{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:40:15Z","timestamp":1777657215937,"version":"3.51.4"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006751","name":"U.S. Army","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006751","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10802716","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"13837-13844","source":"Crossref","is-referenced-by-count":13,"title":["CoNVOI: Context-aware Navigation using Vision Language Models in Outdoor and Indoor Environments"],"prefix":"10.1109","author":[{"given":"Adarsh Jagan","family":"Sathyamoorthy","sequence":"first","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kasun","family":"Weerakoon","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed","family":"Elnoor","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anuj","family":"Zore","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"Ichter","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Xia","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Tan","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhao","family":"Yu","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dinesh","family":"Manocha","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","year":"2023"},{"key":"ref2","article-title":"Gemini: A Family of Highly Capable Multimodal Models","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3187278"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/100.580977"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.51.4282"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2996593"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759200"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3135560"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696579"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630610"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3144491"},{"key":"ref13","first-page":"619","article-title":"Semantic terrain classification for off-road autonomous driving","volume-title":"Conference on Robot Learning","author":"Shaban"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981942"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/icra46639.2022.9811644"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342393"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241281508"},{"key":"ref18","article-title":"Language Models are Few-Shot Learners","author":"Brown","year":"2020"},{"key":"ref19","article-title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","author":"AI","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref21","article-title":"Visual Instruction Tuning","author":"Liu","year":"2023"},{"key":"ref22","article-title":"Learning Transferable Visual Models From Natural Language Supervision","author":"Radford","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.074"},{"key":"ref24","article-title":"Semantic abstraction: Open-world 3d scene understanding from 2d vision-language models","volume-title":"6th Annual Conference on Robot Learning","author":"Ha"},{"key":"ref25","article-title":"PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs","author":"Nasiriany","year":"2024"},{"key":"ref26","article-title":"CLIP-nav: Using CLIP for zero-shot vision-andlanguage navigation","volume-title":"Workshop on Language and Robotics at CoRL 2022","author":"Dorbala"},{"key":"ref27","article-title":"LM-nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"6th Annual Conference on Robot Learning","author":"Shah"},{"key":"ref28","article-title":"Okrobot: What really matters in integrating open-knowledge models for robotics","author":"Liu","year":"2024"},{"key":"ref29","article-title":"Do as i can and not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022"},{"key":"ref30","article-title":"A survey on evaluation of large language models","author":"Chang","year":"2023","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460968"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2013.05.007"},{"key":"ref34","article-title":"Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning","author":"Long","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759329"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206092"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2895390"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/3938502"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/SII.2014.7028109"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20276"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20279"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161403"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref44","article-title":"Navigation with large language models: Semantic guesswork as a heuristic for planning","volume-title":"7th Annual Conference on Robot Learning","author":"Shah"},{"key":"ref45","article-title":"A2Nav: Action-Aware Zero-Shot Robot Navigation by Exploiting Vision-and-Language Ability of Foundation Models","author":"Chen","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/SII58957.2024.10417171"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00566"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1142\/S0218195995000064"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,10,14]]},"end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10802716.pdf?arnumber=10802716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:02:00Z","timestamp":1735196520000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802716\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802716","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}