A Neural Network Aided Target Tracking Algorithm Using Angular Measurements

This paper investigates the problem of maneuvering target tracking by using hybrid (intelligent/classical) methods. The adaptive capability of filters is known to be increased by incorporating a neural network into the filtering procedure. The proposed algorithm is implemented with two second-order Gaussian filters based on the current statistical model and a multilayer feedforward neural network. The two filters, which use the noise corrupted measurements of the target line of sight (LOS) angle, track the same maneuvering target in parallel. The neural network automatically considers all the state information of the two filters and adaptively adjusts the process variance of one of them to achieve better performance in different target maneuver tracking. Simulations results clearly show that the proposed adaptive algorithm tracks maneuvering targets very well with higher precision over a wide range of maneuvers.