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
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;
Conference_Titel :
Decision and Control, 1990., Proceedings of the 29th IEEE Conference on
Conference_Location :
Honolulu, HI
DOI :
10.1109/CDC.1990.203282
