{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:44:40Z","timestamp":1766061880874,"version":"3.48.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010909","name":"Young Scientists Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010909","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011343","name":"Key Laboratory of System Control and Information Processing","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011343","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009950","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247057","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"7925-7932","source":"Crossref","is-referenced-by-count":0,"title":["From Learning to Mastery: Achieving Safe and Efficient Real-World Autonomous Driving with Human-in-the-Loop Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Zeqiao","family":"Li","sequence":"first","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System, School of Electrical and Information Engineering,Tianjin,China,300072"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yijing","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System, School of Electrical and Information Engineering,Tianjin,China,300072"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System, School of Electrical and Information Engineering,Tianjin,China,300072"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Li","sequence":"additional","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System, School of Electrical and Information Engineering,Tianjin,China,300072"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Li","sequence":"additional","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System, School of Electrical and Information Engineering,Tianjin,China,300072"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenfei","family":"Liu","sequence":"additional","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System, School of Electrical and Information Engineering,Tianjin,China,300072"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiqiang","family":"Zuo","sequence":"additional","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System, School of Electrical and Information Engineering,Tianjin,China,300072"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3134702"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3008612"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3024655"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2022.103829"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.ads5033"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2022.05.017"},{"journal-title":"Human-in-the-Loop Machine Learning: Active learning and annotation for human-centered AI. Manning","year":"2021","author":"Munro","key":"ref8"},{"key":"ref9","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Ross"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968287"},{"issue":"136","key":"ref11","first-page":"1","article-title":"A survey of preference-based reinforcement learning methods","volume":"18","author":"Wirth","year":"2017","journal-title":"Journal of Ma\u00acchine Learning Research"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-021-10006-9"},{"key":"ref13","first-page":"1","article-title":"Efficient learning of safe driving policy via human-AI copilot optimization","volume-title":"International Conference on Learning Representations","author":"Li"},{"key":"ref14","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Lillicrap"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_36"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.64"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3026111"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3537087"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s42154-023-00260-1"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594353"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341714"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.056"},{"journal-title":"Query-efficient imitation learning for end-to-end autonomous driving","year":"2016","author":"Zhang","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793698"},{"key":"ref26","first-page":"598","article-title":"Thriftydagger: Budget-aware novelty and risk gating for interactive imitation learning","volume-title":"Proceedings of the 5th Conference on Robot Learning","volume":"164","author":"Hoque"},{"journal-title":"Human-in-the-loop imitation learning using remote tele\u00acoperation","year":"2020","author":"Mandlekar","key":"ref27"},{"key":"ref28","first-page":"4299","article-title":"Deep reinforcement learning from human preferences","author":"Christiano","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","first-page":"519","article-title":"Batch active preference-based learning of reward functions","volume-title":"Proceedings of The 2nd Conference on Robot Learning","volume":"87","author":"Biyik"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.023"},{"key":"ref31","first-page":"7969","article-title":"Learning from active human involvement through proxy value propagation","author":"Peng","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International Conference on Machine Learning","author":"Haarnoja"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3190471"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref35","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Kumar"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198538677.003.0006"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247057.pdf?arnumber=11247057","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:39:49Z","timestamp":1766061589000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247057\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247057","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}