Robot assembly motion planning method based on demonstration trajectory

A technology of motion planning and robotics, applied in the direction of manipulators, program-controlled manipulators, manufacturing tools, etc., to achieve the effects of energy-saving assembly motion planning, solving strange phenomena, and reducing difficulty

Pending Publication Date: 2022-07-29
SICHUAN UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It aims to solve the problem of trajectory planning and control of robots in complex, time-varying, and unstructured environments

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 assembly motion planning method based on demonstration trajectory
  • Robot assembly motion planning method based on demonstration trajectory
  • Robot assembly motion planning method based on demonstration trajectory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of the present invention.

[0049] like figure 1 Shown is a schematic diagram of a motion planning system for the installation of electronic components. The system mainly includes actual assembly scene, multimodal sensor module and software algorithm module. The system provides functions such as data acquisition, data transmission, and assembly interaction for the method of the present invention, which is beneficial to the efficient execution of the method.

[0050] Among them, the actual assembly scene includes: PCB board, to-be-plugged-in, robot, workbench and human; the multi-modal sensor module includes: vision sensor, force-torque sensor, robot body sensor; the software module includes: demonstration learning module, Representation learning module and reinforcement learning module.

[0051] like figure 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 belongs to the field of robot autonomous assembly. The invention particularly relates to a robot assembly motion planning method based on a demonstration track. The method comprises the following steps: a robot demonstration learning stage: obtaining an assembly demonstration track of a robot, wherein the robot learns assembly operation skills based on the demonstration track; a multi-modal representation learning stage: the robot introduces noise and environment interaction by using an imitation learning strategy to obtain multi-modal data and labels, and learns the representation of the corresponding multi-modal data by fully considering the energy consumption and singularity of the robot in the movement process; and a robot reinforcement learning stage: building a robot trajectory planning reinforcement learning process based on the multi-modal representation and demonstration trajectory, and performing reinforcement learning training to obtain a final planning strategy. The method can be applied to a robot system which comprises a demonstration assembly track and needs to realize a flexible assembly task in an uncertain environment, and is used for improving the success rate and efficiency of the assembly task.

Description

technical field [0001] The invention belongs to the field of robot intelligent assembly, in particular to a robot assembly motion planning method based on a demonstration trajectory. Background technique [0002] With the rapid development of intelligent manufacturing, industrial robots with high precision, high speed and strong repeatability are widely used in industrial production. At present, the traditional control methods, such as PID control and impedance control, are a kind of compliant robot control method that uses a small amount of adaptive means to achieve a compliant robot along a preset trajectory. However, due to the machining error of parts, the complex contact state during assembly, the inherent mechanism in the robot assembly process and other factors, many robot assembly tasks require strong adaptive ability, and it is difficult to complete high-precision, multi-contact assembly only by traditional control methods. Task. [0003] In recent years, control ...

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): B25J9/16B25J9/00
CPCB25J9/1664B25J9/163B25J9/1694B25J9/161B25J9/0081
Inventor 汤卿裘方舟
Owner SICHUAN UNIV
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