{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T15:50:29Z","timestamp":1776181829947,"version":"3.50.1"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Science, Technology & Innovation Project of Xiongan New Area","award":["2022XAGG0114"],"award-info":[{"award-number":["2022XAGG0114"]}]},{"name":"JST ASPIRE","award":["JPMJAP2325"],"award-info":[{"award-number":["JPMJAP2325"]}]},{"name":"ROIS NII Open Collaborative Research","award":["24S0601"],"award-info":[{"award-number":["24S0601"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Veh."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tiv.2024.3412916","type":"journal-article","created":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T14:44:01Z","timestamp":1718117041000},"page":"359-372","source":"Crossref","is-referenced-by-count":5,"title":["Autonomous Driving via Knowledge-Enhanced Safe Reinforcement Learning"],"prefix":"10.1109","volume":"10","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\/0000-0002-3673-0043","authenticated-orcid":false,"given":"Shuang","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou, 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\/0000-0001-6853-5878","authenticated-orcid":false,"given":"Celimuge","family":"Wu","sequence":"additional","affiliation":[{"name":"Meta-Networking Research Center, The University of Electro-Communications, Tokyo, Japan"}],"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"}]},{"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"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3223131"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3276218"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3283021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3046646"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"issue":"1","key":"ref7","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garcia","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2024.3379246"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3292253"},{"key":"ref11","article-title":"Saferl-kit: Evaluating efficient reinforcement learning methods for safe autonomous driving","author":"Zhang","year":"2022"},{"key":"ref12","article-title":"Accelerated primal-dual policy optimization for safe reinforcement learning","author":"Liang","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070252"},{"key":"ref14","first-page":"784","article-title":"Model-free safe control for zero-violation reinforcement learning","volume-title":"Proc. 5th Annu. Conf. Robot Learn.","author":"Zhao","year":"2021"},{"key":"ref15","first-page":"291","article-title":"Safe reinforcement learning with chance-constrained model predictive control","volume-title":"Proc. Learn. Dyn. Control Conf.","author":"Pfrommer","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3152724"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CISS56502.2023.10089763"},{"key":"ref18","first-page":"36593","article-title":"Enforcing hard constraints with soft barriers: Safe reinforcement learning in unknown stochastic environments","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3024161"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102662"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3250720"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.088"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3160202"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3249564"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2022.3190850"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25826"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3238656"},{"key":"ref29","first-page":"9133","article-title":"Responsive safety in reinforcement learning by pid lagrangian methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Stooke"},{"key":"ref30","article-title":"Provably safe reinforcement learning: Conceptual analysis, survey, and benchmarking","author":"Krasowski","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3457538"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103656"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05732-2"},{"key":"ref34","article-title":"Prioritized experience replay","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schaul","year":"2016"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3135927"},{"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","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_36"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3225538"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2638961"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2017.2654063"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3009082"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1080\/00207721.2024.2304665"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2015.11.152"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS.2018.00018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147463"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3233592"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2016.7524935"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029455"},{"key":"ref49","first-page":"104","article-title":"Safe and efficient reinforcement learning using disturbance-observer-based control barrier functions","volume-title":"Proc. Learn. Dyn. Control Conf.","author":"Cheng","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2022.3216996"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2017.2710943"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17272"},{"key":"ref54","first-page":"1078","article-title":"Worst cases policy gradients","volume-title":"Proc. Conf. Robot Learn.","author":"Tang","year":"2020"},{"key":"ref55","volume-title":"Constrained Optimization and Lagrange Multiplier Methods","author":"Bertsekas","year":"2014"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/520"},{"key":"ref57","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. Conf. Robot Learn.","author":"Dosovitskiy","year":"2017"},{"key":"ref58","volume-title":"Implementation of the pure pursuit path tracking algorithm","author":"Coulter","year":"1992"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45103-X_50"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"}],"container-title":["IEEE Transactions on Intelligent Vehicles"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7274857\/11080505\/10553273.pdf?arnumber=10553273","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T05:55:56Z","timestamp":1752645356000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10553273\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":61,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tiv.2024.3412916","relation":{},"ISSN":["2379-8904","2379-8858"],"issn-type":[{"value":"2379-8904","type":"electronic"},{"value":"2379-8858","type":"print"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}