{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T16:00:47Z","timestamp":1782576047515,"version":"3.54.5"},"reference-count":39,"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\/iros60139.2025.11246147","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"16923-16930","source":"Crossref","is-referenced-by-count":3,"title":["SmartWay: Enhanced Waypoint Prediction and Backtracking for Zero-Shot Vision-and-Language Navigation"],"prefix":"10.1109","author":[{"given":"Xiangyu","family":"Shi","sequence":"first","affiliation":[{"name":"Australian Institute for Machine Learning at the University of Adelaide,Adelaide,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zerui","family":"Li","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning at the University of Adelaide,Adelaide,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenqi","family":"Lyu","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning at the University of Adelaide,Adelaide,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiatong","family":"Xia","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning at the University of Adelaide,Adelaide,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feras","family":"Dayoub","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning at the University of Adelaide,Adelaide,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanyuan","family":"Qiao","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning at the University of Adelaide,Adelaide,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Wu","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning at the University of Adelaide,Adelaide,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"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","article-title":"Bevbert: Topo-metric map pre-training for language-guided navigation","author":"An","year":"2023","journal-title":"ICCV"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01432"},{"key":"ref8","article-title":"Etpnav: Evolving topological planning for vision-language navigation in continuous environments","author":"An","year":"2023","journal-title":"CoRR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref11","article-title":"Dinov2: Learning robust visual features without supervision","volume":"2024","author":"Oquab","year":"2024","journal-title":"TMLR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611565"},{"key":"ref14","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023","journal-title":"CoRR"},{"key":"ref15","article-title":"Constraint-aware zero-shot vision-language navigation in continuous environments","author":"Chen","year":"2024","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127584"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3386695"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref19","article-title":"Vision-and-language navigation today and tomorrow: A survey in the era of foundation models","author":"Zhang","year":"2024","journal-title":"TMLR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref21","first-page":"394","article-title":"Vision-and-dialog navigation","author":"Thomason","year":"2020","journal-title":"CoRL"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127275"},{"key":"ref24","article-title":"Mo-vln: A multi-task benchmark for open-set zero-shot vision-and-language navigation","author":"Liang","year":"2023","journal-title":"CoRR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29858"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.079"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01444"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.60"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01293"},{"key":"ref30","article-title":"Mapgpt: Map-guided prompting for unified vision-and-language navigation","author":"Chen","year":"2024","journal-title":"ACL"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref32","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","volume":"34","author":"Chen","year":"2021","journal-title":"NeurIPS"},{"key":"ref33","article-title":"DD-PPO: Learning near-perfect pointgoal navigators from 2.5 billion frames","author":"Wijmans","year":"2020","journal-title":"ICLR"},{"key":"ref34","article-title":"Recognize anything: A strong image tagging model","author":"Zhang","year":"2023","journal-title":"ArXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref37","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"ICLR"},{"key":"ref38","first-page":"2737","article-title":"Bevbert: Multimodal map pre-training for language-guided navigation","author":"An","year":"2023","journal-title":"ICCV"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"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\/11246147.pdf?arnumber=11246147","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:09:57Z","timestamp":1765519797000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246147\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246147","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}