Acquisition of viewpoint representation in imitative learning from own sensory-motor experiences

Ryoichi Nakajo, Shingo Murata, Hiroaki Arie, Tetsuya Ogata

研究成果: Conference contribution

7 被引用数 (Scopus)

抄録

This paper introduces an imitative model that enables a robot to acquire viewpoints of the self and others from its own sensory-motor experiences. This is important for recognizing and imitating actions generated from various directions. Existing methods require coordinate transformations input by human designers or complex learning modules to acquire a viewpoint. In the proposed model, several neurons dedicated to generated actions and viewpoints of the self and others are added to a dynamic nueral network model reffered as continuous time recurrent neural network (CTRNN). The training data are labeled with types of actions and viewpoints, and are linked to each internal state. We implemented this model in a robot and trained the model to perform actions of object manipulation. Representations of behavior and viewpoint were formed in the internal states of the CTRNN. In addition, we analyzed the initial values of the internal states that represent the viewpoint information. We confirmed the distinction of the observational perspective of other's actions self-organized in the space of the initial values. Combining the initial values of the internal states that describe the behavior and the viewpoint, the system can generate unlearned data.

本文言語English
ホスト出版物のタイトル5th Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2015
出版社Institute of Electrical and Electronics Engineers Inc.
ページ326-331
ページ数6
ISBN(電子版)9781467393201
DOI
出版ステータスPublished - 2015 12月 2
外部発表はい
イベント5th Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2015 - Providence, United States
継続期間: 2015 8月 132015 8月 16

出版物シリーズ

名前5th Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2015

Conference

Conference5th Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2015
国/地域United States
CityProvidence
Period15/8/1315/8/16

ASJC Scopus subject areas

  • 人工知能

フィンガープリント

「Acquisition of viewpoint representation in imitative learning from own sensory-motor experiences」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル