{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T15:43:16Z","timestamp":1779291796641,"version":"3.51.4"},"reference-count":54,"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\/icra55743.2025.11128264","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"2391-2398","source":"Crossref","is-referenced-by-count":2,"title":["VLM-GroNav: Robot Navigation Using Physically Grounded Vision-Language Models in Outdoor Environments"],"prefix":"10.1109","author":[{"given":"Mohamed","family":"Elnoor","sequence":"first","affiliation":[{"name":"University of Maryland,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kasun","family":"Weerakoon","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gershom","family":"Seneviratne","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiqi","family":"Xian","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianrui","family":"Guan","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed Khalid","family":"M Jaffar","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vignesh","family":"Rajagopal","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dinesh","family":"Manocha","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/app13179877"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3455788"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801962"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3187278"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3320016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TFR.2024.3464369"},{"key":"ref7","first-page":"403","article-title":"Legged locomotion in challenging terrains using egocentric vision","volume-title":"Conference on robot learning","author":"Agarwal"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/robotics12030086"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jterra.2020.12.001"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801833"},{"key":"ref11","author":"Dingkun Guo","year":"2024","journal-title":"Phygrasp: Generalizing robotic grasping with physics-informed large multimodal models"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610090"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01676"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611475"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3418270"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60337-3_2"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2021.103760"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw53098.2021.00121"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/rs13245094"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00633"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/app132212462"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124926"},{"key":"ref23","article-title":"Semantic abstraction: Open-world 3d scene understanding from 2d vision-language models","author":"Ha","year":"2022","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611218"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610712"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.3003230"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1002\/adfm.202306249"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.066"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2024.emnlp-main.64","volume-title":"A survey on in-context learning","author":"Dong","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/100.580977"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/01423312211062972"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610673"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3304992"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812238"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561291"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.55417\/fr.2023013"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/PHM-Jinan48558.2020.00012"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3015976"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2020.107693"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SITIS.2013.118"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3390\/aerospace11070598"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610665"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/SII58957.2024.10417171"},{"key":"ref44","article-title":"Lancar: Leveraging language for context-aware robot locomotion in unstructured environments","author":"Shek","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref47","first-page":"287","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"Conference on robot learning","author":"Brohan"},{"key":"ref48","first-page":"492","article-title":"Lm-nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Conference on robot learning","author":"Shah"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref50","article-title":"ViNT: A foundation model for visual navigation","volume-title":"7th Annual Conference on Robot Learning","author":"Shah"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802716"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981942"},{"key":"ref53","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3390\/s23198045"}],"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\/11128264.pdf?arnumber=11128264","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:07:15Z","timestamp":1756879635000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128264\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128264","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}