Dexterous Skills Transfer by Extending Human Body Schema to a Robotic Hand

We propose a framework for skills transfer to robots, exploiting the plasticity of the human brain in representing its body parts - the body schema. The conceptual idea is, in the first stage, to incorporate the target robotic platform into the experimenter´s neural representation of his/her own body. In the second stage, the dexterity on a task exhibited with the new external limb -the robot- then can be used for imitation or designing controllers for the task under consideration. In this study, following the steps outlined, we show how dexterous skill transfer can be achieved on a 16-DOF robotic hand, justifying the effectiveness of the proposed method and confirming the flexibility of the human brain in representing the body schema