Comparison of Wheelchair User Interfaces for the Paralysed: Head-Joystick vs. Verbal Path Selection from an offered Route-Set.

Abstract

Within this work we compare two human-robot interfaces that enable handicapped people who may not move their arms and legs to steer an automated wheelchair. As a technically more ambitious solution we first propose a simple speech recognition system that enables the paralysed to select a path from a set of spatially meaningful solutions, that is subsequently executed by a geometric path planner. The contrasting approach is given by a proportional head-joystick that evaluates the user’s head posture with the help of a small-size three degrees of freedom orientation tracker. Both systems are assessed by the outcome of an empirical study in which untrained participants used the presented interfaces to navigate in a populated office environment.