Live working cross arm angle steel recognition method and device based on point cloud

CN115375895BActive Publication Date: 2026-06-19YIJIAHE TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
YIJIAHE TECH CO LTD
Filing Date
2022-08-23
Publication Date
2026-06-19

AI Technical Summary

Technical Problem

In live-line working robots, existing technologies struggle to accurately detect the position and orientation of crossbeam angle steel under conditions of strong light interference and uneven angle steel surfaces, resulting in large errors in point cloud data and affecting operational accuracy.

Method used

A method combining LiDAR and RGBD camera is adopted. LiDAR is used for global modeling and coarse localization, while RGBD camera is used for precise acquisition and preprocessing of point cloud data. The RANSAC plane fitting algorithm is then used for fine localization of angle steel, thereby improving detection accuracy.

Benefits of technology

It enables high-precision identification of the position and orientation of crossbeam angle steel in environments with strong light interference and uneven angle steel planes, improving the operational reliability and identification accuracy of the live-line working robot.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115375895B_ABST
    Figure CN115375895B_ABST
Patent Text Reader

Abstract

The method and device for identifying crossarm angle steel in live-line working based on point cloud technology employs two sensing sensors: LiDAR and RGBD camera. First, LiDAR acquires global point cloud data of the working scene for coarse positioning of the angle steel. Then, based on the coarse positioning results, the RGBD camera collects point cloud data of the crossarm angle steel to complete fine positioning. In implementation, the live-line working robot first acquires global scene data through sliding scan of LiDAR. After obtaining coarse positioning data for the crossarm, the robot arm is controlled to reach the angle steel position to collect point cloud data for precise identification of the crossarm. Finally, the appropriate working tools are called to perform the work at the precise location.
Need to check novelty before this filing date? Find Prior Art