{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:32:07Z","timestamp":1777865527844,"version":"3.51.4"},"reference-count":40,"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\/iccv51701.2025.00605","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"6416-6425","source":"Crossref","is-referenced-by-count":0,"title":["RoboTron-Nav: A Unified Framework for Embodied Navigation Integrating Perception, Planning, and Prediction"],"prefix":"10.1109","author":[{"given":"Yufeng","family":"Zhong","sequence":"first","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengjian","family":"Feng","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Yan","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fanfan","family":"Liu","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liming","family":"Zheng","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Ma","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Anderson","year":"2018","journal-title":"On evaluation of embodied navigation agents"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66823-5_24"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01445"},{"key":"ref4","first-page":"4283","article-title":"Semantic visual navigation by watching youtube videos","volume":"33","author":"Chang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume":"33","author":"Singh Chaplot","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00252"},{"key":"ref8","author":"Eftekhar","year":"2023","journal-title":"Selective visual representations improve convergence and generalization for embodied ai"},{"key":"ref9","author":"Eftekhar","year":"2024","journal-title":"The one ring: a robotic indoor navigation generalist"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01537"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.769"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731099"},{"key":"ref13","author":"Huang","year":"2024","journal-title":"Drivemm: All-in-one large multimodal model for autonomous driving"},{"key":"ref14","author":"Hurst","year":"2024","journal-title":"Gpt-4o system card"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01441"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref18","author":"Liu","year":"2024","journal-title":"Robouniview: Visual-language model with unified view representation for robotic manipulation"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680665"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793493"},{"key":"ref21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01716"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.089"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160473"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref26","first-page":"2881","article-title":"Situational fusion of visual representation for visual navigation","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"William","year":"2019"},{"key":"ref27","first-page":"34556","article-title":"Jump-start reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Uchendu","year":"2023"},{"key":"ref28","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00682"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612100"},{"key":"ref31","author":"Yan","year":"2024","journal-title":"Robomm: All-in-one multimodal large model for robotic manipulation"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802709"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00647"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.013"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01039"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01293"},{"key":"ref38","author":"Zheng","year":"2024","journal-title":"Robocas: A benchmark for robotic manipulation in complex object arrangement scenarios"},{"key":"ref39","author":"Zheng","year":"2025","journal-title":"Dataplatter: Boosting robotic manipulation generalization with minimal costly data"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981766"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444639.pdf?arnumber=11444639","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:46:19Z","timestamp":1777531579000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444639\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00605","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}