Regresar

Distinguishing Aerial Intruders from Ambient Trajectory Data: Model-Based and Data-Driven Approaches

Abstract:

The identification of intruders to protected airspace (e.g., birds vs. drones) is pursued, using ambient fluctuations in their speed responses. The identification problem is posed as a statistical hypothesis testing or detection problem, wherein inertial feedback-controlled objects subject to stochastic actuation must be distinguished from speed data. The maximum a posteriori probability detector is obtained, and is then simplified to an explicit computation based on two points in the sample autocorrelation of the data. We also show that this special structure additionally permits an entirely data-based approach for constructing and applying the detector (classifier). Simulations based on synthesized data are presented to illustrate and supplement the formal analyses.