Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Robot posture recognition method and device based on multi-sensor fusion

A multi-sensor fusion and recognition device technology, applied in neural learning methods, biometric recognition, character and pattern recognition, etc., can solve problems such as insufficient information reliability, improve reliability, improve accuracy and speed, and improve The effect of accuracy

Active Publication Date: 2020-03-24
BEIHANG UNIV
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem of insufficient reliability of information obtained from a single or a small number of sensors in a robot. The multi-sensor fusion-based robot attitude recognition method and device, through multi-sensor fusion in exchange for reliability, propose A robot attitude recognition method based on the idea of ​​multi-sensor fusion is proposed. This method uses various sensors integrated in the robot to analyze and process the data through the connection between the data, improve the reliability of the results, and then better understand the robot. gesture recognition

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
  • Robot posture recognition method and device based on multi-sensor fusion
  • Robot posture recognition method and device based on multi-sensor fusion
  • Robot posture recognition method and device based on multi-sensor fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of one or more embodiments. It may be evident, however, that these embodiments may be practiced without these specific details. In other instances, well-known structures and devices are shown in block diagram form in order to facilitate describing one or more embodiments.

[0047] Various embodiments according to the present invention will be described in detail below with reference to the accompanying drawings.

[0048] figure 1 It is a schematic diagram of the flow chart of the robot posture recognition method based on multi-sensor fusion in the present invention, as figure 1 As shown, the robot gesture recognition method includes:

[0049] Step S1, collecting data from various sensors built in the robot;

[0050] Step S3, extracting features from the collected sensor data, the features include position features, moment fe...

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 provides a robot posture recognition method and device based on multi-sensor fusion. The robot posture recognition method comprises the steps that data of various built-in sensors in a robot are collected; features are extracted from the acquired data of the sensor, wherein the features comprise a position feature, a moment feature and an environment feature; the extracted features are screened to obtain associated features of which the relevancy of each feature reaches a set value, and each feature and the associated features thereof are fused; and a neural network model is constructed, all the fused features are input into the neural network model, posture information of the robot is obtained, and the posture information comprises three-dimensional position information andthree-dimensional direction information. According to the method and the device, the data of various sensors are fused, and the neural network algorithm is utilized to perform unified recognition andjudgment, so that the accuracy and rapidity of posture recognition and judgment are improved.

Description

technical field [0001] The present invention relates to the technical field of computer mobile computing, and more specifically, to a multi-sensor fusion-based robot gesture recognition method and device. Background technique [0002] With the rapid development of artificial intelligence, robot technology has also been greatly improved. At the same time, as one of the most widely used computer technologies, artificial neural networks are increasingly used in computer-related fields. [0003] The posture recognition during the operation of the robot is inseparable from the various data collected in real time by various sensors in the robot. On the basis of these collected data, the robot uses integrated algorithms to process and analyze separately, so as to obtain information from various aspects, and then Identify the current pose. The data obtained from the sensors are of various types and the relationship between them is complicated. The traditional processing method basi...

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): G06K9/62G06N3/04G06N3/08G06K9/00
CPCG06N3/084G06V40/10G06N3/048G06F18/214G06F18/25
Inventor 牛建伟李延祺金鑫任涛
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
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