A network for learning kinematics with application to human reaching models

Author

Fiala, John C.

Author_Institution

Dept. of Cognitive & Neural Syst., Boston Univ., MA, USA

Volume

5

fYear

1994

fDate

27 Jun-2 Jul 1994

Firstpage

2759

Abstract

A model for self-organization of the coordinate transformations required for spatial reaching is presented. During a motor babbling phase, a mapping from spatial coordinate directions to joint motion directions is learned. After learning, the model is able to produce straight-line spatial trajectories with characteristic bell-shaped spatial velocity profiles, as observed in human reaches. Simulation results are presented for transverse plane reaching using a two degree-of-freedom arm

Keywords

biomechanics; learning (artificial intelligence); manipulator kinematics; manipulators; neural nets; physiological models; bell-shaped spatial velocity profiles; coordinate transformations; human reaching models; joint motion directions; kinematics; motor babbling phase; self-organization; spatial reaching; straight-line spatial trajectories; transverse plane reaching; wo degree-of-freedom arm; Ear; Equations; Humans; Orbital robotics; Robot kinematics; Robot sensing systems; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-1901-X

Type

conf

DOI

10.1109/ICNN.1994.374667

Filename

374667