強化学習による物体識別のための探索行動の獲得

• 郷古 学

  東北学院大学工学部　機械知能工学科

• 金 天海

  ホンダ・リサーチ・インスティチュート・ジャパン

• 小林 祐一

  静岡大学大学院工学研究科　機械工学専攻

書誌事項

タイトル別名

• Learning of Exploratory Behaviors for Object Recognition Using Reinforcement Learning

抄録

In this study, we propose a reinforcement learning method for discernment behaviors of robot. Discernment behavior, which is a type of exploratory behaviors that support object feature extraction, is a fundamental tool for a robot to orientate itself, operate objects and establish higher classes of knowledge. In this method, a robot learns the discernment behaviors through the interaction with multiple objects. While the interaction, the robot takes reinforcement signal according to the cluster distance of the observed data. We validated the effectiveness of the model in a mobile robot simulation. Three different shaped objects were placed beside the robot one by one. In this learning, the robot learned different behaviors corresponding to each object. Then, we confirmed the kind of feature that is extracted from an object using learned exploratory behaviors.

収録刊行物

• 人工知能学会論文誌

  人工知能学会論文誌 29 (1), 120-128, 2014-01-05

  一般社団法人 人工知能学会

キーワード

• exploratory behavior
• active perception
• reinforcement

詳細情報

• CRID: 1390001205108530176
• NII論文ID: 130003382423
• DOI: 10.1527/tjsai.29.120
• BIBCODE: 2014TJSAI..29..120G
• ISSN: 13468030
• ISSN: 13460714
• Web Site: https://www.jstage.jst.go.jp/article/tjsai/29/1/29_A-D42/_pdf
• 本文言語コード: ja
• データソース種別:
  • JaLC
  • Crossref
  • CiNii Articles
  • KAKEN
• 抄録ライセンスフラグ: 使用不可