Design of IMM Estimators with Nearly Constant Velocity Modes for Tracking Maneuvering Targets

In numerous studies, the interacting multiple model (IMM) estimator has been shown to be significantly better than a conventional single model Kalman filter for tracking maneuvering targets. However, the design and criteria for which the IMM achieves maximum improvement over the conventional single model Kalman filter have received only little study. In this paper, a method for the design of IMM estimators with two nearly constant velocity (NCV) models is developed to maximize the reduction in average error and ensure the most consistent error covariance over NCV Kalman filters designed to minimize the maximum mean squared error (MMSE). Equations that determine the process noise standard deviation for each NCV model (nonmaneuver and maneuver models) in the IMM estimator are given as a function of the deterministic tracking index for targets with sustained maneuvers and sensors that have constant data rates. The design equations are verified via single sensor, single target Monte Carlo simulations by varying the deterministic tracking index from 0.01 to 100. The results of this paper characterize the performance bounds of the IMM estimator with two NCV models as compared to an NCV Kalman filter and provide a method for engineers to easily design IMM estimators with NCV models so that the benefits over the NCV Kalman filter are maximized.