Three-Dimensional Neural Net for Learning Visuomotor Coordination of a Robot Arm

Thomas M. Martinetz, Helge J. Ritter, Klaus J. Schulten

Research output: Contribution to journalArticlepeer-review

Abstract

An extension of T. Kohonen's (1982) self-organizing mapping algorithm together with an error-correction scheme based on the Widrow-Hoff learning rule is applied to develop a learning algorithm for the visuomotor coordination of a simulated robot arm. Learning occurs by a sequence of trial movements without the need of an external teacher. Using input signals from a pair of cameras, the closed robot arm system is able to reduce its positioning error to about 0.3% of the linear dimensions of its work space. This is achieved by choosing the connectivity of a three-dimensional lattice consisting of the units of the neural net.

Original languageEnglish (US)
Pages (from-to)131-136
Number of pages6
JournalIEEE Transactions on Neural Networks
Volume1
Issue number1
DOIs
StatePublished - Mar 1990
Externally publishedYes

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Three-Dimensional Neural Net for Learning Visuomotor Coordination of a Robot Arm'. Together they form a unique fingerprint.

Cite this