Supercharge Your Innovation With Domain-Expert AI Agents!

Learning type robot action data collection method

A motion data, robot technology, applied in the direction of electrical digital data processing, special data processing applications, digital data information retrieval, etc.

Pending Publication Date: 2019-05-03
李强
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Based on the narrowness of the current learning robot's action data collection and the limitations of the fixed scene, the purpose of the present invention is to provide a more comprehensive and shortcut robot action data collection method, which can effectively break through the current learning robot. The limitations of the robot's motion data collection method break the fixed scene mode

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
  • Learning type robot action data collection method
  • Learning type robot action data collection method
  • Learning type robot action data collection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Step S1: Through design, it is determined that the main learning robot is a natural human appearance, which is highly dependent on its functional nature and scope.

[0030] Step S2: Set the sphere person

[0031] All actions of a natural person must be within a sphere whose diameter is the height of the natural person's standing posture and whose radius is greater than the maximum range and distance of all actions of the natural person. Based on this, the natural person in the sphere is designed as a sphere person. It is suggested that the appearance characteristics of the first type of spherical person be the same as that of the main robot, and the other types of spherical persons are determined according to the appearance characteristics of various natural persons in society. Therefore, when designing the appearance characteristics of a spherical person, the appearance characteristics of all natural persons must be designed.

[0032] Step S3: Set the sphere data of the...

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

Learning type robot action data collection is one of key factors for robots to learn external action skills in the field of artificial intelligence. The invention provides a learning type robot actiondata collection method, a body learning robot learns external demonstrator actions through a preset sphere person stored in a database of the body learning robot. The method comprises the steps thatsphere person and sphere data are preset; according to actions of various natural persons, action data of various sphere bodies are preset; and difference between the body learning robot and the sphere body of the body learning robot is adjusted. Then, the body learning robot is used for selecting the sphere body matched with a demonstrator, through the process of learning of all actions of the demonstrator, action data of the demonstrator are recorded and then further converted into action data of the body learning robot of the demonstrator, and the action data of the body learning robot areconverted into actions of the body learning robot through computer programmed programming.

Description

technical field [0001] The invention relates to an aspect based on artificial intelligence: a method for collecting motion data of a learning robot. Background technique [0002] Body movements are one of the key factors in the process of learning external knowledge and skills for learning robots. Based on the narrowness of the current learning robot's action data collection and the limitations of the fixed scene, the purpose of the present invention is to provide a more comprehensive and shortcut robot action data collection method, which can effectively break through the current learning robot. The limitations of the robot's motion data collection method break the fixed scene mode. Contents of the invention [0003] The purpose of the present invention is to solve one of the technical defects of the limitations of the learning robot's action data collection during learning. In order to realize this object, the present invention provides a kind of method based on learni...

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): B25J19/00G06F16/00G06K9/00
Inventor 李强
Owner 李强
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com