Learning to generate articulated behavior by the "forwarding forward model" network

スポンサーリンク

概要

• 論文の詳細を見る

• This paper reviews our recently propsed idea of the "Forwarding Forward Model" that explains how behavior primitives and their level structures can be self-organized in the context of the robot imitation learning. The model illustrates that (1) the sensory-motor sequences are generated and recognized as hierarchically articulated, (2) behaviors are generated both robustly and flexiblely by means of the bootom-up and the top-down interactions between levels. These claims are verified through the experiments using a 4-degrees of freedom arm robot with a vision system.

• 社団法人電子情報通信学会の論文
• 2002-01-21

著者

• Tani J

  The Brain Science Institute Riken

• TANI Jun

  The Brain Science Institute, RIKEN

• Tani Jun

  The Brain Science Institute Riken

関連論文

• Learning to generate articulated behavior by the "forwarding forward model" network
• Self-Organization of Behavior Primitives as Multiple Attractor Dynamics by the "Forwarding Forward Model" network

スポンサーリンク