We address the problem of representations for anthropomorphic robot hands and their suitability for use in methods for learning or control. We approach hand configuration from the perspective of ultimate hand function and propose 2 parameterizations based on the ability of the hand to engage oppositional forces. These parameters can be extracted from grasp examples making them suitable for use in practical learning-from-demonstration frameworks. We propose a qualitative method to span hand

more »

... ional space in a principled manner. This is used to construct a grasp set for evaluation and a qualitative baseline metric derived from human experience. Our results from human grasp data show that hand representations based on shape are not able to disambiguate hand-function. However, those based on handopposition primitives result in the widest separations among grasps that have radically different functions and can even clearly separate grasps whose functions overlap a great degree. We trust that these "functional parameterizations" can bridge the contrasting goals of task-oriented robotic grasping, that of controlling a dexterous robot hand to manifest hand-shape but with the ability to exercise specific hand-function.