Flight Pattern Recognition and Precision Tracking Algorithm for UAV Cluster Targets Imitating Geese Flocks

The rise of biomimetic unmanned aerial vehicle clusters has brought new challenges to radar target tracking and recognition. The purpose of flying imitating geese flocks is long-distance transport with low energy consumption. In this paper, the methods of recognition and tracking are proposed for cluster targets with flight pattern of geese. The pattern recognition method, by detecting specific distance pairs according to five constraints including distance, vertical, pedal, orientation, and slope, judges whether there is a ’V’ characteristic in the measurement set and selects the key individuals such as the leading or following geese. Based on the pattern recognition result, the hypothetical pattern measurements are introduced into the filtering process as additional observation information, which aims to solve the problem of tracking accuracy decrease caused by high maneuverability in the formation stage of flying geese. Simulation results show that the proposed methods can not only judge the pattern of the cluster effectively and identify the key individuals but also improve the accuracy compared with the traditional tracking algorithms.