KSME International Journal

, 18:1916 | Cite as

A robust control with a neural network structure for uncertain robot manipulator

  • In-Chul Ha
  • Myoung-Chul Han


A robust position control with the bound function of neural network structure is proposed for uncertain robot manipulators. The uncertain factors come from imperfect knowledge of system parameters, payload change, friction, external disturbance, and etc. Therefore, uncertainties are often nonlinear and time-varying. The neural network structure presents the bound function and does not need the concave property of the bound function. The robust approach is to solve this problem as uncertainties are included in a model and the controller can achieve the desired properties in spite of the imperfect modeling. Simulation is performed to validate this law for four-axis SCARA type robot manipulator.

Key Words

Robot Manipulator Robust Control NN (Neural Network) Lyapunov Stability Bound Function 


  1. Chen, Y. H. and Pandey, S., 1990, “Uncertainty Bounded-Based Hybrid Control for Robot Manipulators,”IEEE Transactions on Robotics and Automation, Vol. 6, No. 3, pp. 303–311.MATHCrossRefGoogle Scholar
  2. Chen, Y. H., 1991, “Robust Computed Torque Schemes for Mechanical Manipulators: Non-Adaptive Versus Adaptive,”ASME J. Dynam. Syst. Meas. Contr., Vol. 113, pp. 324–327.CrossRefGoogle Scholar
  3. Chen, Y. H., Leitmann, G. and Chen, J. S., 1998, “Robust Control for Rigid Serial Manipulators; A General Setting,”Proc. Amer. Control Conf. Philadelphia, Pennsylvania, pp. 912–916.Google Scholar
  4. Corless, M. and Leitmann, G., 1981, “Continuous State Feedback Guaranteering Uniform Ultimate Boundedness for Uncertain Dynamic Systems,”IEEE Transactions on Automatic Control, Vol. AC-26, No. 5.Google Scholar
  5. Frank L. Lewis, 1996, “Neural Network Control of Robot Manipulators,”University of Texas at Arlington IEEE. Google Scholar
  6. Frank L. Lewis, Kai Liu and Ajdin Yesildirek, 1995, “Neural Net Robot Controller with Garanteed Tracking Performance,”IEEE Transaction on Neural Network, Vol. 6, No. 3.Google Scholar
  7. Ge, S. S., 1998, “Advanced Control Techniques of Robotic Manipulator,”Proc. Amer. Control Conf., pp. 2185–2199.Google Scholar
  8. Ha, I. C. and Han, M. C, 2000, “Adaptive Robust Control Design for Uncertain Robot Manipulators,”Conference of KSPE, pp. 331–334.Google Scholar
  9. Han, M. C, Hong, K. S. and Lee, S., 1997, “Decentralized Robust Control for Interconnected Nonlinear Systems,”KSME INT. J., Vol. 11, No. 1, pp. 1–9.Google Scholar
  10. Kim, H. S. and Shim, Y., 2002, “Robust Nonlinear Control of a 6 DOF Parallel Manipulator: Task Space Approach,”KSME. INT. J., Vol. 16, No. 8, pp. 1053–1063.Google Scholar
  11. Kumpati S. Narendra and Snehasis Mukhopadhyay, 1997, “Adaptive Control Using Neural Networks and Approximate Models,”IEEE Transaction on Neural Network, Vol. 8, No. 3.Google Scholar
  12. Lee, S. H. and Kim, T. G., 2001, “Robust Control of a Revolute Joint Robot,”Conf. of KSME, Vol. 1, No. 2, pp. 265–270.Google Scholar
  13. Reithmeier, E. and Leitmann, G., 1991, “Tracking and Force Control for a Class of Robotic Manipulators,”Dynamics and Control, Vol. 1, pp. 133–150.MATHCrossRefMathSciNetGoogle Scholar
  14. Shoureshi, R., Corless, M. and Roesler, M. D., 1987, “Control of Industrial Manipulators with Bounded Uncertainties,”ASME J. Dynam. Syst. Meas. Contr., Vol. 109, pp. 53–58.MATHCrossRefGoogle Scholar
  15. Yesildirek, A. Nandegrift, M. W. and Lewis, F. L., 1996“A Nerual Network Controller for Flexible-Link Robots,”Journal of intelligent and Robotics Systems, 17, pp. 327–349.CrossRefGoogle Scholar

Copyright information

© The Korean Society of Mechanical Engineers (KSME) 2004

Authors and Affiliations

  1. 1.Center for Robot Technology & Manufacturing of Institute for Advanced EngineeringKyonggi- doKorea
  2. 2.Department of Mechanical EngineeringPusan National UniversityPusanKorea

Personalised recommendations