Robot teaching reproduction track learning method

A learning method and robot technology, applied in manipulators, program-controlled manipulators, manufacturing tools, etc., can solve problems such as increasing the computational burden of the system, and achieve the effect of improving convergence accuracy and convergence speed

Pending Publication Date: 2021-06-29
JIANGSU UNIVERSITY OF TECHNOLOGY
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method can only be applied when the number of teaching points is small, otherwise it will be time-consuming and increase the computational burden of the system

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 teaching reproduction track learning method
  • Robot teaching reproduction track learning method
  • Robot teaching reproduction track learning method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0071] refer to Figure 1 to Figure 9 , a robot teaching reproduction trajectory learning method, comprising the following steps:

[0072] Step1: Record and save the end position trajectory, velocity trajectory, acceleration trajectory and sampling time after the robot is taught;

[0073] Step2: Establish a standard position dynamic motion primitive model;

[0074] Step3: Establish an improved position dynamic motion primitive model based on the virtual point potential field function;

[0075] Step4: Based on the local weighted regression method, the teaching trajectory is learned and generalized.

[0076] Preferably, in Step1, the teaching trajectory at the end of the robot Collected by the direct teaching system of the robot, and filtered by the system to obtain a continuous and smooth trajectory, which is defined as:

[0077]

[0078] in, Respectively represent the position, velocity and acceleration of the teaching trajectory at the end of the robot; t k is the ...

Embodiment 2

[0125] A robot teaching reproduction trajectory learning method, including: firstly record and save the terminal position trajectory, velocity trajectory, acceleration trajectory and sampling time after the robot teaching; establish a standard position dynamic motion primitive model; establish a virtual point potential field function based The position dynamic motion primitive model is improved; finally, the learning generalization of the teaching trajectory is carried out based on the local weighted regression method.

[0126] 1. Record and save the teaching trajectory at the end of the robot

[0127] Teaching trajectory at the end of the robot It can be collected by the robot’s direct teaching system and filtered by the system to obtain a continuous and smooth trajectory, which is defined as:

[0128]

[0129] in, Respectively represent the position, velocity and acceleration of the teaching trajectory at the end of the robot; t k is the sampling time; k is the sam...

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 teaching reproduction track learning method. According to the technical scheme, the robot teaching reproduction track learning method is characterized by comprising the following steps of: step 1, recording and storing a tail end position track, a speed track, an acceleration track and sampling time after robot teaching; step 2, establishing a standard position dynamic motion primitive model; step 3, establishing an improved position dynamic motion primitive model based on a virtual point potential field function; and step 4, learning the teaching track based on a local weighted regression method. According to the robot teaching reproduction track learning method, a virtual clamp method and a Gaussian kernel function are used for reference, and a virtual point attraction potential field function is established for a small number of data point positions in the teaching track and are coupled into a standard position dynamic motion primitive conversion system function through feedback. Compared with an original virtual clamp method, the improved position dynamic motion primitive model does not need to establish a potential field function for each teaching point, and therefore the convergence precision and convergence speed of the output track of the position dynamic motion primitive can be effectively improved.

Description

technical field [0001] The invention relates to the field of robot trajectory learning, in particular to a method for learning robot teaching and reproduction trajectory. Background technique [0002] At present, although industrial robots can significantly improve the efficiency of industrial manufacturing, they still require precise programming, and each task is broken down into a series of actions. This method cannot gain experience from task learning and is not flexible. If the end task of the robot changes slightly, the robot control system needs to be reprogrammed, which reduces the robot programming efficiency and robot adaptability. Demonstration programming, that is, direct teaching, seems to be a very effective solution to this problem. During the direct teaching process, the robot records the end-task trajectory based on the operator's dragging motion. The dynamic system is often used to learn the demo trajectory recorded by the generalized robot, that is, given...

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): B25J9/00B25J9/16
CPCB25J9/0081B25J9/1605B25J9/1664Y02P90/02
Inventor 万俊张兰春葛敏
Owner JIANGSU UNIVERSITY OF TECHNOLOGY
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