Learning optimization for CPN-based training in robot positioning control
- 31 Downloads
- 1 Citations
Abstract
Artificial neural net (ANN) models have been applied to the inverse kinematic problem for controlling robot positions. The selection of ANN training parameters, however, is an important yet complicated step which has to be taken before an ANN model for robot positioning control can be implemented effectively. The objective of this research is to utilize the counterpropagation network (CPN) for inverse kinematic mapping and obtain the best performance possible by systematic adjustment of network parameters. Taguchi statistical methods, efficient methods for analyzing the capability and accuracy of a system, have been used in this study. The working envelope of the robot simulated in this research is 150×150×60 mm3. The optimal accuracy and standard deviation determined by this research are 2.62 mm and 1.2 mm, respectively.
Keywords
forward kinematics robot positioning control artificial neural networks quality controlPreview
Unable to display preview. Download preview PDF.
References
- Byrne, D. M. and Taguchi, S. (1986) The Taguchi approach to parameter design,1986 ASQC Quality Congress Transactions, Anaheim, CA.Google Scholar
- Guez, A. and Ahmad, Z. (1987) Accelerated convergence in the inverse kinematics via multilayer feedforward network, inProceedings of the IEEE International Conference on Neural Networks, San Diego, CA,2, pp. 617–624.Google Scholar
- Guez, A. and Ahmad, Z. (1988) Solution to the inverse kinematics problem in robotics by neural networks, inProceedings of the IEEE International Conference on Neural Networks, San Diego, CA,2, pp. 617–621.Google Scholar
- Guo, J. and Cherkassky, V. (1988) A solution to the inverse kinematic problem in robotics using neural network processing, inProceedings of the IEEE International Conference on Neural Networks, San Diego, CA,2, pp. 299–304.Google Scholar
- Hecht-Nielsen, R. (1987) Counterpropagation networks.Applied Optics,26 (23) 4979–4984.Google Scholar
- Hool, J. S. and Maghsoodloo, S. (1986) Introduction to product and process design and improvement using statistical experimental design methods with emphasis on Taguchi methods. Short Course Handouts, Auburn University, AL.Google Scholar
- Kohonen, T. (1989)Self-Organization and Associative Memory, Third Edition, Springer-Verlag, Berlin, Heidelberg, and New York, NY.Google Scholar
- Maghsoodloo, S. (1990) The exact relation of Taguchi's signalto-noise ratio to his quality loss function.Journal of Quality Technology,22 (1), 57–67.Google Scholar
- Nasrabadi, N. N. and Feng, Y. (1988) Vector quantization of image based upon the Kohonen organizing feature maps, inProceedings of the IEEE International Conference on Neural Networks, San Diego, CA,1, pp. 101–108.Google Scholar
- Pai, D. K. (1989) Generic singularities of robot manipulators, inProceedings of the IEEE International Conference on Robotics & Automatics, Salem, MA,2, pp. 738–744.Google Scholar
- Phadke, M. S. (1989)Quality Engineering Using Robust Design, AT&T Bell Laboratories, Prentice Hall, Englewood Cliffs, NJ.Google Scholar
- Phadke, M. S., Kackar, R. N., Speeney, D. V. and Grieco, M. J. (1983) Off-line quality control in integrated circuit fabrication using experimental design.AT&T Technical Journal,62 (5), 1273–1309.Google Scholar
- Taguchi, G. (1983)System of Experimental Design, Third Edition, Kraus International Publications, White Plains, NY.Google Scholar
- Taguchi, G. (1986)Introduction to Off-Line Quality into Processes, Asian Productivity Organization, Kraus International Publications, White Plains, NY.Google Scholar
- Taguchi, G. and Wu, Y. (1985)Introduction to Off-Line Quality Control, Central Japan Quality Control Association, Tokyo, Japan.Google Scholar