Development of Seam Tracking Sensor in ROS Environment

Abstract

Seam tracking sensors are critical for improving the accuracy and adaptability of robotic welding systems. In this study, a vision-based seam tracking sensor was developed and simulated entirely within the Robot Operating System (ROS) and Gazebo environment. A structured light sensor, consisting of a line laser and a camera, was modeled to detect weld seam positions through laser triangulation. Real-time image processing algorithms were implemented to extract seam coordinates, while trajectory planning and motion control modules enabled the Cartesian robot to dynamically adjust its path during operation. The developed system architecture ensured synchronized communication between sensor data acquisition and robot control layers. Simulation results demonstrate that the proposed system achieves accurate and responsive seam tracking under varying seam deviations. The study highlights the potential of simulation-driven development for validating sensor designs and control strategies in a risk-free and cost-effective manner before physical deployment. © 2025 IEEE.