Presentation 2003/11/14
A Realization of Motion Diversity of The Robotic Hand by The Hierarchical Motion Schema.
Shiori UOTA, Hirokazu YOKOI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) At present, the robotic hand which can form the optimum operation for the change of various environments is required. However, though it is possible to form operation in the almost equal environment in the robotic hand using conventional neural network with learned environment, it makes it learn, when it was put in the environment which completely differed, again. Then, we make a realization of the robotic hand which forms the optimum operation without newly learning in the new environment to be a purpose. For the reason, we constituted motion control system which constituted the hierarchical motion schema using RNN. Next, this system learned some basic actions. After the learning, we changed operation code of the input and parameter of the neural network. From the result, we examined fact of how the new operation is formed by the fusion of the multiple operations which learned in a past, and fact of how the one operation which learned in a past can be changed in proportion to the new environment, by the computer simulation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Robotic hand / Hierarchical motion schema / Motion diversity / Recurrent Neural Network
Paper # NC2003-75
Date of Issue

Conference Information
Committee NC
Conference Date 2003/11/14(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Realization of Motion Diversity of The Robotic Hand by The Hierarchical Motion Schema.
Sub Title (in English)
Keyword(1) Robotic hand
Keyword(2) Hierarchical motion schema
Keyword(3) Motion diversity
Keyword(4) Recurrent Neural Network
1st Author's Name Shiori UOTA
1st Author's Affiliation Kyushu Institute of Technology()
2nd Author's Name Hirokazu YOKOI
2nd Author's Affiliation Kyushu Institute of Technology
Date 2003/11/14
Paper # NC2003-75
Volume (vol) vol.103
Number (no) 465
Page pp.pp.-
#Pages 4
Date of Issue