Control system for motion control of a piezoelectric micromanipulation robot

Micromanipulation by microrobots has become an issue of primary importance in industry and biomedicine, since human manual capabilities are restricted to certain tolerances. The manipulation of biological cells or the assembl y of a microsystem composed of several microcomponents are good examples. A n automated microrobot-based micromanipulation desktop station has been dev eloped at the University of Karlsruhe. The process of assembly takes place in the field of view of a light optical microscope. This paper focuses on m otion control problems of the piezo-driven microrobots employed by the stat ion. The ability to adapt itself to the process requirements is of great im portance for micromanipulation robots. They must be able to operate in a pa rtially defined environment and to ensure reasonable behavior in unpredicte d situations. A neural control concept based on a reference model is propos ed as a solution. It is shown that the neural controller is able to learn t he desired behavior. It considerably outperforms an analytically designed l inear controller in the real environment.