조선 중공업 환경 내 자율 용접 작업 경로 추출을 위한 특징 형상 인식 기법

Abstract

Many research and development for the autonomous welding have been progressed. It is necessary to extract trajectory lines from the workpieces for welding automation, and various sensors such as laser sensors have been studied. In this study, we propose a vision-based guidance line extraction method for autonomous welding robot systems. The proposed method uses a series of image processes for extracting welding trajectory data. To verify our method, we constructed test beds based on CAD data in heavy industries and conducted several experiments. These experiments confirmed the applicability of our method, which has advantages in terms of speed and cost for automatic welding in heavy industries.