{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:26:24Z","timestamp":1784643984836,"version":"3.55.0"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"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":["51505354"],"award-info":[{"award-number":["51505354"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1109\/tits.2021.3061627","type":"journal-article","created":{"date-parts":[[2021,3,11]],"date-time":"2021-03-11T21:04:03Z","timestamp":1615496643000},"page":"6766-6773","source":"Crossref","is-referenced-by-count":91,"title":["Safe Reinforcement Learning for Autonomous Vehicle Using Monte Carlo Tree Search"],"prefix":"10.1109","volume":"23","author":[{"given":"Shuojie","family":"Mo","sequence":"first","affiliation":[{"name":"Department of Automotive Engineering, Wuhan University of Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8283-9277","authenticated-orcid":false,"given":"Xiaofei","family":"Pei","sequence":"additional","affiliation":[{"name":"Hubei Research Center for New Energy and Intelligent Connected Vehicle, Wuhan University of Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3384-8916","authenticated-orcid":false,"given":"Chaoxian","family":"Wu","sequence":"additional","affiliation":[{"name":"Hubei Key Laboratory of Advanced Technology for Automotive Components, Wuhan University of Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2870983"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917392"},{"key":"ref5","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"issue":"1","key":"ref6","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garc\u00eda","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304744"},{"key":"ref8","first-page":"997","article-title":"Safe exploration for optimization with Gaussian processes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sui"},{"key":"ref9","article-title":"Safety-guided deep reinforcement learning via online Gaussian process estimation","volume-title":"arXiv:1903.02526","author":"Fan","year":"2019"},{"key":"ref10","first-page":"1","article-title":"Tactical decision making for lane changing with deep reinforcement learning","volume-title":"Proc. Workshop Mach. Learn. Intell. Transp. Syst.","author":"Mukadam"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147626"},{"key":"ref12","article-title":"Reinforcement learning with probabilistic guarantees for autonomous driving","volume-title":"arXiv:1904.07189","author":"Bouton","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294262"},{"key":"ref14","first-page":"3121","article-title":"Convergent policy optimization for safe reinforcement learning","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Yu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2017.8329799"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1666"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20255"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20262"},{"key":"ref19","article-title":"End to end learning for self-driving cars","volume-title":"arXiv:1604.07316","author":"Bojarski","year":"2016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.031"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569568"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICICIP.2015.7388193"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917306"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8813903"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015015"},{"key":"ref28","article-title":"Deep recurrent Q-learning for partially observable MDPs","volume-title":"arXiv:1507.06527","author":"Hausknecht","year":"2015"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-75538-8_7"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"ref31","article-title":"Improved Monte-Carlo search","author":"Kocsis","year":"2006"},{"key":"ref32","article-title":"A time-based analysis of road user behaviour in normal and critical encounters","author":"Horst","year":"1990"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1103\/physreve.62.1805"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3141\/1999-10"},{"issue":"8","key":"ref35","first-page":"22","article-title":"The next generation simulation program","volume":"74","author":"Alexiadis","year":"2004","journal-title":"Inst. Transp. Eng. J."}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/9826234\/09376709.pdf?arnumber=9376709","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:39:29Z","timestamp":1704843569000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9376709\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":35,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tits.2021.3061627","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7]]}}}