Presentation 2005/11/12
A Bipedal Robot Using Control System to Imagine and Learn
Takurou KAWANO, Hirokazu YOKOI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The human and primates imagine the best motion and do trial and error by the simulation in the brain when complicated motion. Moreover, they become possible to do the best real motion by learning the imaged motion at the same time. The purpose of this research is to imitate the simulation in brain and the learning ability, and to propose the control system that learn the motion while imagining the walking pattern which reaches the purpose and to apply it to a bipedal robot. This control system is composed of two networks to image motion and to learn it. The neuron network learned the result of imagined motion that uses CPG and GA and the effectiveness of this control system was suggested.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Simulation in Brain / Bipedal Robot / CPG / GA / Neural Network / Volterra Neuron
Paper # NC2005-76
Date of Issue

Conference Information
Committee NC
Conference Date 2005/11/12(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 Bipedal Robot Using Control System to Imagine and Learn
Sub Title (in English)
Keyword(1) Simulation in Brain
Keyword(2) Bipedal Robot
Keyword(3) CPG
Keyword(4) GA
Keyword(5) Neural Network
Keyword(6) Volterra Neuron
1st Author's Name Takurou KAWANO
1st Author's Affiliation Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology()
2nd Author's Name Hirokazu YOKOI
2nd Author's Affiliation Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology
Date 2005/11/12
Paper # NC2005-76
Volume (vol) vol.105
Number (no) 419
Page pp.pp.-
#Pages 4
Date of Issue