Driving control of electric power assisted wheelchair based on neural network learning of human characteristics

This paper describes a novel driving control scheme of electric power assisted wheelchairs based on human characteristics learning. ¿Electric power assisted wheelchair¿ which assists the driving force by electric motors is expected to be widely used as a mobility support system for elderly people and disabled people. However, some handicapped people such as paralysis of the muscles of one side of the body cannot drive as intended due to the difference of right and left input operation. Therefore this study proposes a neural network learning system of such human characteristics and a driving control scheme with variable distribution ratio and variable assistance ratio. Some driving experiments confirm the effectiveness of the proposed control system.