Double-arm collaborative robot three-dimension vision recognizing and grabbing method based on deep learning

A deep learning and three-dimensional vision technology, applied in the field of robot vision, can solve the problems of difficult implementation, inability to solve the problem of two-arm cooperation, and inability to install multiple cameras on the end of the robot arm, so as to improve the ability of operation collaboration and space planning, Increase intelligence and applicability, and facilitate the effect of promotion and use

Active Publication Date: 2020-06-30
SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI
View PDF8 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the actual work process, due to the limitation of the installation of the robot end support tool and the working space, multiple cameras cannot b...

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
  • Double-arm collaborative robot three-dimension vision recognizing and grabbing method based on deep learning
  • Double-arm collaborative robot three-dimension vision recognizing and grabbing method based on deep learning
  • Double-arm collaborative robot three-dimension vision recognizing and grabbing method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] In order to make the object, technical solution and advantages of the present invention more clear and definite, the present invention will be further described in detail below with reference to the accompanying drawings and examples.

[0032] A 3D vision recognition and grasping method for a dual-arm collaborative robot based on deep learning, including the functions of the dual-arm robot and the coordinate system 1 of the 3D vision system, the 3D visual data processing process, and the collaborative processing process.

[0033] Coordinate system of dual-arm robot and 3D vision system mainly refers to:

[0034] Set the desktop coordinate system logo in the work area of ​​the dual-arm robot, identify the logo and establish the coordinate system through the visual system, and obtain the conversion relationship between the visual system coordinate system and the desktop logo coordinate system; the left and right arms of the dual-arm robot are respectively used to establish...

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 a double-arm collaborative robot three-dimension vision recognizing and grabbing method based on deep learning. A double-arm robot and three-dimension vision system coordinatesystem is unified, and accordingly vision and double-arm target recognizing and positioning are achieved. The three-dimension object type and posture of a target are obtained on the basis of deep learning, the grabbing and posture of a double-arm tail end grabbing tool are obtained according to the object type and posture, and then the robot double-arm tail end grabbing tool is controlled to conduct grabbing. According to the double-arm collaborative robot three-dimension vision recognizing and grabbing method, the robot operation collaborating and space planning capability can be improved, the accurate mutual perception collaborating and object recognizing and grabbing capability can be achieved in the double-arm robot operation project, and intelligence and applicability of the robot system are improved.

Description

technical field [0001] The invention relates to a three-dimensional visual recognition and grasping method of a dual-arm collaborative robot based on deep learning, which belongs to the field of robot vision. Background technique [0002] Computer vision refers to using cameras instead of human eyes to identify, track and measure targets. As the most cutting-edge research hotspot at present, robot technology based on computer vision is widely used in the field of robot control. Three-dimensional vision is a method to obtain the three-dimensional geometric information of the object by using the depth and color camera to obtain the image of the measured object. Vision can provide robots with rich environment and target information, and provide a basis for the judgment and decision-making of robots. Deep learning is a method of learning low-level features from original images and combining low-level features to generate more abstract high-level features. 3D vision combined wi...

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): B25J9/16
CPCB25J9/1682B25J9/1697B25J9/163B25J9/1602
Inventor 于晓龙张华良秦锋李庆鑫王福东
Owner SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI
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