DIFNet: Decentralized Information Filtering Fusion Neural Network with Unknown Correlation in Sensor Measurement Noises

TL;DR

DIFNet is a neural network-based decentralized filtering method that learns unknown measurement noise correlations to improve state estimation accuracy in sensor networks with limited communication.

Contribution

This paper introduces DIFNet, a novel data-driven neural network approach for decentralized filtering that handles unknown noise correlations in sensor networks.

Findings

DIFNet outperforms traditional filtering methods in accuracy.

DIFNet demonstrates robustness in complex, time-varying noise scenarios.

The method reduces communication overhead while maintaining estimation quality.

Abstract

In recent years, decentralized sensor networks have garnered significant attention in the field of state estimation owing to enhanced robustness, scalability, and fault tolerance. Optimal fusion performance can be achieved under fully connected communication and known noise correlation structures. To mitigate communication overhead, the global state estimation problem is decomposed into local subproblems through structured observation model. This ensures that even when the communication network is not fully connected, each sensor can achieve locally optimal estimates of its observable state components. To address the degradation of fusion accuracy induced by unknown correlations in measurement noise, this paper proposes a data-driven method, termed Decentralized Information Filter Neural Network (DIFNet), to learn unknown noise correlations in data for discrete-time nonlinear state space models with cross-correlated measurement noises. Numerical simulations demonstrate that DIFNet achieves superior fusion performance compared to conventional filtering methods and exhibits robust characteristics in more complex scenarios, such as the presence of time-varying noise. The source code used in our numerical experiment can be found online at https://wisdom-estimation.github.io/DIFNet_Demonstrate/.