An Algorithm for UAV Track Planning for Sudden Threats

Abstract

The invention discloses an unmanned aerial vehicle track planning algorithm facing sudden threats. Based on the Dubins path, the algorithm establishes the path extension point evaluation function, and selects path extension points by introducing path length evaluation factors and threat evaluation factors, so that the number of path search points can be effectively reduced. At the same time, combined with the idea of ​​heuristic search, the possible path length cost and threat cost are evaluated to achieve the purpose of shortening the path length. The simulation shows that the multi-factor Dubins algorithm can plan a shorter path in a sudden threat scenario, and has fewer path search points than the traditional trajectory planning algorithm, and the obtained path is in line with the actual flight of the UAV. time course change.

Description

technical field [0001] The invention belongs to the field of unmanned aerial vehicles, and particularly relates to an unmanned aerial vehicle track planning algorithm in a sudden threat scenario. Background technique [0002] UAV trajectory planning methods are roughly divided into two categories: one is global path planning or offline path planning, and the other is local path planning or online path planning. The global path planning method usually generates an optimized path based on the known environment or past perception information of the environment, but this method cannot deal with the situation of unknown or sudden threats. The local path planning algorithm does not require environmental prior information, and realizes dynamic trajectory planning and route adjustment through the information provided by airborne sensors in the face of sudden threats. Since the UAV cannot know the location distribution of the global threat area in the emergency threat scenario, the ...

AI Technical Summary

Problems solved by technology

However, the artificial potential field method is prone to fall into local minima and has the disadvantage that the target cannot be reached.

In this case, the path curve will continue to oscillate, greatly increasing the path search time

Images