Outer shape classification in rotation manipulation by Universal Robot Hand

We propose a method for shape classification in continuous rotation manipulation by a multi-fingered robot hand. Our robot hand has five fingers equipped with tactile sensors. Each tactile sensor can measure a pressure distribution once every 10(ms) while the robot hand rotates the object continuously. Our proposed classification method consists of the following processes: A kurtosis is calculated from each pressure distribution, and it quantifies 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, a evaluated value is calculated between the time-series kurtosis and reference patterns through a continuous dynamic programming (CDP) matching scheme. The contact shape is classified if the evaluated value is lower than a threshold. We show the effectiveness of our method through experiments.