{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:16:44Z","timestamp":1792786604019,"version":"4.5.0"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Army Research Lab"},{"name":"University of Washington Hyak program","id":[{"id":"https:\/\/ror.org\/00cvxb145","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1109\/lra.2026.3734870","type":"journal-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T19:15:20Z","timestamp":1789586120000},"page":"13055-13062","source":"Crossref","is-referenced-by-count":0,"title":["VAMOS: A Hierarchical Vision-Language-Action Model for Capability-Modulated and Steerable Navigation"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4335-2538","authenticated-orcid":false,"given":"Mateo Guaman","family":"Castro","sequence":"first","affiliation":[{"name":"University of Washington","place":["Seattle, WA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sidharth","family":"Rajagopal","sequence":"additional","affiliation":[{"name":"University of Washington","place":["Seattle, WA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Gorbatov","sequence":"additional","affiliation":[{"name":"University of Washington","place":["Seattle, WA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matt","family":"Schmittle","sequence":"additional","affiliation":[{"name":"University of Washington","place":["Seattle, WA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8516-229X","authenticated-orcid":false,"given":"Rohan","family":"Baijal","sequence":"additional","affiliation":[{"name":"University of Washington","place":["Seattle, WA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9241-1263","authenticated-orcid":false,"given":"Octi","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Washington","place":["Seattle, WA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rosario","family":"Scalise","sequence":"additional","affiliation":[{"name":"University of Washington","place":["Seattle, WA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2235-2958","authenticated-orcid":false,"given":"Sidharth","family":"Talia","sequence":"additional","affiliation":[{"name":"University of Washington","place":["Seattle, WA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emma","family":"Romig","sequence":"additional","affiliation":[{"name":"University of Washington","place":["Seattle, WA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Celso","family":"de Melo","sequence":"additional","affiliation":[{"name":"DEVCOM Army Research Laboratory","place":["Adelphi, MD, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Byron","family":"Boots","sequence":"additional","affiliation":[{"name":"University of Washington","place":["Seattle, WA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8447-9797","authenticated-orcid":false,"given":"Abhishek","family":"Gupta","sequence":"additional","affiliation":[{"name":"University of Washington","place":["Seattle, WA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610665"},{"key":"ref3","first-page":"711","article-title":"ViNT: A foundation model for visual navigation","volume-title":"Proc. Conf. Robot Learn.","author":"Shah","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20255"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.103"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abp9742"},{"key":"ref7","first-page":"619","article-title":"Semantic terrain classification for off-road autonomous driving","volume-title":"Proc. Conf. Robot Learn.","author":"Shaban","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342108"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160856"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-025-10202-x"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982190"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.001"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610025"},{"key":"ref14","first-page":"3185","article-title":"Long Range Navigator (LRN): Extending robot planning horizons beyond metric maps","volume-title":"Proc. Conf. Robot Learn.","author":"Schmittle","year":"2025"},{"key":"ref15","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. Conf. Robot Learn.","author":"Zitkovich","year":"2023"},{"key":"ref16","first-page":"24040","article-title":"HAMSTER: Hierarchical action models for open-world robot manipulation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li","year":"2025"},{"key":"ref17","first-page":"44918","article-title":"RT-Trajectory: Robotic task generalization via hindsight trajectory sketches","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161227"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2026.3726383"},{"key":"ref21","first-page":"4139","article-title":"TrackVLA: Embodied visual tracking in the wild","volume-title":"Proc. Conf. Robot Learn.","author":"Wang","year":"2025"},{"key":"ref22","article-title":"LOVON: Legged open-vocabulary object navigator","author":"Peng","year":"2025"},{"key":"ref23","first-page":"4005","article-title":"RoboPoint: A vision-language model for spatial affordance prediction in robotics","volume-title":"Proc. Conf. Robot Learn.","author":"Yuan","year":"2025"},{"key":"ref24","article-title":"PaliGemma 2: A family of versatile VLMs for transfer","author":"Steiner","year":"2024"},{"key":"ref25","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yuan","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.568"},{"key":"ref27","article-title":"LoRA without regret","year":"2025"},{"key":"ref28","first-page":"2679","article-title":"OpenVLA: An open-source vision-language-action model","volume-title":"Proc. Conf. Robot Learn.","author":"Kim","year":"2025"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3184025"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611265"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3400831"},{"key":"ref32","first-page":"2953","article-title":"Exploring models and data for image question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren","year":"2015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_38"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3270034"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11690866\/11692608.pdf?arnumber=11692608","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T05:52:18Z","timestamp":1791438738000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11692608\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":35,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3734870","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,11]]}}}