Study on the Trajectory Positioning and Prediction Framework of Unmanned Aerial Vehicle based on Long Short-term Memory Neural Network

Abstract

Unmanned aerial vehicles (U A V) have extensive application value in the military field. It has been deployed on a large scale in the conflict between Armenia and Azerbaijan, the civil war in Yemen and the war in Syria. Therefore, it is of great significance to deal with the threat of unmanned aerial vehicles. The current UAV traj ectory positioning and prediction methods have deficiencies such as low prediction accuracy, poor robustness, and small data scale. To improve the accuracy of positioning, reduce the positioning time, and improve the accuracy of trajectory prediction, this paper firstly uses the time difference information of the electromagnetic signal of the UA V received by the passive observation station, and then uses the Chan method to solve the flight traj ectory of the U A V according to the principle of time difference positioning. Further considering that the space trajectory of UAV is a complex time series with continuity and interaction, the trajectory of UAV can be predicted through long-term memory neural network. Hence, the study in this paper provides a new reference solution for U A V trajectory prediction analysis.