Tutorial on Embodiment

3.3.1. Cheap grasping with a robotic hand*

The 18 degrees-of-freedom (DOF) tendon driven ‘Yokoi hand' (Yokoi et al., 2004; Fig. and Video & which can be used as a robotic and a prosthetic hand, is partly built from elastic, flexible, and defor­mable materials (this hand comes in many versions with different materials, morphologies, sensors, etc.; here we only describe one of them). The tendons are elastic, the finger tips are deformable and between the fingers there is also deformable material. When the hand is closed, the fingers will, because of the anthropomorphic morphology, automatically come together. For grasping an object, a simple control scheme, a ‘close' is applied. Because of the morpho­logy of the hand, the elastic tendons, and the deformable finger tips, the hand will automatically self-adapt to the object it is grasping.

Fig. ‘Cheap' grasping with a robotic hand: exploiting system-environment inter­action. (A) The Yokoi hand exploits deformable and flexible materials to achieve self-adaptation through the interaction between environment and materials. (B)-(C) Final grasp of different objects. The control is the same, but the behavior is very different.





Video and The videos depict the same situation that is displayed in Fig. The hand successfully adapts to different objects while applying the same control command.


* adapted from Pfeifer and Gomez, 2009


Yokoi, H.; Hernandez-Arieta, A.; Katoh, R.; Yu, W.; Watanabe, I. & Maruishi, M.Iida, F.; Pfeifer, R.; Steels, L. & Kuniyoshi, Y., ed., (2004), Embodied Artificial Intelligence, Springer, chapter Mutual adaptation in a prosthetics application, pp. 147-159.
Pfeifer, R. & Gomez, G. (2009). Morphological computation - connecting brain, body, and environment. In B. Sendhoff, O. Sporns, E. Körner, H. Ritter, & K. Doya, K. (eds.), Creating Brain-like Intelligence: From Basic Principles to Complex Intelligent Systems (pp.66-83). Berlin: Springer.