Outer Shape Classification of Object in Rotation Operation by Universal Robot Hand Using Continuous Dynamic Programming

Abstract

We propose a method for outer shape classification in rotation manipulation by a multi-fingered robotic hand. The robotic hand has five fingers equipped with pressure distributed sensors. Each pressure sensor can measure the pressure distribution once every 10ms. Our classification method uses the pressure distributed sensors and consists of the following processes : A kurtosis is calculated from the pressure distribution, and it quantifies the shape of the current contact surface. By rotating an object and measuring a time-series pressure distribution, the hand obtains a time-series kurtosis. Finally, an evaluated value is calculated between the time-series kurtosis and a reference pattern through a continuous dynamic programming (CDP) scheme. This classifies the contact surface shape using thresholds. Laboratory experiments confirm that this method can classify three objects with a high accuracy rate.