{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T17:30:55Z","timestamp":1778347855394,"version":"3.51.4"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127665","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"8434-8441","source":"Crossref","is-referenced-by-count":7,"title":["Occ-LLM: Enhancing Autonomous Driving with Occupancy-Based Large Language Models"],"prefix":"10.1109","author":[{"given":"Tianshuo","family":"Xu","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou),Information Hub,department of AI Thrust"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Lu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou),Information Hub,department of AI Thrust"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Yan","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingjie","family":"Cai","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingbing","family":"Liu","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingcong","family":"Chen","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou),Information Hub,department of AI Thrust"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"ref5","article-title":"Driving with llms: Fusing object-level vector modality for explainable autonomous driving","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3435937"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00425"},{"key":"ref8","article-title":"Multiscale iou: A metric for evaluation of salient object detection with fine structures","author":"Cheng","year":"2021","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3318070"},{"key":"ref10","article-title":"Talk2bev: Language-enhanced bird\u2019s-eye view maps for autonomous driving","author":"Dewangan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Hilm-d: Towards high-resolution hazard identification and intention prediction for autonomous driving","author":"Ding","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"An image is worth 16x 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230965"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref15","article-title":"Driving with vision-language models: Enhancing autonomous vehicles with multimodal ai","author":"Fu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Gaia-1: A generative world model for autonomous driving","author":"Hu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01254"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.31235\/osf.io\/j2u9x","volume-title":"Exploring the impacts of chatgpt on future scientific work","author":"Irons","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00341"},{"key":"ref24","article-title":"Blip-2: Bootstrapping languageimage pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Fb-occ: 3d occupancy prediction based on forward-backward view transformation","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"In Text Summarization Branches Out: Proceedings of the ACL-04 Workshop","author":"Lin","year":"2004"},{"key":"ref27","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00037"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00459"},{"key":"ref30","article-title":"GPT-4 technical report","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.85"},{"key":"ref33","first-page":"2023","article-title":"Evaluating chatgpt as an adjunct for radiologic decision-making","author":"Rao","year":"2023","journal-title":"MedRxiv"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143936"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref37","article-title":"Variational mixture-of-experts autoencoders for multi-modal deep generative models","volume":"32","author":"Shi","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref38","first-page":"948","article-title":"Lip-loc: Lidar image pretraining for cross-modal localization","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"Shubodh","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.28"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i13.26848"},{"key":"ref42","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","volume-title":"The future of driving: Autopilot and full s elf-driving capabilities","year":"2022"},{"key":"ref44","article-title":"Occ3d: A large-scale 3d occupancy prediction benchmark for autonomous driving","author":"Tian","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00772"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00772"},{"key":"ref47","article-title":"Llama2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01636"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16419"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00886"},{"key":"ref53","article-title":"Pangu-a: Large-scale autoregressive pretrained chinese language models with auto-parallel computation","author":"Zeng","year":"2021","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_4"},{"key":"ref56","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127665.pdf?arnumber=11127665","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:05:25Z","timestamp":1756879525000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127665\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127665","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}