Unlock instant, AI-driven research and patent intelligence for your innovation.

Self-adaptive step length estimating method based on gradient descent

A technology of adaptive step size and gradient descent, which is applied in the direction of navigation calculation tools, measuring devices, instruments, etc., can solve the problem of large amount of calculation, and achieve the effect of reducing the amount of calculation, reducing consumption, and reducing cumulative errors

Inactive Publication Date: 2019-03-12
SOUTHEAST UNIV +2
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide an adaptive step size estimation method based on gradient descent, which can solve the problem of relatively large amount of computation when using a fixed step size estimation model and EKF to calculate attitudes in different pedestrian states

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
  • Self-adaptive step length estimating method based on gradient descent
  • Self-adaptive step length estimating method based on gradient descent
  • Self-adaptive step length estimating method based on gradient descent

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The technical solutions and beneficial effects of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0046] Such as figure 1 As shown, the present invention provides an adaptive step size estimation method based on gradient descent. First, the smart phone is used to collect the data of the built-in IMU sensor, including the data of the gyroscope, the data of the accelerometer, and the data of the magnetometer, and then Use accelerometer data for gait detection, use accelerometer data and gait detection to model the adaptive step size estimation model, use gradient descent algorithm to train more accurate parameters of adaptive step size estimation model, use gyroscope The data of the accelerometer, magnetometer, and magnetometer are used to calculate the heading angle, and finally the current position of the pedestrian is calculated by using the principle of dead reckoning.

[0047] Including the following steps:

...

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 self-adaptive step length estimating method based on gradient descent. The method comprises the following steps: step 1, performing gait detection through data collected by an accelerometer, and calculating a step number; step 2, according to a complementary filtering algorithm, correcting gyroscope data by using accelerometer data and magnetometer data, and solving a four-element differential equation, performing attitude solution, and calculating a course angle; step 3, establishing a self-adaptive step length estimating model, collecting a large number of samples and training the model, iterative-calculating a parameter of the step length estimating model by using a gradient descent algorithm; and step 4, speculating a position of a pedestrian by using a trackspeculating algorithm. The method is capable of solving a problem that computation burden is larger when a fixed step length estimating model and EKF solution attitude are used in different pedestrianstates.

Description

technical field [0001] The invention belongs to the field of indoor navigation and positioning, in particular to a method for estimating a step by using an adaptive step-size PDR algorithm based on gradient descent. Background technique [0002] With the sharp increase in the demand for indoor positioning services, the positioning accuracy of the global navigation satellite system (GNSS) has dropped sharply due to the impact of building occlusion and multipath effects, which cannot meet the needs of indoor positioning services. In recent years, indoor positioning technology has become a research topic. The development hotspot of personnel. The currently disclosed indoor positioning technologies mainly include: WIFI positioning, Bluetooth positioning, ultra-wideband positioning, inertial navigation positioning, RFID positioning, ultrasonic positioning, computer vision positioning, etc. [0003] Inertial navigation indoor positioning technology is a popular indoor navigation ...

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): G01C21/20
CPCG01C21/206
Inventor 刘昊蔡磊磊邹涛
Owner SOUTHEAST UNIV