THE DAMPED MODIFIED ITERATED KALMAN FILTER FOR NONLINEAR DISCRETE-TIME-SYSTEMS

The modified iterated Kalman filter, which will be called MIKF for bre vity, is derived from the modified Newton method to approximate a maxi mum likelihood estimate. The MIKF is also obtained by an iteration sch eme for tile extended kalman filter equations. A convergence analysis of the MIKF is given. By the damping method, we can reduce the total C PU time needed to estimate the state variables or may even obtain a co nvergent scheme when the MIKF diverges. A numerical example shows the effective convergence behavior of the damped MIKF.