Advanced Filtering Topics
Bruce P. Gibbs · 2011
This chapter covers a variety of topics that are extensions of the basic Kalman filtering theory. Since model parameters are often poorly known, It discusses maximum likelihood estimation (MLE) of parameters such as initial conditions, process noise variances, measurement noise variances, and dynamic model constants. System characteristics often change with time, so the chapter discuss methods that allow filters to adapt to model changes. The simplest adaptive filters use statistics on filter innovations to adjust the process noise covariance, and this approach can work well when changes in system “ noise ” levels are slow. Robust estimation is another least - squares topic applicable to filtering. The final two topics address alternate methods for nonlinear filtering: unscented Kalman filters and particle filters. Unscented filters use a limited number of carefully selected evaluation points to accurately compute the state and covariance up to third - order terms of the Taylor series. Controlled Vocabulary Terms adaptive filters; Kalman filters; maximum likelihood estimation; particle filters