Fuzzy Logic Based Data Association with Target/Sensor Soft Constraints

Abstract

For the typical case in target association, where both the target tracks and the measurements are described with Gaussian random variables, the standard association uses the chi-squared metric, a weighted inner product of the residual formed by an estimated measurement and the true measurement. There are, however, cases where the measurements are not well described as Gaussian random variables, including when the Gaussian distribution is corrupted by sensor blockage or target constraints. Based upon the proven concept of the chi-squared metric, a straightforward fuzzy-logic based association method was developed to emulate this metric for Gaussian and non-Gaussian measurements. This approach was previously developed for the cases where non-Gaussian measurements and hard constraints were present. In actual operations, soft constraints on sensor performance and target capabilities are often present. This effort develops a penalty-method-based capability into the association scheme to handle operational concerns.