Robust Neurocontrollers for Systems with Model Uncertainties

A two-neural network approach to solving nonlinear optimal control problems is described. This approach, called the adaptive critic method, consists of one neural network, called the supervisor or the critic, and a second network, called an action network or a controller. The inputs to both these networks are the current states of the system to be controlled. Targets for each network updates are obtained with outputs of the other network, state propagation equations, and the conditions for optimal control. When their outputs are mutually consistent, the controller network output is optimal. The optimally is, however, limited by the underlying system model. Hence, a Lyapunov theory-based analysis for robust stability of the system under model uncertainties is developed and an extra control is developed. This extra control added with the basic control effort from the adaptive critic method guarantees good system performance and stablity under model uncertainties. This approach is demonstrated through a helicopter problem