Industrial robot vision system and demonstration method thereof

A technology for industrial robots and vision systems, applied in the field of automation control, can solve problems such as system complexity and user programming, and achieve the effects of small computational complexity, good robustness, and fast training convergence.

Active Publication Date: 2017-09-15
重庆卓来科技有限责任公司
View PDF3 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the above-mentioned deficiencies in the prior art, the purpose of the present invention is to provide a machine vision teaching method for industrial robots, which solves the problems of complex systems and the need for user programming.

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
  • Industrial robot vision system and demonstration method thereof
  • Industrial robot vision system and demonstration method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.

[0028] see figure 1 , an industrial robot vision system, including a camera, a vision controller, an Ethernet switch, a robot controller, and a robot teaching device; wherein, there are multiple cameras, which are set at any fixed position in the work scene or / placed on the robot arm The end moves with the robotic arm, the vision controller and the robot controller communicate through the Gigabit Ethernet network through the Ethernet switch, and the robot controller is connected to the robot teach pendant.

[0029] The working principle of the industrial robot vision system of the present invention is as follows: the picture of the object is recognized by the camera and stored in the vision controller, and the vision controller uses the object picture data set calibrated by the user to train its neural network model using a deep learn...

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 an industrial robot vision system and demonstration method thereof. The vision system includes cameras, a vision controller, an Ethernet switch, a robot controller and a robot demonstrator; the plurality of cameras are arranged in arbitrary fixed positions in a working scene or / placed at the tail end of a robot arm to move together with a mechanical arm, the vision controller and the robot controller communicate through the Ethernet switch by a gigabit Ethernet, and the robot controller is connected with the robot demonstrator. The industrial robot vision system organically integrates visual collection, labeling, training and a recognition system, the system complexity is reduced, and the reliability is improved. A visual recognition capability is added to an industrial robot conveniently through demonstration instead of programming. The method does not require a user to have professional knowledge in the field of machine vision. Applying difficulty of a machine vision product matched with the industrial robot in the fields of object recognition, quality detection, position detection, process detection and safety protection is lowered.

Description

technical field [0001] The invention relates to an industrial robot vision system and a teaching method, belonging to the technical field of automation control. Background technique [0002] In the prior art, the application of visual recognition systems for industrial robots is becoming more and more common, but users need to perform complex, professional and long-term software programming in advance, requiring users to have professional knowledge in machine vision. Existing visual recognition systems generally use traditional algorithms such as feature matching or template matching to realize object recognition. This type of algorithm basically requires a solid-color background and is sensitive to illumination changes. The application scenarios are basically pure industrial occasions, which need to artificially limit the complexity of the scene and the change of illumination. Long deployment time and high cost. If the traditional feature matching method is used for iden...

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): G06K9/62G06N3/04
CPCG06N3/04G06V2201/06G06F18/214
Inventor 黄宇
Owner 重庆卓来科技有限责任公司
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