Improvement of Tracking Control of a Sliding Mode Controller for Robot Manipulators by a Neural Network

  • Seul JungEmail author
Regular Paper Technical Notes and Correspondence


This article presents a neural network control technique to improve the tracking performance of a robot manipulator controlled by the sliding mode control method in a non-model-based framework. The sliding mode controller is a typical nonlinear controller that has been well developed in theory and used in many applications due to its simplicity and practicality. Selection of the gain of the nonlinear function plays an important role in performance as well as stability. When the sliding mode controller is used for the non model-based configuration in robot control, the nonlinear gain should be selected large enough to guarantee the stability. Since the appropriate selection of the gain value is essential and difficult in the sliding mode control framework, a neural network compensator is introduced at the trajectory level to help the fixed gain deal with the stability and performance more intelligently. Stability of the proposed control scheme is analyzed. Simulation studies of following the Cartesian trajectory for a three-link rotary robot manipulator are conducted to confirm the control improvement by the neural network.


Neural network reference compensation technique robot manipulators sliding mode control 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    E. Sariyildiz and K. Ohnishi, “On the explicit robust force control via disturbance observer,” IEEE Trans. Industrial Electronics, vol. 62, no. 3, pp. 1581–1589, 2015. [click]CrossRefGoogle Scholar
  2. [2]
    K. Kong and M. Tomizuka, “Nominal model manipulation for enhancement of stability robustness for disturbance observer-based systems,” International Journal of Control, Automation, and Systems, vol. 11, no. 1, pp. 12–20, 2013.CrossRefGoogle Scholar
  3. [3]
    S. D. Lee and S. Jung, “Analysis of time constant effect in the Q filter for designing a disturbance observer: balancing control of a single-wheel robot,” Journal of The Institute of Electronics and Information Engineers, vol. 53, no. 10, pp. 1711-171, 2016.CrossRefGoogle Scholar
  4. [4]
    W. Gao and Z. P. Jiang, “Adaptive dynamic programming and adaptive optimal output regulation of linear system,” IEEE Trans. on Automatic Control, vol. 61, no. 12, pp. 4164–4169, 2016. [click]MathSciNetCrossRefzbMATHGoogle Scholar
  5. [5]
    W. Gao and Z. P. Jiang, “Nonlinear and adaptive suboptimal control of connected vehicles: A global adaptive dynamic programming approach,” Journal of Intelligent & Robotic Systems, vol. 85, no. 3-4, pp. 597–611, 2017. [click]CrossRefGoogle Scholar
  6. [6]
    H. Gomi and M. Kawato, “Learning control for a closed loop system using feedback error learning,” Proc. of the IEEE International Conf. on Decision and Control, pp. 3289–3294, 1990.Google Scholar
  7. [7]
    R. J. Wai and R. Muthusamy, “Fuzzy-neural network inherited sliding-mode control for robot manipulator including actuator dynamics,” IEEE Trans. on Neural Network and Learning Systems, vol. 24, no. 2, pp. 274–287, 2013. [click]CrossRefGoogle Scholar
  8. [8]
    H. Xin and Q. Chen, “Full-order neural sliding model control of robotic manipulator with unknown dead-zone,” Proc. of Chinese Automation Conference, pp. 1664–1669, 2015.Google Scholar
  9. [9]
    F. L. Lewis, S. Jagannathan, and A. Yesildirek, Neural Network Control of Robot Manipulators and Nonlinear Systems, Taylor & Francis, 1999.Google Scholar
  10. [10]
    R. G. Rodriguez and V. P. Vega, “Tracking control of robot manipulators using second order neuro sliding mode,” Latin American Applied Research, vol. 39, no. 4, pp. 285–294, 2009.Google Scholar
  11. [11]
    H. Zhang, M. Du, and W. Bu, “Sliding mode controller with RBF neural network for manipulator trajectory tracking,” IAENG International Journal of Applied Mathematics, vol. 45, no. 4, 2015.Google Scholar
  12. [12]
    T. Liu and S. Yin, “An improved neural network adaptive sliding mode control used in robot trajectory tracking control,” International Journal of Innovative Computing, Information and Control, vol. 11, no. 5, pp. 1655–1666, 2015.Google Scholar
  13. [13]
    S. Jung and T. C. Hsia, “Neural network inverse control techniques for PDcontrolled robot manipulator,” Robotica, vol. 19, no. 3, pp. 305–314, 2000.CrossRefGoogle Scholar
  14. [14]
    S. Jung, “Stability analysis of reference compensation technique for controlling robot manipulators by neural network,” International Journal of Control, Automation, and Systems, vol. 15, no. 2, pp. 952–958, 2017. [click]CrossRefGoogle Scholar

Copyright information

© Institute of Control, Robotics and Systems and The Korean Institute of Electrical Engineers and Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Mechatronics EngineeringChungnam National UniversityDaejeonKorea

Personalised recommendations