{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T09:25:53Z","timestamp":1725701153674},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,12]],"date-time":"2023-12-12T00:00:00Z","timestamp":1702339200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,12]],"date-time":"2023-12-12T00:00:00Z","timestamp":1702339200000},"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":[[2023,12,12]]},"DOI":"10.1109\/humanoids57100.2023.10375239","type":"proceedings-article","created":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T19:32:51Z","timestamp":1704137571000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Daily Assistive View Control Learning of Low-Cost Low-Rigidity Robot via Large-Scale Vision-Language Model"],"prefix":"10.1109","author":[{"given":"Kento","family":"Kawaharazuka","sequence":"first","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano-Informatics,Tokyo,Japan,113\u20138656"}]},{"given":"Naoaki","family":"Kanazawa","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano-Informatics,Tokyo,Japan,113\u20138656"}]},{"given":"Yoshiki","family":"Obinata","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano-Informatics,Tokyo,Japan,113\u20138656"}]},{"given":"Kei","family":"Okada","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano-Informatics,Tokyo,Japan,113\u20138656"}]},{"given":"Masayuki","family":"Inaba","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano-Informatics,Tokyo,Japan,113\u20138656"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA.2005.1626828"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2017.10.012"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/1729881419857432"},{"article-title":"Semantic Object Search in Large-scale Indoor Environments","volume-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems, Workshop on Active Semantic Perception and Object Search in the Real World","author":"Saito","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1985.1087372"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487281"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3039732"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2014.2303083"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref10","article-title":"Visual Language Maps for Robot Navigation","author":"Huang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460699"},{"key":"ref12","first-page":"1","article-title":"CLIPort: What and Where Pathways for Robotic Manipulation","volume-title":"Proceedings of the 2021 Conference on Robot Learning","author":"Shridhar"},{"key":"ref13","article-title":"Do As I Can and Not As I Say: Grounding Language in Robotic Affordances","author":"Ahn","year":"2022","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Vision-Language Intelligence: Tasks, Representation Learning, and Large Models","author":"Li","year":"2022","journal-title":"arXiv preprint"},{"article-title":"Robotic Applications of Pre-Trained Vision-Language Models to Various Recognition Behaviors (in press)","volume-title":"Proceedings of the 2023 IEEE-RAS International Conference on Humanoid Robots, 2023","author":"Kawaharazuka","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160390"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2002.1005521"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636416"},{"key":"ref19","article-title":"Learning Transferable Visual Models From Natural Language Supervision","author":"Radford","year":"2021","journal-title":"arXiv preprint"},{"key":"ref20","first-page":"1","article-title":"Adam: A Method for Stochastic Optimization","volume-title":"Proceedings of the 3rd International Conference on Learning Representations","author":"Kingma"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2013.2258019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00116-6"}],"event":{"name":"2023 IEEE-RAS 22nd International Conference on Humanoid Robots (Humanoids)","start":{"date-parts":[[2023,12,12]]},"location":"Austin, TX, USA","end":{"date-parts":[[2023,12,14]]}},"container-title":["2023 IEEE-RAS 22nd International Conference on Humanoid Robots (Humanoids)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10375141\/10374561\/10375239.pdf?arnumber=10375239","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T00:24:27Z","timestamp":1705105467000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10375239\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,12]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/humanoids57100.2023.10375239","relation":{},"subject":[],"published":{"date-parts":[[2023,12,12]]}}}