逆ダイナミックスモデルを用いた反復制御による運動適応

IR IR (HANDLE) Web Site 9 References Open Access

Bibliographic Information

Other Title
  • ギャクダイナミックスモデル オ モチイタ ハンプク セイギョ ニ ヨル ウンドウ テキオウ
  • Motion Adaptation with Iterative Control Using Inverse-Dynamics Model

Search this article

Description

It is thought that the human brain has a mechanism called an internal model that works as a feed-forward controller. However, it is difficult to see that there are peculiar internal models corresponding to various movement environments, and it seems natural that the motor command for desired motion is generated by modifying the output from the principal internal models. Based on this idea, we propose a motion adaptation method for the change of movement environment. The method first learns the dynamics of the controlled object, and constructs the inverse model (internal model) in a neural network. After the change of movement environment, the method modifies the motor command by estimating the deviation between the correct and current motor commands using the inverse model. The effectiveness of the proposed method is confirmed by computational simulation and real machine experiments.

Journal

References(9)*help

See more

Related Projects

See more

Keywords

Details 詳細情報について

Report a problem

Back to top