A welding robot positioning method and system based on visual feature matching

By constructing an adaptive response threshold and improving the SuperPoint algorithm, and combining texture complexity and regional importance, the problem of insufficient feature points in the weld seam region was solved, enabling high-precision autonomous positioning and stable welding of the welding robot.

CN122391367APending Publication Date: 2026-07-14SHAANXI YATE ELECTRIC CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SHAANXI YATE ELECTRIC CO LTD
Filing Date
2026-06-11
Publication Date
2026-07-14

AI Technical Summary

Technical Problem

Existing visual feature matching technology cannot effectively extract feature points of key areas of the weld in welding robot positioning, resulting in failure of 3D pose estimation and deviation of welding trajectory, which affects welding quality.

Method used

By constructing an adaptive response threshold and combining texture complexity spatial heterogeneity and regional importance, the feature point screening threshold of the weld region is dynamically adjusted to accurately capture the spatial location of the weld. This improves the SuperPoint algorithm to enhance the accuracy and balance of feature point acquisition.

Benefits of technology

Improving the autonomous positioning accuracy and stability of welding robots under complex working conditions ensures that the welding torch is accurately aligned with the weld start point, reduces welding trajectory deviation, and improves welding quality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122391367A_ABST
    Figure CN122391367A_ABST
Patent Text Reader

Abstract

The present application relates to the technical field of image processing, and more particularly, to a welding robot positioning method and system based on visual feature matching, comprising: acquiring an image containing a weld and depth data, and dividing the image into multiple grid units after preprocessing; calculating the texture complexity spatial differentiation degree of each grid unit, which comprehensively considers the gradient intensity and direction diversity of pixels in the local area, and is used to quantify and distinguish the richness of texture in the image. The present application constructs an adaptive response threshold, and through this method, the extraction threshold of the weld area with extremely high positioning contribution but weak texture can be dynamically adjusted, effectively solving the problems of lack of key area feature points and imbalance of spatial distribution, thereby ensuring the high precision and high stability of the welding robot in complex and harsh working conditions.
Need to check novelty before this filing date? Find Prior Art