A New Cerebellar Model Articulation Controller for Rehabilitation Robots

  • Authors:

  • Shan Liu;Yongji Wang;Yongle Xie;Shuyan Jiang;Jinsong Meng

  • Affiliations:

  • School of Automation, University of Electronic Science and Techenology of China, Chengdu, China 610054;Department of Control Science and Engineering, Key Laboratory of Image Processing and Intelligent Control, Huazhong University of Science and Techenology, Wuhan, China 430074;School of Automation, University of Electronic Science and Techenology of China, Chengdu, China 610054;School of Automation, University of Electronic Science and Techenology of China, Chengdu, China 610054;School of Automation, University of Electronic Science and Techenology of China, Chengdu, China 610054

  • Venue:
  • ISNN 2009 Proceedings of the 6th International Symposium on Neural Networks: Advances in Neural Networks - Part III
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a new cerebellar model articulation controller (CMAC), a sliding-mode-based diagonal recurrent fuzzy CMAC (SDRFCMAC) to robot-assisted rehabilitation for stroke patients. To design the intelligent controller, the CMAC is integrated with some control methods, in which sliding mode technology is used to reduce the dimension of the control system, and fuzzy logic and diagonal recurrent structure is used to solve dynamic problems. The control architecture is represented in terms of stepping optimization system architecture comprising two learning stages to provide robotic assistance for an upper arm rehabilitation task and improve the safety of the human-robot system. Liapunov stability theorem and Barbalat's lemma are adopted to guarantee the asymptotical stability of the system. The effectiveness of the control scheme is demonstrated through a simulated case study.