3D neural net for learning visuomotor-coordination of a robot arm
- 1 January 1989
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
An extension of T. Kohonen's (Biol. Cybern., vol.43, p.59-69, 1982; vol.44, p.135-140, 1982) self-organizing mapping algorithm together with an error-correction rule of the Widrow-Hoff type is applied to develop an unsupervised learning scheme for the visuomotor coordination of a simulated robot arm. 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 3D lattice between the units of the neural net.Keywords
This publication has 8 references indexed in Scilit:
- Adaptive visual-motor coordination in multijoint robots using parallel architecturePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Topology-conserving maps for learning visuo-motor-coordinationNeural Networks, 1989
- Neural Model of Adaptive Hand-Eye Coordination for Single PosturesScience, 1988
- Sensory and motor maps in the mammalian superior colliculusTrends in Neurosciences, 1987
- Learning representations by back-propagating errorsNature, 1986
- Neuronal Population Coding of Movement DirectionScience, 1986
- Analysis of a simple self-organizing processBiological Cybernetics, 1982
- Self-organized formation of topologically correct feature mapsBiological Cybernetics, 1982