A knowledge based approach to robot axis control

Abstract

The paper outlines a novel approach to real-time control which is based on developing and maintaining a "knowledge base" about the system to be controlled. The knowledge base comprises information relating to the plant and its environment and is used to determine the control signals required to obtain the desired response from the plant. The control methodology devised has been used to achieve motion control of a single axis electric module intended for robotic applications. The results obtained are encouraging and show a marked improvement over classical control techniques. For the "knowledge based" controller, methods of updating the system representation for environmental changes are proposed through the use of "indirect" and "direct" identification techniques.