Object Detection and Motion Planning for Automated Welding of Tubular Joints

TL;DR

This paper presents a comprehensive framework for automated tubular joint welding that combines real-time detection, virtual mapping, and collision-free motion planning using advanced algorithms, verified through experimental validation.

Contribution

It introduces a novel integrated approach for detecting tubular joints and planning robot trajectories with collision avoidance, enhancing automation in marine and offshore welding.

Findings

Successful real-time detection of tubular joints using RGB-D sensors

Effective virtual environment mapping for precise positioning

Collision-free trajectory planning verified through experiments

Abstract

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