Real-Time Laser Profile Edge Detection by Voting

Today, automobile and aircraft industry uses more and more robust and light-weight parts made of carbon fibres. To achieve high structural properties the carbon fibre mats are stitched in the preforming process using a sewing robot. The goal of this work is to develop an edge tracking system that continuously follows the seams. To work with the black and reflective carbon fibres a laser-scan sensor is used, though online processing of the range data for seamtracking remains a challenging task. The paper presents a fast and robust two-out-of-three voting image processing method to track the seam and to control the robot motion in realtime. The experimental results demonstrate the feasibility of the fully automated, sensor-guided robotic sewing process.