T oday, industrial painting automation with robots is very efficient and fast and often used in production lines. However, a big disadvantage is the off-line programming paradigm for the painting robots. This is time-consuming and can be justified economically only for large lot sizes. Hence, a totally new approach to robot programming is required to enable painting of small lot sizes. The objective of the FlexPaint project is to automate robot programming applications of small lot sizes with a very high number of part variants (http://www.flexpaint.org). Figure 1 gives an overview of the part variance used during the project in shape and size. A solution for this ambitious task was found in a close cooperation of researchers in academia and private institutions, together with engineers in small and large enterprises and even customer involvement. It was this close cooperation that made possible the start of a new paradigm for robot programming in industrial automation and, particularly, in painting applications. This article reports the new approach, referred to as an inverse approach, that automatically generates the painting motion. This approach opens new markets for robotic applications. The automatic robot program generation enables, for the first time, painting parts of a lot size of one. The principle of this new approach is based on formalizing the technological knowledge in a geometry library and a process library. Laser range sensors are used to obtain an accurate scan of the part. Process-relevant classes of features are detected as specified in the geometry library. Feature classes are linked in the process library to basic paint strategies, which are grouped to automatically generate the robot paint tool trajectory. Finally collisions-free and exe- cutable robot motions are automatically obtained for the actual robot kinematics. Painting results for several parts, e.g., different motors with gearboxes, will result with this new approach. An Inverse Approach to the Painting Process A method for flexible automation of small lot sizes in painting must fulfill strategic, economic, and financial objectives. Studying example cases within FlexPaint shows that target goals can be specified for typical applica- tions. The average human programming effort for robot painting should be reduced by 75%, and the human BY GEORG BIEGELBAUER, ANDREAS PICHLER, MARKUS VINCZE, CHRISTIAN L. NIELSEN, HENRIK JOHN ANDERSEN, AND KURT HAEUSLER 1070-9932/05/$20.00©2005 IEEE IEEE Robotics & Automation Magazine SEPTEMBER 2005 24 © 1996, 1997 DIGITAL STOCK The Inverse Approach of FlexPaint The Inverse Approach of FlexPaint Automatic Generation of Robot Painting Motions for Unknown Parts