{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:21:30Z","timestamp":1765520490849,"version":"3.48.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247702","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"17207-17214","source":"Crossref","is-referenced-by-count":0,"title":["VecNav: Vector Goal Robot Navigation from In-the-wild Videos"],"prefix":"10.1109","author":[{"given":"Ruixiang","family":"Cao","sequence":"first","affiliation":[{"name":"Kyoto University,Learning Machines Group, Graduate School of Informatics,Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoshi","family":"Yagi","sequence":"additional","affiliation":[{"name":"Kyoto University,Learning Machines Group, Graduate School of Informatics,Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoshi","family":"Yamamori","sequence":"additional","affiliation":[{"name":"ATR,Computational Neuroscience Labs,Department of Brain Robot Interface,Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Morimoto","sequence":"additional","affiliation":[{"name":"Kyoto University,Learning Machines Group, Graduate School of Informatics,Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"ViNT: A foundation model for visual navigation","volume-title":"7th Annual Conference on Robot Learning","author":"Shah","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"article-title":"Foundation models in robotics: Applications, challenges, and the future","year":"2023","author":"Firoozi","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref6","first-page":"674","article-title":"Rapid exploration for open-world navigation with latent goal models","volume-title":"Conference on Robot Learning","volume":"164","author":"Shah"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811648"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.012"},{"article-title":"Nomad: Goal masked diffusion policies for navigation and exploration","year":"2023","author":"Sridhar","key":"ref9"},{"article-title":"Gpt-4 technical report","year":"2023","author":"Achiam","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"article-title":"Giving robots a hand: Learning generalizable manipulation with eye-in-hand human video demonstrations","year":"2023","author":"Kim","key":"ref12"},{"article-title":"Mimicplay: Long-horizon imitation learning by watching human play","year":"2023","author":"Wang","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2022.XVIII.019","article-title":"Viking: Vision-based kilometer-scale navigation with geographic hints","author":"Shah","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2463671"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2705103"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3075644"},{"key":"ref20","first-page":"16 558","article-title":"Droid-slam: Deep visual slam for monocular, stereo, and rgb-d cameras","volume":"34","author":"Teed","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00318"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-6168-2_10"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247702.pdf?arnumber=11247702","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:18:10Z","timestamp":1765520290000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247702\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247702","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}