A multivariable robust model reference adaptive controller using a modified least-squares algorithm

This paper proposes a new multivariable model reference adaptive controller (MIMO RMRAC). The development of this controller involves: a) the characterization of the integral structure of the modeled part of the multivariable plant and the associated parameterization of the controller structure; b) the development of a robust adaptive law based on a modified least-squares algorithm for adjusting the controller parameters so that the closed-loop plant is globally stable despite the presence of unmodeled dynamics and bounded disturbances.