Advertisement

Neural-Network Inverse Dynamic Online Learning Control on Physical Exoskeleton

  • Heng Cao
  • Yuhai Yin
  • Ding Du
  • Lizong Lin
  • Wenjin Gu
  • Zhiyong Yang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4234)

Abstract

Exoskeleton system which is to assist the motion of physically weak persons such as disabled, injured and elderly persons is discussed in this paper. The proposed exoskeletons are controlled basically based on the electromoyogram (EMG) signals. And a mind model is constructed to identify person’s mind for predicting or estimating person’s behavior. The proposed mind model is installed in an exoskeleton power assistive system named IAE for walking aid. The neural-network is also be used in this system to help learning. The on-line learning adjustment algorithm based on multi-sensor that are fixed on the robot is designed which makes the locomotion stable and adaptable.

Keywords

Online Learn Environment Disturbance Recursive Least Square Algorithm Weak Person Torque Command 
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.
    Ohta, M., Sato, A.: On a Robot Which Walks with a Person by Keeping a Mind Contact. In: Conf. ROBOTIC 2000, Berlin, Germany, pp. 225–238 (2000)Google Scholar
  2. 2.
    Blaya, J.: Force Controlleble Ankel Foot Orthosis to Assist Drop-foot Gait. Mech. Eng. MS Thesis, MIT (2002)Google Scholar
  3. 3.
    Brown, P., Jones, D., Singh, S.K., Rosen, J.M.: The Exoskeleton Glove for Control of Paralyzed Hands. In: Proceedings IEEE International Conference on Robotics and Automation, pp. 642–647 (1993)Google Scholar
  4. 4.
    Lee, W.J., Ouyang, C.S., Lee, S.J.: Contructing Neuro-Fuzzy Systems with TSK Fuzzy Rules and Hybrid SVD-Based Learning. In: Proc. of IEEE International Conf. on Fuzzy Systems (2002)Google Scholar
  5. 5.
    Hudgins, B., Parker, P., Scott, R.N.: A New Strategy for Multifunction Myoeletric Control. A New Strategy for Multifunction Myoeletric Control 40(1), 82–94 (1993)Google Scholar
  6. 6.
    Diao, Y., Passino, K.M.: Adaptive Neuro-Fuzzy Control for Interpolated Nonlinear Systems. IEEE Trans. On Fuzzy Systems 10(5), 583–595 (2002)CrossRefGoogle Scholar
  7. 7.
    Ishii, A., TAkanishi, A.: Emotion Expression of a Biped Personal Robot. In: IEEE International Conference on Intelligent Robots and Systems, Takamatsu, pp. 191–196 (2000)Google Scholar
  8. 8.
    Takanishi, A., Takanobu, H.: Robot Personalization Based on the Mental Dynamics. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, Takamatsu, pp. 8–14 (2000)Google Scholar
  9. 9.
    Kun, A., Miller, W.: Adaptive Dynamic Balance of a Biped Robot using Neural NetWorks. In: IEEE Int. Conf. on Robotic and Automation, Minneapolis, pp. 240–245 (1966)Google Scholar
  10. 10.
    Kawamoto, H., Sankai, Y.: EMG-based Hybrid Assistive Leg for Walking Aid Using Feedforward Controller. In: ICCAS 2002. International Conference on Control, Automation and Systems, pp. 190–193 (2002)Google Scholar
  11. 11.
    Canales, L., Stanisic, M.M.: Prelliminary Design of an Exoskeleton Shoulder Joint without Dead Positions. In: IEEE International Conference on Systems Engineering, pp. 94–96 (1998)Google Scholar
  12. 12.
    Kosso, E.V.: A minimum Energy Exoskeleton. In: Camahan Conference on Electronic Prosthetics, pp. 86–89 (1973)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Heng Cao
    • 1
  • Yuhai Yin
    • 1
  • Ding Du
    • 1
  • Lizong Lin
    • 1
  • Wenjin Gu
    • 2
  • Zhiyong Yang
    • 2
  1. 1.School of Mechanical and Power, EngineeringEast China University of Science and TechnologyShanghaiChina
  2. 2.Department of Control EngineeringNavy Aeronautical Engineering CollegeYantai, Shandong provinceChina

Personalised recommendations