{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T03:50:24Z","timestamp":1775620224911,"version":"3.50.1"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"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":["62273035"],"award-info":[{"award-number":["62273035"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Natural Science Foundation-Xiaomi Innovation Joint Fund","award":["L253007"],"award-info":[{"award-number":["L253007"]}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4262056"],"award-info":[{"award-number":["4262056"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4242052"],"award-info":[{"award-number":["4242052"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4252045"],"award-info":[{"award-number":["4252045"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/lra.2026.3675928","type":"journal-article","created":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T20:08:55Z","timestamp":1773950935000},"page":"5821-5828","source":"Crossref","is-referenced-by-count":0,"title":["PerlAD: Towards Enhanced Closed-Loop End-to-End Autonomous Driving With Pseudo-Simulation-Based Reinforcement Learning"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3513-1380","authenticated-orcid":false,"given":"Yinfeng","family":"Gao","sequence":"first","affiliation":[{"name":"School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9747-391X","authenticated-orcid":false,"given":"Qichao","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3784-2656","authenticated-orcid":false,"given":"Deqing","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongpu","family":"Xia","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guang","family":"Li","sequence":"additional","affiliation":[{"name":"Xiaomi EV, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Ma","sequence":"additional","affiliation":[{"name":"Xiaomi EV, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guang","family":"Chen","sequence":"additional","affiliation":[{"name":"Xiaomi EV, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hangjun","family":"Ye","sequence":"additional","affiliation":[{"name":"Xiaomi EV, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4985-9516","authenticated-orcid":false,"given":"Long","family":"Chen","sequence":"additional","affiliation":[{"name":"Xiaomi EV, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1201-7785","authenticated-orcid":false,"given":"Da-Wei","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8218-9633","authenticated-orcid":false,"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref3","first-page":"57196","article-title":"Drivetransformer: Unified transformer for scalable end-to-end autonomous driving","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jia","year":"2025"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICICIP47338.2019.9012185"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3448237"},{"key":"ref6","first-page":"1","article-title":"Raw2drive: Reinforcement learning with aligned world models for end-to-end autonomous driving (in CARLA v2)","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Yang","year":"2025"},{"key":"ref7","first-page":"1","article-title":"Rad: Training an end-to-end driving policy via large-scale 3dgs-based reinforcement learning","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Gao","year":"2025"},{"key":"ref8","article-title":"Learning personalized driving styles via reinforcement learning from human feedback","author":"Li","year":"2025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i14.38149"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0025"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3408830"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01319"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128800"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3641129"},{"key":"ref15","article-title":"DiffAD: A unified diffusion modeling approach for autonomous driving","author":"Wang","year":"2025"},{"key":"ref16","first-page":"28632","article-title":"World4drive: End-to-end autonomous driving via intention-aware physical latent world model","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Zheng","year":"2025"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01432"},{"key":"ref18","first-page":"1","article-title":"ReasonPlan: Unified scene prediction and decision reasoning for closed-loop autonomous driving","volume-title":"Proc. Conf. Robot Learn.","author":"Liu","year":"2025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2026.3664120"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3202185"},{"key":"ref21","first-page":"11710","article-title":"Robust autonomy emerges from self-play","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cusumano-Towner","year":"2025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01607"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00757"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73650-6_6"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"ref27","first-page":"27137","article-title":"End-to-end driving with online trajectory evaluation via bev world model","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Li","year":"2025"},{"key":"ref28","first-page":"27305","article-title":"Hydra-next: Robust closed-loop driving with open-loop training","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Li","year":"2025"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3643264"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_9"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11435997\/11447377.pdf?arnumber=11447377","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T02:51:17Z","timestamp":1775616677000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11447377\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":30,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3675928","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}