A deep learning-based item recognition pre-sorting robot and its application method

A technology of deep learning and robotics, applied in manipulators, program-controlled manipulators, manufacturing tools, etc., can solve the problems of sorting robots without protection, single function, simple structure, etc., to improve stability, safety, and accuracy Effect

Active Publication Date: 2022-02-18
DONGGUAN BOTONG TECH SERVICE
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Most of the sorting robots currently on the market have simple structures and single functions. If the general sorting robot falls off during the process of picking up and transporting items, the sorting robot has no protective effect. Items will fall from the top of the sorting robot, and the general sorting robot encounters the phenomenon that the barcode on the item is not clear, and does not have the function of cleaning, which will lead to unclear scanning and recognition. Therefore, in view of the above problems, a A deep learning-based item recognition pre-sorting robot and its application method

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
  • A deep learning-based item recognition pre-sorting robot and its application method
  • A deep learning-based item recognition pre-sorting robot and its application method
  • A deep learning-based item recognition pre-sorting robot and its application method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] see Figure 1-5 , the present invention provides a technical solution:

[0025] An article recognition pre-sorting robot based on deep learning and its use method, comprising a robot mechanical part 6 and an identification part 7, the bottom end of the robot mechanical part 6 is fixedly connected to a base 4, and the left end of the base 4 is fixedly connected to a The controller 5, the other end of the mechanical part 6 of the robot is fixedly connected with a transition plate 8, the bottom end of the transition plate 8 is fixedly connected with a side plate 9, and the inner side of the side plate 9 is fixedly connected with an electric telescopic rod 10, The other end of the electric telescopic rod 10 is fixedly connected with a splint 11, one end of the splint 11 is provided with an article 12, one end of the transition plate 8 is fixedly connected with a protective support device 1, and the top end of the base 4 is fixedly connected with a A support frame 13, the i...

Embodiment 2

[0032] Embodiment 2 is no longer described in the same part as Embodiment 1. When the barcode on the article is cleaned through the identification part 7, the staff controls the third motor 203 to rotate backward with the turning block 204 through the controller 5, and simultaneously turns The block 204 will also rotate backwards with the cleaning brush 206 by the fourth motor 205 . , to ensure that the cleaning brush 206 will not affect the detection of the object 12 by the identification part 7 .

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 present invention relates to the technical field of sorting robots, in particular to a deep learning-based object recognition pre-sorting robot and its use method, including a mechanical part of the robot and a recognition part, the bottom of the mechanical part of the robot is fixedly connected to a base, and the The left end of the base is fixedly connected with a controller, the other end of the mechanical part of the robot is fixedly connected with a transition plate, the bottom end of the transition plate is fixedly connected with a side plate, and the inner side of the side plate is fixedly connected with an electric telescopic rod. The other end of the electric telescopic rod is fixedly connected with a splint. In the present invention, through the fixed block, the first motor, the gear, the gear ring, the limit frame, the telescopic rod, the first spring, the support plate and the ball, when passing through the splint When the item is picked up, the bottom of the item is supported by the gear ring with the support plate to ensure that when the item falls off before the splint, it will not fall to the ground under the action of the support plate, thereby improving the overall stability and security.

Description

technical field [0001] The invention relates to the technical field of sorting robots, in particular to a deep learning-based object recognition pre-sorting robot and a method of use thereof. Background technique [0002] A robot is a mechanical device that performs work automatically; robots can accept human commands, run pre-programmed programs, and act according to principles and programs formulated with artificial intelligence technology; the main tasks of robots are in production, construction, etc. industry, or other dangerous industries, to assist or replace human work, among which sorting robot is a kind of robot, sorting robot (Sorting robot) is a kind of robot equipped with sensors, objective lenses and electronic optical systems, which can Quickly sort the goods, and at the same time, the sorting robot needs to use the deep learning of the software to identify the items. [0003] Most of the sorting robots currently on the market have simple structures and single...

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 Patents(China)
IPC IPC(8): B25J11/00B25J9/10B25J9/16B25J15/08B25J19/00
CPCB25J11/00B25J9/10B25J9/102B25J15/08B25J19/00B25J9/16
Inventor 杜志尧
Owner DONGGUAN BOTONG TECH SERVICE
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