Modeling and evaluation of human-to-robot mapping of grasps

We study the problem of human to robot grasp mapping as a basic building block of a learning by imitation system. The human hand posture, including both the grasp type and hand orientation, is first classified based on a single image and mapped to a specific robot hand. A metric for the evaluation based on the notion of virtual fingers is proposed. The first part of the experimental evaluation, performed in simulation, shows how the differences in the embodiment between human and robotic hand affect the grasp strategy. The second part, performed with a robotic system, demonstrates the feasibility of the proposed methodology in realistic applications.