In this paper, an adaptive neural-network-based torque compensator is developed for the trajectory-tracking control of robot manipulators. The overall control structure employs a classical non-linear decoupling controller for actuating torque computation based on an approximated robot dynamic model. To suppress the effects of uncertainties associated with the estimated model, a supplementary neural network algorithm is developed to generate compensation torques. The weight adaptation rule for this neuro-compensator is derived on the basis of the Lyapunov stability theory. Both global system stability and the error convergence can then be guaranteed. Simulation studies on a two-link robot manipulator demonstrate that high performance of the proposed control algorithm could be achieved under severe modelling uncertainties.
DubowskyS.DesForgesD. T.The application of model-referenced adaptive control to robotic manipulators. J. Dynamic Syst., Measmt, Control, 1979, 101, 193–200.
2.
HorowitzR.TomizukaM.An adaptive control scheme for mechanical manipulators—compensation of nonlinearity and decoupling control. J. Dynamic Syst., Measmt, Control, 1986, 33, 659–668.
3.
CraigJ. J.HsuP.SastryS. S.Adaptive control of mechanical manipulators. Int. J. Robotic Res., 1987, 6, 10–20.
4.
SlotineJ.-J. E.LiW.On the adaptive control of robot manipulators. Int. J. Robotic Res., 1987, 6, 49–59.
5.
SadeghN.HorowitzR.Stability analysis of an adaptive controller for robotic manipulators. In Proceedings of the IEEE International Conference onRobots and Automation, Raleigh, North Carolina, 1987, pp. 1223–1229 (IEEE, New York).
6.
PadenB.PanjaR.A globally asymptotically stable ‘PD+’ controller for robot manipulators. Int. J. Control, 1988, 47.
7.
OrtegaR.SpongM. W.Adaptive motion control of rigid robots: A tutorial. In Proceedings of the 27th IEEE Conference onDecision and Control, Austin, Texas, December 1988 (IEEE, New York).
8.
MiddletonR. H.GoodwinG. C.Adaptive computed-torque control for rigid-link manipulators. Syst. Control Lett., 1988, 10, 9–16.
9.
MiddletonR. H.Hybrid adaptive control of robot manipulators. In Proceedings of the 27th IEEE Conference onDecision and Control, Austin, Texas, December 1988, Vol. 2, pp. 1592–1597 (IEEE, New York).
10.
SlotineJ.-J. E.LiW.Adaptive manipulator control: A new perspective. In Proceedings of the 26th IEEE Conference onDecision and Control, Los Angeles, California, 1987 (IEEE, New York).
TsoS. K.LawP. L.Design on performance studies of model-based variable-structure adaptive controllers for industrial manipulators. Proc. Instn Mech. Engrs, Part I, Journal of Systems and Control Engineering, 1992, 206 (I4), 245–262.
13.
TsoS. K.LaiM. L.LawP. L.Variable-structure linear model-following control of manipulators. Proc. Instn Mech. Engrs, Part I, Journal of Systems and Control Engineering, 1993, 206 (I1), 35–45.
14.
SlotineJ.-J. E.Adaptive control of robot manipulators. Robot Control, 1993 (IEEE, New York).
AlbusJ. S.A new approach to manipulator control: The cerebellar model articulation controller (CMAC). J. Dynamic Syst., Measmt, Control, 1975, 97, 220–227.
17.
MillerW. T.IIIGlanzF. H.KraftL. G.Application of a general learning algorithm to the control of robotic manipulators. Int. J. Robotic Res., 1987, 6, 84–98.
AngM. H.Jr.AndeenG. B.Adaptive robot control based on a neural network paradigm. In Proceedings of the International Conference onAutomatic Robotics and Combined Vision, Singapore, 1990.
20.
LiQ.PooA. N.LimC. M.AngM.Jr.Neuro-based adaptive internal model control for robot manipulators. In Proceedings of the IEEE International Conference onNeural Networks, Perth, Western Australia, 1995 (IEEE, New York).
21.
PooA. N.AngM. H.Jr.TeoC. L.LiQ.Performance of a neuro-model-based robot controller: Adaptability and noise rejection. Intell. Syst. Engng, 1992, 1, 50–62.
22.
TsoS. K.LinN. L.Neural-network-based adaptive controller for uncertainty compensation of robot manipulator systems. In Proceedings of the 13th IFAC World Congress, 1996, pp. 61–66.
23.
TsoS. K.LinN. L.Adaptive control of robot manipulator with radial-basis-function neural network. In Proceedings of the IEEE International Conference onNeural Networks, 1996, Vol. 3, pp. 1807–1811 (IEEE, New York).
24.
WidrowB.LehrM. A.30 years of adaptive neural networks: Perceptron, madaline and backpropagation. Proc. IEEE, 1990, 78, 1415–1443.
25.
CraigJ. J.Introduction to Robotics: Mechanics and Control, 2nd edition, 1989 (Addison-Wesley, Reading, Massachusetts).
26.
KhemaissiaS.MorrisA. S.Neuro-adaptive control of robotic manipulators. Robotica, 1993, 11.
27.
NordgrenR. E.MecklP. H.An analytical comparison of a neural network and a model-based adaptive controller. IEEE Trans. Neural Networks, 1993, 4.
28.
NarendraK.AnnaswamyA. M.Stable Adaptive Systems, 1989 (Prentice-Hall, Englewood Cliffs, New Jersey).
