Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Mechanical arm action learning method and system based on third-person imitation learning

An action learning and third-person technology, applied in manipulators, program-controlled manipulators, manufacturing tools, etc., can solve problems such as increased learning costs and domain confusion, and achieve the effect of reducing the amount of calculation, reducing the impact, and speeding up the training process

Active Publication Date: 2020-05-12
NANJING UNIV
View PDF6 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method needs to add an additional type of demonstration data to achieve the purpose of domain confusion. This type of demonstration is generated in the demonstrator's domain using a random strategy.
The introduction of this type of demonstration also greatly increases the cost of learning

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
  • Mechanical arm action learning method and system based on third-person imitation learning
  • Mechanical arm action learning method and system based on third-person imitation learning
  • Mechanical arm action learning method and system based on third-person imitation learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] Below in conjunction with specific embodiment, further illustrate the present invention, should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention, after having read the present invention, those skilled in the art will understand various equivalent forms of the present invention All modifications fall within the scope defined by the appended claims of the present application.

[0035] The method for learning the action of a mechanical arm based on third-person imitation learning includes the following steps:

[0036] S1, the input demonstration sample τ E Only by observing the image sequence {o 1 ,o 2 ,o 3 ,...,o T} instead of the state-action sequence {s in traditional imitation learning 1 ,a 1 ,s 2 , a 2 ,...,s T-1 , a T-1 ,s T}. where T is the maximum time step, and o is the RGB image extracted directly from the video;

[0037] S2. The robotic arm execute...

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 mechanical arm action learning method and system based on third-person imitation learning. The method and system are used for automatic control of a mechanical arm so that the mechanical arm can automatically learn how to complete a corresponding control task by watching a third-party demonstration. According to the method and system, samples exist in a video form, and the situation that a large number of sensors are needed to be used obtaining state information is avoided; an image difference method is used in a discriminator module so that the discriminator module can ignore the appearance and the environment background of a learning object, and then third-party demonstration data can be used for imitation learning; the sample acquisition cost is greatly reduced; a variational discriminator bottleneck is used in the discriminator module to restrain the discriminating accuracy of a discriminator on demonstration generated by the mechanical arm, and the training process of the discriminator module and a control strategy module is better balanced; and the demonstration action of a user can be quickly simulated, operation is simple and flexible, and the requirements for the environment and demonstrators are low.

Description

technical field [0001] The invention relates to a method and system for learning a mechanical arm action based on third-person imitation learning, and belongs to the technical field of automatic learning of mechanical arm actions. Background technique [0002] The robotic arm is currently the most important actuator of the robot, and it is also the most widely used automatic mechanical device. Traditional robotic arm control needs to be realized based on motion planning programming. This method is highly complex, requires high professional knowledge and ability of the user, and has very low learning efficiency and intelligence. As the action tasks required by reality become more and more complex, the traditional manipulator action control system has been difficult to meet the needs of users. [0003] Imitation is the most direct and effective learning method for human beings to acquire motor skills. By watching other people's demonstrations, human beings can quickly learn t...

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
CPCB25J9/16B25J9/163
Inventor 章宗长俞扬姜冲
Owner NANJING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com