Abstract
A hierarchical network for visuo-motor coordination is proposed. The hierarchical approach allows learning geometric models of realistic robots with six or more axes. The network consists of several one-dimensional subnetworks, which learn the coordinate transform and rotation axis for each joint. In our simulation, the network reduces the end-effector error of a 7-axis anthropomorphic robot and 20-axis robot below the visual error.
Supported by a grant from the DFG (GK KOGNET).
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
J. J. Craig. Introduction to Robotics (2nd ed.), Addison-Wesley Publishing Company, 1989
H. J. Ritter, T. M. Martinetz, K. J. Schulten. Topology-concerving maps for learning visuo-motor-coordination. Neural Networks, Vol. 2:, pp. 159–168, 1989
J. Paillard. Brain and Space, Oxford University Press, 1991
Y. Burnod, P. Grandguillaume, I. Otto, S. Ferraine, P. B. Johnson, R. Caminiti. Visuomotor transformations underlying arm movements toward visual targets: A Neural Network model of Cerebral Cortical Operations. The Journal of Neuroscience, Vol. 12(4), pp. 1435–1453, April 1992
B. Fritzke. A growing neural gas network learns topologies. In G. Tesauro,D. S. Touretzky, and T. K. Leen, editors, Advances in Neural Information Processing Systems, Vol. 7, pp 625–632. MIT Press, Cambrige MA, 1995
B. Fritzke. Incremental learning of local linear mappings. In F. Fogelman, editor, ICANN'95: International Conference on Artificial Neural Networks, pp. 217–222, Paris, France, 1995. EC2 & Cie.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Maël, E. (1996). A hierarchical network for learning robust models of kinematic chains. In: von der Malsburg, C., von Seelen, W., Vorbrüggen, J.C., Sendhoff, B. (eds) Artificial Neural Networks — ICANN 96. ICANN 1996. Lecture Notes in Computer Science, vol 1112. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61510-5_105
Download citation
DOI: https://doi.org/10.1007/3-540-61510-5_105
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61510-1
Online ISBN: 978-3-540-68684-2
eBook Packages: Springer Book Archive