Cooperative Space Object Tracking Based on Distributed Adaptive Variational Bayesian Cubature Kalman Filter

Abstract

In this paper, we investigate noise covariance adaptive distributed Bayesian filter based on variational Bayesian method. In Bayesian filter framework, the joint distribution of state and noise covariance is approximated by variational Bayesian (VB) method, where the unknown noise covariance is modeled by inverse-Wishart distribution. In order to solve the problem in distributed way, we show that estimation of state can be approximated by averaging local information, and estimation of noise covariance can be achieved in each sensor locally. Then we use cubature Kalman filter (CKF) to approximate Gaussian interval, and propose variational Bayesian based distributed adaptive cubature Kalman filter (VB-DACKF). Finally, we illustrate the effectiveness of the proposed estimation algorithm by a cooperative space object tracking problem.