Slip detection by a tactile neural network

Abstract

Detection of incipient slippage is of great importance in robotics for the control of grasping and manipulation tasks. Together with fine-form reconstruction and primitive recognition, it has to be the main feature of an artificial tactile system. The system presented here is based on a neural network devoted to detecting incipient slippage of a body pressing on a skin-like sensor. Normal and shear stress components inside the sensor are the input data. An important feature of the system is that the a priori knowledge of the friction coefficient between the sensor and the object being manipulated is not needed. The finite element method is used to solve the direct problem of elastic contact in its full non-linearity by resorting to the lowest number of approximations with respect to the real problem. Simulations show that the network learns and is robust with respect to noise.<>