In this paper, a back-stepping scheme for rigid-link electrically driven (RLED) robot systems is proposed. A two-step controller is presented: the first step is a virtual controller, while the second step is an actual one. A neural network is used to approximate the unknown non-linear dynamics in the system. The stability can be guaranteed by using a rigid proof. A simulation is used to illustrate the effectiveness of the proposed algorithm.
EfratiT.FlashnerH.Neural network based tracking control for mechanical systems. In Proceedings of the 36th Conference on Decision and Control, San Diego, California, 1997, pp. 2501–2505.
2.
LevinA. U.NarendraK. S.Control of nonlinear dynamical systems using neural networks-part II: Observability, identification, and control. IEEE Trans. Neural Networks, 1996, 7 (1), 30–42.
3.
LewisF. L.LiuK.YesildirekA.Neural net robot controller with guaranteed tracking performance. IEEE Trans. Neural Networks, 1995, 6 (3), 705–715.
4.
HuangS. N.RenW.Use of neural fuzzy networks with mixed genetic/gradient algorithm in automated vehicle control. IEEE Trans. Ind. Electronics, 1999, 46 (6), 1090–1102.
5.
HuangS. N.TanK. K.LeeT. H.A combined PID/ adaptive controller for a class of nonlinear systems. Automatica, 2001, 37, 611–618.
6.
HuangS. N.TanK. K.LeeT. H.Adaptive motion control using neural network approximations. Automatica, 2002, 38 (2), 227–233.
7.
MillerW. T.GlanzF. H.KraftL. G.Application of a general learning algorithm to the control of robotic manipulators. Int. J. Robotic Res., 1987, 3, 84–98.
8.
GoldbergK. Y.PearlmutterB. A.Using backpropagation with temporal windows to learn the dynamics of the CMU direct drive arm II. In Advances in Neural Information Processing Systems (Ed. TouretzkyD. S.), 1989 (Morgan Kaufmann, San Mateo, California).
9.
KoradanM. I.Supervised learning and systems with excess degree of freedom. University of Massachusetts, Amherst, COINS Technical Report 88–27.
10.
MiyamotoH.KawatoM.SetoyamaT.SuzukiR.Feedback error learning neural networks for trajectory control of a robotic manipulator. Neural Networks, 1988, 1, 251–265.
11.
BeheraL.GopalM.ChaudhuryS.On adaptive trajectory tracking of a robot manipulator using inversion of its neural emulator. IEEE Trans. Neural Networks, 19967, 1401–1414.
12.
LyshevskiS. E.Nonlinear control of mechatronic systems with permanent-magnet DC motors. Mechatronics, 1999, 9 (5), 539–552.
13.
TarnT.BejczyA.YunX.LiZ.Effect of motor dynamics on nonlinear feedback robot arm control. IEEE Trans. Robotics and Automn, 1991, 7, 114–122.
14.
EppingerS.SeeringW.Introduction to dynamic models for robot force control. IEEE Control Syst. Mag., 1987, 7 (2), 48–52.
15.
HolcombT.MorariM.Local training of radial basis function networks: Towards solving the hidden unit problem. In Proceedings of the American Control Conference, 1991, pp. 2331–2336.
16.
SannerR. M.SlotineJ. E.Gaussian networks for direct adaptive control. IEEE Trans. Neural Networks, 1992, 3 (6), 837–863.
17.
TanK. K.LimS. Y.HuangS. N.Two-degree-of-freedom controller incorporating RBF adaptation for precision motion control applications. In IEEE/ASME International Conference onAdvanced Intelligent Mechatronics (AIM'99), USA, 1999, pp. 848–853.
18.
DawsonD. M.BridgesM. M.QuZ.Nonlinear Control of Robotic Systems for Environmental Waste and Restoration, 1995 (Prentice-Hall, Englewood Cliffs, New Jersey).
19.
KosmatopoulosE. B.PolycarpouM. M.ChristodoulouM. A.IoannouP. A.High-order neural network structures for identification of dynamical systems. IEEE Trans. Neural Networks, 1995, 6, 422–431.
20.
ChenF. C.LiuC. C.Adaptively controlling nonlinear continuous-time systems using multilayer neural networks. IEEE Trans. Autom. Control, 1994, 39 (6), 1306–1310.
