Castellón, España
This paper addresses the problem of executing complex manipulation tasks under uncertainty in unstructured environments. The proposed approach follows the manipulation primitives paradigm, which is based on the use of atomic controllers specifically designed to perform robustly elemental manipulation actions.
The primitives are sensor based and implement a reactive controller that adapts to the uncertain real environment. The specific scenario addressed consists in emptying a box which contains an undefined number of unknown objects. The solution proposed combines a set of manipulation primitives within in a Finite State Machine, which sequentially searches, grasps and transports all the objects in the box to a predefined location. Two perceptual approaches to obtain the main parameters of the task are compared: blind and vision based.
Performance results are presented, compared and discussed.+
© 2001-2024 Fundación Dialnet · Todos los derechos reservados