{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:37:51Z","timestamp":1757608671375,"version":"3.44.0"},"reference-count":30,"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\/icra55743.2025.11127651","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"8752-8758","source":"Crossref","is-referenced-by-count":0,"title":["Uncertainty-Guided Enhancement on Driving Perception System Via Foundation Models"],"prefix":"10.1109","author":[{"given":"Yunhao","family":"Yang","sequence":"first","affiliation":[{"name":"University of Texas at Austin,Austin,TX,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxin","family":"Hu","sequence":"additional","affiliation":[{"name":"Cruise,San Francisco,CA,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mao","family":"Ye","sequence":"additional","affiliation":[{"name":"Cruise,San Francisco,CA,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zaiwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Cruise,San Francisco,CA,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhichao","family":"Lu","sequence":"additional","affiliation":[{"name":"Cruise,San Francisco,CA,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Xu","sequence":"additional","affiliation":[{"name":"Northeastern University,Boston,MA,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ufuk","family":"Topcu","sequence":"additional","affiliation":[{"name":"University of Texas at Austin,Austin,TX,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ben","family":"Snyder","sequence":"additional","affiliation":[{"name":"Cruise,San Francisco,CA,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"2023","journal-title":"OpenAI","article-title":"Gpt-4 technical report","key":"ref1"},{"key":"ref2","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"year":"2021","author":"Yuan","journal-title":"Florence: A new foundation model for computer vision","key":"ref4"},{"year":"2023","author":"Zohar","journal-title":"Open world object detection in the era of foundation models","key":"ref5"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/JPROC.2023.3238524"},{"key":"ref7","article-title":"Motiongpt: Human motion as a foreign language","volume":"36","author":"Jiang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/IV55156.2024.10588694"},{"key":"ref9","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/CVPR52688.2022.00293"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1007\/978-3-031-19833-5_7"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.18653\/v1\/2021.findings-acl.370"},{"year":"2024","author":"Yan","journal-title":"Forging vision foundation models for autonomous driving: Challenges, methodologies, and opportunities","key":"ref13"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1117\/12.3054764"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/CVPR52729.2023.01712"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICCV51070.2023.00766"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1007\/978-3-031-19839-7_31"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1007\/978-3-031-73650-6_6"},{"key":"ref19","article-title":"Gpt-driver: Learning to drive with gpt","author":"Mao","year":"2023","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1016\/j.commtr.2023.100116"},{"key":"ref21","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 preprint"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/ICCV51070.2023.00790"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/IV55156.2024.10588373"},{"year":"2024","author":"Wang","journal-title":"Omnidrive: A holistic llm-agent framework for autonomous driving with 3d perception, reasoning and planning","key":"ref24"},{"volume-title":"Proceedings of the Seventh Annual Conference on Machine Learning and Systems","author":"Yang","article-title":"Fine-tuning language models using formal methods feedback: A use case in autonomous systems","key":"ref25"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/iv55156.2024.10588851"},{"key":"ref27","article-title":"Pre-trained transformer-enabled strategies with human-guided fine-tuning for end-to-end navigation of autonomous vehicles","author":"Hu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Vision-language foundation models as effective robot imitators","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"issue":"3","key":"ref29","article-title":"A tutorial on conformal prediction","volume":"9","author":"Shafer","year":"2008","journal-title":"Journal of Machine Learning Research"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/CVPR42600.2020.01164"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","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\/11127651.pdf?arnumber=11127651","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:11:38Z","timestamp":1756879898000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127651\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127651","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}