{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T08:18:54Z","timestamp":1773562734711,"version":"3.50.1"},"reference-count":66,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2019YFB1803300"],"award-info":[{"award-number":["2019YFB1803300"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Central Government Funds for Guiding Local Scientific and Technological Development","award":["YDZJSX2021A037"],"award-info":[{"award-number":["YDZJSX2021A037"]}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program of Science and Technology","doi-asserted-by":"publisher","award":["Z191100001119028"],"award-info":[{"award-number":["Z191100001119028"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/tits.2023.3250720","type":"journal-article","created":{"date-parts":[[2023,3,6]],"date-time":"2023-03-06T13:45:47Z","timestamp":1678110347000},"page":"5765-5780","source":"Crossref","is-referenced-by-count":16,"title":["SRL-TR<sup>2<\/sup>: A Safe Reinforcement Learning Based TRajectory TRacker Framework"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1910-6297","authenticated-orcid":false,"given":"Chengyu","family":"Wang","sequence":"first","affiliation":[{"name":"Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7056-5416","authenticated-orcid":false,"given":"Luhan","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0182-1770","authenticated-orcid":false,"given":"Zhaoming","family":"Lu","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9363-6336","authenticated-orcid":false,"given":"Xinghe","family":"Chu","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2342-0986","authenticated-orcid":false,"given":"Zhengrui","family":"Shi","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6772-9168","authenticated-orcid":false,"given":"Jiayin","family":"Deng","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0591-1331","authenticated-orcid":false,"given":"Tianyang","family":"Su","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8271-0246","authenticated-orcid":false,"given":"Guochu","family":"Shou","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2793-6696","authenticated-orcid":false,"given":"Xiangming","family":"Wen","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","author":"camacho","year":"2013","journal-title":"Model Predictive Control"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2928630"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2008.2011697"},{"key":"ref56","first-page":"97","article-title":"Learning transferable features with deep adaptation networks","author":"long","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6123"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46024-6_3"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-020-09925-w"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref11","author":"snider","year":"2009","journal-title":"Automatic Steering Methods for Autonomous Automobile Path Tracking"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/87.572125"},{"key":"ref54","article-title":"EPOpt: Learning robust neural network policies using model ensembles","author":"rajeswaran","year":"2016","journal-title":"arXiv 1610 01283"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2922849"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2918071"},{"key":"ref18","article-title":"Hierarchical reinforcement learning with hindsight","author":"levy","year":"2018","journal-title":"arXiv 1805 08180"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.088"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3024161"},{"key":"ref46","article-title":"A Lyapunov-based approach to safe reinforcement learning","author":"chow","year":"2018","journal-title":"arXiv 1805 07708"},{"key":"ref45","first-page":"22","article-title":"Constrained policy optimization","author":"achiam","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916645661"},{"key":"ref47","article-title":"Lyapunov-based safe policy optimization for continuous control","author":"chow","year":"2019","journal-title":"arXiv 1901 10031"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2960872"},{"key":"ref41","article-title":"Simulation-based reinforcement learning for real-world autonomous driving","author":"osi?ski","year":"2019","journal-title":"arXiv 1911 12905"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3066366"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3014628"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2976272"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5772\/51314"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2011.08.005"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.4218\/etrij.15.0114.0123"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0468-y"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.2966631"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2892926"},{"key":"ref5","author":"coulter","year":"1992","journal-title":"Implementation of the Pure Pursuit Path Tracking Algorithm"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2955959"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2255286"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref37","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"ref31","first-page":"263","article-title":"Issues in using function approximation for reinforcement learning","author":"thrun","year":"1993","journal-title":"Proc Connectionist Models Summer School"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(98)00073-9"},{"key":"ref33","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref32","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2014.2325395"},{"key":"ref1","author":"maurer","year":"2016","journal-title":"Autonomous Driving Technical Legal and Social Aspects"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2018.12.018"},{"key":"ref38","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2018.09.005"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref26","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2895285"},{"key":"ref64","author":"rajamani","year":"2011","journal-title":"Vehicle Dynamics and Control"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2020.2990863"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2962338"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1982.1163992"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3008612"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8264062"},{"key":"ref28","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"arXiv 1802 09477"},{"key":"ref27","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/BF00938540"},{"key":"ref60","article-title":"Domain separation networks","author":"bousmalis","year":"2016","journal-title":"arXiv 1608 06019"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2608884"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.4271\/R-114"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/10139322\/10061363.pdf?arnumber=10061363","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T17:57:15Z","timestamp":1753379835000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10061363\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":66,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tits.2023.3250720","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6]]}}}