Unmanned aerial vehicle autonomous navigation method of imitating homing pigeon geomorphic perception homing mechanism

An autonomous navigation and pigeon-like technology, applied in the field of navigation, can solve problems such as unsatisfactory navigation of drones and too sensitive initial values

Active Publication Date: 2020-01-10
BEIHANG UNIV
View PDF9 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the past, UAVs mainly relied on Global Positioning System (Global Position System, GPS) and Inertial Navigation Syst

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 navigation method of imitating homing pigeon geomorphic perception homing mechanism
  • Unmanned aerial vehicle autonomous navigation method of imitating homing pigeon geomorphic perception homing mechanism
  • Unmanned aerial vehicle autonomous navigation method of imitating homing pigeon geomorphic perception homing mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] Inspired by the behavior of homing pigeons using landmark information for navigation, the invention proposes a new autonomous navigation method for unmanned aerial vehicles. Combined with convolutional neural network and visual positioning and mapping methods, the positioning is optimized by using the results of target recognition, and the environment perception and autonomous navigation functions of the UAV are realized.

[0051] The effectiveness of the system and method proposed by the present invention will be verified below through a specific simulation test example. Specific steps are as follows:

[0052] Step 1: Initialize the environment field and train the neural network

[0053] Initialize the experimental environment, collect images of landmark samples with distinctive features and common moving objects in the environment to create a training data set. Input the YOLOv3 network to train the target, and get a neural network model suitable for the current envi...

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 autonomous navigation method of an imitating a homing pigeon geomorphic perception homing mechanism. The method comprises the steps of (1) initializing an environment field and training a neural network, (2) performing target detection of an imitating homing pigeon geomorphic perception behavior, (3) performing unmanned aerial vehicle pose estimation and mapping of imitating homing pigeon landmark navigation, (4) performing 3D point cloud segmentation, (5) performing data fusion, (6) performing landmark category judgment of imitating carrier pigeon dynamic perception, (7) updating a flight path of imitating homing pigeon perception decision, and (8) outputting a flight path. According to the invention, the autonomous navigation of an unmanned aerial vehicle in an application scene can be realized, a function of establishing an advanced map with landmark information is achieved, and the perception and interaction capability of the unmanned aerial vehicle to an environment is improved. In addition, semantic information obtained through target recognition is used to eliminate interference brought by a moving target in a pose estimation module, and the accuracy and robustness of unmanned aerial vehicle positioning and navigation are improved.

Description

technical field [0001] The invention relates to an autonomous navigation method of an unmanned aerial vehicle imitating the homing mechanism of homing pigeon landform perception, and belongs to the field of navigation technology. Background technique [0002] In recent years, research on UAVs (Unmanned Aerial Vehicles, UAV) has made great progress. Whether in the military field or in the field of life, the application of UAVs is becoming more and more extensive, and the navigation technology of UAVs has also become an important aspect. An important part of the development of drones. In the past, UAVs mainly relied on Global Positioning System (Global Position System, GPS) and Inertial Navigation System (Inertial Navigation System, INS) for navigation. Not always available and does not meet the needs of drone navigation. [0003] Advances in computer vision technology and camera hardware have made visual navigation possible. Compared with traditional navigation methods, th...

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): G01C21/00G01C21/20G06N3/04
CPCG01C21/005G01C21/20G06N3/045
Inventor 段海滨李皓邓亦敏辛龙魏晨吴江夏洁周锐徐小斌孙永斌陈琳申燕凯霍梦真
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

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