Implementation of self-organizing neural networks for visuo-motorcontrol of an industrial robot

Walter JA, Schulten K (1993)
IEEE Transactions on Neural Networks 4(1): 86-96.

Download
OA
Journal Article | Published | English
Author
;
Abstract
The implementation of two neural network algorithms for visuo-motor control of an industrial robot (Puma 562) is reported. The first algorithm uses a vector quantization technique, the "neural-gas" network, together with an error correction scheme based on a Widrow-Hoff-type learning rule. The second algorithm employs an extended self-organizing feature map algorithm. Based on visual information provided by two cameras, the robot learns to position its end effector without an external teacher. Within only 3000 training steps, the robot-camera system is capable of reducing the positioning error of the robot's end effector to approximately 0.1% of the linear dimension of the work space. By employing adaptive feedback the robot succeeds in compensating not only slow calibration drifts, but also sudden changes in its geometry. Hardware aspects of the robot-camera system are discussed
Publishing Year
ISSN
PUB-ID

Cite this

Walter JA, Schulten K. Implementation of self-organizing neural networks for visuo-motorcontrol of an industrial robot. IEEE Transactions on Neural Networks. 1993;4(1):86-96.
Walter, J. A., & Schulten, K. (1993). Implementation of self-organizing neural networks for visuo-motorcontrol of an industrial robot. IEEE Transactions on Neural Networks, 4(1), 86-96.
Walter, J. A., and Schulten, K. (1993). Implementation of self-organizing neural networks for visuo-motorcontrol of an industrial robot. IEEE Transactions on Neural Networks 4, 86-96.
Walter, J.A., & Schulten, K., 1993. Implementation of self-organizing neural networks for visuo-motorcontrol of an industrial robot. IEEE Transactions on Neural Networks, 4(1), p 86-96.
J.A. Walter and K. Schulten, “Implementation of self-organizing neural networks for visuo-motorcontrol of an industrial robot”, IEEE Transactions on Neural Networks, vol. 4, 1993, pp. 86-96.
Walter, J.A., Schulten, K.: Implementation of self-organizing neural networks for visuo-motorcontrol of an industrial robot. IEEE Transactions on Neural Networks. 4, 86-96 (1993).
Walter, Jörg A., and Schulten, Klaus. “Implementation of self-organizing neural networks for visuo-motorcontrol of an industrial robot”. IEEE Transactions on Neural Networks 4.1 (1993): 86-96.
Main File(s)
File Name
Access Level
OA Open Access

This data publication is cited in the following publications:
This publication cites the following data publications:

9 Citations in Europe PMC

Data provided by Europe PubMed Central.

Learning inverse kinematics: reduced sampling through decomposition into virtual robots.
de Angulo VR, Torras C., IEEE Trans Syst Man Cybern B Cybern 38(6), 2008
PMID: 19022727
Speeding up the learning of robot kinematics through function decomposition.
Ruiz de Angulo V, Torras C., IEEE Trans Neural Netw 16(6), 2005
PMID: 16342491
Kinematic coordination of reach and balance.
Crowe A, Porrill J, Prescott T., J Mot Behav 30(3), 1998
PMID: 20037080
Self-calibration of a space robot.
de Angulo VR, Torras C., IEEE Trans Neural Netw 8(4), 1997
PMID: 18255698
Discrete time neural network synthesis using input and output activation functions.
Novakovic BM., IEEE Trans Syst Man Cybern B Cybern 26(4), 1996
PMID: 18263052
Canonical parameterization of excess motor degrees of freedom with self-organizing maps.
Demers D, Kreutz-Delgado K., IEEE Trans Neural Netw 7(1), 1996
PMID: 18255557
Phase diagrams of self-organizing maps.
Bauer H, Riesenhuber M, Geisel T., Phys Rev E Stat Phys Plasmas Fluids Relat Interdiscip Topics 54(3), 1996
PMID: 9965396
Alignment of coexisting cortical maps in a motor control model.
Chen Y, Reggia JA., Neural Comput 8(4), 1996
PMID: 8624960

Export

0 Marked Publications

Open Data PUB

Web of Science

View record in Web of Science®

Sources

PMID: 18267706
PubMed | Europe PMC

Search this title in

Google Scholar