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

Robot control method, controller and system based on layered thread framework

A control method and robot technology, applied in the direction of program-controlled manipulators, comprehensive factory control, manipulators, etc., can solve the problems of long training time and high cost, and achieve the effects of improving training efficiency, reducing workload, and good robustness

Active Publication Date: 2019-11-01
SHANDONG UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, non-experts on the shop floor are required to complete the reprogramming to produce different products
[0004] The inventor found that simply using deep learning and other methods to complete the training of the robot requires a long training time, or a high-cost training case

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 control method, controller and system based on layered thread framework
  • Robot control method, controller and system based on layered thread framework
  • Robot control method, controller and system based on layered thread framework

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] The scene of the robot control method based on the layered thread framework of this embodiment also includes a vision system and a robot motion control system, wherein both the vision system and the robot motion control system are existing structures.

[0039] For example: the vision system can be implemented with industrial cameras;

[0040] The robot motion control system includes the driving device, the mechanical arm, the industrial computer and the workbench.

[0041] The scenario of this embodiment is as figure 1 As shown, the process of realizing the assembly operation is as follows figure 2 As shown, the industrial camera guides the manipulator to the initial position specified in the assembly experiment, and then the manipulator performs the assembly operation, stores the experience pool samples, and then trains the network parameters, and uses the action output by the network as the input of the control system to adjust the movement of the manipulator, there...

Embodiment 2

[0063] like Figure 5 As shown, a robot controller based on a layered thread framework of the present embodiment includes:

[0064] (1) Assembly initial position determination module, which is used to determine the target workpiece pose, and guide the mechanical arm to move directly above the workpiece as the initial assembly position;

[0065] (2) Assembly task decomposition module, which is used to call the assembly task to be completed in the task layer, and then determine the corresponding skill in the skill layer associated with the assembly task and the assembly state parameter in the primitive language layer associated with the corresponding skill;

[0066] (3) a network initialization module, which is used to declare the main network and multiple threads and initialize network parameters; threads include acquisition threads and training threads; the number of training threads is equal to the number of skills associated with the assembly task;

[0067] The main network...

Embodiment 3

[0078] A robot control system based on a layered thread framework, including the above Figure 5 The robot controller based on the hierarchical threading framework is shown.

[0079] In this embodiment, assembly tasks, skills, and assembly states are stored hierarchically in the task layer, skill layer, and primitive layer, and the main network and multiple threads are declared, and the threads include acquisition threads and training threads; the number of training threads is related to the assembly The number of skills associated with tasks is equal; multiple threads do not interfere with each other, which can improve update convergence and reduce correlation compared with previous networks.

[0080] In this embodiment, a collection sample thread and multiple training threads are set up, which improves the training efficiency and reduces the total training time.

[0081] This embodiment takes robot skill learning into consideration, and is suitable for small-batch and multi...

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 control method, controller and system based on a layered thread framework. The method includes the steps that the pose of a target workpiece is confirmed, a mechanical arm is guided to move to the position over the workpiece, and the position is used as an assembly initial position; a to-be-completed assembly task in a task layer is acquired, and then a correspondingskill in a skill layer relevant to the assembly task and an assembly state parameter in a primitive layer relevant to the corresponding skill are confirmed; a main network and multiple threads are stated, and network parameters are initialized; the threads include the collecting thread and the training thread; assembly state parameter sample data relevant to the current assembly task are collected through the collecting thread and are stored in an experience pool, and till the sample number reaches the threshold value, the training thread is synchronously started, and the main network is renewed; the action of a mechanical arm is adjusted through the result output by the renewed main network, whether the assembly task is completed or not is judged, and if the assembly task is completed, assembly is finished; and otherwise, the process returns, and the training thread continues to be executed till the assembly task is completed.

Description

technical field [0001] The disclosure belongs to the field of robot control, and in particular relates to a robot control method, controller and system based on a layered thread framework. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] At present, the manufacturing industry is increasingly shifting from mass production to mass production, which promotes the production system to handle more product changes, shorter production cycles and smaller batches. This transformation requires a new type of soft robot to cope with the uncertainty in production so as to adapt to the new industrial environment. At the same time, non-experts on the shop floor are required to complete the reprogramming to produce different products. [0004] The inventors found that simply using deep learning and other methods to complete the training of the robot requ...

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 Applications(China)
IPC IPC(8): B25J9/16
CPCB25J9/1602B25J9/1687B25J9/1697Y02P90/02
Inventor 宋锐权威李凤鸣李贻斌姬冰
Owner SHANDONG 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