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

Robot rapid assembly method and system based on near-end strategy optimization algorithm

An optimization algorithm and assembly method technology, applied in manipulators, program-controlled manipulators, manufacturing tools, etc., can solve the problems of fast and accurate assembly of robots, difficulty in reward function, difficulty in parameter selection, etc., and achieve good sample complexity and generalization. The effect of improving the generalization ability, improving the generalization ability, and improving the robustness

Active Publication Date: 2022-01-28
SHANDONG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The general learning method has very high requirements on the learning rate. If the learning rate is too high or too low, the training will fail, and the establishment of the reward function is also very sensitive to changes in the environment. It is very difficult to design a suitable reward function.
[0006] The problems caused by the above-mentioned assembly are: the general learning method cannot realize the fast and accurate assembly of the robot, and the selection of various parameters in the learning process is very difficult

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 rapid assembly method and system based on near-end strategy optimization algorithm
  • Robot rapid assembly method and system based on near-end strategy optimization algorithm
  • Robot rapid assembly method and system based on near-end strategy optimization algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] This embodiment discloses a robot rapid assembly system based on a proximal strategy optimization algorithm, such as figure 1 As shown, it consists of a six-dimensional force sensor at the end of the robotic arm, a host computer, a robotic arm, and complex assembly objects (electronic connectors such as USB and VGA). The six-dimensional force sensor is used to obtain the force and moment at the end of the manipulator, and feed back the force information to the host computer training network. The robotic arm is the main actuator, which is used to execute the actions output by the network. The assembly object is the main part of the physical contact environment, and the assembly strategies of different assembly objects are different. The upper computer trains the proximal strategy optimization algorithm network according to the status information fed back by the robot and the force sensor, and builds a fuzzy reward system.

[0036] The above fuzzy reward system consists...

Embodiment 2

[0039] The purpose of this embodiment is to provide a robot rapid assembly method based on the proximal strategy optimization algorithm, including:

[0040] Control the manipulator to search for holes in a spiral, and judge whether the hole position is found. If so, obtain the current state and send it to the proximal strategy optimization algorithm network. The proximal strategy optimization algorithm network outputs the action command of the manipulator. hole assembly until the assembly is complete.

[0041] When the mechanical arm performs socket assembly based on the received instruction, it also performs fuzzy logic processing based on the obtained current state to obtain impedance parameters, and performs socket assembly based on the impedance parameter and the received instruction.

[0042] According to the proximal strategy optimization algorithm and combined with fuzzy logic, the present invention proposes a method capable of quickly assembling the shaft hole. This m...

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 rapid assembly method and a system based on a near-end strategy optimization algorithm. The robot rapid assembly system comprises a force detection unit, a mechanical arm and a control system. The force detection unit is used for acquiring force information of the tail end of the mechanical arm and feeding back the force information to the control system; the control system is used for inputting a training near-end strategy optimization algorithm network according to the posture of the mechanical arm and the assembling force / torque of the tail end of the mechanical arm as states, the network is used for outputting an action value needed by the mechanical arm, and the mechanical arm is controlled to conduct shaft hole assembling based on the action value. The near-end strategy optimization algorithm enhances the utilization efficiency of the data, the learning rate does not need to be set, and the method has better sample complexity and generalization ability.

Description

technical field [0001] The invention belongs to the technical field of robot assembly, and in particular relates to a method and system for rapid robot assembly based on a proximal strategy optimization algorithm. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] In robotic assembly operations, due to the complexity of the assembly model and the changing environment, the usual assembly strategies are not accurate and have poor adaptability to different assembly environments. There are mainly two approaches to robotic assembly operations, model-based assembly and model-free assembly. [0004] Model-based assembly performs robotic assembly by establishing an accurate environmental contact model, but in actual industrial scenarios, factors such as noise interference, variable environments, complex shapes of assembled objects, and heterogeneous...

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): B25J9/16B25J18/00B25J19/00
CPCB25J9/1679B25J18/00B25J19/007Y02P90/02
Inventor 宋锐门渔李凤鸣靳李岗王艳红
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