Unmanned aerial vehicle (UAV) autonomous navigation method and system

An autonomous navigation system and autonomous navigation technology, applied in the direction of control/regulation system, three-dimensional position/channel control, non-electric variable control, etc., can solve problems such as failure, unintelligent technology, and inability to complete teaching tasks in advance

Active Publication Date: 2017-12-08
TSINGHUA UNIV
View PDF17 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

First of all, the starting point and ending point of drone delivery may be random, so the task of teaching in advance is too large, and it is often impossible to complete the teaching task in advance. Even if it can complete large-scale teaching tasks in advance, the technology is not smart.
Secondly, if the environmental scene changes and the drone cannot perceive it, the technology will fail

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 (UAV) autonomous navigation method and system
  • Unmanned aerial vehicle (UAV) autonomous navigation method and system
  • Unmanned aerial vehicle (UAV) autonomous navigation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0099] This embodiment uses simulation means to verify the effectiveness of the method and system provided by the present invention. In order to reduce the complexity of the problem without losing generality, a virtual drone is generated through simulation, and it is assumed that the flying height and speed of the drone are constant, and only the direction of the drone needs to be controlled. Given that the flying height of the UAV is constant, the following results are generated through simulation: figure 1 (a)~ figure 1 (e) shows five kinds of virtual two-dimensional complex environments, and each virtual environment covers an area of ​​one square kilometer.

[0100] figure 2 It is a flow chart of the autonomous navigation method of the UAV in the large-scale unknown complex environment in the embodiment of the present invention. Combine below figure 2 Each step and its principle are explained in detail.

[0101] Step S10, using the sensing device and the positioning ...

Embodiment 2

[0171] Based on the same inventive concept, an embodiment of the present invention also provides an autonomous navigation system for a UAV in a large-scale unknown complex environment. Such as Figure 9 As shown, the autonomous navigation system 10 includes:

[0172] State obtaining module 100, for obtaining the state of unmanned aerial vehicle;

[0173] The control vector module 200 is used to determine the control vector of the unmanned aerial vehicle;

[0174] A revenue function module 300, which is connected to the state acquisition module, is used to determine the revenue function according to the state of the drone and the environment in which the drone is located;

[0175] Function training module 400, it connects described state acquisition module, control vector module and revenue specifying module, is used for carrying out depth reinforcement learning based on revenue function, training unmanned aerial vehicle from state mapping to the control function of control; ...

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 relates to an unmanned aerial vehicle (UAV) autonomous navigation method and system capable of being applied to a large-scale unfamiliar complex environment. The method includes the steps of obtaining the state of a UAV by using sensing equipment and positioning equipment of the UAV; then determining a control vector of the UAV; determining a revenue function according to the state of the UAV and the environment in which the UAV is located; performing deep enhanced learning based on the revenue function to train a control function from the UAV state mapping to control; and by using the control function through training, generating a corresponding control instruction according to the state of the UAV and controlling the autonomous navigation of the UAV in a large-scale unknown complex scene. According to the invention, a navigation task can be independently accomplished only by using the perception information and position information of the UAV on the surrounding environment and the adaptive control of the UAV in a large-scale unknown complex environment is realized.

Description

technical field [0001] The invention relates to the field of intelligent autonomous navigation of unmanned aerial vehicles, in particular to an autonomous navigation method and system for unmanned aerial vehicles that can be applied in large-scale unfamiliar and complex environments. Background technique [0002] The wide application of small UAVs in the military and civilian fields has led to the rapid development of intelligent applications based on small UAVs, such as the use of UAVs for reconnaissance, monitoring, aerial photography, delivery, etc. The use of drones to deliver goods is the most respected technical vision of major online retail platforms, but due to technical bottlenecks, its application has been limited to a small range of simple applications. Therefore, solving the problem of autonomous navigation of UAVs in large-scale unknown complex environments has become a prerequisite for the realization of UAV delivery and other similar applications. [0003] At...

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): G05D1/10
CPCG05D1/101
Inventor 王剑王超张旭东
Owner TSINGHUA 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

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