ABSTRACT
The Gaussian-type tracking methods presented in the previous chapter-Kalman lter (KF), extended Kalman lter (EKF), and adaptive Gaussian mixture model (AGMM)—are based on the assumption that the nature of exogenous inputs to the tracking system (i.e., input disturbances and reference tracking) exhibit normal or Gaussian properties. In addition, it is assumed that the dynamic model of the system, which models the propagation of the state between samples, follows a linear model.
