Pre-slip detection based Tactile Sensing

Abstract

Numerous researchers have investigated robot gripper manipulation control. A method to detect and reduce the risk of slippage by controlling the normal force as measured by tactile sensor arrays has been developed. A predictive model has been proposed which uses a basic method adapted to real applications in grasp optimization. Prevention of premature release with minimum prehension force is addressed without the need to measure the coefficient of friction between an object and a robot gripper. Predictive models have been used to develop a set of rules which predict the pre-slip based on fluctuations in tactile signal data. The proposed tactile sensor will be applied in grasp experimentation by identifying the least force required for prehension - the method appropriately called pre-slip detections. The subjects used for the experiments consist of objects with different sizes and weights.