MOVING MARK RECOGNITION AND MOVING OBJECT MANIPULATION IN FUZZY CONTROLLED ROBOT.

A robot-arm system which is able to recognize a moving pattern and to manipulate a moving object on a belt-conveyor at various speeds is built. This system consists of two parts. The first part is related to recognizing patterns. In this part, a method of constructing a discriminant-tree is proposed. The robot-arm-system is able to recognize the shape and the size of moving patterns on a belt-conveyor based on the discriminant-tree. The second part is concerned with replacing a moving object (i. e. , grasping a moving object and putting it on an indicated moving mark) based on fuzzy-inference rules with the aid of image-processing technique. The main idea is based on the concept of probabilistic sets in extended fuzzy expression. Ambiguous instructions in terms of membership and vagueness are generated by the robot itself, using imagery data from a CCD-camera.