Abstract
An ART2 and a Madaline combined neural network is applied to predicting object motions in dynamic environments. The ART2 network extracts a set of coherent patterns of the object motion by its self-organizing and unsupervised learning features. The identified patterns are directed to the Madaline network to generate a quantitative prediction of the future motion states. The method does not require any presumption of the mathematical models, and is applicable to a variety of situations.
Similar content being viewed by others
References
Q. Zhu. Hidden Markov model for visual guidance of robot motion in dynamic environment,IEEE Transactions on Robotics and Automation, Vol.7, No.3, June 1991.
J. Philip. Estimation of three-dimensional motion of rigid objects from noisy observations,IEEE transactions on Pattern Analysis and Machine Intelligence, Vol, 13, No. 1, pp. 61–66, January 1991.
A. Y. Tawfik, Q. Zhu. Neural network prediction of short-term motions of mobile objects in noisy environments,Proceedings of the SPIE's 1993 International Symposium on Optical Engineering and Photonics, Orlando, FL., April 1993.
J. B. Elsner. Predicting time series using a neural network as a method of distinguishing chaos from noise,Journal of Physics A: Mathematical and General, Vol. 25, No. 4, pp. 843–850, 1992.
C. R. Gent, C. P. Sheppard. Predicting time series by a fully connected neural network trained by backpropagation,Computings and Control Engineering Journal, Vol. 3, No. 3, pp. 109–112, May 1992.
E. Sorheim. A combined network architecture using ART2 and back propagation for adaptive estimation of dynamical processes,Modeling, Identification and Control, Vol. 11, No. 4, pp. 191–199, 1990.
G.A. Carpenter, S. Grossberg. ART2: self-organization of stable category recognitiÒn codes for analog input patterns,Applied Optics, Vol. 26, No. 23, pp. 4919–4930, December 1987.
B. Widrow, R. Winter. Neural nets for adaptive filtering and adaptive pattern recognition,IEEE Computer, Vol. 21, No. 3, pp. 25–39, March 1988.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Zhu, Q., Tawfik, A.Y. Quantitative object motion prediction by an ART2 and Madaline combined neural network. Neural Process Lett 2, 19–21 (1995). https://doi.org/10.1007/BF02312378
Issue Date:
DOI: https://doi.org/10.1007/BF02312378