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

Method, robot and chip for vision robot to construct map

A robot and map technology, applied in the field of intelligent robots, can solve problems such as feature point matching errors, low displacement accuracy, and large map errors, and achieve the effects of reducing map errors, reducing feature matching errors, and improving displacement calculation accuracy

Active Publication Date: 2021-11-09
AMICRO SEMICON CORP
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the possible existence of periodic textures in the current environment, it may lead to feature point matching errors, which leads to low accuracy of calculated displacements, resulting in large errors in the constructed map.

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
  • Method, robot and chip for vision robot to construct map
  • Method, robot and chip for vision robot to construct map
  • Method, robot and chip for vision robot to construct map

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0021] In the existing robot positioning and map construction technology, in the process of drawing the map, it is necessary to obtain the image of the current environment, perform feature matching on the images before and after the displacement, and obtain the displacement of the robot according to the matching result. Since there may be periodic textures in the current environment, it may cause feature point matching errors, which will result in low accuracy of the calculated displacement, resulting in a large error in the constructed map.

[0022] In order to solve the disadvantage of relatively large errors in the constructed map, an embodiment of the present invention proposes a method for constructing a map by a vision robot, a robot and a chip. Wherein, the main solution of the method for constructing a map by ...

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 intelligent robots, and relates to a method for constructing a map by a visual robot, a robot and a chip. By acquiring photographed data, stripe pattern detection is performed on the photographed data; when it is detected that the photographed data contains a stripe pattern At the same time, a light spot of a preset shape is formed on the position corresponding to the stripe pattern by a laser irradiation device; the first picture frame and the second picture frame containing the light spot in the shooting data are obtained; for the first picture frame and performing feature extraction and feature matching with the second picture frame, so as to construct a map according to feature matching results. By reducing feature matching errors and improving the accuracy of displacement calculations, the effect of reducing map errors is achieved.

Description

technical field [0001] The invention relates to the technical field of intelligent robots, in particular to a method for constructing a map by a vision robot, a robot and a chip. Background technique [0002] With the development of robot technology, intelligent robots have been slowly participating in our daily life, and these intelligent robots generally have the function of positioning and navigation. The current mainstream robot positioning and mapping technology is SLAM (Simultaneous Localization And Mapping, real-time positioning and map construction), that is, in an unknown environment, let the robot draw a map of the current environment while moving. In the process of drawing the map, it is necessary to obtain the image of the current environment, perform feature matching on the images before and after the displacement, and obtain the displacement of the robot according to the matching result. Since there may be periodic textures in the current environment, it may c...

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): G01C21/32G01C11/02G01C11/04
CPCG01C11/02G01C11/04G01C21/32
Inventor 肖刚军赖钦伟
Owner AMICRO SEMICON CORP