Online control of a mobility assistance Smart Walker

Abstract

This work presents the ASBGo Smart Walker, developed at Minho University with the Adaptive System Behavior Group. It includes the conceptual design, implementation and validation of a Smart Walker with a new interface approach integrated. It was addressed the assembly of the ASBGo with the required electronics, as well as the implementation of the interface based on a joystick. This sensor is intended to read the user's movement intentions to command the walker. Thus, preliminary sets of experiments were performed with 10 healthy volunteers walking with the device. This was followed by the signal processing and extensive analysis of the joystick signals, which showed the capability of the joystick to extract navigation commands from the user. Based on this real-time identification of user's commands, an approach to the control architecture of the ASBGo was developed and it is based on a fuzzy logic algorithm that allowed the control of the walker's motors. A set of validation experiments were then performed. In addition, it was addressed the security of the user by adding a set of sensors to detect if the user falls.