Automatic 3D Seam Extraction Method for Welding Robot Based on Monocular Structured Light

Lu, Zhenfeng; Fan, Junfeng; Hou, Zhanxin; Deng, Sai; Zhou, Chao; Jing, Fengshui

doi:10.1109/jsen.2021.3076341

Cited by 29 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But the boundary points generated by the intersection of the triangular mesh and the slice were not uniform, as shown in FIGURE 9(a). To generate a uniform contact point trajectory, this paper used the B-spline curve interpolation represented by (7) to fit the point set. The basis function of the curve is:…”

Section: ) Seed Curve Generationmentioning

confidence: 99%

See 1 more Smart Citation

Research on Point Cloud Processing and Grinding Trajectory Planning of Steel Helmet Based on 3D Scanner

Meng,

Jiang,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

As the continuous expansion of robot grinding objects, the traditional manual teaching and offline programming methods can no longer meet people's requirements for grinding trajectories. With the help of a 3D scanner, model data can be acquired quickly and accurately, which facilitates trajectory planning and effective grinding for workpieces. In this paper, a point cloud hole repair method is proposed based on B-spline surface. It integrates point cloud segmentation, feature point removal, smoothing and hole repair, aiming to solve the hole problem in steel helmet scanning. In addition, to generate a uniform grinding trajectory, a planning method is proposed based on an improved B-spline curve. This method combines curve homogenization with equidistant offset and uses k-nearest neighbor search. Iteratively identify and eliminate unreliable point data to determine the best point of contact. The effectiveness of the two methods is verified by trajectory planning on three types of steel helmets.INDEX TERMS Robotic grinding, point cloud processing, holes repairing, trajectory planning, posture optimization.

show abstract

Section: ) Seed Curve Generationmentioning

confidence: 99%

“…(2) The normal of the tool and the contact area is collinear. The common grinding trajectory planning methods are manual teaching, offline and online programming [7]. The manual teaching process is complex and inaccurate, and it is only suitable for simple working scenarios.…”

Section: Introductionmentioning

confidence: 99%

Research on Point Cloud Processing and Grinding Trajectory Planning of Steel Helmet Based on 3D Scanner

Meng,

Jiang,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…With the advancement of machine learning and computer vision, visual sensors are increasingly being applied in robotic automated welding [3,4]. How to make use of visual sensors and design intelligent visual algorithms for identification and localization has become a key and inevitable trend in achieving autonomous and intelligent welding robots [5,6].…”

Section: Introductionmentioning

confidence: 99%

Initial point positioning of weld seam and robot pose estimation based on binocular vision

Ye,

Yao,

Ran

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

In order to rapidly identify and locate the weld seam initial point in robotic automated welding, we established a binocular vision system and proposed a weld seam initial point localization algorithm named WIPL-Net. Built upon the Fully Convolutional One-Stage (FCOS) object detection network, WIPL-Net introduces a lightweight ResNext as its backbone network and incorporates channel attention and enhanced feature fusion mechanisms to enhance feature detection and extraction capabilities. Subsequently, WIPLNet is utilized to obtain the weld seam's initial point, and its three-dimensional coordinates are determined through trigonometric measurements. To further estimate the robot's posture at the initial point, we performed sparse three-dimensional reconstruction of the local region centered on the weld seam initial point based on You Only Look At Coefficients of Tensors (YOLACT) instance segmentation and feature point matching. Finally, we conducted comparative experiments on WIPL-Net and conducted weld seam initial point localization experiments in real welding scenarios. The results demonstrate that our proposed method achieves a positioning error of less than 1.2 mm for the weld seam's initial point and a pose error of less than 10 degrees for the robot, meeting the requirement for real-time positioning of the weld seam's initial point.

show abstract

“…Three-dimensional (3D) reconstruction sensor based on structured light has been widely used in industry because of its advantage of non-contact and convenience [1][2][3]. By utilizing the camera to capture images of the structured light modulated by the object and utilizing corresponding demodulation algorithms in conjunction with intrinsic and extrinsic parameters calibrated in advance, the geometric information of the object can be acquired.…”

Section: Introductionmentioning

confidence: 99%

Surface structured light sensor with simultaneous color mapping

Yuan

Kang

Feng

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

To obtain geometric information and color texture simultaneously, a surface structured light sensor consisting of a monochrome camera, a color camera, and a projector is proposed. The sensor uses a color camera to acquire surface color information while using it as a geometric measurement unit and matching with the monochrome camera to obtain geometric information. Due to the Bayer array and demosaicing algorithm of the color camera, pixel RGB components are always coupled with interference from other channels. However, existing color de-crosstalk in reconstruction is merely applied to the decoupling of color composite patterns, ignoring the intensity errors present in color fringe patterns under monochrome illumination. In our sensor, de-crosstalk of monochromatic patterns is considered to guarantee the reconstruction accuracy. The high-accuracy measurement of the sensor is validated by reconstructing standard steps, yielding a mean absolute error of 0.008 mm for distance measurements. In addition, the reconstruction experiment of a terracotta warrior verifies that the proposed sensor has potential application in the digital preservation of cultural relics.

show abstract

Automatic 3D Seam Extraction Method for Welding Robot Based on Monocular Structured Light

Cited by 29 publications

References 27 publications

Research on Point Cloud Processing and Grinding Trajectory Planning of Steel Helmet Based on 3D Scanner

Research on Point Cloud Processing and Grinding Trajectory Planning of Steel Helmet Based on 3D Scanner

Initial point positioning of weld seam and robot pose estimation based on binocular vision

Surface structured light sensor with simultaneous color mapping

Contact Info

Product

Resources

About