Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Pedestrian self-adaptive zero-speed updating point selection method based on neural network

A zero-speed update and neural network technology, applied in the design field of pedestrian adaptive zero-speed update point selection method, can solve the problems of large accumulation error, poor generalization performance, inaccurate detection in the zero-speed update stage, etc., and achieve the purpose of suppressing accumulation The effect of error growth and generalization performance improvement

Active Publication Date: 2019-12-10
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF8 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem that the existing fixed threshold method or dynamic threshold method is not accurate in the detection of the zero-speed update stage, there is a large cumulative error, and the generalization performance is poor, and a method based on Pedestrian adaptive zero-speed update point selection method based on neural network

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
  • Pedestrian self-adaptive zero-speed updating point selection method based on neural network
  • Pedestrian self-adaptive zero-speed updating point selection method based on neural network
  • Pedestrian self-adaptive zero-speed updating point selection method based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] Exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be understood that the implementations shown and described in the drawings are only exemplary, intended to explain the principle and spirit of the present invention, rather than limit the scope of the present invention.

[0051] The embodiment of the present invention provides a neural network-based pedestrian adaptive zero-speed update point selection method, such as figure 1 As shown, the following steps S1-S4 are included:

[0052] S1. Collect inertial navigation data of different pedestrians in different motion modes.

[0053] In the embodiment of the present invention, the device used is a new generation inertial measurement unit NGIMU, which mainly includes a three-axis gyroscope and a three-axis accelerometer. The NGIMU is attached to any foot of a pedestrian, and the three-axis gyroscope collects Angular velocity data at each sa...

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 pedestrian self-adaptive zero-speed updating point selection method based on a neural network. The convolutional neural network is applied to the zero-speed update point selection method, the zero-speed update points of different pedestrians in different motion states can be adaptively selected, and the selection precision is obviously improved compared with the existingzero-speed update point detection method. Zero-speed updating and a track plotting motion model are fused by combining a zero-speed updating point selected from a neural network and an extended Kalmanfilter, so that accumulated error growth can be remarkably inhibited, the generalization performance of the pedestrian inertial navigation system is greatly improved, and the method has commercial use conditions.

Description

technical field [0001] The invention belongs to the technical field of pedestrian inertial navigation, and in particular relates to the design of a neural network-based pedestrian adaptive zero-speed update point selection method. Background technique [0002] At present, due to its complex structure, large volume, high production cost and high precision, the platform inertial navigation system is mostly used in aviation, large ships and other fields. Strapdown inertial navigation system is mostly used in pedestrian inertial navigation system because of its simple structure, small size, light weight and easy to carry. In the pedestrian inertial navigation system, the inertial measurement unit (Inertial Measurement Unit, IMU) is mostly used. The inertial measurement unit, consisting of a three-axis accelerometer and a three-axis gyroscope, can measure a pedestrian's step length and heading. However, the acceleration and angular velocity values ​​in the inertial measurement ...

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): G01C21/16G06N3/04G06N3/08
CPCG01C21/16G06N3/084G06N3/045G01C21/18G01C25/005
Inventor 肖卓凌余新国何怡阎波
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com