Multi-vision based both-arm robot hand-eye coordination method

A robot hand and multi-eye vision technology, applied in the field of robot vision, can solve problems such as the failure of the robot arm to grasp, the blind spot of the target object, the inability of the binocular camera to capture the target object at the same time, etc., so as to improve the probability of successfully capturing the target and improve the Accuracy, the effect of solving visual blind spots

Active Publication Date: 2017-12-15
NANJING UNIV OF SCI & TECH
View PDF6 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the actual ranging process, there is often a visual blind spot problem for capturing the target object, that is, the binocular camera cannot capture the target object at the same time, so the robot arm fails to capture

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
  • Multi-vision based both-arm robot hand-eye coordination method
  • Multi-vision based both-arm robot hand-eye coordination method
  • Multi-vision based both-arm robot hand-eye coordination method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0072] like Figure 4 As shown, a stereo vision model of two cameras with random positions is established, and two single cameras are randomly placed. In the traditional binocular system, the world coordinate system is set on a camera coordinate system to reduce the amount of calculation, but in the present invention, the camera that collects the image is unknown, so it is meaningless to set the origin of the world coordinate system on the camera coordinate system. , so the present invention takes the end of any robot arm as the origin to establish the world coordinate system.

[0073] The two images with the target feature used in this embodiment are captured by two cameras on the same manipulator, and the end of the manipulator is used as the origin of the world coordinate system, then according to the target object p, the image coordinate system of the two images is The coordinates (x, y) in , respectively get the coordinates (x, y) of the target object p in the two camera...

Embodiment 2

[0077] The two images with target features used in this embodiment are captured by cameras on two robotic arms respectively, and one of the images is captured by a camera on a robotic arm that establishes a world coordinate system, then the target object is in the camera coordinate system. The relationship between the coordinates in and the coordinate system in the world coordinate system is:

[0078]

[0079] Another picture comes from another robotic arm, at this time the matrix M=M 2 T 1 T 2 T 3 , where T 1 represents the transformation matrix from the end of the other robotic arm to the base, T 2 represents the transformation matrix between the two manipulator bases, T 3 Represents the transformation matrix from the base of the manipulator that establishes the world coordinate system to the end of the manipulator, M 2 Represents the transfer matrix from the camera on the robotic arm that establishes the world coordinate system to the end of the robotic arm, then 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 multi-vision based both-arm robot hand-eye coordination method, and belongs to the field of robot vision. Two multi-vision cameras are used for target positioning, a mechanical arm close to a target object is selected for grabbing, meanwhile, the target object can be positioned again, and the target object is grabbed to be fed to a fixed zone. According to the multi-vision based both-arm robot hand-eye coordination method, the problem that in the existing scheme, only one camera in binocular cameras shoot the object, and consequently the binocular distance measurement and positioning cannot be achieved is solved, and the accuracy of target object grabbing by the mechanical arm is improved.

Description

technical field [0001] The invention relates to the field of robot vision, in particular to a hand-eye coordination method for a dual-arm robot based on multi-eye vision. Background technique [0002] Computer vision refers to the use of 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. Binocular stereo vision is a method of obtaining three-dimensional geometric information of an object by using imaging equipment to obtain two images of the object to be measured from different positions, and calculating the positional deviation between the corresponding points of the images. Vision can provide the robot with rich environment and target information, and provide the basis for the robot's judgment and decision-making. [0003] In the actual operation process, there are various problems in the distance measurement usin...

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): B25J9/16
CPCB25J9/1697
Inventor 罗雨龙崔宪阳虞文杰吴巍郭毓黄颖苏鹏飞郭飞陈宝存肖潇
Owner NANJING UNIV OF SCI & TECH
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