Material Recognition Using Robotic Hand With Capacitive Tactile Sensor Array and Machine Learning

Autonomous manipulation using robot hands can benefits from tactile sensing, as it can collect information on variation in applied force and surface properties. This paper presents a capacitive tactile sensor placed on robot hand fingers. Due to its unique structure and high sensitivity to material permittivity, this sensing system can obtain capacitive data both when a robot finger is approaching to an object and when it has touched the object. With three dimension reduction methods i.e. Principal Component Analysis (PCA), Independent Component Analysis (ICA), and Multi-Dimensional Scaling (MDS), a dataset is transformed to be two-dimensional and then fed into two supervised classifications algorithms, i.e. K Nearest Neighbors (KNN) and Support Vector Machine (SVM). In comparison to previous studies, the MDS-based SVM achieves high material recognition accuracy, up to 98% for recognition of three different material classes, i.e. plastic, paper and glass using capacitance data only. Furthermore, it performs well in recognition of five different materials, i.e. dry plastic, plastic with water drops, paper, dry glass, and glass with water drops. The recognition accuracy is as high as 93%. Computational time can be reduced about 60% by combining the dimension reduction methods with classification algorithms. The results indicate that different material properties can be identified efficiently using the proposed method.