A neuro-fuzzy control approach for intelligent microrobots

Abstract

Presents a neuro-fuzzy control approach for intelligent microrobots. Typical tasks of such industrial or medical robots are both exploration and fine manipulation, what demands task planning and motion/force control capabilities. For this kind of microsystems the authors investigate the system technical aspects of information processing. The concept for the control system architecture is based on the combination of a neural network approach for the adaptation of process parameters and a fuzzy logic approach for the correction of parameter values given to a conventional controller. A planning component deals with the determination of initial manipulation parameters. Together with a sensor fusion procedure and a supervising and reasoning subsystem this allows reliable operation of a microrobot.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>