{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T14:23:31Z","timestamp":1779373411160,"version":"3.53.1"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"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":["61977019"],"award-info":[{"award-number":["61977019"]}],"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":["U1813206"],"award-info":[{"award-number":["U1813206"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Shenzhen Fundamental Research","doi-asserted-by":"publisher","award":["JCYJ20220818102415033"],"award-info":[{"award-number":["JCYJ20220818102415033"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Shenzhen Fundamental Research","doi-asserted-by":"publisher","award":["JSGG20201103093802006"],"award-info":[{"award-number":["JSGG20201103093802006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Shenzhen Fundamental Research","doi-asserted-by":"publisher","award":["KJZD20230923114222045"],"award-info":[{"award-number":["KJZD20230923114222045"]}],"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":[[2024,10]]},"DOI":"10.1109\/tits.2024.3397700","type":"journal-article","created":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T17:32:14Z","timestamp":1716226334000},"page":"13653-13666","source":"Crossref","is-referenced-by-count":21,"title":["Safe Reinforcement Learning in Autonomous Driving With Epistemic Uncertainty Estimation"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7173-9138","authenticated-orcid":false,"given":"Zheng","family":"Zhang","sequence":"first","affiliation":[{"name":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7485-6344","authenticated-orcid":false,"given":"Qi","family":"Liu","sequence":"additional","affiliation":[{"name":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7890-9677","authenticated-orcid":false,"given":"Yanjie","family":"Li","sequence":"additional","affiliation":[{"name":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3429-5877","authenticated-orcid":false,"given":"Ke","family":"Lin","sequence":"additional","affiliation":[{"name":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linyu","family":"Li","sequence":"additional","affiliation":[{"name":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3150668"},{"key":"ref2","first-page":"1","article-title":"Alvinn: An autonomous land vehicle in a neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"1","author":"Pomerleau"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3024655"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/RCAR52367.2021.9517610"},{"key":"ref5","article-title":"Concrete problems in AI safety","author":"Amodei","year":"2016","journal-title":"arXiv:1606.06565"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2983149"},{"issue":"1","key":"ref7","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":"ref8","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref9","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Achiam"},{"issue":"167","key":"ref10","first-page":"1","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref11","first-page":"5580","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Kendall"},{"key":"ref12","first-page":"6405","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lakshminarayanan"},{"key":"ref13","first-page":"1110","article-title":"Learning to walk in the real world with minimal human effort","volume-title":"Proc. Conf. Robot Learn.","author":"Ha"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.11"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461233"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref17","article-title":"Feasible actor-critic: Constrained reinforcement learning for ensuring statewise safety","author":"Ma","year":"2021","journal-title":"arXiv:2105.10682"},{"key":"ref18","article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","author":"Shalev-Shwartz","year":"2016","journal-title":"arXiv:1610.03295"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304614"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636480"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8813791"},{"key":"ref22","first-page":"4697","article-title":"Bayesian deep learning and a probabilistic perspective of generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wilson"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CASE49439.2021.9551544"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00167"},{"key":"ref25","first-page":"7436","article-title":"Uncertainty-based offline reinforcement learning with diversified q-ensemble","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"An"},{"key":"ref26","first-page":"220","article-title":"Perceptual attention-based predictive control","volume-title":"Proc. Conf. Robot Learn.","author":"Lee"},{"key":"ref27","volume-title":"Constrained Markov Decision Processes","volume":"7","author":"Altman","year":"1999"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1126\/science.153.3731.34"},{"issue":"1","key":"ref29","first-page":"6070","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3152724"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref32","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013445"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1063\/pt.3.2314"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3190471"},{"key":"ref36","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref37","first-page":"1167","article-title":"Classes of multiagent Q-learning dynamics with epsilon-greedy exploration","volume-title":"Proc. 27th Int. Conf. Mach. Learn. (ICML-10)","author":"Wunder"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3185180"},{"key":"ref40","article-title":"Rewarding episodic visitation discrepancy for exploration in reinforcement learning","author":"Yuan","year":"2022","journal-title":"arXiv:2209.08842"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119217"},{"key":"ref42","volume-title":"Stochastic Approximation: A Dynamical Systems Viewpoint","volume":"48","author":"Borkar","year":"2009"},{"key":"ref43","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref44","first-page":"437","article-title":"On the convergence of stochastic iterative dynamic programming algorithms","volume":"1","author":"Peng","year":"1993","journal-title":"Proc. Adapt. Behav."},{"key":"ref45","article-title":"Quantifying epistemic uncertainty in deep learning","author":"Huang","year":"2021","journal-title":"arXiv:2110.12122"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05946-3"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974682"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2010.03.003"},{"key":"ref49","volume-title":"Understanding Aleatory and Epistemic Parameter Uncertainty in Statistical Models","author":"Porter","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956231"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012997331639"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"ref53","article-title":"Reward constrained policy optimization","author":"Tessler","year":"2018","journal-title":"arXiv:1805.11074"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3348422"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/10705407\/10534899.pdf?arnumber=10534899","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T02:46:36Z","timestamp":1733885196000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10534899\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":54,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tits.2024.3397700","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}