Design of nonlinear observers has received considerable attention since the early development of methods for linear state estimation. The most popular approach is the extended Kalman filter (EKF), that goes through significant degradation in the presence of nonlinearities, particularly if unmodeled dynamics are coupled to the process and measurement. For uncertain nonlinear systems, adaptive observers have been introduced to estimate the unknown parameters along with state variables. Over the recent years, neural network (NN) based identification and estimation schemes have been proposed that relax the assumptions on the system at the price of sacrificing the global nature of the results. However, most of the NN based adaptive observer approaches require knowledge of the full dimension of the system, therefore may not be suitable for systems with unmodeled dynamics. In this book, a novel approach to nonlinear state estimation is proposed by augmenting an EKF with an NN. EKFs find their applications mostly in target tracking problems. The proposed approach is robust to unmodeled dynamics and unmodeled disturbances.

Данное издание не является оригинальным. Книга печатается по технологии принт-он-деманд после получения заказа.