Data-efficient Skill Transfer for Robotics using Virtual Reality and Imitation Learning

Data-efficient Skill Transfer for Robotics using Virtual Reality and Imitation Learning

目次あり

Nishanth Koganti

生駒 : 奈良先端科学技術大学院大学, 2018.7

授業アーカイブ

巻号情報

全1件
No. 刷年 所在 請求記号 資料ID 貸出区分 状況 予約人数

1

  • LA-I-R[MPDASH][Mobile]

M015592

内容紹介

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.

詳細情報

刊年

2018

形態

電子化映像資料(31分48秒)

シリーズ名

情報科学領域・コロキアム ; 平成30年度

注記

講演者所属: Mathmatical Informatics Lab

講演日: 平成30年7月18日

講演場所: 情報科学棟大講義室L1

標題言語

英語 (eng)

本文言語

英語 (eng)

著者情報

Koganti, Nishanth