Presentation 2005/6/16
Self-Organizing Adaptive Controllers based on modular network SOM : Application to the Inverted Pendulum
Tetsuya MINATOHARA, Tetsuo FURUKAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, a novel framework of adaptive controller called 'Self-Organizing Adaptive Controller (SOAC)', based on modular network SOM (mnSOM), is proposed. The mnSOM is a generalization of conventional SOM, each nodal unit of which is replaced by a functional module. The SOAC is an mnSOM that employs pairs of controller and predictor as the functional modules. In this study, we made a simulation experiment on an inverted pendulum, the weight and the length of which were suddenly changed. As the result, SOAC succeeded to control the pendulum adaptively, even though the parameters were suddenly varied. This result suggests that SOAC has a high adaptive control ability.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) mnSOM / adaptive control / feedback-error-learning / inverted pendulum
Paper # NC2005-16
Date of Issue

Conference Information
Committee NC
Conference Date 2005/6/16(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) Self-Organizing Adaptive Controllers based on modular network SOM : Application to the Inverted Pendulum
Sub Title (in English)
Keyword(1) mnSOM
Keyword(2) adaptive control
Keyword(3) feedback-error-learning
Keyword(4) inverted pendulum
1st Author's Name Tetsuya MINATOHARA
1st Author's Affiliation Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology()
2nd Author's Name Tetsuo FURUKAWA
2nd Author's Affiliation Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology
Date 2005/6/16
Paper # NC2005-16
Volume (vol) vol.105
Number (no) 130
Page pp.pp.-
#Pages 6
Date of Issue