Sample Complexity for Evaluating the Robust Linear Observers Performance under Coprime Factors Uncertainty

TL;DR

This paper establishes sample complexity bounds for learning robust H2 controllers for unknown LTI systems using coprime factor uncertainty, linking system identification with robust control synthesis.

Contribution

It introduces a convex reformulation of the optimal linear observer problem within the Youla parameterization, enabling robust controller design under uncertainty.

Findings

Derived sample complexity bounds for system identification

Formulated a min-max robust H2 control problem

Provided H-infinity bounds on model error estimates

Abstract

This paper addresses the end-to-end sample complexity bound for learning in closed loop the state estimator-based robust H2 controller for an unknown (possibly unstable) Linear Time Invariant (LTI) system, when given a fixed state-feedback gain. We build on the results from Ding et al. (1994) to bridge the gap between the parameterization of all state-estimators and the celebrated Youla parameterization. Refitting the expression of the relevant closed loop allows for the optimal linear observer problem given a fixed state feedback gain to be recast as a convex problem in the Youla parameter. The robust synthesis procedure is performed by considering bounded additive model uncertainty on the coprime factors of the plant, such that a min-max optimization problem is formulated for the robust H2 controller via an observer approach. The closed-loop identification scheme follows Zhang et al. (2021), where the nominal model of the true plant is identified by constructing a Hankel-like matrix from a single time-series of noisy, finite length input-output data by using the ordinary least squares algorithm from Sarkar et al. (2020). Finally, a H-infinity bound on the estimated model error is provided, as the robust synthesis procedure requires bounded additive uncertainty on the coprime factors of the model.