Geometric and neuromorphic learning for nonlinear modeling, control and forecasting

The author describes an algorithm based on results from computational geometry that learns nonlinear dynamical system mappings. The algorithm was applied to (a) the control of robot motion along a nominal trajectory on the basis of a learned model of its inverse dynamics, and (b) prediction of the b...

Full description

Saved in:
Bibliographic Details
Published inProceedings of the 1992 IEEE International Symposium on Intelligent Control pp. 158 - 163
Main Author Zografski, Z.
Format Conference Proceeding
LanguageEnglish
Published IEEE 1992
Subjects
Computational geometry
Motion control
Neuromorphics
Nonlinear control systems
Nonlinear dynamical systems
Power system modeling
Predictive models
Robot control
Robot motion
Solid modeling
Online AccessGet full text
ISBN0780305469
9780780305465
ISSN2158-9860
DOI10.1109/ISIC.1992.225085

Cover

More Information
Summary:The author describes an algorithm based on results from computational geometry that learns nonlinear dynamical system mappings. The algorithm was applied to (a) the control of robot motion along a nominal trajectory on the basis of a learned model of its inverse dynamics, and (b) prediction of the behavior of a complex nonlinear dynamic system for forecasting regional electric power consumption on the basis of a model learned from noisy time series data. The algorithm is shown to compare favorably to a neural learning algorithm.< >
ISBN:0780305469
9780780305465
ISSN:2158-9860
DOI:10.1109/ISIC.1992.225085