Grasp and manipulation of objects with a multi-fingered hand in unstructured environments

In this thesis, new methods to grasp and to manipulate unknown objects with a robotic multi-fingered hand have been proposed. These methods have the goals to reduce the time of the execution of the grasp to be suitable with real-time applications and to exploit the redundancy in the ``multi-fingered hand + object" system in order to optimize other subtasks during manipulation. In particular, a visual system has been used to cope with the problem of unknown objects grasping. Then, it is straightforward to recognize that two main tasks have to be performed in such a context: object recognition/reconstruction and grasp planning. The motivation behind the proposed algorithm is that the visual reconstruction algorithm should guide the object's grasp planner in a coordinated manner. The same coordination aspects are the key-points of the proposed method about manipulation of objects: now, the fingers of the robotic hand have to cooperate in order to manipulate the object in the desired way with a good dexterity and this can be done exploiting the redundancy of the whole system.