Vision-force guided precise robotic assembly for 2.5D components in a semistructured environment

Abstract

Purpose Many manufacturing sites require precision assembly. Particularly, similar to cell phones, assembly at the sub-mm scale is not easy, even for humans. In addition, the system should assemble each part with adequate force and avoid breaking the circuits with excessive force. The purpose of this study is to assemble high precision components with relatively reasonable vision devices compared to previous studies. Design/methodology/approach This paper presents a vision-force guided precise assembly system using a force sensor and two charge coupled device (CCD) cameras without an expensive 3-dimensional (3D) sensor or computer-aided design model. The system accurately estimates 6 degrees-of-freedom (DOF) poses from a 2D image in real time and assembles parts with the proper force. Findings In this experiment, three connectors are assembled on a printed circuit board. This system obtains high accuracy under 1 mm and 1 degree error, which shows that this system is effective. Originality/value This is a new method for sub-mm assembly using only two CCD cameras and one force sensor.