Experiments on Dextrous Manipulation without Prior Object Models

Olac Fuentes and Randal C. Nelson
Department of Computer Science
University of Rochester
Rochester, NY 14627

Abstract: In this paper we present a kinematic method for 6-degree-of-freedom manipulation of rigid objects using a dextrous robotic hand. Our method does not require prior models of the objects to be manipulated; all the information needed can be obtained directly from the hand's sensors. The method allows arbitrary (within the robot's physical limits) translations and rotations of the object, and its low computational cost makes real-time performance easy to achieve. We present experimental results of manipulation using the Utah/MIT hand, a 16-DOF dextrous manipulator, and show that with the addition of a Cartesian controller a high degree of accuracy can be attained.