A method and system for real-time prediction of cooperative UAV trajectory

Abstract

The invention discloses a method and system for real-time prediction of trajectory of a cooperative unmanned aerial vehicle. The method includes: obtaining the location information of the cooperative UAV with a time stamp; selecting the position coordinates of the k track points closest to the current moment according to the location information of the cooperative UAV with a time stamp, and obtaining the predicted flight trajectory Input vector; according to the input vector of the predicted flight trajectory, the trajectory points are dynamically weighted to obtain the weight vector corresponding to the input vector; according to the weight vector, based on the weighted least squares method, determine the polynomial trajectory prediction output model; according to The polynomial trajectory prediction output model predicts the trajectory of the cooperative UAV in real time. The invention can accurately match different flight modes in the flight process of the cooperative unmanned aerial vehicle, and improve the real-time prediction accuracy of the future short-term flight trajectory of the cooperative unmanned aerial vehicle.

Description

technical field [0001] The invention relates to the field of track prediction of cooperative unmanned aerial vehicle, in particular to a method and system for real-time forecasting of track of cooperative unmanned aerial vehicle. Background technique [0002] Cooperative drones refer to cooperative drones that share information such as aircraft models and real-time flight status through communication links during flight. In our country, during the flight of cooperative drones, they need to upload their real-time operation data (operation information, location and altitude, etc.) to the designated supervision platform according to a certain frequency. At present, the supervision of the flight of cooperative UAVs through the supervision platform is still at the monitoring level. If the data obtained by the platform can be used to realize real-time prediction of the future flight trajectory of cooperative UAVs, it will be able to better meet the needs of cooperation. UAV-like ...

AI Technical Summary

Problems solved by technology

When cooperative UAVs have strong flight maneuverability and complex flight trajectories, traditional polynomial fitting prediction algorithms may be difficult to accurately grasp the flight trend of cooperative UAVs, and their fixed-order polynomial models may also be difficult to accurately match cooperative UAVs. Different flight modes during the flight of similar UAVs, resulting in a decline in prediction accuracy

Images