Unmanned aerial vehicle cooperative positioning system and method based on graph neural network

A technology of co-location and neural network, applied in the field of UAV co-location system, it can solve the problems of difficult to achieve real-time performance and increased computing requirements, and achieve the effect of high positioning accuracy, strong anti-interference ability and low server requirements.

Active Publication Date: 2021-02-26
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF9 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, with the increase in the complexity of the UAV cluster, this control method requires an exponential increase in the computing requirements of the central server, making it difficult to achieve real-time performance.

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 cooperative positioning system and method based on graph neural network
  • Unmanned aerial vehicle cooperative positioning system and method based on graph neural network
  • Unmanned aerial vehicle cooperative positioning system and method based on graph neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0136] The UAV collaborative positioning system is built by using the server, UAV simulation platform and 16 UAVs. A heat source target is set 1000 meters away from the server, and the UAV is equipped with an infrared detection sensor.

[0137] The 8th generation i5 integrated display notebook is used as the server. The performance of this server is weak. In the normal centralized control mode, it can support the control command calculation of up to 8 drones.

[0138] Set the predicted target position on the server to deviate from the actual target position by 100 meters.

[0139] A graph neural network model is set in the UAV. The graph neural network model includes a graph convolutional network and multiple fully connected networks. The input of the graph convolutional network is the UAV's own low-dimensional features and the low-dimensional Dimensional features and graph adjacency matrix, low-dimensional features, the UAV's own low-dimensional features are obtained by compu...

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 an unmanned aerial vehicle cooperative positioning system and method based on a graph neural network, and the system comprises a plurality of unmanned aerial vehicles, a server, and an unmanned aerial vehicle simulation platform. A graph neural network model carried by the unmanned aerial vehicle is obtained through building a neural network training model on the unmanned aerial vehicle simulation platform, so that the unmanned aerial vehicle can autonomously generate a control instruction, and cooperative positioning of multiple unmanned aerial vehicles is realized. According to the unmanned aerial vehicle cooperative positioning system and method based on the graph neural network, a decentralized control system is adopted, the requirement for a server is low, real-time control over the unmanned aerial vehicle can be achieved, the positioning accuracy is high, and the anti-interference capacity is high.

Description

[0001] technology neighborhood [0002] The invention relates to a UAV collaborative positioning system and method, in particular to a UAV cooperative positioning system and method based on a graph neural network, which belongs to the UAV positioning neighborhood. Background technique [0003] In recent years, due to the advantages of low cost, low loss, zero casualties, high mobility, and high concealment, UAVs have been widely used in military and civilian scientific research and other adjacent fields. [0004] However, when a single UAV handles larger scenes and more complex tasks, there will be problems such as robustness and stability. For example, in the case of strong interference, the sensor of a single UAV may be interfered and cause large errors. , leading to large positioning errors. [0005] This problem can be solved by the cooperative positioning of multiple drones, the integration of local perception of multiple drones, and the fusion of multiple sensors, so as...

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): G01C21/16G01C21/20G05D1/10G06N3/04
CPCG01C21/165G01C21/20G05D1/104G06N3/045
Inventor 张福彪周天泽林德福王亚凯杨希雯郎帅鹏刘明成毛杜芃
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap