{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T15:42:22Z","timestamp":1775144542477,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127275","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"5266-5273","source":"Crossref","is-referenced-by-count":2,"title":["Ground-Level Viewpoint Vision-and-Language Navigation in Continuous Environments"],"prefix":"10.1109","author":[{"given":"Zerui","family":"Li","sequence":"first","affiliation":[{"name":"Australian Institute for Machine Learning, The University of Adelaide,Adelaide,Australia,5005"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gengze","family":"Zhou","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning, The University of Adelaide,Adelaide,Australia,5005"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haodong","family":"Hong","sequence":"additional","affiliation":[{"name":"The University of Queensland,Brisbane,Australia,4072"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanyan","family":"Shao","sequence":"additional","affiliation":[{"name":"Zhejiang University of Technology,Hangzhou,China,310014"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenqi","family":"Lyu","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning, The University of Adelaide,Adelaide,Australia,5005"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanyuan","family":"Qiao","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning, The University of Adelaide,Adelaide,Australia,5005"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Wu","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning, The University of Adelaide,Adelaide,Australia,5005"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01500"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01103"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561806"},{"key":"ref8","article-title":"Bevbert: Topo-metric map pre-training for language-guided navigation","author":"An","year":"2022","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.079"},{"key":"ref10","article-title":"Sim-to-real transfer via 3d feature fields for vision-and-language navigation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Human-aware vision-andlanguage navigation: Bridging simulation to reality with dynamic human interactions","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610712"},{"key":"ref13","article-title":"Vision-and-language navigation today and tomorrow: A survey in the era of foundation models","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01432"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3386695"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref17","first-page":"394","article-title":"Vision-and-dialog navigation","volume-title":"Conference on Robot Learning","author":"Thomason"},{"key":"ref18","article-title":"Speakerfollower models for vision-and-language navigation","volume":"31","author":"Fried","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","author":"Ma","year":"2019","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00690"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_5"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_18"},{"key":"ref25","article-title":"Language and visual entity relationship graph for agent navigation","volume":"33","author":"Hong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1159"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_16"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956561"},{"key":"ref33","article-title":"Language-aligned waypoint (law) supervision for vision-andlanguage navigation in continuous environments","author":"Raychaudhuri","year":"2021","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01488"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3386695"},{"key":"ref37","article-title":"Habitat-matterport 3d dataset (hm3d): 1000 large-scale 3d environments for embodied ai","author":"Ramakrishnan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref41","first-page":"2737","article-title":"Bevbert: Multimodal map pre-training for language-guided navigation","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"An"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127275.pdf?arnumber=11127275","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:27:58Z","timestamp":1756880878000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127275\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127275","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}