DC Field | Value | Language |
---|---|---|
dc.contributor.author | Seo, Younggyo | ko |
dc.contributor.author | Kim, Junsu | ko |
dc.contributor.author | James, Stephen | ko |
dc.contributor.author | Lee, Kimin | ko |
dc.contributor.author | Shin, Jinwoo | ko |
dc.contributor.author | Abbeel, Pieter | ko |
dc.date.accessioned | 2023-12-08T01:04:19Z | - |
dc.date.available | 2023-12-08T01:04:19Z | - |
dc.date.created | 2023-12-07 | - |
dc.date.issued | 2023-07-25 | - |
dc.identifier.citation | 40th International Conference on Machine Learning, ICML 2023 | - |
dc.identifier.uri | http://hdl.handle.net/10203/316035 | - |
dc.description.abstract | Visual robotic manipulation research and applications often use multiple cameras, or views, to better perceive the world. How else can we utilize the richness of multi-view data? In this paper, we investigate how to learn good representations with multi-view data and utilize them for visual robotic manipulation. Specifically, we train a multi-view masked autoencoder which reconstructs pixels of randomly masked viewpoints and then learn a world model operating on the representations from the autoencoder. We demonstrate the effectiveness of our method in a range of scenarios, including multi-view control and single-view control with auxiliary cameras for representation learning. We also show that the multi-view masked autoencoder trained with multiple randomized viewpoints enables training a policy with strong viewpoint randomization and transferring the policy to solve real-robot tasks without camera calibration and an adaptation procedure. Video demonstrations are available at: https://sites.google.com/view/mv-mwm. | - |
dc.language | English | - |
dc.publisher | International Machine Learning Society (IMLS) | - |
dc.title | Multi-View Masked World Models for Visual Robotic Manipulation | - |
dc.type | Conference | - |
dc.identifier.scopusid | 2-s2.0-85172440844 | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | 40th International Conference on Machine Learning, ICML 2023 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Honolulu, HI | - |
dc.contributor.localauthor | Lee, Kimin | - |
dc.contributor.localauthor | Shin, Jinwoo | - |
dc.contributor.nonIdAuthor | Seo, Younggyo | - |
dc.contributor.nonIdAuthor | James, Stephen | - |
dc.contributor.nonIdAuthor | Abbeel, Pieter | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.