{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:21:49Z","timestamp":1780053709207,"version":"3.54.0"},"reference-count":56,"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":["52394261"],"award-info":[{"award-number":["52394261"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52202494"],"award-info":[{"award-number":["52202494"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52202495"],"award-info":[{"award-number":["52202495"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Veh. Technol."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tvt.2025.3629119","type":"journal-article","created":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:39:30Z","timestamp":1762367970000},"page":"7327-7342","source":"Crossref","is-referenced-by-count":1,"title":["VLM-Driver: Human-Like Autonomous Driving Decision-Making via Vision Language Model"],"prefix":"10.1109","volume":"75","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1597-1961","authenticated-orcid":false,"given":"Rui","family":"Zhao","sequence":"first","affiliation":[{"name":"College of Automotive Engineering, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qirui","family":"Yuan","sequence":"additional","affiliation":[{"name":"College of Automotive Engineering, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8463-7732","authenticated-orcid":false,"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"College of Automotive Engineering, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqiang","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Automotive Engineering, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7824-7751","authenticated-orcid":false,"given":"Yun","family":"Li","sequence":"additional","affiliation":[{"name":"Graduate School of Information and Science Technology, University of Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4623-3956","authenticated-orcid":false,"given":"Zhenhai","family":"Gao","sequence":"additional","affiliation":[{"name":"College of Automotive Engineering and the National Key Laboratory of Automotive Chassis Integration and Bionics, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8083-6403","authenticated-orcid":false,"given":"Hongyu","family":"Hu","sequence":"additional","affiliation":[{"name":"College of Automotive Engineering and the National Key Laboratory of Automotive Chassis Integration and Bionics, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9020-6720","authenticated-orcid":false,"given":"Fei","family":"Gao","sequence":"additional","affiliation":[{"name":"College of Automotive Engineering and the National Key Laboratory of Automotive Chassis Integration and Bionics, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A survey on data-driven modeling of human drivers\u2019 lane-changing decisions","author":"Huang","year":"2025"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2900416"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852110"},{"issue":"1","key":"ref5","first-page":"20","article-title":"A rule-based expert system for automobile fault diagnosis","volume":"7","author":"Ahmad","year":"2021","journal-title":"Int. J. Perceptive Cogn. Comput."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASYU58738.2023.10296611"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2022.3177788"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564912"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3216288"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00886"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_21"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01254"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3225250"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"issue":"PMLR","key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref20","article-title":"Palm-E: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref24","article-title":"A language agent for autonomous driving","author":"Mao","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/s24134113"},{"key":"ref26","article-title":"DriveVLM: The convergence of autonomous driving and large vision-language models","author":"Tian","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.075"},{"key":"ref29","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"issue":"240","key":"ref30","first-page":"1","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref31","first-page":"46595","article-title":"Judging LLM-as-a-judge with MT-bench and chatbot arena","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zheng","year":"2024"},{"key":"ref32","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref33","article-title":"LLaMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32902"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611485"},{"key":"ref36","article-title":"GPT-driver: Learning to drive with GPT","author":"Mao","year":"2023"},{"key":"ref37","article-title":"Senna: Bridging large vision-language models and end-to-end autonomous driving","author":"Jiang","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref39","first-page":"91","article-title":"SIFT-the scale invariant feature transform","volume":"2","author":"Lowe","year":"2004","journal-title":"Int. j"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92611-2_4"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref42","article-title":"LLaVA-next-interleave: Tackling multi-image, video, and 3D in large multimodal models","author":"Li","year":"2024"},{"key":"ref43","article-title":"SigLIP 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025"},{"key":"ref44","article-title":"Qwen2 technical report","author":"Team","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01430"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref47","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. and\/or Summarization","author":"Banerjee","year":"2005"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref49","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128800"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01408"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73650-6_6"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02659"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01463"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0025"}],"container-title":["IEEE Transactions on Vehicular Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/25\/11526914\/11229878.pdf?arnumber=11229878","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T19:53:08Z","timestamp":1779306788000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11229878\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":56,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tvt.2025.3629119","relation":{},"ISSN":["0018-9545","1939-9359"],"issn-type":[{"value":"0018-9545","type":"print"},{"value":"1939-9359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}