Discrete-Time Lyapunov Design for Neuroadaptive Control of Elastic-Joint Robots

Abstract

A neural-network controller operating in discrete time is shown to result in stable trajectory tracking for rigid and elastic-joint robots. The technique assumes continuous-time state feedback. The proof of stability uses discrete-time Lyapunov functions. For the elastic-joint case, a discrete-time version of the adaptive backstepping technique is used. The result is that the neural network can be run at a very slow control rate, suitable for online calculations. The neural network used is referred to as the CMAC-RBF Associative Memory (CRAM), a modification of Albus’s Cerebellar Model Arithmetic Computer (CMAC) algorithm using radial basis functions (RBFs). Simulation results are provided for a two-link planar elastic-joint robot and show that performance can be improved by using a larger network at a slower control rate.

Get full access to this article

View all access options for this article.

References

Albus, J. 1975a. A new approach to manipulator control: The cerebellar model articulation controller (CMAC) . J. Dyn. Sys. Meas. Contr. 97: 220–227 .

Albus, J. 1975b. Data storage in the cerebellar model articulation controller (CMAC) . J. Dyn. Sys. Meas. Contr. 97: 228–233 .

Albus, J. 1981. Brains, Behaviour, and Robotics. BYTE.

Brogliato, B., Ortega, R., and Lozano, R. 1995. Global tracking controllers for flexible-joint manipulators: A comparative study . Automatica 31(7): 941–956 .

Ciliz, M., and Isik, Can. 1992. Stability and convergence of neurologic model based robotic controllers . Proc. IEEE Int. Conf. Robotics and Automation, Nice, France, pp. 2051–2055 .

Commuri, S., and Lewis, F. L. 1997. CMAC neural networks for control of nonlinear dynamical systems: Structure, stability, and passivity . Automatica 33(4): 635–641 .

Ioannou, P. A., and Kokotovic, P. V. 1983. Adaptive Systems with Reduced Models. New York: Springer-Verlag .

Kanellakopoulos, I. 1994. A discrete-time adaptive nonlinear system . IEEE Trans. Aut. Control 39(11): 2362–2365 .

Krstic, M., Kanellakopoulos, I., and Kokotovic, P. 1995. Nonlinear Adaptive Control Design. New York: John Wiley .

10.

Kwan, C. M., Lewis, F. L., and Kim, Y. H. 1995. Robust neural network control of flexible-joint robots . Proc. 34th Conf. Decision and Control, New Orleans, pp. 1296–1301 .

11.

Macnab, C.J.B, and D’Eleuterio, G.M.T. 1998. Stable, online learning using CMACs for neuroadaptive tracking control of flexible-joint manipulators . Proc. IEEE Int. Conf. Robotics and Automation, Leuven, Belgium.

12.

Miller, Thomas W. 1990. Real-time dynamic control of an industrial manipulator using a neural-network-based learning controller . IEEE Trans. Robot. Autom. 6(1): 1–8 .

13.

Narendra, K. S., and Annaswamy, A. M. 1989. Stable Adaptive Systems. Englewood Cliffs, NJ: Prentice Hall .

14.

Nicosia, S., and Tomei, P. 1992. A method to design adaptive controllers for flexible joint robots . Proc. IEEE Int. Conf. Robotics and Automation, Nice, France, pp. 701–706 .

15.

Rokui, M. R., and Khorasani, K. 1997. An indirect adaptive control for fully feedback linearizable discrete-time nonlinear systems . Int. J. Adap. Cntrl. Sig. Proc. 11: 665–680 .

16.

Sanner, R. M., and Slotine, J. 1992. Gaussian networks for direct adaptive control . IEEE Trans. Neural Networks 3: 837–863 .

17.

Slotine, J., and Li, W. 1987. Adaptive robot control: A new perspective . Proc. 28th Conf. Decision and Control, Los Angeles, pp. 192–198 .

18.

Slotine, J., and Li, W. 1991. Applied Nonlinear Control. Englewood Cliffs, NJ: Prentice Hall .

19.

Spong, M. W., and Vidyasagar, M. 1989. Robot Dynamics and Control. New York: John Wiley .

20.

Yang, S., Woo, P., and Wang, R. 1996. Discrete-time model reference adaptive controller designs for robotic manipulators . Int. J. Robotics Research 15(3): 280–289 .

21.

Yeh, P., and Kokotovic, P. 1995. Adaptive control of a class of nonlinear discrete-time systems . Int. J. Control 62(2): 303–324 .