For both humans and robots, tactile sensing is important for interaction with the environment: it is the core sensing used for exploration and manipulation of objects. In this paper, we present a method for determining object texture by active exploration with a robotic ﬁngertip equipped with a dynamic tactile transducer based on polyvinylidene ﬂuoride (PVDF) piezoelectric ﬁlm. Different test surfaces are actively explored and the signal from the sensor is used for feature extraction, which is subsequently used for classiﬁcation. A comparison between the signiﬁcance of different extracted features and performance of learning algorithms is done and the best method is further used to classify objects by their surface textures with recognition results higher than 90 percent.
active exploration; object recognition; piezoelectric sensors