{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T08:05:19Z","timestamp":1773734719857,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,18]]},"DOI":"10.1109\/itsc60802.2025.11423581","type":"proceedings-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T20:10:23Z","timestamp":1773691823000},"page":"3596-3603","source":"Crossref","is-referenced-by-count":0,"title":["VLAD: A VLM-Augmented Autonomous Driving Framework with Hierarchical Planning and Interpretable Decision Process"],"prefix":"10.1109","author":[{"given":"Cristian","family":"Gariboldi","sequence":"first","affiliation":[{"name":"Gifu University,Gifu,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hayato","family":"Tokida","sequence":"additional","affiliation":[{"name":"Gifu University,Gifu,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ken","family":"Kinjo","sequence":"additional","affiliation":[{"name":"DENSO CORPORATION,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Asada","sequence":"additional","affiliation":[{"name":"DENSO CORPORATION,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Carballo","sequence":"additional","affiliation":[{"name":"Gifu University,Gifu,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref2","article-title":"Senna: Bridging Large VisionLanguage Models and End-to-End Autonomous Driving","author":"Jiang","year":"2024","journal-title":"arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref4","article-title":"Judging LLM-as-aJudge with MT- Bench and Chatbot Arena","author":"Zheng","year":"2023","journal-title":"NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref6","article-title":"LanguageMPC: Large Language Models as Decision Makers for Autonomous Driving","author":"Sha","year":"2025","journal-title":"arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_15"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"ref10","article-title":"Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives","author":"Xie","year":"2025","journal-title":"arXiv"},{"key":"ref11","article-title":"CARLA: An Open Urban Driving Simulator","author":"Dosovitskiy","year":"2017","journal-title":"CoRL"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611590"},{"key":"ref13","article-title":"LMDrive: Closed-Loop End-toEnd Driving with Large Language Models","author":"Shao","year":"2024","journal-title":"arXiv"},{"key":"ref14","article-title":"CarLLaVA: Vision language models for camera-only closed-loop driving","author":"Renz","year":"2024","journal-title":"arXiv"},{"key":"ref15","article-title":"DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving","author":"Wang","year":"2023","journal-title":"arXiv"},{"key":"ref16","article-title":"DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models","author":"Tian","year":"2024","journal-title":"CoRL"},{"key":"ref17","article-title":"VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Driving","author":"Huang","year":"2024","journal-title":"arXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01120"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IV55156.2024.10588479"},{"key":"ref20","article-title":"EMMA: End-to-End Multimodal Model for Autonomous Driving","author":"Hwang","year":"2024","journal-title":"arXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW65960.2025.00113"},{"key":"ref22","article-title":"VLM-AD: End-to-End Autonomous Driving through Vision-Language Model Supervision","author":"Xu","year":"2024","journal-title":"arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/s24134113"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160326"},{"key":"ref25","article-title":"Hint-AD: Holistically Aligned Interpretability in End-to-End Autonomous Driving","author":"Kairui","year":"2024","journal-title":"CoRL"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref27","article-title":"VLM-E2E: Enhancing End-to-End Autonomous Driving with Multimodal Driver Attention Fusion","author":"Liu","year":"2025","journal-title":"arXiv"},{"key":"ref28","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref29","article-title":"Attention Is All You Need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref30","article-title":"Bleu: a method for automatic evaluation of machine translation","volume-title":"ACL","author":"Papineni","year":"2002"},{"key":"ref31","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"ACL","author":"Banerjee","year":"2005"},{"key":"ref32","article-title":"ROUGE: A Package for Automatic Evaluation of Summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref34","article-title":"GPTScore: Evaluate as You Desire","author":"Fu","year":"2023","journal-title":"arXiv"},{"key":"ref35","article-title":"LoRA: Low-Rank Adaptation of Large Language Models","volume-title":"ICLR","author":"Hu","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"},{"key":"ref38","article-title":"Learning by Cheating","author":"Chen","year":"2020","journal-title":"CoRL"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01254"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"}],"event":{"name":"2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)","location":"Gold Coast, Australia","start":{"date-parts":[[2025,11,18]]},"end":{"date-parts":[[2025,11,21]]}},"container-title":["2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11422813\/11423000\/11423581.pdf?arnumber=11423581","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T05:49:09Z","timestamp":1773726549000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11423581\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,18]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/itsc60802.2025.11423581","relation":{},"subject":[],"published":{"date-parts":[[2025,11,18]]}}}