부산대학교 도서관

The wide spread prevalence of lost limbs and sensing system is of major concern in present day due to accident, age and health problems. To assist people with such defects, the proposed intelligent wheelchair system uses dual control for navigation in familiar environments. The two modes of input control to the wheelchair are voice recognition and touch screen. When one want to change the direction, the touch screen sensor is modelled by pressing finger against the various quadrants on the touch screen, which has different values programmed for different direction. This can also be controlled through simple voice commands using voice controller. By storing a single letter in voice recognition kit for each direction control, the recognition time is reduced drastically and thus quick reach to destination is obtained. The wheelchair consists of DC brushless motors at the rear end and it is controlled by using PWM technique. A brake control mechanism is included to control the wheelchair. From previous literature surveys observed, the accuracy of the touch screen was found to be 50%. In this proposed system achievement of wheelchair movement in all direction is obtained with an accuracy of 94.6%. Voice recognition has accuracy of 80.8% which is 30% higher than the study done by Prathyusha et al. This device helps the disabled to have automatic advancement to their destination through predefined paths in the indoor system.