{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:52:51Z","timestamp":1784645571444,"version":"3.55.0"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFA1004702"],"award-info":[{"award-number":["2022YFA1004702"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62173085"],"award-info":[{"award-number":["62173085"]}],"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":["U22B2046"],"award-info":[{"award-number":["U22B2046"]}],"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":["62073079"],"award-info":[{"award-number":["62073079"]}],"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":["62088101"],"award-info":[{"award-number":["62088101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"General Joint Fund of the Equipment Advance Research Program of Ministry of Education","award":["8091B022114"],"award-info":[{"award-number":["8091B022114"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Veh."],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1109\/tiv.2022.3233592","type":"journal-article","created":{"date-parts":[[2023,1,2]],"date-time":"2023-01-02T18:59:21Z","timestamp":1672685961000},"page":"2332-2344","source":"Crossref","is-referenced-by-count":96,"title":["Safe Reinforcement Learning for Model-Reference Trajectory Tracking of Uncertain Autonomous Vehicles With Model-Based Acceleration"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0756-6157","authenticated-orcid":false,"given":"Yifan","family":"Hu","sequence":"first","affiliation":[{"name":"School of Mathematics, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1528-8727","authenticated-orcid":false,"given":"Junjie","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Mathematics, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0070-8597","authenticated-orcid":false,"given":"Guanghui","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Mathematics, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2021.109597"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914537130"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084685"},{"key":"ref34","article-title":"Soft actor-critic algorithms and applications","author":"haarnoja","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2920206"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3189836"},{"key":"ref14","article-title":"Safe exploration in continuous action spaces","author":"dalal","year":"2018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.05.049"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2659727"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3000264"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2021.109689"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3141071"},{"key":"ref10","first-page":"22","article-title":"Constrained policy optimization","author":"achiam","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2022.3203928"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2021.3119989"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3186280"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2638961"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2019.2919467"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref38","article-title":"Model-ensemble trust-region policy optimization","author":"kurutach","year":"2018"},{"key":"ref19","first-page":"1861","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2021.3058064"},{"key":"ref24","first-page":"2829","article-title":"Continuous deep Q-learning with model-based acceleration","author":"gu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","first-page":"4759","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","author":"chua","year":"0","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref26","first-page":"12519","article-title":"When to trust your model: Model-based policy optimization","author":"janner","year":"0","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref25","article-title":"Model-based value expansion for efficient model-free reinforcement learning","author":"feinberg","year":"2018"},{"key":"ref20","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3185159"},{"key":"ref21","article-title":"Safe multi-agent reinforcement learning through decentralized multiple control barrier functions","author":"cai","year":"2021"},{"key":"ref28","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"0","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref8","article-title":"Model-based reinforcement learning: A survey","author":"moerland","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3167271"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3086033"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.088"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3168577"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3167103"}],"container-title":["IEEE Transactions on Intelligent Vehicles"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274857\/10109992\/10005026.pdf?arnumber=10005026","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T18:53:00Z","timestamp":1684176780000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10005026\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3]]},"references-count":39,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tiv.2022.3233592","relation":{},"ISSN":["2379-8904","2379-8858"],"issn-type":[{"value":"2379-8904","type":"electronic"},{"value":"2379-8858","type":"print"}],"subject":[],"published":{"date-parts":[[2023,3]]}}}