Unmanned aerial vehicle autonomous landing method and model training method

A technology of unmanned aerial vehicles and network models, applied in neural learning methods, biological neural network models, computer components, etc., can solve problems such as GPS signal influence, accidents, low safety and reliability of unmanned aerial vehicles, etc., to achieve The effect of improving reliability and safety

Pending Publication Date: 2021-02-05
深圳中科保泰空天技术有限公司
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the anti-interference ability of GPS is weak. If the UAV encounters electronic interference, the GPS signal may not be able to support the positioning and navigation functions, which will cause accidents during the autonomous landing process of the UAV.
Also, even in natural environments, GPS signals can be affected by many factors
Therefore, relying on GPS signals for autonomous drone landings is less safe and less reliable

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 autonomous landing method and model training method
  • Unmanned aerial vehicle autonomous landing method and model training method
  • Unmanned aerial vehicle autonomous landing method and model training method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] UAVs or their equipment are often expensive to manufacture. If an accident occurs during the flight and landing of the UAV, it will not only seriously damage the UAV or its equipment, but also cause unpredictable damage to ground facilities or people. . Therefore, the safety and reliability of the UAV landing process are particularly important.

[0065] An embodiment of the present application provides an autonomous landing solution for a drone, so as to improve the safety and reliability during the landing process of the drone. In the following, the model training phase and the application phase will be respectively introduced and explained for the UAV autonomous landing solution provided by the embodiment of the present application. In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present applica...

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 embodiment of the invention provides an unmanned aerial vehicle autonomous landing method and a model training method. The unmanned aerial vehicle autonomous landing method comprises the steps that an unmanned aerial vehicle acquires a real environment image of a to-be-landed area through an airborne image acquisition device; the unmanned aerial vehicle converts the real environment image intograph structure data; the unmanned aerial vehicle inputs the graph structure data into a pre-trained graph convolution decision network model to obtain the action of the graph structure data output by the graph convolution decision network model; and the unmanned aerial vehicle executes an action to land. Through the embodiment of the invention, the safety and reliability of autonomous landing ofthe unmanned aerial vehicle are improved.

Description

technical field [0001] The application belongs to the technical field of unmanned aerial vehicles and artificial intelligence, and in particular relates to a method for autonomously landing an unmanned aerial vehicle and a model training method. Background technique [0002] With the continuous development of drone technology, drones play an increasingly important role in many real-world scenarios, such as surveillance, environmental mapping, package delivery, and search and rescue. [0003] In specific applications, drones may need to land autonomously. Existing drone autonomous landing or autonomous landing technologies generally rely on GPS to perform positioning and navigation tasks. However, the anti-interference ability of GPS is weak. If the UAV encounters electronic interference, the GPS signal may not be able to support positioning and navigation functions, which will cause accidents during the autonomous landing process of the UAV. In addition, even in natural en...

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): G06K9/00G06K9/62G06N3/04G06N3/08G05D1/10
CPCG05D1/101G06N3/08G06V20/00G06N3/048G06N3/045G06F18/22G06F18/24G06F18/29G06F18/214
Inventor 陈杰李坚强张一帆杜威铭刘桂彬
Owner 深圳中科保泰空天技术有限公司
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