Skip to content. | Skip to navigation

Personal tools
Document Actions

Anna L Ciancio, Loredana Zollo, Gianluca Baldassarre, Daniele Caligiore, and Eugenio Giglielmelli (2013)

The role of learning and kinematic features in dexterous manipulation: a comparative study with two robotic hands

International Journal of Advanced Robotic Systems.

Abstract—Performance of dexterous movements accomplished by the human hand is by far more sophisticated than the one exhibited by current humanoid robotic hands and the systems used to control them. This work aims at providing a contribution to overcome this gap by proposing a bio-inspired control architecture that captures two key elements at the basis of human dexterity. The first one is the progressive development of skillful control, often starting from – or involving – cyclic movements, based on trial-and-error learning processes and central pattern generators. The latter is the exploitation of particular kinematic features of the human hand, such as the thumb opposition. The architecture is tested with two simulated robotic hands possessing different kinematic features and engaged in rotating spheres, cylinders, and cubes with different size. The results give a first support to the feasibility of the proposed approach and show the potentiality of the model to allow a better understanding of the control mechanisms and kinematic principles underlying human dexterity and make them transferable to anthropomorphic robotic hands.