Abstract
A prestructured neural network, capable of learning and generating smooth multi-dimensional desired trajectories was designed for the control of robotic manipulators. The recurrent network structure combines adaptive parceling of the workspace with a second order differential equation for the relation between force vector and fingertip position. Network performance for storage (using a modified δ-rule) and generation of a given 2-dimensional trajectory was successfully tested. Simulation results showed that additional implementation of adaptive parceling significantly improved the storage accuracy relative to learning of accelerations with fixed parceling.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
K. Doya, Y. Shuji, A neural network model of temporal pattern memory: adaptive neural oscillator using continuous-time back-propagation learning. Neural Networks, 2: 375–385, 1989.
R. Eckmiller, Neural nets for sensorimotor trajectories. IEEE Control Systems Magazine, 9: 53–59, 1989.
R. Eckmiller, N. Goerke, J. Hakala, Neural networks for internal representation of movements. In: Neural Networks, Theory and Applications, R. J. Mammone, Y. Zeevi, (eds.), Academic Press, San Diego, pp 97–112, 1991.
R. Eckmiller, J. Beerhold, G. Fahner, N. Goerke, J. Hakala, M. Jansen, B. Kreimeier and H.W. Werntges, Neural network applications for robot control. In: Proc. of BMFT Status-Seminar Neuroinformatics, Oct. 1992, In Press 1993.
N. Goerke, M. Schöne, B. Kreimeier, R. Eckmiller, A network with pulse processing neurons for generation of arbitrary temporal sequences. In: Proc. IEEE Int. Joint Conf. Neural Networks, June 1990, Vol. III, pp 315–320, San Diego, 1990.
S. Grossberg, Some networks that can learn, remember, and reproduce any number of complicated space-time patterns. J. Math. and Mechan., 19: 53–91, 1969.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1993 Springer-Verlag London Limited
About this paper
Cite this paper
Goerke, N.HR., Müllender, C.M., Eckmiller, R. (1993). A Recurrent Trajectory Storage Network with Parceling of the Workspace. In: Gielen, S., Kappen, B. (eds) ICANN ’93. ICANN 1993. Springer, London. https://doi.org/10.1007/978-1-4471-2063-6_70
Download citation
DOI: https://doi.org/10.1007/978-1-4471-2063-6_70
Published:
Publisher Name: Springer, London
Print ISBN: 978-3-540-19839-0
Online ISBN: 978-1-4471-2063-6
eBook Packages: Springer Book Archive