{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T20:15:01Z","timestamp":1784146501579,"version":"3.55.0"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611590","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"6687-6694","source":"Crossref","is-referenced-by-count":31,"title":["Drive Anywhere: Generalizable End-to-end Autonomous Driving with Multi-modal Foundation Models"],"prefix":"10.1109","author":[{"given":"Tsun-Hsuan","family":"Wang","sequence":"first","affiliation":[{"name":"MIT CSAIL"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alaa","family":"Maalouf","sequence":"additional","affiliation":[{"name":"MIT CSAIL"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Xiao","sequence":"additional","affiliation":[{"name":"MIT CSAIL"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yutong","family":"Ban","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Amini","sequence":"additional","affiliation":[{"name":"MIT CSAIL"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guy","family":"Rosman","sequence":"additional","affiliation":[{"name":"TRI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sertac","family":"Karaman","sequence":"additional","affiliation":[{"name":"MIT LIDS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniela","family":"Rus","sequence":"additional","affiliation":[{"name":"MIT CSAIL"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref2","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.066"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref5","article-title":"Alvinn: An autonomous land vehicle in a neural network","volume":"1","author":"Pomerleau","year":"1988","journal-title":"Advances in neural information processing systems"},{"key":"ref6","article-title":"End to end learning for self-driving cars","author":"Bojarski","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793579"},{"key":"ref8","first-page":"1099","article-title":"Learning stability attention in vision-based end-to-end driving policies","volume-title":"Learning for Dynamics and Control Conference","author":"Wang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3249564"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812276"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref12","article-title":"Drake: Model-based design and verification for robotics","author":"Tedrake","year":"2019"},{"key":"ref13","first-page":"1","article-title":"Carla: An open urban driving simulator","volume-title":"Conference on robot learning","author":"Dosovitskiy"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67361-5_40"},{"key":"ref15","article-title":"Driving policy transfer via modularity and abstraction","author":"M\u00fcller","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00718"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340641"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-101119-071628"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.703"},{"key":"ref20","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1055\/a-1858-6495"},{"key":"ref22","first-page":"31199","article-title":"Pre-trained language models for interactive decision-making","volume":"35","author":"Li","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160969"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00677"},{"key":"ref25","article-title":"Follow anything: Openset detection, tracking, and following in real-time","author":"Maalouf","year":"2023"},{"key":"ref26","article-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection","author":"Liu","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref28","article-title":"Language-driven semantic segmentation","author":"Li","year":"2022"},{"key":"ref29","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International Conference on Machine Learning","author":"Ramesh"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_6"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref32","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01084"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3122865"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811928"},{"key":"ref36","article-title":"Language conditioned traffic generation","author":"Tan","year":"2023"},{"key":"ref37","article-title":"Language-guided traffic simulation via scene-level diffusion","author":"Zhong","year":"2023"},{"key":"ref38","article-title":"Deep ViT features as dense visual descriptors","author":"Amir","year":"2021"},{"key":"ref39","article-title":"Don\u2019t stop learning: Towards continual learning for the clip model","author":"Ding","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref41","article-title":"Fast segment anything","author":"Zhao","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref43","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref45","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref46","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref48","first-page":"1","article-title":"Guided policy search","volume-title":"International conference on machine learning","author":"Levine"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029455"},{"key":"ref50","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299025"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611590.pdf?arnumber=10611590","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:08:27Z","timestamp":1723349307000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611590\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611590","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}