{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T20:53:13Z","timestamp":1775508793795,"version":"3.50.1"},"reference-count":96,"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":[{"name":"Agency for Science, Technology and Research (A*STAR), Singapore"},{"name":"MTC Individual Research","award":["M22K2c0079"],"award-info":[{"award-number":["M22K2c0079"]}]},{"DOI":"10.13039\/501100001459","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","award":["MOE-T2EP50222-0002"],"award-info":[{"award-number":["MOE-T2EP50222-0002"]}],"id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001475","name":"Nanyang Technological University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001475","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tpami.2026.3653866","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:40:13Z","timestamp":1768423213000},"page":"5774-5792","source":"Crossref","is-referenced-by-count":0,"title":["Reinforced Refinement With Self-Aware Expansion for End-to-End Autonomous Driving"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3628-8777","authenticated-orcid":false,"given":"Haochen","family":"Liu","sequence":"first","affiliation":[{"name":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3838-160X","authenticated-orcid":false,"given":"Tianyu","family":"Li","sequence":"additional","affiliation":[{"name":"OpenDriveLab, School of Computing and Data Science, The University of Hong Kong, Pok Fu Lam, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1545-2793","authenticated-orcid":false,"given":"Haohan","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Chen","sequence":"additional","affiliation":[{"name":"OpenDriveLab, School of Computing and Data Science, The University of Hong Kong, Pok Fu Lam, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0113-2373","authenticated-orcid":false,"given":"Caojun","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Innovation Institute, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haochen","family":"Tian","sequence":"additional","affiliation":[{"name":"OpenDriveLab, School of Computing and Data Science, The University of Hong Kong, Pok Fu Lam, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongchen","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Innovation Institute, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyang","family":"Li","sequence":"additional","affiliation":[{"name":"OpenDriveLab, School of Computing and Data Science, The University of Hong Kong, Pok Fu Lam, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6897-4512","authenticated-orcid":false,"given":"Chen","family":"Lv","sequence":"additional","affiliation":[{"name":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"DECODE: Domain-aware continual domain expansion for motion prediction","author":"Li","year":"2024"},{"key":"ref2","first-page":"28706","article-title":"Navsim: Data-driven non-reactive autonomous vehicle simulation and benchmarking","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Dauner","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3223131"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3435937"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3526936"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/03611981211018697"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05732-2"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3225538"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8813817"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00361"},{"key":"ref13","article-title":"Vista: A generalizable driving world model with high fidelity and versatile controllability","author":"Gao","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3024655"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_9"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827073"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3142822"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917306"},{"key":"ref19","article-title":"Rad: Training an end-to-end driving policy via large-scale 3dgs-based reinforcement learning","author":"Gao","year":"2025"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610550"},{"key":"ref21","article-title":"Centaur: Robust end-to-end autonomous driving with test-time training","author":"Sima","year":"2025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3283542"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00610-y"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3524609"},{"key":"ref25","article-title":"Sustainable adaptation for autonomous driving with the mixture of progressive experts network","author":"Cui","year":"2025"},{"issue":"2","key":"ref26","first-page":"1","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","volume":"1","author":"Hu","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3333838"},{"key":"ref28","article-title":"VADv2: End-to-end vectorized autonomous driving via probabilistic planning","author":"Chen","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01124"},{"key":"ref30","article-title":"DriveVLM: The convergence of autonomous driving and large vision-language models","author":"Tian","year":"2024"},{"key":"ref31","article-title":"Unleashing generalization of end-to-end autonomous driving with controllable long video generation","author":"Ma","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3314762"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3372625"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01530"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01421"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02105"},{"key":"ref39","article-title":"AdaWM: Adaptive world model based planning for autonomous driving","author":"Wang","year":"2025"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00731"},{"key":"ref41","article-title":"TAIL: Task-specific adapters for imitation learning with large pretrained models","author":"Liu","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00368"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00605"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02271"},{"key":"ref45","article-title":"ActiveAD: Planning-oriented active learning for end-to-end autonomous driving","author":"Lu","year":"2024"},{"key":"ref46","article-title":"Robust autonomy emerges from self-play","author":"Cusumano-Towner","year":"2025"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_9"},{"key":"ref48","article-title":"Finetuning generative trajectory model with reinforcement learning from human feedback","author":"Li","year":"2025"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3069497"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-60916-4_20"},{"key":"ref51","first-page":"14927","article-title":"Deep evidential regression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Amini","year":"2020"},{"key":"ref52","first-page":"32633","article-title":"Improving expert predictions with conformal prediction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Straitouri","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3231833"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28323"},{"key":"ref55","first-page":"774","article-title":"Motion style transfer: Modular low-rank adaptation for deep motion forecasting","volume-title":"Proc. Conf. Robot Learn.","author":"Kothari","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128750"},{"key":"ref57","first-page":"1","article-title":"Carla: An open urban driving simulator","volume-title":"Proc. Conf. Robot Learn.","author":"Dosovitskiy","year":"2017"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2023.10.011"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3322166"},{"key":"ref60","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":"ref61","first-page":"1268","article-title":"Parting with misconceptions about learning-based vehicle motion planning","volume-title":"Proc. Conf. Robot Learn.","author":"Dauner","year":"2023"},{"key":"ref62","article-title":"DeepSeekMath: Pushing the limits of mathematical reasoning in open language models","author":"Shao","year":"2024"},{"key":"ref63","article-title":"Hydra-MDP: End-to-end multimodal planning with multi-target hydra-distillation","author":"Li","year":"2024"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00925"},{"key":"ref65","first-page":"1356","article-title":"Posterior network: Uncertainty estimation without OOD samples via density-based pseudo-counts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Charpentier","year":"2020"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-3675-0"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176343003"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.2307\/1269343"},{"key":"ref69","article-title":"Pseudo-simulation for autonomous driving","author":"Cao","year":"2025"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0025"},{"key":"ref71","article-title":"Pre-crash scenario typology for crash avoidance research","author":"Najm","year":"2007","journal-title":"United States. Dept. Transp. Nat. Highway Traffic Saf."},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref73","article-title":"Hidden biases of end-to-end driving datasets","author":"Zimmerlin","year":"2024"},{"key":"ref74","article-title":"Navsim leaderboard","year":"2024"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200245"},{"key":"ref76","article-title":"ResAD: Normalized residual trajectory modeling for end-to-end autonomous driving","author":"Zheng","year":"2025"},{"key":"ref77","article-title":"iPad: Iterative proposal-centric end-to-end autonomous driving","author":"Guo","year":"2025"},{"key":"ref78","article-title":"RAP: 3D Rasterization augmented end-to-end planning","author":"Feng","year":"2025"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i14.38178"},{"key":"ref80","article-title":"FlowDrive: Energy flow field for end-to-end autonomous driving","author":"Jiang","year":"2025"},{"key":"ref81","article-title":"Generalized trajectory scoring for end-to-end multimodal planning","author":"Li","year":"2025"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"ref83","first-page":"3053","article-title":"RLlib: Abstractions for distributed reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liang","year":"2018"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00157"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0443"},{"key":"ref86","article-title":"Rethinking the open-loop evaluation of end-to-end autonomous driving in nuscenes","author":"Zhai","year":"2023"},{"key":"ref87","first-page":"1","article-title":"DriveTransformer: Unified transformer for scalable end-to-end autonomous driving","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jia","year":"2025"},{"key":"ref88","article-title":"Hydra-NeXt: Robust closed-loop driving with open-loop training","author":"Li","year":"2025"},{"key":"ref89","article-title":"TransDiffuser: End-to-end trajectory generation with decorrelated multi-modal representation for autonomous driving","author":"Jiang","year":"2025"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01607"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127286"},{"key":"ref92","article-title":"LoRA learns less and forgets less","author":"Biderman","year":"2024"},{"key":"ref93","first-page":"2025","article-title":"Welcome to the era of experience","volume-title":"Preprint Chapter Appear Designing Intell.","author":"Silver"},{"key":"ref94","article-title":"Does reinforcement learning really incentivize reasoning capacity in LLMS beyond the base model?","author":"Yue","year":"2025"},{"key":"ref95","article-title":"MTGS: Multi-traversal Gaussian splatting","author":"Li","year":"2025"},{"key":"ref96","article-title":"Decoupled diffusion sparks adaptive scene generation","author":"Zhou","year":"2025"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11474534\/11353028.pdf?arnumber=11353028","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:56:26Z","timestamp":1775505386000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11353028\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":96,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3653866","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}