Abstract
This paper presents an entirely Transputer based system conceived to investigate the performance of different types of neural networks applied to robot-control. A robot of 5 degrees of freedom is to be controlled by an unsupervised associative neural network relying on visual feedback. The modular concept of the system allows to easily upgrade processing power and to add optional extensions. Training and performance testing are supported by a Silicon Graphics Workstation.
Preview
Unable to display preview. Download preview PDF.
Bibliography
J.M Auger, Parallel Implementation on Transputers of Kohonen's Algorithms, Euro Courses in Computing with Parallel Architectures, September 10–14, 1990.
T. Kohonen, Self-Organization and associative Memory, Springer-Verlag 1984.
M. Kuperstein, Infant Neural Controller for Adaptive Sensory-Motor Coordination, Neural Networks, Vol 4, pp 131–145, 1991.
H.J. Ritter, T.M. Martinetz, K.J. Schulten, Three-dimensional Neural Net for Learning Visuomotor Coordination of a robot arm, IEEE Transactions on Neural Networks, Vol 1, pp 131–136, 1990.
J.A. Walter, K.J. Schulten, Implementation of Self-Organizing Neural Networks for Visuo-Motor Control of an Industrial Robot, IEEE Transactions on Neural Networks, Vol 4, pp 86–95, 1993.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hagmann, S., Kihl, H., Kuhn, D., Urban, J.P. (1994). A Transputer based visually guided robot system using neuro-control. In: Gentzsch, W., Harms, U. (eds) High-Performance Computing and Networking. HPCN-Europe 1994. Lecture Notes in Computer Science, vol 796. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020404
Download citation
DOI: https://doi.org/10.1007/BFb0020404
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57980-9
Online ISBN: 978-3-540-48406-6
eBook Packages: Springer Book Archive