The simulation and testing of several state tracking techniques over a range of process and measurement noise environments is considered. The problem is placed in the context of tracking a maneuvering vehicle from noisy position data with the vehicle accelerations considered as a random process about which the first and second order statistics are known. The tracking filters under test are the fixed α-β filter, the double α-β filter, the second order Kalman filter, the augmented Kalman filter, and the double Kalman filter. All filters show improved performance as the measurement noise increases and the process noise decreases. The superiority of the Kalman filter over the simpler deterministic digital trackers decreases as the measurement noise increases and the process noise decreases. The double Kalman filter, with the capability of adaptive adjustments of threshold values, indicates the best overall tracking for combined maneuver and non-maneuver tracking. / Master of Science