Multi-unmanned aerial vehicle cooperative flight path double-layer optimization method based on cultural algorithm framework

Abstract

The invention relates to a multi-unmanned aerial vehicle cooperative flight path double-layer optimization method based on cultural algorithm framework. On the basis of cultural algorithm optimizationframework, two parallel evolution layers with primary and secondary relations are arranged, wherein the primary evolution layer and the secondary evolution layer have the same belief set acceptance function, population set influence function and belief knowledge set updating form, but have mutually independently stored belief knowledge set data, and the iteration modes of the primary evolution layer and the secondary evolution layer are different: the primary evolution layer is constructed by an initial belief knowledge set and serves as a base layer to run through iterative optimization allthe time; and the secondary evolution layer merges results to the primary evolution layer when updating the belief knowledge set each time and reconstructs itself, wherein the reconstruction mode is to clear all belief knowledge sets of the layer participating in iteration and reconstruct the layer with the updated belief knowledge set. According to the double-layer optimization method, development and exploration of track search space information can be expanded, the utilization degree of existing knowledge and the iterative derivation effect of the knowledge is further improved, the track iterative optimization rate is increased, and a track optimization result with high precision is obtained.

Description

technical field [0001] The invention relates to the technical field of collaborative flight path planning, in particular to a multi-unmanned aerial vehicle cooperative flight path double-layer optimization method based on a cultural algorithm framework. Background technique [0002] With the rapid development of science and technology in today's world, the complexity and task requirements of the tasks to be performed are constantly increasing, and the collaborative trajectory planning technology of multiple unmanned aerial vehicles is attracting attention day by day. Compared with single track planning technology, collaborative trajectory planning is more complicated, and it needs to comprehensively consider a series of factors such as environmental information and its own performance, task characteristics and coordination relationship, and space-time coordination relationship, which has higher requirements for optimization scheme design. [0003] The cultural algorithm fram...

AI Technical Summary

Problems solved by technology

A careful analysis of the update and utilization of belief knowledge sets in the framework of cultural algorithms reveals that although specific evolutionary operators are directly used to perform optimization in this framework to obtain a certain degree of improvement in solution accuracy, the updated knowledge set information and its intergenerational derivatives The benefits are not fully utilized: when the environmental knowledge is updated, its new trajectory group usually has a higher cost value than the trajectory group that has been optimized for multiple generations, and it is difficult to retain it in the optimization process, resulting in insufficient utilization of the knowledge set update

Images