A Marginal Distributionally Robust Kalman Filter for Centralized Fusion

TL;DR

This paper introduces a novel distributionally robust Kalman filter that accounts for correlated sensor noise uncertainties using a moment-constrained approach, improving state estimation in multi-sensor systems.

Contribution

It proposes a new marginal distributional uncertainty set and formulates a convex minimax optimization problem for robust state estimation, addressing correlation and uncertainty in sensor noise.

Findings

Demonstrates robustness in multi-sensor target tracking

Outperforms traditional Kalman filters in correlated noise scenarios

Efficient convex optimization formulation for practical implementation

Abstract

State estimation is a fundamental problem for multi-sensor information fusion, essential in applications such as target tracking, power systems, and control automation. Previous research mostly ignores the correlation between sensors and assumes independent or known distributions. However, in practice, these distributions are often correlated and difAcult to estimate. This paper proposes a novel moment constrained marginal distributionally robust Kalman Alter (MC-MDRKF) for centralized state estimation in multi-sensor systems. First, we introduce a marginal distributional uncertainty set using a moment-constrained approach, which can better capture the uncertainties of Gaussian noises compared to Kullback-Leibler (KL) divergence-based methods. Based on that, a minimax optimization problem is formulated to identify the least favorable joint distribution and the optimal MMSE estimator thereunder. It is proved that this problem can be reformulated as a convex optimization problem, allowing for efficient solution Anding. Subsequently, by accounting for marginal distributional uncertainty within the state space model, the proposed MC-MDRKF is devised in a minimax approach. Simulation result demonstrates the robustness and superiority of the proposed method in a multi-sensor target tracking scenario.