Unlock instant, AI-driven research and patent intelligence for your innovation.

Robot micro-assembly grabbing system based on deep reinforcement learning

A reinforcement learning and robotics technology, applied in the field of robotics, can solve the problems of complex surface contours of workpieces, inability to grasp system grasping, and difficult assembly.

Pending Publication Date: 2021-09-21
DONGGUAN UNIV OF TECH
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, in the existing technology, there are many workpieces with complex surface contours, especially in the field of micro-assembly with a small assembly scale, which cannot be grasped by conventional grasping systems, which makes assembly difficult. Therefore, we propose a method based on Robotic Micro-assembly Grasping System Based on Deep Reinforcement 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
  • Robot micro-assembly grabbing system based on deep reinforcement learning
  • Robot micro-assembly grabbing system based on deep reinforcement learning
  • Robot micro-assembly grabbing system based on deep reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0045] refer to Figure 1-4, a robot micro-assembly grasping system based on deep reinforcement learning, including a surface detector and a substrate 1 set at the gripping end of the robot. The surface detector can identify the detailed outline of the workpiece surface. The substrate 1 is a disc-shaped structure. 1 is provided with an annular chute 2, and a plurality of sliders 3 are slidably connected in the chute 2, and each slider 3 is fixedly connected with a grasping plate 4, and the grasping plate 4 is provided with a groove 5. The groove 5 is connected with a screw 6 for rotation, the screw 6 is screwed with a sliding sleeve 7, and the end of the groove 5 away from the base plate 1 is provided with a positioning rod 8; the servo motor 31 works to drive the sliding sleeve 7 to move, and the thimble 9 moves with it. , and during the displacement process, the length of the metal spring 10 is changed by controlling the current flowing through the metal spring 10, thereby a...

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 robot micro-assembly grabbing system based on deep reinforcement learning. The robot micro-assembly grabbing system comprises a surface detector and a base disc arranged at a robot grabbing end; the surface detector can identify the detail contour of the surface of a workpiece; the base disc is of a disc-shaped structure; an annular sliding groove is formed in the base disc; a plurality of sliding blocks are connected into the sliding groove in a sliding mode; each sliding block is fixedly connected with a grabbing plate; a groove is formed in each grabbing plate; a threaded rod is rotationally connected into each groove; a sliding sleeve is connected to each threaded rod in a threaded mode; and a positioning rod is arranged at the end, away from the base disc, of each groove. The robot micro-assembly grabbing system has the advantages that after the characteristics of the workpiece are detected, a servo motor works to drive the sliding sleeve to move, the position of the tip of an ejector pin is adjusted, the ejector pin is made to move along the contour line of the workpiece according to a set program, the ejected electrorheological fluid moves along the trajectory, and the electrorheological fluid and the workpiece can be grabbed in a perfect fit mode only by selecting the local contour characteristics of the workpiece.

Description

technical field [0001] The invention relates to the field of robot technology, in particular to a robot micro-assembly grasping system based on deep reinforcement learning. Background technique [0002] With the continuous development of industrial automation, robots have been widely used in machining, assembly and handling. The application of robots has greatly improved product quality, reduced labor intensity, reduced labor costs and improved labor efficiency. [0003] However, in the existing technology, there are many workpieces with complex surface contours, especially in the field of micro-assembly with a small assembly scale, which cannot be grasped by conventional grasping systems, which makes assembly difficult. Therefore, we propose a method based on Robotic microassembly grasping system with deep reinforcement learning. Contents of the invention [0004] The purpose of the present invention is to solve the problems in the prior art, and propose a robot micro-as...

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): B25J15/10B25J15/00B25J9/16B25J19/02G06K9/00G06K9/62
CPCB25J15/10B25J9/163B25J9/1697B25J19/02B25J15/00B25J15/0076G06F18/2321G06F18/2411
Inventor 王福杰李超凡秦毅任斌郭芳胡耀华姚智伟
Owner DONGGUAN UNIV OF TECH