{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T06:48:38Z","timestamp":1769928518114,"version":"3.49.0"},"reference-count":41,"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\/icra57147.2024.10611210","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"10874-10880","source":"Crossref","is-referenced-by-count":6,"title":["ForceSight: Text-Guided Mobile Manipulation with Visual-Force Goals"],"prefix":"10.1109","author":[{"given":"Jeremy A.","family":"Collins","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology (GT),Institute for Robotics and Intelligent Machines"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cody","family":"Houff","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology (GT),Institute for Robotics and Intelligent Machines"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"You Liang","family":"Tan","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology (GT),Institute for Robotics and Intelligent Machines"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Charles C.","family":"Kemp","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology (GT),Institute for Robotics and Intelligent Machines"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918802346"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref3","first-page":"894","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"conference on Robot Learning","author":"Shridhar"},{"key":"ref4","first-page":"785","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"key":"ref5","first-page":"991","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","volume-title":"conference on Robot Learning","author":"Jang"},{"key":"ref6","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.026"},{"key":"ref9","article-title":"Vip: Towards universal visual reward and representation via value-implicit pre-training","author":"Ma","year":"2023"},{"key":"ref10","article-title":"R3m: A universal visual representation for robot manipulation","author":"Nair","year":"2022"},{"key":"ref11","article-title":"Mimicplay: Long-horizon imitation learning by watching human play","author":"Wang","year":"2023"},{"key":"ref12","first-page":"651","article-title":"Dexvip: Learning dexterous grasping with human hand pose priors from video","volume-title":"conference on Robot Learning","author":"Mandikal"},{"key":"ref13","article-title":"Unsupervised learning of object key-points for perception and control","volume":"32","author":"Kulkarni","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-95459-8_9"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01337"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981982"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560942"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-013-9344-1"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2006.10.005"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0119794"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/027836490302210010"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/NIR52917.2021.9666138"},{"key":"ref23","article-title":"Cfvs: Coarse-to-fine visual servoing for 6-dof object-agnostic peg-in-hole assembly","author":"Lu","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/70.538972"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811922"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1985.1087242"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/027836498400300101"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917712421"},{"key":"ref29","article-title":"Intel\u00ae Realsense\u2122 D405 \u2013 intelrealsense.com"},{"key":"ref30","volume-title":"F\/T Sensor: mini45","year":"2022"},{"key":"ref31","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"issue":"1","key":"ref32","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref33","article-title":"Imagenet-21k pretraining for the masses","author":"Ridnik","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341422"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10131-7"},{"key":"ref37","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":"ref38","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022"},{"key":"ref39","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref40","article-title":"Inner monologue: Embodied reasoning through planning with language models","author":"Huang","year":"2022"},{"key":"ref41","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"}],"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\/10611210.pdf?arnumber=10611210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:15:19Z","timestamp":1723349719000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611210\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611210","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}