A Novel Walking Speed Control Strategy for Power Augmentation Exoskeletons based on Neural Networks

Abstract

This paper addresses a novel sensing technique to minimize the interaction force of walking speed transitions during the navigation of a coupled human-exoskeleton power augmentation system. The proposed technique is able to classify the intended walking speed based on Dual Reaction Force (DRF) Sensor. The human brain as a complex information processing device is quite difficult to be simulated, especially when considering the processing speed and the speed of sensed signals through the human nervous system throughout the human body. We developed the DRF sensors for preemptive identification of pilot intentions for walking speed transitions to augment the response of the exoskeleton to shadow pilot's movements. The Dynamic Threshold Neural Networks (DTNNs) is used to classify the input signals and make a decision on the transition of system's walking speed according to the pilot's intentions and walking speed limitation. The actions for walking speed transitions are simulated in MATLAB/Simulink, and Variable Admittance Controller (VAC) and applied. To show the efficiency of the proposed walking speed control strategy, comparison is conducted with ordinary VAC algorithm technique.