Pursuing a maneuvering target which uses a hidden Markov model for its control

For a partially observed linear pursuit-evasion problem in which the evader's control is modeled as an unknown jump Markov process and a quadratic criterion involving the terminal miss, the optimal control is expressed as a linear function of the predicted miss. Determining the predicted miss involves estimating the evader's terminal position from past system measurements. Expressions for unnormalized conditional probabilities are given which determine the conditional expectation of the evader's terminal position.<
>