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

Inertial measurement data correction method and device based on convolutional neural network model

A convolutional neural network and measurement data technology, applied in measurement devices, instruments, etc., can solve problems such as large errors, reduced positioning and navigation progress, measurement data deviations, etc., to reduce errors, enhance reliability, improve training accuracy and effect of speed

Active Publication Date: 2021-06-18
智道网联科技(北京)有限公司
View PDF12 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the accelerometer and gyroscope in the inertial measurement unit are affected by various factors. After a period of use, its parameters and performance will change, making the measured data biased, and it will accumulate a large error over time. error, resulting in a reduction in the progress of positioning and navigation using the measurement data of the inertial measurement unit

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
  • Inertial measurement data correction method and device based on convolutional neural network model
  • Inertial measurement data correction method and device based on convolutional neural network model
  • Inertial measurement data correction method and device based on convolutional neural network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] figure 1 It is a schematic flowchart of a method for correcting inertial measurement data based on a convolutional neural network model according to an embodiment of the present application.

[0055] see figure 1 , a method for correcting inertial measurement data based on a convolutional neural network model, including:

[0056] In step 101, the convolutional neural network model is initialized, including: defining the convolution kernel size of the convolutional neural network model as N, and setting parameter values ​​for each convolution kernel, where N is an integer greater than 1.

[0057] In a specific implementation, the convolutional neural network model is initialized, a convolution kernel with a size of N can be defined, the N convolution kernels are sorted in turn, and the parameter values ​​​​are set for each convolution kernel in turn; set The loss value LOSS of the convolutional neural network model; set the learning rate learn_rate of the convolutional...

Embodiment 2

[0093] figure 2 It is a schematic flowchart of a method for correcting inertial measurement data based on a convolutional neural network model according to another embodiment of the present application. figure 2 compared to figure 1 The protocol of the present application is described in more detail.

[0094] see figure 2 , a method for correcting inertial measurement data based on a convolutional neural network model, including:

[0095]In step 201, the convolutional neural network model is initialized, including: defining the convolution kernel size of the convolutional neural network model as N, and setting parameter values ​​for each convolution kernel, where N is an integer greater than 1.

[0096] For this step, reference may be made to the description of step 101, and details are not repeated here.

[0097] In step 202, the measurement data of the inertial measurement unit for a period of time is divided to obtain K groups of measurement data sequences including ...

Embodiment 3

[0140] Corresponding to the aforementioned embodiment of the application function realization method, the present application also provides a device for correcting inertial measurement data based on a convolutional neural network model, electronic equipment, and corresponding embodiments.

[0141] image 3 It is a structural schematic diagram of an inertial measurement data correction device based on a convolutional neural network model shown in an embodiment of the present application.

[0142] see image 3 , an inertial measurement data correction device based on a convolutional neural network model, including an initial module 301, a segmentation module 302, a window adjustment module 303, an input module 304, an estimated trajectory module 305, an error module 306, a first judgment module 307, a second Two judgment module 308 , update module 309 , stop module 310 , estimated data acquisition module 311 .

[0143] The initialization module 301 is used to initialize the co...

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 inertial measurement data correction method and a device based on a convolutional neural network model. The method comprises the following steps: segmenting measurement data of an IMU by using a sliding window; enabling the convolutional neural network model to output IMU estimation data at the moment N + I-1 according to the Ith group of measurement data sequences of the IMU from the moment I to the moment N + I-1; according to the IMU estimation data at the moment N + I-1, obtaining a track point calculation position at the moment N + I-1 through calculation; obtaining the cumulative sum of K difference values between the track point calculation position at each moment N + I-1 and the position data of the positioning module; if the cumulative sum of the K difference values is smaller than a set first threshold value, obtaining a trained convolutional neural network model; and outputting IMU estimation data at each moment according to the trained convolutional neural network model. According to the scheme provided by the invention, the measurement error of the inertial measurement unit can be reduced based on the convolutional neural network model.

Description

technical field [0001] The present application relates to the field of navigation technology, in particular to a method and device for correcting inertial measurement data based on a convolutional neural network model. Background technique [0002] Vehicle navigation in the related art mostly relies on a satellite positioning module such as a GPS (Global Positioning System, Global Positioning System) satellite positioning module. However, in some scenarios, such as under bridges, culverts, tunnels, between dense buildings and other locations with poor GPS signals, the positioning deviation of the satellite positioning module of related technologies is very large, and even the positioning results cannot be provided. An inertial navigation system including an inertial measurement unit (IMU) can use the measurement data of the inertial measurement unit to calculate the accurate speed, attitude and position information of the vehicle. [0003] The inertial navigation system use...

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): G01C25/00
CPCG01C25/005
Inventor 费再慧贾双成朱磊李成军
Owner 智道网联科技(北京)有限公司
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com