Unlock instant, AI-driven research and patent intelligence for your innovation.

A multi-style calligraphy copying method for robots based on force-sense learning

A robot and multi-style technology, applied in the direction of manipulators, program-controlled manipulators, manufacturing tools, etc., can solve the problem of not taking into account the influence of the writing force on the calligraphy effect

Active Publication Date: 2021-01-15
XIANGTAN UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the calligraphy robot only uses image analysis to plan the trajectory of the robot, without considering the influence of the writing force on the calligraphy effect. In order to better retain the characteristics of different styles of calligraphy, a robot calligraphy method that combines force sense is urgently needed.

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
  • A multi-style calligraphy copying method for robots based on force-sense learning
  • A multi-style calligraphy copying method for robots based on force-sense learning
  • A multi-style calligraphy copying method for robots based on force-sense learning

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0072] refer to figure 1 , The invention discloses a robot multi-style calligraphy copying method based on force sense learning, which includes a multi-style standard font library, a calligraphy style recognition module, a stroke information extraction module, and a robot joint trajectory planning module. The specific implementation steps are as follows:

[0073] Step 1. Establish the kinematic model of the industrial robot, obtain the forward and inverse kinematic solutions of the industrial robot, and design a brush holding tool that can be fixed on the force sensor, and obtain the robot tool coordinate system through four-point calibration. The three-point method is calibrated to obtain the robot workpiece coordinate system;

[0074] Described a kind of writing brush clamping tool that can be fixed on the force sensor, its three-dimensional model refers to figure 2 , the flange (1) can be fixed on the flange of the sensing area of ​​the force sensor, the elastic clamp (2...

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 a robot multi-style calligraphy copy method based on force sense learning, and belongs to the field of control and application of industrial robots. The robot includes a multi-style standard word library module, a calligraphy style recognition module, a stroke information extraction module, and a robot joint trajectory planning module. The robot multi-style calligraphy copymethod extracts the characteristics of different calligraphy styles by collecting force signals, the calligraphy styles are learned by using the convolutional neural network, the stroke information isobtained by using an image processing algorithm, and the force features and stroke information of the corresponding style are converted into the end trajectory of the robot. By means of the robot multi-style calligraphy copy method, through the imitation learning of several standard words, under the premise of retaining the style characteristics of the original work, the purpose that the robot copies the input calligraphy image is achieved.

Description

technical field [0001] The invention relates to the field of robot trajectory planning, and more specifically, relates to a robot multi-style calligraphy copying method based on force sense learning. Background technique [0002] Calligraphy is the most important part of traditional Chinese art, and the importance of its inheritance and development is self-evident. However, with the advancement of intelligent manufacturing and the rapid development of robot technology, industrial robots, as a multi-degree-of-freedom mechanical device oriented to the industrial field, can be programmed and automatically perform specific actions. In recent years, they have been widely used in production. Spraying, welding, milling and other work in relatively harsh environments have a wide range of application prospects. At present, the calligraphy robot only uses image analysis to plan the trajectory of the robot, without considering the influence of the pen force on the calligraphy effect. ...

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 Patents(China)
IPC IPC(8): B25J9/16B25J15/00
CPCB25J9/1605B25J9/163B25J9/1664B25J9/1694B25J15/0019
Inventor 李明富刘真兴曾令城吴帆谢思晨
Owner XIANGTAN UNIV