A Navigation System for a Wheelchair User Based on a multi-modal Design

A multi-modal system to control the movement of an Electric wheelchair, using small vocabulary word recognition system and a set of sensors to detect and avoid obstacles, is implemented. The methodology adopted is based on grouping a speech recognition microprocessor for isolated word from a dependent speaker and the set of sensors. The resulting design is used to control a wheelchair for a handicapped person based on the vocal command. The input of the system is a set of ten Arabic words used to control the movement of an automated guided vehicle (AGV) and information on the environment given by the sensors; the output is a corresponding command avoiding obstacles and planning collision-free paths. The system is developed in order to be installed on the wheelchair. Therefore it should be accurate, no bulky easy in operation and low power consumption.