{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T20:34:21Z","timestamp":1778531661902,"version":"3.51.4"},"reference-count":27,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"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":["52572475"],"award-info":[{"award-number":["52572475"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Development Project of Jilin Province","award":["20250102130JC"],"award-info":[{"award-number":["20250102130JC"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/lra.2025.3621971","type":"journal-article","created":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T17:41:20Z","timestamp":1760550080000},"page":"12580-12587","source":"Crossref","is-referenced-by-count":7,"title":["Sce2DriveX: A Generalized MLLM Framework for Scene-to-Drive Learning"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1597-1961","authenticated-orcid":false,"given":"Rui","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Automotive Engineering, Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qirui","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Automotive Engineering, Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8463-7732","authenticated-orcid":false,"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"School of Automotive Engineering, Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0124-6040","authenticated-orcid":false,"given":"Haofeng","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Automotive Engineering, Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7824-7751","authenticated-orcid":false,"given":"Yun","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information and Science Technology, The University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4623-3956","authenticated-orcid":false,"given":"Zhenhai","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Automotive Engineering and the National Key Laboratory of Automotive Chassis Integration and Bionics, Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9020-6720","authenticated-orcid":false,"given":"Fei","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Automotive Engineering and the National Key Laboratory of Automotive Chassis Integration and Bionics, Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00886"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.075"},{"key":"ref6","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref9","article-title":"GPT-driver: Learning to drive with GPT","author":"Mao","year":"2023"},{"key":"ref10","article-title":"DriveVLM: The convergence of autonomous driving and large vision-language models","author":"Tian","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28253"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32902"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611485"},{"key":"ref16","article-title":"Senna: Bridging large vision-language models and end-to-end autonomous driving","author":"Jiang","year":"2024"},{"key":"ref17","article-title":"LanguageBind: Extending video-language pretraining to N-modality by language-based semantic alignment","author":"Zhu","year":"2023"},{"key":"ref18","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee","year":"2005"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref20","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref22","article-title":"Qwen-Vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref23","article-title":"LLaVA-Onevision: Easy visual task transfer","author":"Li","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01254"},{"key":"ref26","article-title":"Omnidrive: A holistic LLM-agent framework for autonomous driving with 3D perception, reasoning and planning","author":"Wang","year":"2024","journal-title":"CoRR"},{"key":"ref27","first-page":"819","article-title":"Bench2Drive: Towards multi-ability benchmarking of closed-loop end-to-end autonomous driving","volume":"37","author":"Jia","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11215960\/11203976.pdf?arnumber=11203976","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T19:02:18Z","timestamp":1764010938000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11203976\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":27,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3621971","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}