This chapter discusses the estimation of the state of discrete‐time nonlinear dynamic systems observed via nonlinear measurements. The optimal estimator for this problem is presented, and the difficulty in its implementation is discussed. Also a comparison is made between the optimal nonlinear estimator and the best linear estimator for a simple problem. The suboptimal filter known as the extended Kalman filter (EKF) is derived, and some of the problems encountered in its implementation are illustrated in an example. Methods of compensation for linearized filters are explained. Also included is the description of a numerical procedure that relies on the technique of dynamic programming to obtain the maximum a posteriori (MAP) estimate of the sequence of states of a nonlinear dynamic system—the modal trajectory. The chapter concludes with a discussion of the continuous‐discrete estimation—when the system evolves in continuous time and the measurements are obtained in discrete time. A problem solving section appears at the end of the chapter.
State Estimation for Nonlinear Dynamic Systems
2002-01-04
50 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Grid-Based Object Tracking with Nonlinear Dynamic State and Shape Estimation
BASE | 2019
|Smoothed State Estimation for Nonlinear Markovian Switching Systems
Online Contents | 2008
|