A neural extended Kalman filter multiple model tracker

Abstract

Abstract-A neural extended Kalman filter algorithm was embedded in an interacting multiple model architecture for target tracking. The neural extended Kalman filter algorithm is used to improve motion model prediction during maneuvers. With a better target motion mode, noise reduction can be achieved through a maneuver. Unlike the interacting multiple model architecture which, uses a high process noise model to hold a target through a maneuver with poor velocity and acceleration estimates, a neural extended Kalman filter is used to predict the correct velocity and acceleration states of a target through a maneuver. The neural extended Kalman filter estimates the weights of a neural network, which in turn is used to modify the state estimate predictions of the filter as measurements are processed. The neural network training is performed on-line as data is processed. In this paper, the results of a neural extended Kalman filter embedded in an interacting multiple model tracking architecture will be shown using a high fidelity model of a phased array radar. Six different targets of varying maneuverability will be tracked. The phased array radar is controlled via Level 4 Data Fusion feedback to the Level 0 radar process. Highly maneuvering threats are a major concern for the Navy and DoD and this technology will help address this issue.

Robust passive fault tolerant control applied to a Fuel Metering Valve of a jet engine

“…To circumvent this problem, we propose a Neural Extended Kalman Filter, which compensates the lack of information given by the state space representation resulting from the experimental identification. We find in the literature some works (Kramer et al2008, Owen et al 2003, Stubberud (2006, Lobbia et al 1995) dealing with the robust estimation using NEKF.…”

GPS Timer Transfer Smooth Based on Kalman Filter

“…Kalman filter is used popularly and has strong function: the filter can estimate the past and current status, and can even estimate the status in the future, even if we do not know the precise character of the model. There are two main characters in Kalman filter [3,4]:…”

Analysis of the NEKF performance in a multisensor environment

“…The Kalman filter results thus provide baseline mean error values for comparing the standard deviations of the position error. Overall performance comparisons between the Kalman filter and the NEKF in various formats can be found in a number of previous works including [1], [2], [3], [5], [6], and [7]. Figure 3 shows that the relative variation is less for the NEKF, but varies according to the relative offset in time of the measurements with the minimum variation occurring when the measurements are exactly aligned.…”

“…One approach that has been developed for tracking a target through a maneuver is that of the neural extended Kalman filter (NEKF) [1], [2], and [3]. The neural extended Kalman filter is a coupled system of a standard extended Kalman filter (EKF) that provides state estimates and an EKF neural network training parameter, as developed in [4].…”