Unmanned aerial vehicle optimal path planning method based on adaptive ant colony algorithm

Abstract

The present invention discloses an unmanned aerial vehicle optimal path planning method based on an adaptive ant colony algorithm. The method comprises: performing meshing of a flight area, performingparameter initialization, and putting ants at a starting point of grids; moving each ant to a feasible path point until all ants reach target points, and calculating a feasible path cost and findingout a cycle optimal path; performing information updating, and performing adaptive regulation for [Rho]; and finally, outputting the optimal path. The unmanned aerial vehicle optimal path planning method based on an adaptive ant colony algorithm can effectively improve a success rate when an unmanned aerial vehicle executes a defense penetration reconnaissance mission, and an efficient unmanned aerial vehicle flight path must be planned and designed prior to execution of the reconnaissance mission in an enemy defense area, so that it is ensured that the unmanned aerial vehicle can reach a target point with the minimum detected probability and the optimal path. Sizes of pheromone volatilization factors are regulated according to the enemy defense area, and an adaptive ant colony algorithm suitable for path planning is used. The adaptive ant colony algorithm is employed to obtain an optimal path length, and an algorithm convergence time is obviously shortened compared to other methods.

Description

technical field [0001] The invention belongs to the field of information technology, and relates to an optimal path planning method for an unmanned aerial vehicle, in particular to an optimal path planning method for an unmanned aerial vehicle based on an adaptive ant colony algorithm. Background technique [0002] In recent years, the development of drones has been very rapid, and various types of drones have appeared one after another. However, the path planning of drones has many deficiencies in the following aspects: [0003] Scholars at home and abroad mainly use optimization algorithms to solve the UAV path planning problem. Some of them use genetic algorithms, but genetic algorithms still have "premature" phenomenon in the process of searching paths and take a long time to plan paths. There are also some that use the A* algorithm, but there are also problems such as slow search speed and large memory space during operation; a series of solutions have appeared for the ...

AI Technical Summary

Problems solved by technology

[0003] Scholars at home and abroad mainly use optimization algorithms to solve the problem of UAV path planning.

There are also some that use the A* algorithm, but there are also problems such as slow search speed and large memory space during operation; a series of solutions have appeared for the above defects, and the theory used in it can be summarized in detail as follows:

Images