Robust Design is a statistical methodology based on the use of the information drawn from experiments on a physical prototype of a system to design (i.e. a product or a process). Many physical processes are so complex that it is difficult or even impossible to study them by conventional experimental methods. These limitations can be overcome by conducting simulated experiments (Computer Experiments) on a reliable and fast simulation model of the product or process. The combination of Robust Design and Computer Experiments can become a key methodology to sustain, in a systematic way, innovation in industrial design, while keeping cost under control. In this book new methodological developments for Robust Design using computer simulations are proposed. These methods have been successfully applied to the design of an optical profilometer, a device used for the high precision reconstruction of the micro-geometry of mechanical parts. The most important result is a significant improvement of the profilometer performance in terms of measurement uncertainty, speed and cost. The applied methodology can be profitably extended to other measurement systems/processes.