Bearings-only tracking with a Gaussian-sum based ensemble Kalman filter

Abstract

The paper presents a novel nonlinear filtering algorithm called the Gaussian-sum ensemble Kalman filter (GSEnKF) for the bearings-only tracking problem. It extends the ensemble Kalman filter within a Gaussian-sum framework by using range-parameterized strategy. As a sequential Monte Carlo algorithm, it is not quite computationally demanding, whilst demonstrating better performance than conventional algorithms. Simulation results validate the effectiveness and robustness of the proposed algorithm.