{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:45:54Z","timestamp":1793493954549,"version":"4.5.0"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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":["62273135"],"award-info":[{"award-number":["62273135"]}],"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":["62373356"],"award-info":[{"award-number":["62373356"]}],"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":["U24B20162"],"award-info":[{"award-number":["U24B20162"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Hubei Province in China","award":["2025AFA083"],"award-info":[{"award-number":["2025AFA083"]}]},{"name":"Original Exploration Seed Project of Hubei University","award":["202416403000001"],"award-info":[{"award-number":["202416403000001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tsmc.2025.3648508","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:40:50Z","timestamp":1768423250000},"page":"2076-2088","source":"Crossref","is-referenced-by-count":11,"title":["Long- and Short-Term Constraint-Driven Safe Reinforcement Learning for Autonomous Driving"],"prefix":"10.1109","volume":"56","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3918-8461","authenticated-orcid":false,"given":"Xuemin","family":"Hu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Hubei University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pan","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Hubei University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yijun","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Hubei University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5708-766X","authenticated-orcid":false,"given":"Bo","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4925-0572","authenticated-orcid":false,"given":"Long","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems and the State Key Laboratory of Management and Control for Complex Systems, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3365997"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.124182"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3312777"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tsmc.2023.3276218"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3282073"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.geits.2025.100279"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3274536"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3004984"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3287223"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2529582"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2017.07.019"},{"key":"ref12","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3025671"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"issue":"1","key":"ref15","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":"ref16","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Achiam"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref18","first-page":"15338","article-title":"First order constrained optimization in policy space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref19","first-page":"9133","article-title":"Responsive safety in reinforcement learning by PID Lagrangian methods","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Stooke"},{"key":"ref20","first-page":"14","volume-title":"Benchmarking Safe Exploration in Deep Reinforcement Learning","author":"Ray","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3223728"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3223131"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3186639"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3009674"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2921918"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197027"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3225340"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968225"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2017.2712561"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2870983"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917192"},{"key":"ref33","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Lillicrap"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197132"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304668"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3026111"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3116063"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3153848"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.geits.2024.100156"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3285442"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3352543"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3226424"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.geits.2025.100334"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3066409"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3439557"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2024.3412172"},{"key":"ref47","article-title":"Query-efficient imitation learning for end-to-end autonomous driving","author":"Zhang","year":"2016","journal-title":"arXiv:1605.06450"},{"key":"ref48","first-page":"1","article-title":"Reward constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Tessler"},{"key":"ref49","first-page":"18828","article-title":"Direct behavior specification via constrained reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Roy"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/520"},{"key":"ref51","article-title":"Safe exploration in continuous action spaces","author":"Dalal","year":"2018","journal-title":"arXiv:1801.08757"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070252"},{"key":"ref53","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":"ref54","article-title":"Feasible actor-critic: Constrained reinforcement learning for ensuring statewise safety","author":"Ma","year":"2021","journal-title":"arXiv:2105.10682"},{"key":"ref55","first-page":"1","article-title":"SafeRL-kit: Evaluating efficient reinforcement learning methods for safe autonomous driving","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Zhang"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3238656"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3152724"},{"key":"ref58","first-page":"7553","article-title":"Constrained reinforcement learning has zero duality gap","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"32","author":"Paternain"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3190471"},{"key":"ref60","first-page":"1554","article-title":"Safe driving via expert guided policy optimization","volume-title":"Proc. Conf. Robot Learn.","author":"Peng"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2025.125201"},{"key":"ref62","first-page":"1","article-title":"Projection-based constrained policy optimization","volume-title":"Proc. 8th Int. Conf. Learn. Represent. (ICLR)","author":"Yang"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221021\/11406734\/11353266.pdf?arnumber=11353266","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T20:58:37Z","timestamp":1771966717000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11353266\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":62,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2025.3648508","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}