Detection of screws on metal ceiling structures for dismantling systems

Abstract

In the dismantling works of office interiors for renewal, a robotic system is needed in order to assist the human workers engaged in this kind of job. Regarding to the items in the ceiling side, after a dismantling task of the ceiling boards, it is necessary to remove the screws that once held these boards to the Light Gauge Steel (LGS) with the purpose of reusing. At first, the paper presents the method to measure the 3D pose of the LGS. Thus the control system generates a trajectory under and near of that metal ceiling structure to measure the screws more precisely. The trajectory is followed for a robot arm which includes an eye-in-hand system. During the motion, the screws are detected by applying a template matching process to every single captured image. The detection of targets is tested under different lighting conditions and the effect of the number of images per meter is analyzed.