{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T16:00:52Z","timestamp":1782576052363,"version":"3.54.5"},"reference-count":47,"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\/icra55743.2025.11127584","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"6710-6717","source":"Crossref","is-referenced-by-count":10,"title":["Open-Nav: Exploring Zero-Shot Vision-and-Language Navigation in Continuous Environment with Open-Source LLMs"],"prefix":"10.1109","author":[{"given":"Yanyuan","family":"Qiao","sequence":"first","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":"Hui","family":"Wang","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning at the University of Adelaide,Adelaide,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology,Guangzhou,China"}],"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":"Yuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning at the University of Adelaide,Adelaide,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingkui","family":"Tan","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology,Guangzhou,China"}],"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\/ICCV48922.2021.01488"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00689"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01103"},{"key":"ref9","first-page":"1634","article-title":"Airbert: Indomain pretraining for vision-and-language navigation","volume-title":"in Int. Conf. Comput. Vis.","author":"Guhur","year":"2021"},{"key":"ref10","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","author":"Chen","year":"2021","journal-title":"in Adv. Neural Inform. Process. Syst."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01293"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.079"},{"key":"ref13","article-title":"Do as i can and not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611565"},{"key":"ref16","article-title":"Instructblip: Towards generalpurpose vision-language models with instruction tuning","volume":"abs\/2305.06500","author":"Dai","year":"2023","journal-title":"ArXiv"},{"key":"ref17","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2022","journal-title":"in Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01500"},{"key":"ref19","article-title":"Spatialbot: Precise spatial understanding with vision language models","volume":"abs\/2406.13642","author":"Cai","year":"2024","journal-title":"ArXiv"},{"key":"ref20","article-title":"Recognize anything: A strong image tagging model","volume":"abs\/2306.03514","author":"Zhang","year":"2023","journal-title":"ArXiv"},{"key":"ref21","article-title":"Clip-nav: Using clip for zero-shot vision-and-language navigation","volume":"abs\/2211.16649","author":"Dorbala","year":"2022","journal-title":"ArXiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_18"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475282"},{"key":"ref25","article-title":"Language and visual entity relationship graph for agent navigation","author":"Hong","year":"2020","journal-title":"in Adv. Neural Inform. Process. Syst."},{"key":"ref26","first-page":"3318","article-title":"Speakerfollower models for vision-and-language navigation","author":"Fried","year":"2018","journal-title":"in Adv. Neural Inform. Process. Syst."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00254"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00750"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_16"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234243"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref34","article-title":"Etpnav: Evolving topological planning for vision-language navigation in continuous environments","author":"An","year":"2023","journal-title":"IEEE Transactions on pattern analysis and machine intelligence"},{"key":"ref35","first-page":"2737","article-title":"Bevbert: Multimodal map pre-training for language-guided navigation","volume-title":"in Int. Conf. Comput. Vis.","author":"An","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01432"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00280"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01444"},{"key":"ref39","article-title":"A2 nav: Action-aware zero-shot robot navigation by exploiting vision-and-language ability of foundation models","volume":"abs\/2308.07997","author":"Chen","year":"2023","journal-title":"CoRR"},{"key":"ref40","article-title":"Mc-gpt: Empowering vision-andlanguage navigation with memory map and reasoning chains","author":"Zhan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Instructnav: Zero-shot system for generic instruction navigation in unexplored environment","author":"Long","year":"2024","journal-title":"ArXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref43","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"in Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref46","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","author":"Banerjee","year":"2005","journal-title":"IEEvaluation@ACL"},{"key":"ref47","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"in Annual Meeting of the Association for Computational Linguistics","author":"Lin","year":"2004"}],"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\/11127584.pdf?arnumber=11127584","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:17:50Z","timestamp":1756880270000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127584\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127584","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}