Distributed Filter Design for Cooperative H-Infinity-Type Estimation

TL;DR

This paper presents a decentralized method for designing distributed robust filters using coupled LMIs, enabling local estimators to compute gains iteratively with neighbor communication, ensuring convergence.

Contribution

It introduces a novel decentralized approach for distributed H-infinity filtering based on LMIs and the method of multipliers, improving efficiency and scalability.

Findings

Efficient decentralized filter design via coupled LMIs.

Convergence analysis of the iterative algorithm.

Local estimators can compute gains with neighbor communication.

Abstract

In this paper, we consider the distributed robust filtering problem, where estimator design is based on a set of coupled linear matrix inequalities (LMIs). We separate the problem and show that the method of multipliers can be applied to obtain a solution efficiently and in a decentralized fashion, i.e. all local estimators can compute their filter gains locally and iteratively, with communications restricted to their neighbours. The convergence properties of the iterative algorithm are analyzed and interpreted.