{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:31:41Z","timestamp":1775579501902,"version":"3.50.1"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Veh."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tiv.2024.3463468","type":"journal-article","created":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T13:26:52Z","timestamp":1726838812000},"page":"3782-3791","source":"Crossref","is-referenced-by-count":11,"title":["Safe Reinforcement Learning for Autonomous Driving by Using Disturbance-Observer-Based Control Barrier Functions"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6317-6149","authenticated-orcid":false,"given":"Zhengyu","family":"Hou","sequence":"first","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6917-4111","authenticated-orcid":false,"given":"Wenjun","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4840-076X","authenticated-orcid":false,"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich, Munich, Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1142\/S2301385023310027"},{"issue":"1","key":"ref2","first-page":"111","article-title":"Introduction to reinforcement learning","volume-title":"Generative AI, Business & Information Systems Engineering","volume":"66","author":"Ernst","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070252"},{"key":"ref4","article-title":"Model-based reinforcement learning for atari","author":"Kaiser","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3086033"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.118460"},{"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","first-page":"9797","article-title":"Safe reinforcement learning in constrained Markov decision processes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wachi","year":"2020"},{"key":"ref9","article-title":"A primal-dual approach to constrained Markov decision processes","author":"Chen","year":"2021"},{"key":"ref10","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achiam","year":"2017"},{"key":"ref11","article-title":"A Lyapunov-based approach to safe reinforcement learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"31","author":"Chow","year":"2018"},{"key":"ref12","article-title":"Safe exploration in continuous action spaces","author":"Dalal","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636468"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561561"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3049335"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2019.2949757"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2015.2478397"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2638961"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2015.11.152"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2016.7524935"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029455"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110684"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.5132"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.088"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2920206"},{"key":"ref28","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":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9303829"},{"key":"ref30","article-title":"Modeling purposeful adaptive behavior with the principle of maximum causal entropy","author":"Ziebart","year":"2010"},{"key":"ref31","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018"},{"key":"ref32","volume-title":"Control of Nonlinear Systems","author":"Khalil","year":"2002"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3105491"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995816"}],"container-title":["IEEE Transactions on Intelligent Vehicles"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7274857\/11199363\/10684598.pdf?arnumber=10684598","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:36:19Z","timestamp":1760160979000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10684598\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":34,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tiv.2024.3463468","relation":{},"ISSN":["2379-8904","2379-8858"],"issn-type":[{"value":"2379-8904","type":"electronic"},{"value":"2379-8858","type":"print"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}