Haptic object recognition with a dextrous hand based on volumetric shape representations

A haptic object recognition methodology suitable for application with a multifingered robot hand is presented. The methodology exploits the peculiar features of robot hands such as their distributed sensoriality and parallel kinematics for fast acquisition of contact data, and is based on volumetric representation models for efficient dynamic integration of the perceived information. Experimental results demonstrate the effectiveness and applicability of the methodology to non-trivial examples.<>