Self-tuning Weighted Measurement Fusion Kalman Smoother

For the multisensor system with unknown noise statistics and with identical measurement matrices, based on the solution of the matrix equations for correlation function, the online estimators of the noise variance matrices are obtained, further, a self-tuning weighted measurement fusion Kalman smoother is presented. Based on the stability of the dynamic error system, a new convergence analysis tool is presented for self-tuning fuser. A new concept of convergence in a realization is presented, which is weaker than the convergence with probability one. It is strictly proved that the proposed self-tuning fuser converges to the optimal Kalman fuser in a realization or with probability one, so that it has asymptotic global optimality. Compared with centralized self-tuning Kalman fuser, it can reduce the computational burden, and is suitable for real time applications. A simulation example for a target tracking system with 3-sensor shows its effectiveness.