Calibration method suitable for visual servo plug-pull operation

A technology of visual servoing and calibration method, which is applied in the directions of manipulators, program-controlled manipulators, manufacturing tools, etc., can solve the problems of low servo alignment control accuracy, poor plug-in operation effect, etc., and achieve good visual servo effect, improved operation accuracy, The effect of prolonging the service life

Active Publication Date: 2019-02-12
HARBIN INST OF TECH
View PDF6 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problems of low accuracy of servo alignment control based on visual servoing and poor effect of plugging and unplug

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
  • Calibration method suitable for visual servo plug-pull operation
  • Calibration method suitable for visual servo plug-pull operation
  • Calibration method suitable for visual servo plug-pull operation

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0040] A calibration method suitable for visual servo plugging and unplugging operations in this embodiment, the method includes the following steps, such as figure 1 Shown:

[0041] Step 1. Calibration preparation:

[0042] Set a plug clamping device for the end joint of the robot arm, and set a calibration plate on the two symmetrical clips of the plug clamping device, as shown in figure 2 As shown, a camera is also installed on the robotic arm of the robot, and the camera is aimed at the target, and the socket and plug clamping device are included in the field of view of the camera; where, the target refers to the socket where the pin is inserted;

[0043] Step 2, using the camera to collect images including pins, sockets and plug holding devices; wherein, during the image collection process, a laser light source is used to provide illumination, and the laser light source is aligned with the plug holding device and the socket;

[0044] Step 3: Use the deep learning algor...

specific Embodiment approach 2

[0052] The difference from Embodiment 1 is that this embodiment is a calibration method suitable for visual servo plugging and unplugging operations. In the first step, a camera is also installed on the robotic arm of the robot. Specifically, a camera is installed on the end joint of the robot arm. A camera is installed.

specific Embodiment approach 3

[0053] The difference from the specific embodiment 1 or 2 is that in this embodiment, a calibration method suitable for visual servo plugging and unplugging operations, in the step 3, when using the deep learning algorithm to perform feature recognition, it uses the neural network built by pyTorch. For the identification of the socket position and the position of the plug holder. PyTorch belongs to a neural network architecture, similar to building blocks, and uses it to build neural networks. PyTorch is a GPU- and CPU-optimized tensor library for deep learning. It is a python-based scientific computing package that mainly has the following two functions:

[0054] A deep learning research platform that provides maximum flexibility and speed as an alternative to the numpy library when using GPUs.

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 calibration method suitable for a visual servo plug-pull operation, and belongs to the field of image identification. The problems that servo alignment control precision based on the visual servo is low, and the effect of the plug-pull operation controlled by an open loop is poor in a plug-pull stage are solved; the calibration method suitable for the visual servo plug-pull operation is provided, an image containing pins, a socket and a plug clamping device is collected by using a camera; a depth learning algorithm is utilized to obtain a center point of each pin inthe socket and the center point of each calibration board on the plug clamping device; then a socket middle point coordinate, a socket deflection angle, a plug clamping device middle point and a plugclamping device deflection angle are calculated; the point coordinate is transferred into a joint coordinate system at the tail end of a mechanical arm of a robot; the socket middle point coordinatesin a tail end coordinate system of the robot is obtained; a visual servo image feature error is calculated in the tail end coordinate system; and a visual servo feature is sent to a robot visual servoalgorithm, and the robot is controlled to move. According to the method, the operation precision in visual servo plug-pull operation is improved.

Description

technical field [0001] The invention relates to a calibration method suitable for visual servo plugging and unplugging operations. Background technique [0002] At present, various types of robots and mechanical arms are widely used in industrial automation, and the use of robots for assembly operations is even more widely used. However, getting the robot to precisely align with the slot in the assembly operation is a major difficulty in this operation. One of the more difficult assembly operations is the plug socket assembly operation. Most of the visual servoing technologies aim the target at a fixed position in the image, which is determined by humans based on specific experience or mechanical structure measurement. In order to protect the durability of the socket and the plug, we often use the visual servo method to make the plug accurately align with the socket. However, since the visual servo is an open-loop control during the insertion and removal process after ser...

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
CPCB25J9/1687B25J9/1697
Inventor 林伟阳邓肖珂邱剑彬佟明斯李湛高会军
Owner HARBIN INST OF 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