{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T14:18:41Z","timestamp":1784211521084,"version":"3.55.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610751","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T13:51:05Z","timestamp":1723125065000},"page":"7867-7873","source":"Crossref","is-referenced-by-count":18,"title":["Interactive Navigation in Environments with Traversable Obstacles Using Large Language and Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Zhen","family":"Zhang","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anran","family":"Lin","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Computer Science and Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun Wai","family":"Wong","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyu","family":"Chu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Dou","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Computer Science and Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"K. W.","family":"Samuel Au","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2967706"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9993397"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3187278"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574719000183"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696416"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"798","DOI":"10.1016\/j.proeng.2012.07.246","article-title":"Real-time hand gestures system for mobile robots control","volume":"41","author":"Kuzman Ali","year":"2012","journal-title":"Procedia Engineering"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968598"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3507471"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2893432"},{"key":"ref10","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Galactica: A large language model for science","author":"Taylor","year":"2022"},{"key":"ref12","article-title":"Training compute-optimal large language models","author":"Hoffmann","year":"2022"},{"key":"ref13","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","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":"ref15","article-title":"Vint: A foundation model for visual navigation","author":"Shah","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3193464"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref19","article-title":"a2nav: Action-aware zero-shot robot navigation by exploiting vision-and-language ability of foundation model","author":"Chen","year":"2023"},{"key":"ref20","article-title":"Pix2seq: A language modeling framework for object detection","author":"Chen","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref23","article-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection","author":"Liu","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2010.2049527"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980048"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6942636"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ECMR.2015.7324184"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7140063"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2016.7745154"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1968.300136"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511811685"},{"key":"ref32","article-title":"legged_control","author":"Liao","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389727"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487258"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CASE56687.2023.10260538"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610751.pdf?arnumber=10610751","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T04:36:51Z","timestamp":1769488611000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610751\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610751","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}