EMG-based neuro-fuzzy control of a 4DOF upper-limb power-assist exoskeleton

Annu Int Conf IEEE Eng Med Biol Soc. 2007:2007:3040-3. doi: 10.1109/IEMBS.2007.4352969.

Abstract

We have been developing a 4DOF exoskeleton robot system in order to assist shoulder vertical motion, shoulder horizontal motion, elbow motion, and forearm motion of physically weak persons such as elderly, injured, or disabled persons. The robot is directly attached to a user's body and activated based on EMG (Electromyogram) signals of the user's muscles, since the EMG signals directly reflect the user's motion intention. A neuro-fuzzy controller has been applied to control the exoskeleton robot system. In this paper, controller adaptation method to user's EMG signals is proposed. A motion indicator is introduced to indicate the motion intention of the user for the controller adaptation. The experimental results show the effectiveness of the proposed method.

Publication types

  • Evaluation Study
  • Research Support, Non-U.S. Gov't

MeSH terms

  • Adult
  • Algorithms
  • Bone and Bones / physiology
  • Electromyography / instrumentation*
  • Electromyography / methods
  • Equipment Design
  • Equipment Failure Analysis
  • Feedback
  • Humans
  • Male
  • Man-Machine Systems*
  • Movement / physiology
  • Muscle Contraction / physiology
  • Neural Networks, Computer*
  • Orthotic Devices*
  • Pattern Recognition, Automated / methods*
  • Robotics / instrumentation*
  • Robotics / methods
  • Upper Extremity / physiology*
  • User-Computer Interface