{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T05:50:09Z","timestamp":1776145809502,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000003","name":"Boeing Company","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100000003","id-type":"DOI","asserted-by":"crossref"}]},{"name":"ONR Science of Autonomy programunder","award":["N00014-23-1-2354"],"award-info":[{"award-number":["N00014-23-1-2354"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/lra.2026.3678454","type":"journal-article","created":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T19:52:45Z","timestamp":1774641165000},"page":"6480-6487","source":"Crossref","is-referenced-by-count":0,"title":["Flex: End-to-End Text-Instructed Visual Navigation From Foundation Model Features"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6807-7042","authenticated-orcid":false,"given":"Makram","family":"Chahine","sequence":"first","affiliation":[{"name":"Computer Science and Artificial Intelligence Laboratory CSAIL, Massachusetts Institute of Technology (MIT), Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alex","family":"Quach","sequence":"additional","affiliation":[{"name":"Computer Science and Artificial Intelligence Laboratory CSAIL, Massachusetts Institute of Technology (MIT), Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3800-9460","authenticated-orcid":false,"given":"Alaa","family":"Maalouf","sequence":"additional","affiliation":[{"name":"Computer Science and Artificial Intelligence Laboratory CSAIL, Massachusetts Institute of Technology (MIT), Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7259-5686","authenticated-orcid":false,"given":"Tsun-Hsuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Computer Science and Artificial Intelligence Laboratory CSAIL, Massachusetts Institute of Technology (MIT), Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5473-3566","authenticated-orcid":false,"given":"Daniela","family":"Rus","sequence":"additional","affiliation":[{"name":"Computer Science and Artificial Intelligence Laboratory CSAIL, Massachusetts Institute of Technology (MIT), Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3318070"},{"key":"ref2","article-title":"End to end learning for self-driving cars","author":"Bojarski","year":"2016"},{"key":"ref3","first-page":"305","article-title":"ALVINN: An autonomous land vehicle in a neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"1","author":"Pomerleau","year":"1988"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3249564"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adc8892"},{"key":"ref6","first-page":"1069","article-title":"Gaussian splatting to real world flight navigation transfer with liquid networks","volume-title":"Proc. 8th Conf. Robot Learn.","volume":"270","author":"Quach","year":"2024"},{"key":"ref7","first-page":"1099","article-title":"Learning stability attention in vision-based end-to-end driving policies","volume-title":"Proc. Learn. Dyn. Control Conf.","author":"Wang","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342229"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812276"},{"key":"ref12","article-title":"Drake: Model-based design and verification for robotics","author":"Tedrake","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/iros51168.2021.9635857"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67361-5_40"},{"key":"ref15","first-page":"1","article-title":"Driving policy transfer via modularity and abstraction","volume-title":"Proc. 2nd Conf. Robot Learn.","volume":"87","author":"Mller","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","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01857"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00371"},{"key":"ref23","article-title":"Language-driven semantic segmentation","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Li","year":"2022"},{"key":"ref24","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202","author":"Li","year":"2023"},{"key":"ref25","first-page":"2238","article-title":"GIT: A generative image-to-text transformer for vision and language","volume-title":"Proc. IEEE\/CVF Conf. Comp. Vis. Pattern Recognit.","author":"Wang","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10161534"},{"key":"ref27","first-page":"1","article-title":"Moka: Open-vocabulary robotic manipulation through mark-based visual prompting","volume-title":"Proc. Robotics: Sci. Syst. (RSS) 2024","author":"Liu","year":"2024"},{"key":"ref28","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"Proc. 6th Conf. Robot Learn.","volume":"205","author":"Ahn","year":"2022"},{"key":"ref29","first-page":"2165","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. 7th Conf. Robot Learn.","volume":"229","author":"Brohan","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3366013"},{"key":"ref31","first-page":"711","article-title":"ViNT: A foundation model for visual navigation","volume-title":"Proc. 7th Conf. Robot. Learn.","author":"Shah","year":"2023"},{"key":"ref32","article-title":"Audio visual language maps for robot navigation","volume-title":"Proc. 18th Int. Symp. Exp. Robot.","author":"Huang","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00677"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.066"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01084"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3122865"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811928"},{"key":"ref39","article-title":"Language conditioned traffic generation","volume-title":"Proc. 7th Annu. Conf. Robot Learn.","author":"Tan","year":"2023"},{"key":"ref40","first-page":"144","article-title":"Language-guided traffic simulation via scene-level diffusion","volume-title":"Proc. 7th Annu. Conf. Robot Learn.","volume":"229","author":"Zhong","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref42","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref43","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_6"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref46","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref47","first-page":"39","article-title":"Deep ViT features as dense visual descriptors","volume-title":"Proc. Comput. Vis. Workshops","author":"Amir","year":"2023"},{"key":"ref48","article-title":"Dont stop learning: Towards continual learning for the CLIP model","author":"Ding","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3366013"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611590"},{"key":"ref51","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1979.4766909"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11435997\/11457248.pdf?arnumber=11457248","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T05:04:35Z","timestamp":1776143075000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11457248\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":52,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3678454","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}