We propose an approach to output stabilization of multiply connected control systems with uncertainty based on structural decomposition of the original system and asymptotic invariance methods. The proposed approach solves the stabilization problem for minimum-phase systems. Bounds are obtained on the rate of convergence of the stabilization algorithms. Conditions are derived expanding the class of vector controlled systems with uncertainty that are stabilizable by asymptotic invariance methods.

We consider the problem of robust inversion of an uncertain dynamical system with unstable zero dynamics. The solution of the problem is reduced to estimating in real time the bounded solution of an unstable linear differential equation. Estimation algorithms are proposed for one- and two-output systems. Convergence of the inversion algorithms is assessed and the effect of observation errors on the algorithms, i.e., their robustness, is investigated.

An efficient robust inversion algorithm is proposed, which generates asymptotic estimates of the input signal from noisy output observations with uncertainty in the system parameters.

We propose an approach to output stabilization of multiply connected control systems with uncertainty based on structural decomposition of the original system and asymptotic invariance methods. The proposed approach solves the stabilization problem for minimum-phase systems. Bounds are obtained on the rate of convergence of the stabilization algorithms. Conditions are derived expanding the class of vector controlled systems with uncertainty that are stabilizable by asymptotic invariance methods.