Presentation 1998/10/24
Inverse Kinematics Model Learning by Modular Architecture Networks
Eimei Oyama, Susumu Tachi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Inverse kinematics computation by using artificial neural networks that learn the inverse kinematics model of a robot arm has been proposed. However, the conventional methods do not pay enough attention on the discontinuity of the inverse kinematics system. It is difficult for the popular multi-layer neural network to approximate the discontinuous inverse kinematics system. In this paper, a novel modular neural net architecture for the inverse model learning is proposed. The inverse kinematics system can be approximated by the appropriate mixture of continuous functions. The modular networks can learn the discontinuous inverse kinematics system by appropriate switching of multiple continuous neural networks.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) neural networks / robot control / inverse kinematics / modular networks / sensorimotor integration
Paper # NC98-45
Date of Issue

Conference Information
Committee NC
Conference Date 1998/10/24(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) Inverse Kinematics Model Learning by Modular Architecture Networks
Sub Title (in English)
Keyword(1) neural networks
Keyword(2) robot control
Keyword(3) inverse kinematics
Keyword(4) modular networks
Keyword(5) sensorimotor integration
1st Author's Name Eimei Oyama
1st Author's Affiliation Mechanical Engineering Laboratory()
2nd Author's Name Susumu Tachi
2nd Author's Affiliation Faculty of Engineering, The University of Tokyo
Date 1998/10/24
Paper # NC98-45
Volume (vol) vol.98
Number (no) 365
Page pp.pp.-
#Pages 8
Date of Issue