Discrete-Time Adaptive State Tracking Control Schemes Using Gradient Algorithms

TL;DR

This paper introduces new discrete-time adaptive control schemes using gradient algorithms for state tracking, addressing a previously unresolved problem with Lyapunov-based methods.

Contribution

The paper develops novel gradient-based adaptive control schemes for discrete-time systems, expanding the design framework beyond traditional Lyapunov methods.

Findings

Successfully designed discrete-time adaptive control schemes

Both direct and indirect adaptive methods are developed

Framework applicable to continuous-time systems as well

Abstract

This paper conducts a comprehensive study of a classical adaptive control problem: adaptive control of a state-space plant model: $\dot{x}(t) = A x(t) + B u(t)$ in continuous time, or $x(t+1) = A x(t) + B u(t)$ in discrete time, for state tracking of a chosen stable reference model system: $\dot{x}_m(t) = A_m x_m(t) + B_m r(t)$ in continuous time, or $x_m(t+1) = A_m x_m(t) + B_m r(t)$ in discrete time. Adaptive state tracking control schemes for continuous-time systems have been reported in the literature, using a Lyapunov design and analysis method which has not been successfully applied to discrete-time systems, so that the discrete-time adaptive state tracking problem has remained to be open. In this paper, new adaptive state tracking control schemes are developed for discrete-time systems, using a gradient method for the design of adaptive laws for updating the controller parameters. Both direct and indirect adaptive designs are presented, which have the standard and desired adaptive law properties. Such a new gradient algorithm based framework is also developed for adaptive state tracking control of continuous-time systems, as compared with the Lyapunov method based framework.