Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Robot polishing method based on multiple sensors

A multi-sensor and robot technology, applied in the field of industrial robot grinding, can solve the problems of low grinding efficiency and difficult quality assurance.

Pending Publication Date: 2020-10-27
TIANJIN POLYTECHNIC UNIV
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Aiming at the problems of low defect grinding efficiency and difficult quality assurance, this paper proposes a robot grinding system based on multi-sensors, which includes two subsystems: a defect detection system based on visual sensors and a defect grinding system based on torque sensors

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
  • Robot polishing method based on multiple sensors
  • Robot polishing method based on multiple sensors
  • Robot polishing method based on multiple sensors

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention has realized a kind of robot grinding method based on multi-sensor through the following steps, and specific implementation steps are as follows:

[0028] Step 1: Select the hardware of the robot grinding system, and at the same time calibrate the hardware components of the visual sensor, including camera calibration, hand-eye calibration and grinding tool calibration, and establish the coordinate transformation relationship between the robot, camera, grinding tool and grinding workpiece ;The camera perspective projection model is used in the camera calibration, the coordinate conversion between each coordinate system is completed, and finally the conversion formula from the world coordinate system to the image coordinate system is obtained:

[0029]

[0030] where f x =f / s x is the image coordinate system u i The normalized focal length of the axis, f y =f / s y for v i axis scale factor, M 1 by f x , f y , u o , v o Four parameters, wh...

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 robot polishing method based on multiple sensors. The robot polishing method based on the multiple sensors comprises the steps that (1) type selection is conducted on hardware of a robot polishing system, and the composition of hardware of the visual sensor is calibrated; (2) the surfaces of automobile punching parts are subjected to defect collection through the visual sensor, collected image data are manually marked, true value images are obtained, and a defect data set is established; (3) the partition of workpiece surface defects is accomplished by a PixelNet convolutional neural network; (4) signals collected by the torque sensor are preprocessed in three aspects of static calibration, filtering and gravity compensation; and (5) the robot defect polishing system which carries the torque sensor conducts the polishing operation on the defects by utilizing known defect information and a force / position mixed control algorithm and adopting an orthogonal path polishing scheme. The robot polishing method based on the multiple sensors can be widely applied to lots of production and manufacturing fields including the science and technology fields requiring industrial robots such as the aerospace field, the rail transit field, the medical equipment field and the furniture making field.

Description

technical field [0001] The invention belongs to the field of machine vision and sensors, and relates to a multi-sensor-based robot polishing method, which can be used for industrial robot polishing. Background technique [0002] With the gradual maturity of related technologies in hardware and software for industrial robots, the accuracy of the robot body and movement has been greatly improved, and its cost has also been greatly reduced. Aiming at the problem that large-sized and complex-shaped workpieces are difficult to grind, experts and scholars at home and abroad have begun to conduct corresponding research on industrial robot grinding technology on the basis of a large number of research results on industrial robots. At present, the main research direction is based on the factors that affect the grinding of industrial robots, including grinding tool materials, grinding path planning, robot speed control, and grinding contact force. [0003] Aiming at the problems of l...

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): B25J9/16B25J11/00G06T7/00G06T7/70
CPCB25J11/0065B25J9/16B25J9/1694B25J9/1697G06T7/0004G06T7/70
Inventor 肖志涛杨梅耿磊张芳吴骏刘彦北王雯温宇翔
Owner TIANJIN POLYTECHNIC UNIV
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
Eureka Blog
Learn More
PatSnap group products