{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T09:07:53Z","timestamp":1771924073826,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"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":[],"published-print":{"date-parts":[[2025,12,3]]},"DOI":"10.1109\/robio66223.2025.11376130","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:43:52Z","timestamp":1771879432000},"page":"1626-1633","source":"Crossref","is-referenced-by-count":0,"title":["Learning the References of Online Model Predictive Control for Urban Self-Driving"],"prefix":"10.1109","author":[{"given":"Yubin","family":"Wang","sequence":"first","affiliation":[{"name":"The Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou),Guangzhou,China,511453"}]},{"given":"Zengqi","family":"Peng","sequence":"additional","affiliation":[{"name":"The Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou),Guangzhou,China,511453"}]},{"given":"Yusen","family":"Xie","sequence":"additional","affiliation":[{"name":"The Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou),Guangzhou,China,511453"}]},{"given":"Yulin","family":"Li","sequence":"additional","affiliation":[{"name":"The Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou),Guangzhou,China,511453"}]},{"given":"Hakim","family":"Ghazzai","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology,The Division of Computer, Electrical and Mathematical Sciences and Engineering,Thuwal,Saudi Arabia,23955"}]},{"given":"Jun","family":"Ma","sequence":"additional","affiliation":[{"name":"The Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou),Guangzhou,China,511453"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3088009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2771351"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3148460"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3064284"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561049"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2926677"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2019.2949757"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3144787"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2015.xi.012"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341439"},{"key":"ref11","article-title":"Plan online, learn offline: Efficient learning and exploration via model-based control","author":"Lowrey","year":"2018","journal-title":"arXiv preprint"},{"key":"ref12","first-page":"211","article-title":"Practical reinforcement learning for MPC: Learning from sparse objectives in under an hour on a real robot","author":"Karnchanachari","year":"2020","journal-title":"in Learning for Dynamics and Control. PMLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/ECC54610.2021.9655042"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340823"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3141602"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160712"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610522"},{"key":"ref18","first-page":"1861","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"in International Conference on Machine Learning. PMLR","author":"Haarnoja"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s12532-018-0139-4"},{"key":"ref21","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref23","first-page":"1","article-title":"Carla: An open urban driving simulator","volume-title":"in Conference on Robot Learning. PMLR","author":"Dosovitskiy"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2964159"}],"event":{"name":"2025 IEEE International Conference on Robotics and Biomimetics (ROBIO)","location":"Chengdu, China","start":{"date-parts":[[2025,12,3]]},"end":{"date-parts":[[2025,12,7]]}},"container-title":["2025 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11373909\/11375854\/11376130.pdf?arnumber=11376130","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:12:42Z","timestamp":1771920762000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11376130\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/robio66223.2025.11376130","relation":{},"subject":[],"published":{"date-parts":[[2025,12,3]]}}}