Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multi-unmanned aerial vehicle cooperative task scheduling method based on improved discrete particle swarm algorithm

A technique of discrete particle swarm and task scheduling, applied in computing, computing models, artificial life, etc., can solve the problems of reducing algorithm efficiency, increasing algorithm complexity, and fast speed of particle swarm algorithm

Active Publication Date: 2019-09-13
NANJING UNIV OF POSTS & TELECOMM
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Technical problem: In the scheduling of multi-UAV cooperative multi-target attack tasks, the task scheduling scheme must meet multiple complex constraints, and when using the discrete particle swarm optimization algorithm, new particles can be generated through iteration It is often difficult to meet the constraints of the task. After the update is completed, it is necessary to perform secondary detection and modification on the generated new particles, which greatly increases the complexity of the algorithm and reduces the efficiency of the algorithm, and the particle swarm algorithm is extremely fast. Fast, very easy to fall into local extremum

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Multi-unmanned aerial vehicle cooperative task scheduling method based on improved discrete particle swarm algorithm
  • Multi-unmanned aerial vehicle cooperative task scheduling method based on improved discrete particle swarm algorithm
  • Multi-unmanned aerial vehicle cooperative task scheduling method based on improved discrete particle swarm algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] A multi-UAV cooperative task scheduling method based on improved discrete particle swarm algorithm, comprising the following steps:

[0050] Step 1) Input the total number M of enemy targets, traverse each target T j , enter the target T j The vertical and horizontal coordinates of The j represents the serial number of the target;

[0051] Step 2) Input the total number of drones N, traverse each drone U k , enter UAV U k The vertical and horizontal coordinates of and types of drones The type of the unmanned aerial vehicle includes two kinds of reconnaissance unmanned aerial vehicle and combat unmanned aerial vehicle, and said k represents the serial number of unmanned aerial vehicle;

[0052] Step 3) Initialize an empty task scheduling set PList, put all targets into a queue, each target T j reconnaissance missions that in turn include targets attack mission and strike effect assessment tasks Randomly select a target from the target queue to take out th...

Embodiment 2

[0087] A multi-UAV cooperative task scheduling method based on improved discrete particle swarm algorithm, comprising the following steps

[0088] Step 1) Enter the total number of targets 2, and input the position T of the target 1 (50, 100), T 2 (75, 75).

[0089] Step 2) Input the total number of drones 4, input the initial position and type U of the drones 1 (25, 75, scout drone), U 2 (80, 90, Scout Drone), U 3 (50, 50, Combat Drone), U 4 (75, 50, Combat Drone).

[0090] Step 3) Initialize task scheduling set Plist, set

[0091] Step 4) Calculate the fitness value of each individual in the collection Plist, below with D 1 To illustrate the calculation method with an example, by P 1 0 It can be seen but

[0092] Step 5) Update the individual extremum of each individual, since it is the first iteration, the individual extremum of all individuals is itself.

[0093] Step 6) Update the group extremum value of the population, traverse each individual in th...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a multi-unmanned aerial vehicle cooperative task scheduling method based on an improved discrete particle swarm optimization algorithm, and solves the problem of unmanned aerial vehicle cooperative multi-target attack task scheduling according to the position of an enemy target and basic information of an unmanned aerial vehicle. According to the method, the constraint condition of task scheduling is fused into particle updating, the particle iteration mode is improved by using cross mutation, and the algorithm is prevented from falling into a local extreme value by using mutation operation. According to the invention, an improved discrete particle swarm optimization algorithm is used to carry out comparative study on a scheduling scheme according to the voyage costof finishing tasks by the unmanned aerial vehicle and the maximum exposure time of the unmanned aerial vehicle, and an optimal task scheduling scheme is obtained through multiple iterations.

Description

technical field [0001] The invention relates to the field of multi-UAV collaboration, in particular to an improved multi-UAV task scheduling method based on discrete particle swarm algorithm. Background technique [0002] In the multi-UAV self-organizing task, the task scheduling control directly affects the work efficiency of the multi-machine cooperative system, so the present invention will use the particle swarm algorithm to focus on the multi-UAV self-organizing task scheduling control. The multi-unmanned aerial vehicle task scheduling control researched by the present invention means that after the enemy target is found in the coverage area, the task of reconnaissance, attack and strike evaluation of the enemy target is reasonably assigned to the unmanned aerial vehicle performing the task. Different from traditional task scheduling, when executing multi-UAV cooperative target attack tasks, the task scheduling of UAVs needs to meet multiple complex constraints. The UA...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06Q10/06G06Q50/26G06N3/00
CPCG06N3/006G06Q10/06311G06Q50/26
Inventor 陈志王福星岳文静汪皓平狄小娟
Owner NANJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com