Adaptive control algorithm with parameter optimization using neural networks for an omni-directional walker

Renpeng Tan, Shuoyu Wang, Yinlai Jiang, Kenji Ishida, Masakatsu Fujie

    Research output: Contribution to journalArticle

    3 Citations (Scopus)

    Abstract

    An omni-directional walker, which is able to realize diverse motion groups, has been developed for walking rehabilitation. In a previous study, to improve the path tracking accuracy, an adaptive control algorithm was developed to deal with the center of gravity shift and the load changes caused by the users. However, the control parameters in the nonlinear adaptive control law were manually adjusted. In this paper, a neural network for automatically adjustment of the adaptive control parameters is proposed. According to the rehabilitation program designed by the physical therapists, we simulate the walker's movement along a linear path. The simulation results verify the effectiveness of the parameter optimization using neural network. ICIC International

    Original languageEnglish
    Pages (from-to)201-207
    Number of pages7
    JournalICIC Express Letters, Part B: Applications
    Volume1
    Issue number2
    Publication statusPublished - 2010 Dec

    Keywords

    • Adaptive control
    • Neural networks
    • Omni-directional walker
    • Parameters optimization

    ASJC Scopus subject areas

    • Computer Science(all)

    Fingerprint Dive into the research topics of 'Adaptive control algorithm with parameter optimization using neural networks for an omni-directional walker'. Together they form a unique fingerprint.

  • Cite this