Sensor fusion for swarms of unmanned aerial vehicles using modeling field theory

We are developing a technique, based upon modeling field theory, for performing automatic target detection, discrimination, and localization from information measured by a swarm of small unmanned aerial vehicles (UAVs) equipped with visual sensors. Swarms of sensors can facilitate detecting and discriminating low signal-to-clutter targets by allowing correlation between different sensor types and/or different aspect angles. However, for deployment of swarms to be feasible, UAVs must operate more autonomously. The current approach is designed to reduce the load on humans controlling UAVs by providing computerized interpretation of a set of images from multiple sensors. This method yields the bonus feature of estimating precise tracks for UAVs, which may be applicable for automatic collision avoidance. Modeling field theory (MFT) is particularly well suited for this problem because it uses fuzzy dynamic logic to mitigate combinatorial complexity by comparing all models and data simultaneously. Sample results are presented using simulated target signatures and two-dimensional UAV trajectories.