Extraction of Weld Seam in 3D Point Clouds for Real Time Welding Using 5 DOF Robotic Arm

Welding involves the union of two workpiece halves along a common edge of interface, also called as the weld seam. In this paper a novel algorithm has been proposed which is independent of the shape of the workpiece to classify and extract weld seams from 3D point clouds. The real time tracking of the weld seam is also demonstrated on a 5 axis robotic manipulator. The aim was to eliminate the need for manual computation of the robot trajectory and also ensure that the overall pipeline is computationally efficient. The two workpiece halves have been clustered into different point clouds and the edge of interface on either of the halves has been specified using the centroid shift method. The precision recall metrics of our algorithm were very close to the ideal values on any shape of the weld seam. Singularity avoidance, trajectory planning, kinematics of the robotic manipulator is beyond the scope of this paper.

[1]  Jan Dirk Wegner,et al.  Contour Detection in Unstructured 3D Point Clouds , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Vijay V. Raghavan,et al.  A critical investigation of recall and precision as measures of retrieval system performance , 1989, TOIS.

[3]  Reinhard Klein,et al.  Efficient RANSAC for Point‐Cloud Shape Detection , 2007, Comput. Graph. Forum.

[4]  Hans Hagen,et al.  Sharp feature detection in point clouds , 2010, 2010 Shape Modeling International Conference.

[5]  George Chryssolouris,et al.  MACHINING WITH ROBOTS: A CRITICAL REVIEW , 2011 .

[6]  V. Kalaichelvi,et al.  Performance Evaluation of Digital Image Processing and Artificial Neural Networks for Weld Line Detection of Robotic Manipulator , 2017, 2017 9th IEEE-GCC Conference and Exhibition (GCCCE).

[7]  Xiao Lin.  3 D Point Cloud Segmentation Using a Fully Connected Conditional Random Field , 2017 .

[8]  Henrik I. Christensen,et al.  RGB-D edge detection and edge-based registration , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[9]  Markus Vincze,et al.  Fast and accurate normal estimation by efficient 3d edge detection , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[10]  Tao Lin,et al.  Robot welding seam tracking method based on passive vision for thin plate closed-gap butt welding , 2010 .

[11]  R. Karthikeyan,et al.  Real-Time Tracing Of A Weld Line Using Artificial Neural Networks , 2018, 2018 IEEE/ACIS 17th International Conference on Computer and Information Science (ICIS).

[12]  Morgan Quigley,et al.  ROS: an open-source Robot Operating System , 2009, ICRA 2009.

[13]  Chee-Meng Chew,et al.  Object detection and motion planning for automated welding of tubular joints , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[14]  Abdullah Al Mamun,et al.  Edge and Corner Detection for Unorganized 3D Point Clouds with Application to Robotic Welding , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[15]  Zhang Hua,et al.  Study of robot seam tracking system with laser vision , 2009, 2009 International Conference on Mechatronics and Automation.

[16]  Xiangguo Lin,et al.  Edge Detection and Feature Line Tracing in 3D-Point Clouds by Analyzing Geometric Properties of Neighborhoods , 2016, Remote. Sens..

[17]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[18]  Radu Bogdan Rusu,et al.  3D is here: Point Cloud Library (PCL) , 2011, 2011 IEEE International Conference on Robotics and Automation.