Learning of Grasp Behaviors for an Artificial Hand by Time Clustering and Takagi-Sugeno Modeling

The focus of the paper is the learning of grasp primitives for a five-Angered anthropomorphic robotic hand via teaching-by-demonstration and fuzzy modeling. In this approach, a number of basic grasps is demonstrated by a human operator wearing a data glove which continuously captures the hand pose. The resulting fingertip trajectories and joint angles are clustered and modeled in time and space so that the motions of the fingers forming a particular grasp are modeled in a most effective and compact way. Classification and learning are based on fuzzy clustering and Takagi Sugeno (TS) modeling. The presented method allows to learn, imitate and recognize the motion sequences forming specific grasps.