UAV (unmanned aerial vehicle) autonomous path-finding strategy method

Abstract

The invention discloses an UAV (unmanned aerial vehicle) autonomous path-finding strategy method, which is characterized by carrying out modeling on environment through an improved polar coordinate system grid method; serving a part of optimal solutions obtained through an MMAS algorithm as an initial solution of an EGA algorithm; carrying out path optimization through the MMAS algorithm and the EGA algorithm simultaneously; and continuing to carry out path optimization through an improved mutation operator and the MMAS algorithm, and finally, finding an optimal path. The method carries out environment modeling through a polar coordinate system, thereby greatly reducing computational complexity; and meanwhile, a quick convergence algorithm is carried out through the MMAS algorithm and the EGA algorithm, thereby improving search efficiency of the optimal solution.

Description

technical field [0001] The invention mainly relates to the autonomous pathfinding strategy of the unmanned aerial vehicle based on the genetic ant algorithm. Background technique [0002] UAVs have been vigorously developed this year, mainly used in geological exploration, film and television photography, environmental monitoring, object tracking and other aspects. In addition to manual control, the UAV also has an autonomous intelligent search function, which can intelligently avoid and select the optimal path according to environmental obstacles. [0003] At present, it is more commonly used, and the global path planning is carried out by classifying obstacles. The main steps include environment modeling and pathfinding strategy algorithms. Recently, the grid method is widely used in environmental modeling, that is, by dividing the overall space into different grids, the grid without obstacles is a free grid, and the non-free grid with obstacles exists. The pathfinding s...

AI Technical Summary

Problems solved by technology

At present, it is usually used to divide the x-y-z three-dimensional coordinate system space into multiple grid spaces according to a certain distance plane. This method is simple and easy to implement, but with the increase of the number of grids, the number of search combinations will increase exponentially. However, the pathfinding strategy based on the genetic ant algorithm is a random search algorithm that draws on natural selection and natural genetic mechanisms, including selection and retention elitist algorithm (elitist genetic algorithm, EGA) and maximum-minimum ant colony system (max- min ant system), its basic idea is to retain the individual with the best fitness value in each iteration, this algorithm improves the search efficiency to a certain extent, but there is still the problem that the search efficiency decreases in the later stage of the algorithm; the maximum and minimum ant colony system ( max-min ant system) is an improved ant colony algorithm proposed by German scholar Thomas Stutzle. The main improvements are as follows: not all ants update the information elements, but only update the pheromone of one ant. It can only be the optimal solution ants found in the current cycle or the ants that may find the known optimal path; at the same time, in order to prevent the pheromone on a certain path from being too large or too small, the pheromone concentration range is set, and at the same time, for Start to attract more ants to search, and the initial value of pheromone concentration is set to an interval value instead of a constant

However, the simple MMAS algorithm still has the problem of low search efficiency and too long time to find the optimal solution

Images