Range imaging and visual servoing for industrial applications

High-tech systems play a key role in Printed Circuit Board (PCB) manufacturing. Two of these systems are presented in this thesis. The first system is range imaging, which is a measuring technique for determining three-dimensional shape. The second system is visual servoing, which is a method of adaptively controlling a mechanical system by acting upon measurements done with a computer vision system. Range imaging is used for quality inspection of the PCB during and after the manufacturing process. Visual servoing is used to quickly and accurately guide a component placement robot to the correct position on a PCB. The Position Sensitive Device (PSD) range imaging sensor is discussed in detail. Ways of calibrating such sensors are discussed; lens parameters are calibrated using the requirement that straight lines must be straight and sensor geometry is calibrated independently from the lens parameters. A discussion is given on predicting sensor artifacts, i.e. systematic errors that occur under specific circumstances. Recommendations for designing and using PSD range imaging sensors are given. Furthermore, the design and implementation of a vision-guided component placement robot is discussed. A general design for the entire component placement system is given, in which speed and accuracy are the two main design requirements. A design for the vision software is given; the software includes an offline (preparatory) part and an online (real-time) part. The offline part uses a CAD description of the PCB to compose a set of fast image processing operations. The online (real-time) part executes this set of operations to guide the component placement robot to the correct position within a very small time. Requirements for a vision sensor for the application are drawn up, and a particular sensor is proposed. Implementation details and experimental results of a working prototype of the designed component placement robot are presented.Applied Science