Attitude update method and device based on neural network model

A neural network model and attitude technology, applied in the field of navigation, can solve the problems of large cumulative error, failure to achieve positioning and navigation accuracy, and increase in error, and achieve the effect of improving accuracy

Active Publication Date: 2021-11-09
ZHIDAO NETWORK TECH (BEIJING) CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the update of attitude, since the inertial navigation system obtains a new attitude by means of angular velocity integration, the error of attitude update will increase with time, and there is a large cumulative error, which cannot reach the position required by positioning and navigation. precision

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
  • Attitude update method and device based on neural network model
  • Attitude update method and device based on neural network model
  • Attitude update method and device based on neural network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] figure 1It is a schematic flow chart of the attitude update method based on the neural network model shown in the embodiment of the present application.

[0051] see figure 1 , a posture update method based on a neural network model, comprising:

[0052] In step 101, an angular velocity compensation model to be trained is established based on a neural network model according to an angular velocity fitting compensation formula.

[0053] In one embodiment, when the inertial navigation system updates the attitude based on the equivalent rotation vector, the angular increment can be obtained by integrating the angular velocity; through the angular increment, the equivalent rotation vector of the attitude update is obtained; through the equivalent rotation vector update The attitude of the inertial navigation system. In the process of updating the attitude, the angular velocity is compensated according to the fitting compensation formula of the angular velocity. Accordin...

Embodiment 2

[0069] figure 2 It is another schematic flowchart of the pose update method based on the neural network model shown in the embodiment of the present application. figure 2 compared to figure 1 The protocol of the present application is described in more detail.

[0070] see figure 2 , a posture update method based on a neural network model, comprising:

[0071] In step 201, the fitting compensation equation is solved to obtain parameters of the fitting compensation equation.

[0072] In a specific implementation, when the inertial navigation system updates the attitude based on the equivalent rotation vector, the angular increment can be obtained by integrating the angular velocity ω , the angular increment Include direction and magnitude; pass angle increments , to obtain the equivalent rotation vector ; Update the attitude of the inertial navigation system by the equivalent rotation vector. The equivalent rotation vector means that the attitude from the previou...

Embodiment 3

[0102] Corresponding to the aforementioned embodiment of the application function realization method, the present application also provides a neural network model-based attitude update device, electronic equipment, and corresponding embodiments.

[0103] image 3 It is a schematic structural diagram of the pose update device based on the neural network model shown in the embodiment of the present application.

[0104] see image 3 , a pose update device based on a neural network model, including a model building module 301 , a first input module 302 , a pose determination module 303 , a training module 304 , a second input module 305 , and an update module 306 .

[0105] The model establishing module 301 is used for establishing an angular velocity compensation model to be trained based on the neural network model according to the fitting compensation formula of the angular velocity.

[0106] In one embodiment, when the inertial navigation system updates the attitude based o...

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

This application is about a method and device for updating attitude based on a neural network model. The method includes: establishing an angular velocity compensation model to be trained based on a neural network model based on an angular velocity fitting compensation formula; making the angular velocity compensation model to be trained output a compensated corrected angular velocity sequence according to the input angular velocity sequence; determining the corrected angular velocity sequence based on the corrected angular velocity sequence The first attitude sequence; according to the measurement data of the satellite positioning module, determine the second attitude sequence; make the first attitude sequence converge to the second attitude sequence, and obtain the trained angular velocity compensation model; output the corrected angular velocity according to the trained angular velocity compensation model Update the attitude of the inertial navigation system. The solution provided by the present application can reduce the cumulative error of the attitude update of the inertial navigation system based on the neural network model, and improve the accuracy of the attitude update of the inertial navigation system.

Description

technical field [0001] The present application relates to the field of navigation technology, in particular to a method and device for updating attitude based on a neural network model. Background technique [0002] A satellite positioning module such as a GPS (Global Positioning System, Global Positioning System) positioning module has the characteristics of good performance, high precision, and wide application. However, in some scenarios, such as under bridges, culverts, tunnels, and places with poor positioning signals, the satellite positioning module of the related technology has a large positioning deviation, and even cannot provide positioning results, so it cannot provide accurate positioning. navigation information. An inertial navigation system including an inertial measurement unit (IMU) can use the measurement data of the inertial measurement unit to update navigation information without external force. [0003] The inertial navigation system derives the navig...

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 Patents(China)
IPC IPC(8): G01C21/16G01C21/20G01S19/49G06N3/08G06F30/27
CPCG01C21/165G01C21/20G01S19/49G06N3/08G06F30/27
Inventor 费再慧贾双成朱磊李成军
Owner ZHIDAO NETWORK TECH (BEIJING) CO LTD
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