{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:02:45Z","timestamp":1784131365476,"version":"3.55.0"},"reference-count":143,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Innovate U.K","award":["10063539"],"award-info":[{"award-number":["10063539"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tits.2025.3628969","type":"journal-article","created":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T18:44:49Z","timestamp":1763750689000},"page":"187-210","source":"Crossref","is-referenced-by-count":9,"title":["Large (Vision) Language Models for Autonomous Vehicles: Current Trends and Future Directions"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5025-6833","authenticated-orcid":false,"given":"Hanlin","family":"Tian","sequence":"first","affiliation":[{"name":"Department of Civil and Environmental Engineering, Centre for Transport Engineering and Modelling, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kethan","family":"Reddy","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, Centre for Transport Engineering and Modelling, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5530-2503","authenticated-orcid":false,"given":"Yuxiang","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, Centre for Transport Engineering and Modelling, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6969-2365","authenticated-orcid":false,"given":"Mohammed","family":"Quddus","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, Centre for Transport Engineering and Modelling, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4917-3343","authenticated-orcid":false,"given":"Yiannis","family":"Demiris","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Personal Robotics Laboratory, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6778-8264","authenticated-orcid":false,"given":"Panagiotis","family":"Angeloudis","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, Centre for Transport Engineering and Modelling, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref2","first-page":"1","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref3","article-title":"Dolphins: Multimodal language model for driving","author":"Ma","year":"2023","journal-title":"arXiv:2312.00438"},{"key":"ref4","article-title":"DriveLM: Driving with graph visual question answering","author":"Sima","year":"2023","journal-title":"arXiv:2312.14150"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01389"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00101"},{"key":"ref7","article-title":"LLM4Drive: A survey of large language models for autonomous driving","author":"Yang","year":"2023","journal-title":"arXiv:2311.01043"},{"key":"ref8","article-title":"A survey for foundation models in autonomous driving","author":"Gao","year":"2024","journal-title":"arXiv:2402.01105"},{"key":"ref9","article-title":"Towards knowledge-driven autonomous driving","author":"Li","year":"2023","journal-title":"arXiv:2312.04316"},{"key":"ref10","article-title":"Large language models for mobility analysis in transportation systems: A survey on forecasting tasks","author":"Zhang","year":"2024","journal-title":"arXiv:2405.02357"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28253"},{"key":"ref12","article-title":"A survey of large language models","author":"Xin Zhao","year":"2023","journal-title":"arXiv:2303.18223"},{"key":"ref13","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref14","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref15","first-page":"1","article-title":"ALVINN: An autonomous land vehicle in a neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"1","author":"Pomerleau"},{"key":"ref16","article-title":"End to end learning for self-driving cars","author":"Bojarski","year":"2016","journal-title":"arXiv:1604.07316"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref18","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref20","volume-title":"DALL-E: Creating Images From Text","author":"Ramesh et al","year":"2021"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.01042","volume-title":"High-Resolution Image Synthesis With Latent Diffusion Models","author":"Rombach","year":"2022"},{"key":"ref22","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"arXiv:2006.11239"},{"key":"ref23","article-title":"Diffusion models beat GANs on image synthesis","author":"Dhariwal","year":"2021","journal-title":"arXiv:2105.05233"},{"key":"ref24","article-title":"GAIA-1: A generative world model for autonomous driving","author":"Hu","year":"2023","journal-title":"arXiv:2309.17080"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33130"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10132-6"},{"key":"ref27","article-title":"Zelda: Video analytics using vision-language models","author":"Romero","year":"2023","journal-title":"arXiv:2305.03785"},{"key":"ref28","article-title":"Talk2BEV: Language-enhanced bird\u2019s-eye view maps for autonomous driving","author":"Choudhary","year":"2023","journal-title":"arXiv:2310.02251"},{"key":"ref29","article-title":"ChatBEV: A visual language model that understands BEV maps","author":"Xu","year":"2025","journal-title":"arXiv:2503.13938"},{"key":"ref30","article-title":"X-driver: Explainable autonomous driving with vision-language models","author":"Liu","year":"2025","journal-title":"arXiv:2505.05098"},{"key":"ref31","volume-title":"ChatGPT 3.5","year":"2023"},{"key":"ref32","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. 1st Annu. Conf. Robot Learn.","volume":"78","author":"Dosovitskiy"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.14778\/3570690.3570695"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_35"},{"key":"ref35","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. (ICML)","author":"Li"},{"key":"ref36","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref37","first-page":"1","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Dai"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10421993"},{"key":"ref39","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref40","article-title":"DiLu: A knowledge-driven approach to autonomous driving with large language models","author":"Wen","year":"2023","journal-title":"arXiv:2309.16292"},{"key":"ref41","volume-title":"An Environment for Autonomous Driving Decision-Making","author":"Leurent","year":"2018"},{"key":"ref42","article-title":"Empowering autonomous driving with large language models: A safety perspective","author":"Wang","year":"2023","journal-title":"arXiv:2312.00812"},{"key":"ref43","article-title":"LanguageMPC: Large language models as decision makers for autonomous driving","author":"Sha","year":"2023","journal-title":"arXiv:2310.03026"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI50451.2021.9660172"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3390\/s23229225"},{"key":"ref46","volume-title":"Zephyr 7b Alpha","year":"2024"},{"key":"ref47","volume-title":"Fatality Analysis Reporting System (FARS) 2020","year":"2020"},{"key":"ref48","article-title":"Driving with LLMs: Fusing object-level vector modality for explainable autonomous driving","author":"Chen","year":"2023","journal-title":"arXiv:2310.01957"},{"key":"ref49","article-title":"A language agent for autonomous driving","author":"Mao","year":"2023","journal-title":"arXiv:2311.10813"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref51","article-title":"Evaluation of large language models for decision making in autonomous driving","author":"Tanahashi","year":"2023","journal-title":"arXiv:2312.06351"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446745"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2024.3381793"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3621971"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.564"},{"key":"ref56","article-title":"GPT-driver: Learning to drive with GPT","author":"Mao","year":"2023","journal-title":"arXiv:2310.01415"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01416"},{"key":"ref58","article-title":"NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles","author":"Caesar","year":"2021","journal-title":"arXiv:2106.11810"},{"key":"ref59","article-title":"Diffusion-ES: Gradient-free planning with diffusion for autonomous driving and zero-shot instruction following","author":"Yang","year":"2024","journal-title":"arXiv:2402.06559"},{"key":"ref60","article-title":"LC-LLM: Explainable lane-change intention and trajectory predictions with large language models","author":"Peng","year":"2024","journal-title":"arXiv:2403.18344"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569552"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127665"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3325300"},{"key":"ref64","volume-title":"Simulation and Model-Based Design","author":"Documentation","year":"2020"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3115\/1628275.1628283"},{"key":"ref66","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref67","volume-title":"Introducing MPT-7b: A New Standard for Open-Source, Commercially Usable LLMs","author":"Team","year":"2023"},{"key":"ref68","article-title":"Towards human-centric autonomous driving: A fast-slow architecture integrating large language model guidance with reinforcement learning","author":"Xu","year":"2025","journal-title":"arXiv:2505.06875"},{"key":"ref69","article-title":"LingoQA: Visual question answering for autonomous driving","author":"Marcu","year":"2023","journal-title":"arXiv:2312.14115"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33001"},{"key":"ref71","article-title":"Multi-frame, lightweight & efficient vision-language models for question answering in autonomous driving","author":"Gopalkrishnan","year":"2024","journal-title":"arXiv:2403.19838"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11247360"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01129"},{"key":"ref74","volume-title":"Vicuna: An Open-Source Chatbot Impressing GPT-4 With 90%* ChatGPT Quality","author":"Chiang et al","year":"2023"},{"key":"ref75","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Cho"},{"key":"ref76","article-title":"End-to-end autonomous driving: Challenges and frontiers","author":"Chen","year":"2023","journal-title":"arXiv:2306.16927"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00102"},{"key":"ref78","article-title":"HiLM-D: Towards high-resolution understanding in multimodal large language models for autonomous driving","author":"Ding","year":"2023","journal-title":"arXiv:2309.05186"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00110"},{"key":"ref80","article-title":"DriveGPT4: Interpretable end-to-end autonomous driving via large language model","author":"Xu","year":"2023","journal-title":"arXiv:2310.01412"},{"key":"ref81","article-title":"On the road with GPT-4V(ision): Early explorations of visual-language model on autonomous driving","author":"Wen","year":"2023","journal-title":"arXiv:2311.05332"},{"key":"ref82","volume-title":"GPT-4v(Ision) System Card","year":"2023"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_24"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.11922\/sciencedb.00603"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413827"},{"key":"ref87","volume-title":"Chinese Traffic Sign Database","author":"University","year":"2024"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106766"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02067"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1177\/03611981231185768"},{"key":"ref91","article-title":"LMDrive: Closed-loop end-to-end driving with large language models","author":"Shao","year":"2023","journal-title":"arXiv:2312.07488"},{"key":"ref92","article-title":"DriveMLM: Aligning multi-modal large language models with behavioral planning states for autonomous driving","author":"Wang","year":"2023","journal-title":"arXiv:2312.09245"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref94","article-title":"DriveVLM: The convergence of autonomous driving and large vision-language models","author":"Tian","year":"2024","journal-title":"arXiv:2402.12289"},{"key":"ref95","article-title":"Omnidrive: A holistic LLM-agent framework for autonomous driving with 3D perception, reasoning and planning","author":"Wang","year":"2024","journal-title":"arXiv:2405.01533"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/fllm63129.2024.10852498"},{"key":"ref97","article-title":"Senna: Bridging large vision-language models and end-to-end autonomous driving","author":"Jiang","year":"2024","journal-title":"arXiv:2410.22313"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802555"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.354"},{"key":"ref100","article-title":"WiseAD: Knowledge augmented end-to-end autonomous driving with vision-language model","author":"Zhang","year":"2024","journal-title":"arXiv:2412.09951"},{"key":"ref101","article-title":"VLM-E2E: Enhancing end-to-end autonomous driving with multimodal driver attention fusion","author":"Liu","year":"2025","journal-title":"arXiv:2502.18042"},{"key":"ref102","article-title":"ORION: A holistic end-to-end autonomous driving framework by vision-language instructed action generation","author":"Fu","year":"2025","journal-title":"arXiv:2503.19755"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0025"},{"key":"ref104","article-title":"AlphaDrive: Unleashing the power of VLMs in autonomous driving via reinforcement learning and reasoning","author":"Jiang","year":"2025","journal-title":"arXiv:2503.07608"},{"key":"ref105","article-title":"OpenDriveVLA: Towards end-to-end autonomous driving with large vision language action model","author":"Zhou","year":"2025","journal-title":"arXiv:2503.23463"},{"key":"ref106","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01127"},{"key":"ref108","first-page":"144","article-title":"Language-guided traffic simulation via scene-level diffusion","volume-title":"Proc. Conf. Robot Learn.","author":"Zhong"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10422308"},{"key":"ref110","volume-title":"Asam Openxontology","year":"2023"},{"key":"ref111","article-title":"Surrealdriver: Designing generative driver agent simulation framework in urban contexts based on large language model","author":"Jin","year":"2023","journal-title":"arXiv:2309.13193"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/IV55156.2024.10588848"},{"key":"ref113","first-page":"183","article-title":"SUMO (simulation of urban mobility)\u2014An open-source traffic simulation","volume-title":"Proc. 4th Middle East Symp. Simul. Model.","author":"Krajzewicz"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01428"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1016\/j.tranpol.2024.03.006"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3363232"},{"key":"ref117","article-title":"INTERACTION dataset: An INTERnational, adversarial and cooperative moTION dataset in interactive driving scenarios with semantic maps","author":"Zhan","year":"2019","journal-title":"arXiv:1910.03088"},{"key":"ref118","article-title":"Enhancing autonomous vehicle training with language model integration and critical scenario generation","author":"Tian","year":"2024","journal-title":"arXiv:2404.08570"},{"key":"ref119","article-title":"Mistral 7B","author":"Jiang","year":"2023","journal-title":"arXiv:2310.06825"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01464"},{"key":"ref121","article-title":"DiffVLA: Vision-language guided diffusion planning for autonomous driving","author":"Jiang","year":"2025","journal-title":"arXiv:2505.19381"},{"key":"ref122","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"},{"key":"ref123","article-title":"ReasonPlan: Unified scene prediction and decision reasoning for closed-loop autonomous driving","author":"Liu","year":"2025","journal-title":"arXiv:2505.20024"},{"issue":"140","key":"ref124","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref125","article-title":"MagicDrive: Street view generation with diverse 3D geometry control","author":"Gao","year":"2023","journal-title":"arXiv:2310.02601"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref128","article-title":"ADriver-I: A general world model for autonomous driving","author":"Jia","year":"2023","journal-title":"arXiv:2311.13549"},{"key":"ref129","article-title":"FutureSightDrive: Thinking visually with spatio-temporal CoT for autonomous driving","author":"Zeng","year":"2025","journal-title":"arXiv:2505.17685"},{"key":"ref130","article-title":"GEM: A generalizable ego-vision multimodal world model for fine-grained ego-motion, object dynamics, and scene composition control","author":"Hassan","year":"2024","journal-title":"arXiv:2412.11198"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32902"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611018"},{"key":"ref133","article-title":"Reason2Drive: Towards interpretable and chain-based reasoning for autonomous driving","author":"Nie","year":"2023","journal-title":"arXiv:2312.03661"},{"key":"ref134","article-title":"LaMPilot: An open benchmark dataset for autonomous driving with language model programs","author":"Ma","year":"2023","journal-title":"arXiv:2312.04372"},{"key":"ref135","article-title":"Automated evaluation of large vision-language models on self-driving corner cases","author":"Chen","year":"2024","journal-title":"arXiv:2404.10595"},{"key":"ref136","article-title":"Fine-grained evaluation of large vision-language models in autonomous driving","author":"Li","year":"2025","journal-title":"arXiv:2503.21505"},{"key":"ref137","article-title":"Strategic fusion of vision language models: Shapley-credited context-aware dawid-skene for multi-label tasks in autonomous driving","author":"Feng","year":"2025","journal-title":"arXiv:2510.01126"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01364"},{"key":"ref139","article-title":"On-board vision-language models for personalized autonomous vehicle motion control: System design and real-world validation","author":"Cui","year":"2024","journal-title":"arXiv:2411.11913"},{"key":"ref140","article-title":"LiteVLM: A low-latency vision-language model inference pipeline for resource-constrained environments","author":"Huang","year":"2025","journal-title":"arXiv:2506.07416"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10422153"},{"key":"ref142","article-title":"Graph-based topology reasoning for driving scenes","author":"Li","year":"2023","journal-title":"arXiv:2304.05277"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-51313-2"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/11322649\/11264491.pdf?arnumber=11264491","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T18:17:57Z","timestamp":1767377877000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11264491\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":143,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tits.2025.3628969","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.172963218.80161917\/v1","asserted-by":"object"}]},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}