Ground unmanned platform path planning method based on improved global fruit fly optimization algorithm

Abstract

The invention discloses a ground unmanned platform path planning method based on an improved global fruit fly optimization algorithm. The method comprises the following steps: acquiring a target function of ground unmanned platform path planning, randomly generating the positions of fruit fly individuals in a set search range, substituting the position of each fruit fly individual into the target function, acquiring the fitness value of each fruit fly individual, determining that a fruit fly population gathers towards the position where the optimal fruit fly individual is located according to the fitness values, performing flight search on common fruit flies according to adaptive flight radiuses, performing flight search on elite fruit flies according to a flight radius, and determining the optimal path of a ground unmanned platform. With the method, the path planning effect of the ground unmanned platform can be remarkably improved.

Description

technical field [0001] The invention relates to the technical field of path planning, and more specifically relates to a path planning method for ground unmanned platforms based on an improved global fruit fly algorithm. Background technique [0002] Ground unmanned platform is an important category of ground professional vehicles, and it has been more and more widely used in the fields of industry, military, transportation, logistics, and services. For many unmanned ground platforms, the ability to move autonomously is a prerequisite for their completion of specified tasks, and to be able to move autonomously, they must have the ability to plan the movement path. In other words, path planning is one of the keys to ground unmanned platform technology. The path planning of the ground unmanned platform means that after sensing the surrounding environment, it can plan an optimal movement path from the starting point to the end point by itself. This optimal path can satisfy the...

AI Technical Summary

Problems solved by technology

However, the fruit fly optimization algorithm has shortcomings such as uneven solution generation, fixed flying radius of fruit flies, and easy to fall into local optimum. When planning the path of the ground unmanned platform, the ideal path planning effect is often not achieved.

[0004] 1. The candidate solution is obtained by the reciprocal of the distance between the position of the fruit fly individual and the origin of the coordinates, and the distance cannot be negative, which makes it impossible for the candidate solution to appear in the negative value range, which greatly reduces the understanding Uniformity and makes the solution very easy to converge to the origin of the coordinates;

[0005] 2. The flight radius of the fruit fly individual is set as a constant at the very beginning, and it will not change with the increase of the number of iterations. If the constant is set unreasonably, it is easy to cause the algorithm to fall into local optimum or reduce the performance of the algorithm. search capabilities;

[0006] 3. In the real fruit fly foraging behavior, individual fruit flies will jump in a small range near the food in order to find a more accurate food location, but this real foraging behavior is not simulated in the fruit fly algorithm

[0007] The above three deficiencies lead to the inability to achieve the best path planning effect when using the fruit fly algorithm for path planning of ground unmanned platforms

Images