2A1-E21 因果関係の再現に基づく社会的行動の逐次的獲得モデル : 視線追従から社会的参照へ(認知ロボティクス)

• 住岡 英信

  科学技術振興機構ERATO浅田共創知能システムプロジェクト:阪大院

• 吉川 雄一郎

  科学技術振興機構ERATO浅田共創知能システムプロジェクト

• 浅田 稔

  科学技術振興機構ERATO浅田共創知能システムプロジェクト:阪大院

書誌事項

タイトル別名

• 2A1-E21 Finding A Chain of Causality Leads Social Referencing

抄録

The development of joint attention related actions, such as gaze following and gaze alternation, is one of mysteries in infant development. Previous synthetic studies have proposed learning methods for gaze following without any explicit instructions as first step to understand such development. However, a robot was given a priori knowledge about which pair of sensory information and action should be associated. In this paper, we propose a learning mechanism that automatically and iteratively acquires social behavior by detecting and reproducing the causality inherent in interaction with a caregiver without such knowledge. The measurement of causality based on transfer entropy [1] is used to detect appropriate pairs of variables for acquiring social actions. The reproduction of the detected causality promotes other causality. In the computer simulation of human-robot interaction, we examine what kinds of behavior related to joint attention can be acquired sequentially by changing the behaviors of caregiver agent. The result indicates the actions are acquired in similar order to infant development.

収録刊行物

• ロボティクス・メカトロニクス講演会講演概要集

  ロボティクス・メカトロニクス講演会講演概要集 2008 (0), _2A1-E21_1-_2A1-E21_4, 2008

  一般社団法人 日本機械学会

キーワード

• joint attention
• transfer entropy
• contingency learning
• sequential acquisition of social behavior

詳細情報

• CRID: 1390001205934110720
• NII論文ID: 110008696319
• DOI: 10.1299/jsmermd.2008._2a1-e21_1
• ISSN: 24243124
• Web Site: https://www.jstage.jst.go.jp/article/jsmermd/2008/0/2008__2A1-E21_1/_pdf
• 本文言語コード: ja
• データソース種別:
  • JaLC
  • Crossref
  • CiNii Articles
• 抄録ライセンスフラグ: 使用不可