{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:08:50Z","timestamp":1777486130397,"version":"3.51.4"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Program for Changjiang Scholars and Innovative Research Team in University","award":["IRT-16R06"],"award-info":[{"award-number":["IRT-16R06"]}]},{"name":"Program for Changjiang Scholars and Innovative Research Team in University","award":["T2014224"],"award-info":[{"award-number":["T2014224"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61903034"],"award-info":[{"award-number":["61903034"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61973034"],"award-info":[{"award-number":["61973034"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1913203"],"award-info":[{"award-number":["U1913203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["91120003"],"award-info":[{"award-number":["91120003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2019TQ0035"],"award-info":[{"award-number":["2019TQ0035"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012236","name":"Beijing Institute of Technology Research Fund Program for Young Scholars","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012236","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Veh. Technol."],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/tvt.2020.2979493","type":"journal-article","created":{"date-parts":[[2020,3,9]],"date-time":"2020-03-09T19:40:42Z","timestamp":1583782842000},"page":"4740-4750","source":"Crossref","is-referenced-by-count":68,"title":["Stabilization Approaches for Reinforcement Learning-Based End-to-End Autonomous Driving"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4140-9729","authenticated-orcid":false,"given":"Siyuan","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3618-7423","authenticated-orcid":false,"given":"Meiling","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4121-908X","authenticated-orcid":false,"given":"Wenjie","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3964-2433","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujun","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengyin","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref38","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"0","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref33","article-title":"Deep reinforcement learning for simulated autonomous vehicle control","author":"yu","year":"2016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252823"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/FBIT.2007.37"},{"key":"ref37","article-title":"End-to-end deep reinforcement learning for lane keeping assist","author":"sallab","year":"0","journal-title":"Proc 30th Conf Neural Inf Process Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500556"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICICIP.2015.7388193"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102426"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref40","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"0","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2760281"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022672621406"},{"key":"ref13","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015"},{"key":"ref14","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref15","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"Comput Sci"},{"key":"ref16","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"},{"key":"ref17","first-page":"2891","article-title":"Query-efficient imitation learning for end-to-end simulated driving","author":"zhang","year":"0","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref18","article-title":"TORCS: The open racing car simulator","author":"wymann","year":"2015"},{"key":"ref19","first-page":"305","article-title":"Alvinn: An autonomous land vehicle in a neural network","author":"pomerleau","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","first-page":"4","article-title":"Reinforcement learning techniques for autonomous vehicle control","volume":"3","author":"kontoravdis","year":"1992","journal-title":"Neural Netw World"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MIE.2019.2913015"},{"key":"ref27","first-page":"666","article-title":"Collision-free movement of an autonomous vehicle using reinforcement learning","author":"kontoravdis","year":"0","journal-title":"Proc 10th Eur Conf Artif Intell"},{"key":"ref3","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2019.113755"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-2217(97)00372-X"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2015.2475419"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2724060"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2019.113708"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref9","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref1","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016"},{"key":"ref20","first-page":"739","article-title":"Off-road obstacle avoidance through end-to-end learning","author":"lecun","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.376"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref42","first-page":"265","article-title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.031"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.312"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3293353.3293364"},{"key":"ref44","article-title":"vehicle_simulator","author":"du","year":"0"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3618-5_8"},{"key":"ref43","article-title":"velodyne_simulator","author":"kevin","year":"0"},{"key":"ref25","first-page":"237","article-title":"Conditional affordance learning for driving in urban environments","author":"sauer","year":"0","journal-title":"Proc Conf Robot Learn"}],"container-title":["IEEE Transactions on Vehicular Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/25\/9094045\/09028159.pdf?arnumber=9028159","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T13:45:02Z","timestamp":1651067102000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9028159\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":44,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tvt.2020.2979493","relation":{},"ISSN":["0018-9545","1939-9359"],"issn-type":[{"value":"0018-9545","type":"print"},{"value":"1939-9359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5]]}}}