Design of an Artificial Neural Network Based Tactile Sensor for the UTAH/MIT Dexterous Hand
AIR FORCE INST OF TECH WRIGHT-PATTERSON AFB OH SCHOOL OF ENGINEERING
Pagination or Media Count:
The Neural Tactile Sensor NTS is a high resolution, easily manufactured tactile sensor consisting of electrodes, a thin resistive skin, and pattern recognition circuitry that is capable of resolving dynamic and static contact location, force, and slip throughout the continuum of the sensors active region. The sensor operates by means of a resistive skin harboring the electric field generated when a current is injected into it, and a plurality of electrodes for taking measurements of said electric field. When current flows through the resistive medium from the location of tactile contact, an electric field within the resistive medium is established, with a voltage distribution pattern dependent on where the contact was made. The contact generated electric field is measured at a plurality of locations on or in the resistive medium by the electrodes. The outputs of these electrodes can be interpreted as a continuum of field representing voltage patterns that are unique, repeatable, and dependent upon the location that field establishing contact was made. The dynamics of said voltage patterns are related to contact trajectory and slip. These voltage patterns are then used as input to appropriate pattern recognizer circuitry, such as the multilayer perceptron Artificial Neural Network ANN.