Sensor fusion system for improving the recognition of 3D object

摘要

Human being recognizes the physical world by intcgrating a grcat variety of sensory inputs, the information acquired by their own action, and their knowledge of the world using hierarchically parallcldistributed mechanism. In this paper, authors propose the sensor fusion system that can recognize multiple 3D objects from 2D projection images and tactile information. Thc proposed system focuses on improving object recognition rate. Unlike the conventional object, recognition system that uses image scnsor alone, the proposed method USCS tactual sensors in addition to visual scnsor. Tactual signals arc obtained from the reaction forcc by the pressure scnsars at the fingertips when unknown objects are grasped by four-fingcrcd robot hand. The experiment evaluates the recognition rate and thc number of lesrning iterations of various objects, The experimental results show that the proposed system can improve recognition rate and reduce learning time. These results verify the effcctiveness of the proposed sensor fusion system as 3D object recognition scheme.