抄録
This paper is concerned with the sequential state estimation for linear discrete-time systems with the interrupted observation mechanisms. The interrupted observation process is expressed in terms of the Markov chain taking on the values of 0 or 1. On the basis of the Bayesian approach, the approximate minimum variance estimator is derived for the case where the transition probabilities of the Markov chain are known priori.
An adaptive estimator algorithm is also established when the values of the transition probabilities are unknown, but fixed throughout the time interval of operation. Unlike the usual Kalman filter algorithm, all the estimators derived here are nonlinear with respect to observations and the associated covariance equations are directly related to observations. Digital computer simulations are carried out to compare the performance of the estimator presented here with that of the best linear estimator due to Nahi.
