DocumentCode
3073666
Title
Solving linear quadratic discrete-time optimal controls using neural networks
Author
Lan, Ming-Shong ; Chand, Sujeet
Author_Institution
Rockwell Int. Sci. Center, Thousand Oaks, CA, USA
fYear
1990
fDate
5-7 Dec 1990
Firstpage
2770
Abstract
The authors describe a unique implementation of linear quadratic (LQ) optimal control using the Hopfield type of neural network. They discuss the neural network architecture for LQ optimal control and present simulation results. They also discuss its extension to the solution of linear quadratic Gaussian optimal control problems
Keywords
discrete time systems; linear systems; neural nets; optimal control; Hopfield neural nets; architecture; linear quadratic Gaussian optimal control; linear quadratic discrete-time optimal controls; neural networks; Capacitance; Constraint optimization; Control systems; Cost function; Neural networks; Neurons; Optimal control; Riccati equations; Sampling methods; Symmetric matrices;
fLanguage
English
Publisher
ieee
Conference_Titel
Decision and Control, 1990., Proceedings of the 29th IEEE Conference on
Conference_Location
Honolulu, HI
Type
conf
DOI
10.1109/CDC.1990.203282
Filename
203282
Link To Document