Proposes a self tuning fuzzy inference method based on genetic algorithms for the fuzzy-sliding mode control of a robot. Using this method the number of inference rules and the shape of membership functions are optimized without an expert in robotics. The fuzzy outputs of the consequent part are updated by the gradient descent method, and it is guaranteed that the selected solution becomes the global optimal solution by optimizing Akaike's information criterion. A trajectory tracking experiment with the automatic polishing robot system shows that the optimal fuzzy inference rules are automatically selected by the genetic algorithm and the proposed fuzzy-sliding mode controller provides reliable tracking performance during the polishing process.

This paper shows a self tuning fuzzy inference method by the genetic algorithm in the fuzzy-sliding mode control for a polishing robot. Using this method, the number of inference rules and the shape of membership functions are optimized without an expert in robotics. The fuzzy outputs of the consequent part are updated by the gradient descent method, and it is guaranteed that the selected solution become the global optimal solution by optimizing Akaike's information criterion expressing the quality of the inference rules. Also, trajectory tracking simulation shows that the optimal fuzzy inference rules by the genetic algorithm are automatically selected and the trajectory control result is almost similar to the result which uses the inference rules to be selected through the trial and error method by an expert. Therefore, although a designer is a non-expert of robot systems, the fuzzy-sliding mode controller can be designed by the proposed self tuning fuzzy inference method based on the genetic algorithm.

Polishing work of a freely-curved surface die demands simple and repetitive operations but requires a considerable amount of time for high precision. Some workers tend to gradually avoid the polishing work because of the poor environment caused by dust and noise. In order to reduce the polishing time and solve the problem of the shortage of skilled workers, an automatic polishing system should be developed. In this study, a user-friendly automatic polishing system was developed. It is composed of two different systems: a three-axis machining center and a two-axis polishing robot. The developed polishing system with five degrees of freedom is able to keep the polishing tool normal to the die surface. In order to operate the polishing system, the host computer should transmit the polishing data to the FANUC controller of the machining center and DSP controller of the polishing robot, respectively. A driving program (P-PROS: Pusan National University-polishing robot operating system) in the Windows environment was developed to easily operate the polishing robot system. A communication program was developed for transmitting the polishing data to each controller. To evaluate the performance of the P-PROS and the developed DSP (digital signal processing) controller, a polishing experiment on the shadow-mask die was done.