{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T04:41:37Z","timestamp":1783226497274,"version":"3.54.6"},"reference-count":56,"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"}],"funder":[{"DOI":"10.13039\/100016364","name":"Amazon Robotics","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016364","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610178","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"3296-3303","source":"Crossref","is-referenced-by-count":21,"title":["Think, Act, and Ask: Open-World Interactive Personalized Robot Navigation"],"prefix":"10.1109","author":[{"given":"Yinpei","family":"Dai","sequence":"first","affiliation":[{"name":"University of Michigan,Computer Science and Engineering Division"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Run","family":"Peng","sequence":"additional","affiliation":[{"name":"University of Michigan,Computer Science and Engineering Division"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sikai","family":"Li","sequence":"additional","affiliation":[{"name":"University of Michigan,Computer Science and Engineering Division"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joyce","family":"Chai","sequence":"additional","affiliation":[{"name":"University of Michigan,Computer Science and Engineering Division"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"32340","article-title":"Zson: Zero-shot object-goal navigation using multi-modal goal embeddings","volume":"35","author":"Majumdar","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","article-title":"Esc: Exploration with soft commonsense constraints for zero-shot object navigation","author":"Zhou","year":"2023"},{"issue":"4","key":"ref3","first-page":"7","article-title":"Clip on wheels: Zero-shot object navigation as object localization and exploration","volume":"3","author":"Gadre","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02219"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161534"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref7","volume-title":"Habitat challenge 2022","author":"Yadav"},{"key":"ref8","volume-title":"Habitat challenge 2023","author":"Yadav"},{"key":"ref9","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":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.074"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21320"},{"key":"ref13","article-title":"Space-2: Tree-structured semi-supervised contrastive pre-training for task-oriented dialog understanding","author":"He","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532069"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531920"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907844"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v32i4.2381"},{"key":"ref18","article-title":"Learning to interpret natural language commands through human-robot dialog","volume-title":"Proceedings of the 24th International Joint Conference on Artificial Intelligence","author":"Thomason"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610443"},{"key":"ref20","article-title":"Inner monologue: Embodied reasoning through planning with language models","author":"Huang","year":"2022"},{"key":"ref21","first-page":"20","article-title":"Chatgpt for robotics: Design principles and model abilities","volume":"2","author":"Vemprala","year":"2023","journal-title":"Microsoft Auton. Syst. Robot. Res"},{"key":"ref22","article-title":"Robots that ask for help: Uncertainty alignment for large language model planners","author":"Ren","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1150"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4313"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v37i4.2684"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.065"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3568162.3578623"},{"key":"ref28","first-page":"394","article-title":"Vision-and-dialog navigation","volume-title":"Conference on Robot Learning","author":"Thomason"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/1"},{"key":"ref30","first-page":"16553","article-title":"A framework for learning to request rich and contextually useful information from humans","volume-title":"International Conference on Machine Learning","author":"Nguyen"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.57"},{"key":"ref32","first-page":"33","article-title":"Collaborative effort towards common ground in situated human-robot dialogue","volume-title":"Proceedings of the 2014 ACM\/IEEE international conference on Human-robot interaction","author":"Chai"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2004.1374720"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aat7451"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/robotics10040120"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN53752.2022.9900554"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341370"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2003.1251796"},{"key":"ref39","first-page":"319","article-title":"Personalization in hri: A longitudinal field experiment","volume-title":"Proceedings of the seventh annual ACM\/IEEE international conference on Human-Robot Interaction","author":"Lee"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2157689.2157693"},{"key":"ref41","article-title":"Personalized dialogue generation with diversified traits","author":"Zheng","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3213586.3226198"},{"key":"ref43","article-title":"Towards generalized models for beyond domain api task-oriented dialogue","volume-title":"AAAI-21 DSTC9 Workshop","author":"Mi"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016794"},{"key":"ref45","article-title":"Language-driven semantic segmentation","volume-title":"International Conference on Learning Representations","author":"Li"},{"key":"ref46","article-title":"Openclip","volume-title":"Zenodo","author":"Ilharco","year":"2021"},{"key":"ref47","article-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection","author":"Liu","year":"2023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CIRA.1997.613851"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref51","article-title":"Habitat-matterport 3d dataset (hm3d): 1000 large-scale 3d environments for embodied ai","author":"Ramakrishnan","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.93.4.1591"},{"key":"ref53","first-page":"116","article-title":"Parameter estimation for agenda-based user simulation","volume-title":"Proceedings of the SIGDIAL 2010 Conference","author":"Keizer"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5007"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.13"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2006.889486"}],"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\/10610178.pdf?arnumber=10610178","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:45:19Z","timestamp":1723268719000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610178\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610178","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}