A scheme for robust distributed sensor fusion based on average consensus

TLDR

A network of distributed sensors each measures unknown parameters linearly, with independent Gaussian noise corrupting the observations. The authors propose a simple distributed iterative scheme based on average consensus to compute the maximum‑likelihood estimate of the parameters. The scheme diffuses information by having each node update its data with a weighted average of its neighbors, enabling local weighted least‑squares estimates that converge to the global maximum‑likelihood solution without explicit point‑to‑point message passing. The method is robust to unreliable communication links and remains effective in dynamically changing topologies as long as the infinitely occurring communication graphs are jointly connected.

Abstract

We consider a network of distributed sensors, where where each sensor takes a linear measurement of some unknown parameters, corrupted by independent Gaussian noises. We propose a simple distributed iterative scheme, based on distributed average consensus in the network, to compute the maximum-likelihood estimate of the parameters. This scheme doesn't involve explicit point-to-point message passing or routing; instead, it diffuses information across the network by updating each node's data with a weighted average of its neighbors' data (they maintain the same data structure). At each step, every node can compute a local weighted least-squares estimate, which converges to the global maximum-likelihood solution. This scheme is robust to unreliable communication links. We show that it works in a network with dynamically changing topology, provided that the infinitely occurring communication graphs are jointly connected.