Assembly of Non-Standard Electrical Components Using Stereoscopic Image Processing Techniques

Abstract

Summary Although the assembly of standard, well defined, high volume electrical components into printed circuit boards is adequately handled using high speed automatic equipment, more irregular parts such as those found in Dower supply designs are not suited to such techniques. This paper outlines an approach to solving this problem using a robot to perform the insertion and a vision system to identify the precise location of the part being held in the robot's gripper. To enable the vision system to produce the required accuracy, the camera has to be located close to the component being held by the robot. The design of a low cost, miniature, lightweight image sensor to accomplish this objective is outlined together with its interfacing to a small computer. Using this system, together with a camera model based on the pinhole concept, both the forward and inverse object/image transformations may be defined. Although the missing depth information is not available directly from the inverse camera transformation, it may be calculated using stereoscopic (triangulation) type image processing techniques. A novel approach to generating the data for this process is outlined. Finally experimental tests comparing the estimated position of the leads of a large capacitor with those by direct measurement are presented. It is concluded that sufficient accuracy is available to complete insertion.