Synergistic Neural Models of a Robot Sensor for Part Orientation Detection

Abstract

This paper describes the use of neural networks to compute the orientation of a part from the output signals of an inertial sensor which is a device for determining the location of parts by measuring their inertial parameters. The paper investigates an approach for increasing the accuracy of the computed orientation. This involves employing a group of neural networks and combining their outputs. The paper presents the results obtained for several neural network combinations. These show that the accuracy achieved in a combined system is higher than that of its individual components provided the number of components is not too large.