Object recognition by grasping

In this paper, we describe a method for recognizing both the three-dimensional pattern and the size of objects by grasping them with multijointed fingers equipped with tactile sensors. First, the bending data of the joint is sorted out by analyzing the distribution pattern of the sensors in contact. Then the appropriate pattern is determined by calculating the values of the several linear discriminant functions provided for each contact pattern. Classification of the size of an object is achieved by applying a linear machine with a maximum-value selector to the bending form of the joints. The results of the experiments show that the most useful discriminant function is a linear one. Its percentage of total correctness is highest for the pattern recognition of an object.