Estimation of drone intention using trajectory frequency defined in radar's measurement phase planes

Abstract

Abstract This paper presents a radar‐based algorithm for autonomous estimation of drone intention. The algorithm is based on radar's kinematic measurements, providing fast and robust intention estimation for multiple targets. The core idea of the proposed algorithm is to build intention‐specific features for each intention in advance and use them in actual drone surveillance situations. To effectively depict the trajectory characteristics of various intentions, the trajectory frequency is computed on multiple phase planes through Monte Carlo Simulations. Finally, a naive Bayes classifier is applied to integrate the trajectory likelihood in different phases and ultimately compute the intention likelihood of all intentions concerned. Numerical simulations for the three candidate intentions of image acquisition, smuggling, and kamikaze attack demonstrated the performance of the presented method. The simulation results show that one can estimate the true intention of a specific drone by comparing the value of each intention likelihood.

Keywords

• Bayes methods
• pattern classification
• radar target recognition
• radar tracking
• statistical analysis