Self-tuning Measurement Fusion Kalman Filter

Abstract

For the multisensor systems with unknown noise statistics and with the same measurement matrices, using the weighted least squares method, an equivalent fused measurement equation with unknown noise variance is obtained, by the modern time series analysis method, based on on-line identification of the moving average (MA) innovation model parameters, the estimators of noise statistics are obtained, and a self-tuning weighted measurement fusion Kalman filter is presented. Its convergence is proved, i.e. if the parameter estimation of the MA innovation models is consistent, then it converges to the optimal weighted measurement fusion Kalman filter in a realization, so that it has asymptotic global optimality. A simulation example for a tracking system shows its effectiveness