A method for automatically generating an action plan of an unmanned aerial vehicle group

An action plan and automatic generation technology, applied in genetic rules, instruments, data processing applications, etc., can solve problems that cannot be called automatic generation methods, and cannot reach the automation accuracy of drone swarms

Active Publication Date: 2019-01-18
BEIHANG UNIV +1
View PDF6 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this generation method cannot be called an automatic generation method due to human participation in the subtask decomposition and priority generation stages. It has great limitations and cannot be separated from human factors.
At present, there is no fully automatic method for generating action plans in the academic world. Some scholars use the CS (cu

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
  • A method for automatically generating an action plan of an unmanned aerial vehicle group
  • A method for automatically generating an action plan of an unmanned aerial vehicle group
  • A method for automatically generating an action plan of an unmanned aerial vehicle group

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0106] The embodiment is as follows: a fire breaks out in a forest, and there are 10 fire points to be extinguished. 20 fire-fighting drones are now dispatched to the forest to fight the fire. The core of the task is to extinguish all flames at the ignition point and prevent further spread. Firstly, the scene model is established according to the core of the task. In the first step, in the subtask decomposition module, clustering is carried out to decompose it into several subtasks according to the distance from the UAV to the ignition point and the size of the fire. The second step is to use the harmony search algorithm to generate these subtasks. Several priority sequences are waiting for resource scheduling. The third step is to schedule UAV resources for the priority sequences of each harmony individual in the harmony search algorithm, and use parameters such as fire control ability, fire extinguishing ability, and UAV speed as resources. Ability to use multi-dimensional ...

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 method for automatically generating an action plan of an unmanned aerial vehicle group. 1.A task core and scene information are determined; 2, a sub-task decomposition module decomposes the task core into a plurality of sub-tasks by using a genetic algorithm; 3, a subtask priority automatic sort module generates harmonic population; 4, a resource scheduling module carries out harmonic evaluation; 5, a subtask priority automatic sort module updates harmonic memory database; 6. excellent program is output. The invention is free from artificial participation, and realizes high automation, fast response rate and intelligent synergy. The generated scheme guarantees excellence and diversity, and can be selected in order of excellence. Generated action programmes are implemented more efficiently and more purposefully; Searching is more efficient, and excellent solution can be obtained without traversing all permutations; It can evaluate the optimal scheduling and the optimal priority sequence and the acoustic individual at the same time, and ensure the accuracy of timing sequence and resource scheduling, which increases the computational efficiency. Modular algorithms are more compatible.

Description

technical field [0001] The present invention relates to a method for automatically generating action plans for unmanned aerial vehicles, especially an automatic generation of action plans for unmanned aerial vehicle groups based on subtask decomposition genetic algorithm, subtask priority sorting and acoustic search algorithm, and resource scheduling multidimensional dynamic list planning algorithm. The method can quickly, effectively, and completely automatically generate an unmanned aerial vehicle swarm action plan without human intervention, and belongs to the field of intelligent algorithm module and unmanned aerial vehicle swarm task command and dispatch. Background technique [0002] In the process of generating intelligent and coordinated action plans for complex UAV groups, in order to increase the generation efficiency and the excellence and diversity of the plans, various intelligent algorithms are often introduced to use computers for automatic generation. In rece...

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): G06Q10/06G06N3/12
CPCG06N3/126G06Q10/06316
Inventor 周尧明赵浩然陈俊锋郑江安李昊姜晓爱
Owner BEIHANG 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