WEKO3
アイテム
Data-efficient Skill Transfer for Robotics using Virtual Reality and Imitation Learning
http://hdl.handle.net/10061/13306
http://hdl.handle.net/10061/13306d7e6d924-7355-4ec2-85e9-26f388019453
| Item type | ビデオ / Others(1) | |||||
|---|---|---|---|---|---|---|
| 公開日 | 2019-07-03 | |||||
| タイトル | ||||||
| タイトル | Data-efficient Skill Transfer for Robotics using Virtual Reality and Imitation Learning | |||||
| 言語 | ||||||
| 言語 | eng | |||||
| 資源タイプ | ||||||
| 資源タイプ | video | |||||
| アクセス権 | ||||||
| アクセス権 | metadata only access | |||||
| 著者 |
Koganti, Nishanth
× Koganti, Nishanth |
|||||
| 抄録 | ||||||
| 内容記述タイプ | Abstract | |||||
| 内容記述 | Learning from Demonstration (LfD) is a paradigm where humans demonstrate the procedure to perform complex tasks which can be used to train autonomous agents. However, the performance of LfD is highly sensitive to the quality of demonstrations which in turn depends on the user-interface. In this presentation, we propose the use of Virtual Reality (VR) to develop an intuitive interface that enables users to provide good demonstrations. We apply this approach to the task of training a visual attention system which is a crucial component for tasks such as autonomous driving and human-robot interaction. We show that interaction time of few minutes is sufficient to train a deep neural network to successfully learn attention strategies. | |||||
| 内容記述 | ||||||
| 内容記述タイプ | Other | |||||
| 内容記述 | 講演者所属: Mathmatical Informatics Lab 講演場所: 情報科学棟大講義室L1 | |||||
| 書誌情報 |
発行日 2018-07-18 |
|||||
| フォーマット | ||||||
| 内容記述タイプ | Other | |||||
| 内容記述 | video/mp4 | |||||
| 出版者 | ||||||
| 出版者 | Nara Institute of Science and Technology | |||||
| 著者版フラグ | ||||||
| 出版タイプ | VoR | |||||
| 部分である | ||||||
| 関連タイプ | isPartOf | |||||
| 関連名称 | 情報科学領域・コロキアム ; 平成30年度 | |||||
| 本文URL | ||||||
| NAIST Digital Library | ||||||
| https://library.naist.jp/opac/book/87855 | ||||||
| 電子化ID | ||||||
| M015592 | ||||||
