Development of a neural controller for motion control of a piezoelectric three-legged 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 assembly of a microsystem composed of several microcomponents are good examples. An automated microrobot-based micromanipulation desktop station has been developed 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 motion control problems of the piezo-driven microrobots employed by the station. The ability to adapt itself to the process requirements is of great importance for micromanipulation robots. They must be able to operate in a partially defined environment and to ensure reasonable behaviour in unpredicted situations. A neural control concept based on a reference model is proposed as a solution. It is shown, that the neural controller is able to learn the desired behaviour. It considerably outperforms an analytically designed linear controller in the real environment