Artículos de revistas
Neural network-based H(infinity) control for fully actuated and underactuated cooperative manipulators
Fecha
2009Registro en:
CONTROL ENGINEERING PRACTICE, v.17, n.3, p.418-425, 2009
0967-0661
10.1016/j.conengprac.2008.09.007
Autor
SIQUEIRA, Adriano A. G.
TERRA, Marco H.
Institución
Resumen
This paper develops H(infinity) control designs based on neural networks for fully actuated and underactuated cooperative manipulators. The neural networks proposed in this paper only adapt the uncertain dynamics of the robot manipulators. They work as a complement of the nominal model. The H(infinity) performance index includes the position errors as well the squeeze force errors between the manipulator end-effectors and the object, which represents a complete disturbance rejection scenario. For the underactuated case, the squeeze force control problem is more difficult to solve due to the loss of some degrees of manipulator actuation. Results obtained from an actual cooperative manipulator, which is able to work as a fully actuated and an underactuated manipulator, are presented. (C) 2008 Elsevier Ltd. All rights reserved.