Researchers at Essex University have developed a system that allows people suffering from severe physical disabilities, such as spinal cord injury or quadriplegia, to control a wheelchair or mobility scooter.
Lai Wei and Huosheng Hu from the School of Computer Science and Electronic Engineering at Essex University developed the system for the hands-free control of electric-powered wheelchairs using an inexpensive webcam and a sensing headband.
Their prototype system uses pattern recognition and the analysis of electromyographic signals from the user’s forehead and visual signals to identify which of five winking and jaw-clenching movements the user is making.
The combination of a left and right wink, with and without a jaw clench, and a jaw clench alone is mapped to six control commands for the wheelchair.
In tests with users on an indoor obstacle circuit, the researchers found that all users were able to control a wheeled-robot simulator initially. They then demonstrated that they could also control a wheelchair sufficiently well to navigate an obstacle course and to follow specific routes.
The researchers pointed out that individual wheelchair users would have different needs, but the recognition software could be fine-tuned to suit particular facial and muscular characteristics.
In the future, the researchers could also examine whether the same technology might allow additional facial expressions and movements to control other devices as well.