Surface modeling and robot path generation using self-organization

Abstract

A tree-structured variant of the self-organizing map provides an elegant solution for automated surface processing with a robot, e.g. for painting, coating or sandblasting. Given a set of data points in arbitrary order from the object surface, the self-organizing map can be used to generate a tool path that is both smooth and covers the object with equal areas. Input data may come from a laser measurement system, CAD model, digital camera, and human assisted object digitizing system. The proposed solution is reliable and easy to implement, and thus good alternative for costly manual training of a robot.