Unmanned aerial vehicle task allocation method based on group entropy and Q learning

A task assignment, UAV technology, applied in the direction of instruments, data processing applications, resources, etc., can solve the problem of slow convergence speed of task assignment

Active Publication Date: 2020-09-18
XIDIAN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that it is easy to fall into local optimal convergence by excessively seeking the global optimal result, resulting in a slow convergence of task allocation.

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
  • Unmanned aerial vehicle task allocation method based on group entropy and Q learning
  • Unmanned aerial vehicle task allocation method based on group entropy and Q learning
  • Unmanned aerial vehicle task allocation method based on group entropy and Q learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.

[0061] refer to figure 1 , the present invention comprises the following steps:

[0062] Step 1) Initialize UAV task assignment parameters:

[0063] The set of tasks to be executed in the space area with an initial size of X×Y×Z is Ta={ta 1 ,ta 2 ,...,ta i ,...ta m}, the UAV set is A={a 1 ,a 2 ,...,a j ,...,a n}, the jth UAV a j state C j ={c 1,j ,c 2,j ,...,c i,j ,... c m,j}, where ta i Represents the i-th task, m represents the total number of tasks, m≥2, n represents the total number of drones, n≥1, c i,j means a j For the state of the i-th task, c i,j =0 means no execution, c i,j =1 means execution, all unmanned aerial vehicles do not perform tasks before task assignment, in this embodiment, X=800 meters, Y=800 meters, Z=800 meters, m=10, n=1000;

[0064] Step 2) Determine each UAV a j Neighbors, neighbors ref...

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 provides an unmanned aerial vehicle task allocation method based on group entropy and Q learning. The unmanned aerial vehicle task allocation method comprises the steps that parameters are initialized; obtaining a neighbor unmanned aerial vehicle set of each unmanned aerial vehicle according to the position information of the unmanned aerial vehicles and the tasks; determining a sensitive unmanned aerial vehicle and a non-sensitive unmanned aerial vehicle; initializing self-evolution algorithm parameters of the cellular automaton; obtaining an evolution result, and measuring a result of each round of evolution by adopting group entropy; optimal group entropy information is selected from the group entropy information, and a Q table of each unmanned aerial vehicle in Q learningis initialized according to the information; and then initializing Q learning parameters to perform Q learning on the unmanned aerial vehicle, and finally obtaining an unmanned aerial vehicle task allocation result. According to the method, Q learning convergence is accelerated by adopting the method of taking the group entropy as the prior value, global information and local information are fully considered in the Q learning process, the learning efficiency of the algorithm is improved, and the convergence speed of unmanned aerial vehicle task allocation is increased on the basis of ensuringthe reliability of the unmanned aerial vehicle task allocation result.

Description

technical field [0001] The invention belongs to the technical field of unmanned aerial vehicle task allocation, and relates to an unmanned aerial vehicle task allocation method, in particular to an unmanned aerial vehicle task allocation method based on group entropy and Q learning, which can be used for unmanned aerial vehicle detection task allocation. Background technique [0002] Due to the low price, small size, low fuel consumption, and strong mobility of UAVs, UAV task allocation is often used in scenarios such as environmental detection and geographic surveying and mapping. The UAV task allocation problem can be described as multiple UAVs in the scene to perform multiple tasks. Each task requires the UAV to provide a corresponding amount of execution and the execution amount decays with the distance from the UAV to the task. The purpose is Find an effective and reasonable allocation scheme to assign tasks to different UAVs, so that all tasks can get the required amou...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/06
CPCG06Q10/0631Y02T10/40
Inventor 方敏陈烨罗杰豪荆锐杨昊侯志杰丁献硕
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products