2006.02.006"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-005-2631-2"},{"key":"ref31","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Foerster"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05864-5"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref34","first-page":"693","article-title":"On the pitfalls of measuring emergent communication","volume-title":"Proc. Int. Joint Conf. Auto. Agents Multiagent Syst. (AAMAS)","author":"Lowe"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1140\/epjb\/e2010-00201-8"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2015.7225830"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995816"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2019.01.003"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3141\/1999-10"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1103\/physreve.62.1805"},{"issue":"3","key":"ref42","first-page":"128","article-title":"Recent development and applications of SUMO-simulation of urban mobility","volume":"5","author":"Krajzewicz","year":"2012","journal-title":"Int. J. Adv. Syst. Meas."},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-6142-6_2"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2019.08.011"},{"key":"ref45","volume-title":"TORCS: The Open Racing Car Simulator","author":"Wymann","year":"2014"},{"key":"ref46","volume-title":"CarSIM, Mechanical Simulation Corporation","year":"2020"},{"key":"ref47","volume-title":"IPG Automotive","year":"2020"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3390\/electronics8050543"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852110"},{"key":"ref50","volume-title":"Welcome to Udacity\u2019s Self-Driving Car Simulator","year":"2020"},{"key":"ref51","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. 1st Annu. Conf. Robot Learn.","author":"Dosovitskiy"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3390\/s19030648"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2017.8122738"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2019.8914621"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917192"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CINTI.2018.8928230"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.23919\/ChiCC.2019.8866005"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500427"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CCTA.2018.8511514"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2870983"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500556"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICRAS.2019.8808950"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102662"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2018.10.024"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569568"},{"key":"ref66","volume-title":"A survey of state-action representations for autonomous driving","author":"Leurent","year":"2018"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995727"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460934"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.64"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2019.2901089"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.23919\/SICE.2019.8859883"},{"key":"ref72","article-title":"Autonomous driving in reality with reinforcement learning and image translation","author":"Xu","year":"2018","journal-title":"arXiv:1801.05299"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/URAI.2017.7992762"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/2.30720"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20147"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500493"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2019.09.060"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8814124"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1142\/s0129183197000904"},{"key":"ref80","article-title":"Cooperative lane changing via deep reinforcement learning","author":"Wang","year":"2019","journal-title":"arXiv:1906.08662"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917392"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2017.8317735"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2018.11.596"},{"key":"ref84","article-title":"Reinforcement learning with probabilistic guarantees for autonomous driving","author":"Bouton","year":"2019","journal-title":"arXiv:1904.07189"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2010.5586191"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2007.4357682"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2011.2106158"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2011.2157145"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574711000452"},{"key":"ref90","article-title":"End-to-end deep reinforcement learning for lane keeping assist","author":"El Sallab","year":"2016","journal-title":"arXiv:1612.04340"},{"key":"ref91","article-title":"Autonomous ramp merge maneuver based on reinforcement learning with continuous action space","author":"Wang","year":"2018","journal-title":"arXiv:1803.09203"},{"key":"ref92","first-page":"1547","article-title":"Microscopic traffic simulation by cooperative multi-agent deep reinforcement learning","volume-title":"Proc. Int. Joint Conf. Auto. Agents Multiagent Syst. (AAMAS)","author":"Bacchiani"},{"key":"ref93","article-title":"Delay-aware multi-agent reinforcement learning for cooperative and competitive environments","author":"Chen","year":"2020","journal-title":"arXiv:2005.05441"},{"key":"ref94","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2016.7795737"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-8909-3_2"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8916951"},{"key":"ref98","article-title":"CM3: Cooperative multi-goal multi-stage multi-agent reinforcement learning","author":"Yang","year":"2018","journal-title":"arXiv:1809.05188"},{"key":"ref99","article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","author":"Shalev-Shwartz","year":"2016","journal-title":"arXiv:1610.03295"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2019.2955905"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ISCID.2016.2054"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461233"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-31978-6_8"},{"key":"ref104","first-page":"341","article-title":"Reinforcement learning for cooperative overtaking","volume-title":"Proc. Int. Joint Conf. Auto. Agents Multiagent Syst. (AAMAS)","author":"Yu"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2893683"},{"key":"ref106","article-title":"Transfer learning versus multi-agent learning regarding distributed decision-making in highway traffic","author":"Schutera","year":"2018","journal-title":"arXiv:1810.08515"},{"key":"ref107","first-page":"1883","article-title":"MARL-PPS: Multi-agent reinforcement learning with periodic parameter sharing","volume-title":"Proc. Int. Joint Conf. Auto. Agents Multiagent Syst. (AAMAS)","author":"Cicek"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1145\/3352593.3352625"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593758"},{"key":"ref110","article-title":"DeepTraffic: Driving fast through dense traffic with deep reinforcement learning","volume-title":"Proc. Neural Inf. Process. Syst. (NIPS) Deep Reinforcement Learn. Workshop","author":"Fridman"},{"key":"ref111","article-title":"US highway 101 dataset","author":"Colyar","year":"2007"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1016\/j.tra.2016.09.010"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/MS.2017.79"},{"key":"ref114","volume-title":"Automotive SPICE Process Assessment\/Reference Model","year":"2015"},{"key":"ref115","volume-title":"Road Vehicles\u2014Functional Safety\u2014Part 1: Vocabulary","year":"2011"},{"key":"ref116","first-page":"1437","volume-title":"A Comprehensive Survey on Safe Reinforcement Learning","author":"Garcia","year":"2015"},{"key":"ref117","article-title":"Combining deep reinforcement learning and safety based control for autonomous driving","author":"Xiong","year":"2016","journal-title":"arXiv:1612.00147"},{"key":"ref118","article-title":"Uncertainty-aware reinforcement learning for collision avoidance","author":"Kahn","year":"2017","journal-title":"arXiv:1702.01182"},{"key":"ref119","article-title":"Deep reinforcement learning with enhanced safety for autonomous highway driving","author":"Baheri","year":"2019","journal-title":"arXiv:1910.12905"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294262"},{"key":"ref121","article-title":"Safe reinforcement learning","author":"Thomas","year":"2015"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.3311\/PPtr.10753"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5152-4"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref126","volume-title":"Domain Randomization for Sim2Real Transfer","author":"Weng","year":"2019"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.11"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.3156\/jsoft.29.5_177_2"},{"key":"ref129","first-page":"1","article-title":"Quantifying generalization in reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn. (ICML)","author":"Cobbe"},{"key":"ref130","article-title":"Active domain randomization","author":"Mehta","year":"2019","journal-title":"arXiv:1904.04762"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.029"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/9701814\/09210154.pdf?arnumber=9210154","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:52:45Z","timestamp":1704844365000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9210154\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2]]},"references-count":131,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tits.2020.3024655","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2]]}}}