Stable adaptive control with recurrent networks

An adaptive control technique for nonlinear plants with immeasurable state is presented. It is based on a recurrent neural network employed as a dynamical model of the plant. Using this dynamical model, a feedback linearizing control is computed and applied to the plant. Parameters of the model are updated on line to allow for partially unknown and time varying plant. Stability of the scheme is shown theoretically and its performance is illustrated in simulations.