Cooperative unmanned aerial vehicle track real-time prediction method and system

Abstract

The invention discloses a cooperative unmanned aerial vehicle track real-time prediction method and a cooperative unmanned aerial vehicle track real-time prediction system. The method comprises the following steps: acquiring position information with a timestamp of a cooperative unmanned aerial vehicle; selecting position coordinates of k trajectory points closest to the current moment according to the position information with the timestamp of the cooperative unmanned aerial vehicle, and obtaining an input vector of a predicted flight trajectory; according to the input vector of the predicted flight trajectory, performing dynamic weight determination on trajectory points to obtain a weight vector corresponding to the input vector; according to the weight vector, based on a weighted least square method, determining a polynomial trajectory prediction output model; and performing real-time prediction on the trajectory of the cooperative unmanned aerial vehicle according to the polynomial trajectory prediction output model. According to the method, different flight modes in the flight process of the cooperative unmanned aerial vehicle can be accurately matched, and the real-time prediction precision of the future short-time flight trajectory of the cooperative unmanned aerial vehicle is improved.

Description

technical field [0001] The present invention relates to the field of trajectory prediction of cooperative unmanned aerial vehicles, in particular to a method and system for real-time prediction of trajectory of cooperative unmanned aerial vehicles. Background technique [0002] Cooperative drones refer to cooperative drones that share information such as models and real-time flight status through communication links during flight. In my country, cooperative UAVs need to upload their real-time operation data (operation information, location and height, etc.) to the designated supervision platform according to a certain frequency during the flight process. 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-l...

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