Abstract: A new study based on voice command and sensors is being developed to reduce the cognitive and physical requirements of operating a power wheelchair for people with ranging impairment that limit their access to power mobility. The adopted system is based on hybrid method that combines a set of classical speech recognition algorithms and set of four peer of ultrasonic sensors modules. The hybrid method is obtained by mixing zero crossing, extremes, dynamic time warping, energy and fundamental frequency. A weight vector, computed on test results, is used in decision section. To test the study on a real application, a PC interface was designed to control the movement of a wheelchair for a handicapped person by simple vocal messages. On the wheelchair, a set of ultrasonic sensors were installed. The main role of these sensors is to detect frontal obstacles and to enable or disable the left or right rotation of the wheelchair when it is in is Tests showed that the system needs some outputs follow a logic in line with the words uttered.