Advertisement

Neurocontroller Via Adaptive Learning Rates for Stable Path Tracking of Mobile Robots

  • Sung Jin Yoo
  • Jin Bae Park
  • Yoon Ho Choi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4221)

Abstract

In this paper, we present a neurocontroller via adaptive learning rates (ALRs) for stable path tracking of mobile robots. The self recurrent wavelet neural networks (SRWNNs) are employed as two neurocontrollers for the control of the mobile robot. Since the SRWNN combines the advantages such as the multi-resolution of the wavelet neural network and the information storage of the recurrent neural network, it can easily cope with the unexpected change of the system. Specially, the ALR algorithm in the gradient-descent method is extended for the multi-input multi-output system and is applied to train the parameters of the SRWNN controllers. The ALRs are derived from the discrete Lyapunov stability theorem, which are used to guarantee the stable path tracking of mobile robots. Finally, through computer simulations, we demonstrate the effectiveness and stability of the proposed controller.

Keywords

Mobile Robot Learning Rate Mother Wavelet Reference Trajectory Wavelet Neural Network 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Fierro, R., Lewis, F.L.: Control of a nonholonomic mobile robot using neural networks. IEEE Trans. Neural Networks 9, 389–400 (1998)CrossRefGoogle Scholar
  2. 2.
    Hu, T., Yang, S.X., Wang, F., Mittal, G.S.: A neural network controller for a nonholonomic mobile robot with unknown robot parameters. In: Proc. of the IEEE Int. Conf. Robotics and Automation, pp. 3540–3545 (2002)Google Scholar
  3. 3.
    Zhang, Q., Benveniste, A.: Wavelet networks. IEEE Trans. Neural Networks 3, 889–898 (1992)CrossRefGoogle Scholar
  4. 4.
    Sousa, C.D., Hemerly, E.M., Galvão, R.K.H.: Adaptive control for mobile robot using wavelet networks. IEEE Trans. Systems, Man, and Cybernetics 32, 493–504 (2002)Google Scholar
  5. 5.
    Oussar, Y., Rivals, I., Personnaz, L., Dreyfus, G.: Training wavelet networks for nonlinear dynamic input-output modeling. Neurocomputing 20, 173–188 (1998)MATHCrossRefGoogle Scholar
  6. 6.
    Wai, R.J., Chang, J.M.: Intelligent control of induction servo motor drive via wavelet neural network. Electric Power Systems Research 61, 67–76 (2002)CrossRefGoogle Scholar
  7. 7.
    Yoo, S.J., Choi, Y.H., Park, J.B.: Stable predictive control of chaotic systems using self-recurrent wavelet neural network. Int. Jour. Control, Automation and Systems 3, 43–55 (2005)Google Scholar
  8. 8.
    Kim, K.B., Park, J.B., Choi, Y.H., Chen, G.: Control of chaotic nonlinear systems using radial basis network approximatiors. Information Science 130, 165–183 (2000)MATHCrossRefGoogle Scholar
  9. 9.
    Ku, C.C., Lee, K.Y.: Diagonal recurrent neural networks for dynamics systems control. IEEE Trans. Neural Networks 6, 144–156 (1995)CrossRefGoogle Scholar
  10. 10.
    Lee, C.H., Teng, C.C.: Identification and control of dynamic systems using recurrent fuzzy neural network. IEEE Trans. Fuzzy Systems 8, 349–366 (2000)CrossRefGoogle Scholar
  11. 11.
    Wang, C.M.: Location estimation and uncertainty analysis for mobile robots. In: Proc. of the IEEE Int. Conf. Robotics and Automation, pp. 1230–1235 (1988)Google Scholar
  12. 12.
    Haesloop, D., Holt, B.R.: A neural network structure for system identification. In: Proc. of the American Control Conference, pp. 2460–2465 (1990)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Sung Jin Yoo
    • 1
  • Jin Bae Park
    • 1
  • Yoon Ho Choi
    • 2
  1. 1.Yonsei UniversitySeoulKorea
  2. 2.Kyonggi UniversitySuwonKorea

Personalised recommendations