Adaptive EKF-CMAC-Based Multisensor Data Fusion for Maneuvering Target

Abstract

In the multisensor passive location, the direction of arrival (DOA) and time differences of arrival (TDOA) are the most useful detection data. Applying multiple sensors to locate and track a maneuvering target is, in fact, a nonlinear uncertain problem. The extended Kalman filter (EKF) is usually used for maneuvering target tracking; however, this algorithm cannot achieve accurate estimation for uncertain or nonlinear systems. In order to increase the accuracy of locating and tracking of a maneuvering target, this paper proposes a novel EKF-cerebellar-model-articulation-controller (EKF-CMAC) multisensor data fusion algorithm for a 3-D maneuvering target. By combining the EKF with an adaptive CMAC, the tracking error of a maneuvering target can be much reduced. The Monte Carlo numerical simulation results illustrate that the proposed algorithm can achieve high accuracy for locating and tracking a maneuvering target.