{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:06:44Z","timestamp":1791911204693,"version":"4.3.4"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Science Foundation Graduate Research Fellowship","award":["DGE 2236417"],"award-info":[{"award-number":["DGE 2236417"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/lra.2023.3346800","type":"journal-article","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T20:23:13Z","timestamp":1703535793000},"page":"4083-4090","source":"Crossref","is-referenced-by-count":91,"title":["<i>Can an Embodied Agent Find Your \u201cCat-shaped Mug\u201d?<\/i> LLM-Based Zero-Shot Object Navigation"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5697-5219","authenticated-orcid":false,"given":"Vishnu Sashank","family":"Dorbala","sequence":"first","affiliation":[{"name":"University of Maryland, College Park, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4117-1741","authenticated-orcid":false,"given":"James F.","family":"Mullen","sequence":"additional","affiliation":[{"name":"University of Maryland, College Park, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7047-9801","authenticated-orcid":false,"given":"Dinesh","family":"Manocha","sequence":"additional","affiliation":[{"name":"University of Maryland, College Park, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02219"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01832"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref6","article-title":"ObjectNav revisited: On evaluation of embodied agents navigating to objects","author":"Batra","year":"2020"},{"key":"ref7","first-page":"32340","article-title":"ZSON: Zero-shot object-goal navigation using multimodal goal embeddings","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Majumdar","year":"2022"},{"key":"ref8","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chaplot","year":"2020"},{"key":"ref9","article-title":"Object goal navigation with end-to-end self-supervision","author":"Min","year":"2022"},{"key":"ref10","article-title":"Clip on wheels: Zero-shot object navigation as object localization and exploration","author":"Gadre","year":"2022"},{"key":"ref11","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref13","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref14","article-title":"ClipCap: Clip prefix for image captioning","author":"Mokady","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324920000601"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00323"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460699"},{"key":"ref19","article-title":"Large language models are human-level prompt engineers","author":"Zhou","year":"2022"},{"key":"ref20","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref21","first-page":"1507","article-title":"Understanding natural language commands for robotic navigation and mobile manipulation","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"25","author":"Tellex","year":"2011"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794394"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2893432"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561983"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2010.5453186"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2019.8794287"},{"key":"ref27","first-page":"394","article-title":"Vision-and-dialog navigation","volume-title":"Proc. Conf. Robot Learn.","author":"Thomason","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3193254"},{"key":"ref29","article-title":"Clip-NAV: Using clip for zero-shot vision-and-language navigation","volume-title":"Proc. Workshop Lang. Robot.","author":"Dorbala","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CIRA.1997.613851"},{"key":"ref31","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang","year":"2022"},{"key":"ref32","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","author":"Ahn","year":"2022"},{"key":"ref33","article-title":"Inner monologue: Embodied reasoning through planning with language models","author":"Huang","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10133-5"},{"key":"ref35","article-title":"Large language models as commonsense knowledge for large-scale task planning","author":"Zhao","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref37","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21831"},{"key":"ref39","article-title":"ROS: An open-source robot operating system","volume-title":"Proc. ICRA Workshop Open Source Softw.","volume":"3","author":"Quigley","year":"2009"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref41","first-page":"33781","article-title":"Bridging the gap between object and image-level representations for open-vocabulary detection","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Bangalath","year":"2022"},{"key":"ref42","article-title":"Detectron 2","author":"Wu","year":"2019"},{"key":"ref43","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7083369\/10474437\/10373065-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10474437\/10373065.pdf?arnumber=10373065","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:29:38Z","timestamp":1734982178000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10373065\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":43,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3346800","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}