Object Detection and Motion Planning for Automated Welding of Tubular\n Joints

2018/09/27 by Syeda Mariam Ahmed, Ahmed, Syeda Mariam, Yan Zhi Tan +7
Computer Science · Engineering · #FOS: Computer and information sciences #Robot Manipulation and Learning #Robotic Path Planning Algorithms #Robotics (cs.RO) #Robotics and Sensor-Based Localization #Welding Techniques and Residual Stresses

paper · pdf · doi:10.48550/arxiv.1809.10470

openalex publication_date 2018/09/27 · openalex created_date 2022/08/02 · openalex updated_date 2026/07/28

Abstract

Automatic welding of tubular TKY joints is an important and challenging task\nfor the marine and offshore industry. In this paper, a framework for tubular\njoint detection and motion planning is proposed. The pose of the real tubular\njoint is detected using RGB-D sensors, which is used to obtain a\nreal-to-virtual mapping for positioning the workpiece in a virtual environment.\nFor motion planning, a Bi-directional Transition based Rapidly exploring Random\nTree (BiTRRT) algorithm is used to generate trajectories for reaching the\ndesired goals. The complete framework is verified with experiments, and the\nresults show that the robot welding torch is able to transit without collision\nto desired goals which are close to the tubular joint.\n

Related

• The active visual sensing methods for robotic welding: review, tutorial and prospect
• A Point Cloud-Based Method for Automatic Groove Detection and Trajectory Generation of Robotic Arc Welding Tasks
• Intelligent robotic welding based on a computer vision technology approach
• Comparison of robot morphologies and base positioning for welding applications
• Path Planning with Automatic Seam Extraction over Point Cloud Models for Robotic Arc Welding