Method for recognizing human body sewing actions by robot

A technology for identifying human bodies and robots, which is applied in the field of robot visual recognition, can solve the problems of high delay and low accuracy of sewing action recognition, achieve improved response speed, good task learning effect, and solve the effects of poor dynamic real-time performance

Active Publication Date: 2021-01-22
XI'AN POLYTECHNIC UNIVERSITY
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a method for a robot to identify the sewing action of a human body, which solves the problems in the prior art that the identification accuracy of the sewing action is not high and the delay in the dynamic identification process is relatively large

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
  • Method for recognizing human body sewing actions by robot
  • Method for recognizing human body sewing actions by robot
  • Method for recognizing human body sewing actions by robot

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0044] A flow chart of a method for a robot identifying a human sewing action in the present invention, as figure 1 As shown, the specific implementation steps are as follows:

[0045] Step 1. Build a modular multi-robot sewing system, which includes an interconnected two-hand sewing system, a stereo vision system, and a visual servo system;

[0046] The present invention applies the method of robot recognition of human sewing movements to the existing intelligent system of sewing robots, and uses a robot based on stereo vision to recognize human sewing movements. First, a modular multi-robot sewing system is built, and the modular multi-robot The stereo vision system of the sewing system includes two cameras with different angles, the visual information is obtained through the cameras, and the visual information is controlled and fed back t...

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 method for recognizing human body sewing actions by a robot, which comprises the following steps: 1, building a modular multi-robot sewing system which comprises a double-hand sewing system, a stereoscopic vision system and a visual servo system which are connected with one another; 2, human body sewing actions being collected to serve as robot learning samples, and training data being generated; 3, performing task learning on the motion elements obtained by demonstration by using Gaussian mixture model coding; 4, establishing a stereoscopic vision system, and detecting the moving posture of the needle in the task period; and 5, establishing a visual servo system, and guiding and adjusting the movement of the robot through the feedback of closed-loop vision. According to the method, the sewing gesture recognition accuracy is improved, the response speed is increased, and the problem of poor dynamic real-time performance of the current method is solved.

Description

technical field [0001] The invention belongs to the technical field of robot visual recognition, and relates to a method for a robot to recognize the sewing action of a human body. Background technique [0002] Robot visual recognition technology is a key part of the intelligent robot system. It refers to the use of robots to realize human visual functions, that is, the recognition of the objective three-dimensional world, and mainly uses information such as color and shape to identify environmental targets. Robot visual recognition technology has been widely used in robot intelligent systems. The visual recognition system must not only achieve accurate image acquisition but also achieve real-time response to external changes. At the same time, it also needs to track external moving targets in real time. However, the accuracy of the existing methods for sewing motion recognition is not high, and the delay in the dynamic recognition process is relatively large, so that the ro...

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): G06K9/00G06K9/62G06F3/01
CPCG06F3/017G06V40/20G06F18/214
Inventor 王晓华王皞燚
Owner XI'AN POLYTECHNIC UNIVERSITY
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap