Hierarchical neural network model for voluntary movement with application to robotics

Author

Kawato, M. ; Uno, Y. ; Isobe, Michiaki ; Suzuki, Ryoji

Author_Institution

Dept. of Biophys. Eng., Osaka Univ., Japan

Volume

8

Issue

2

fYear

1988

fDate

4/1/1988 12:00:00 AM

Firstpage

8

Lastpage

15

Abstract

In order to control voluntary movements, the central nervous system must solve the following three computational problems at different levels: determination of a desired trajectory in the visual coordinates; transformation of the trajectory from visual coordinates to body coordinates; and generation of motor commands. Based on physiological information and previous models, computational theories are proposed for the first two problems, and a hierarchical neural network model is introduced to deal with motor commands. The application of this approach to robotics is outlined.<>

Keywords

biocontrol; biomechanics; hierarchical systems; neural nets; position control; robots; body coordinates; central nervous system; command generation; hierarchical control; motor commands; neural network model; physiological information; robotics; trajectory determination; transformation; visual coordinates; voluntary movement; voluntary movements; Actuators; Biological neural networks; Centralized control; Computational modeling; Computer networks; Glass; Muscles; Neural networks; Robot kinematics; Torque;

fLanguage

English

Journal_Title

Control Systems Magazine, IEEE

Publisher

ieee

ISSN

0272-1708

Type

jour

DOI

10.1109/37.1867

Filename

1867