Title :
A neural network for tactile sensing: the Hertzian contact problem
Author :
Worth, Andrew J. ; Spencer, Richard R.
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., California Univ., Davis, CA, USA
Abstract :
A neural network has been developed for use in local closed-loop gripper control using a tactile sensor array. Backpropagation is used to train a network with a single hidden layer to recognize the angle of contact between a cylindrical finger with an embedded sensor array and a cylindrical rod. Simulation results are presented and discussed
Keywords :
closed loop systems; neural nets; tactile sensors; Hertzian contact problem; angle of contact; backpropagation; cylindrical finger; cylindrical rod; embedded sensor array; local closed-loop gripper control; neural network; single hidden layer; tactile sensing; Array signal processing; Capacitive sensors; Fingers; Geometry; Grippers; Neural networks; Sensor arrays; Skin; Speech; Tactile sensors;
Journal_Title :
Systems, Man and Cybernetics, IEEE Transactions on
