Enhancing Wheelchair Manoeuvrability for Severe Impairment Users

Abstract

A significant number of individuals with severe motor impairments are unable to control their wheelchair using a standard joystick. Even when they can facilitate the control input, navigation in a confined space or crowded environments is still a great challenge. Here we propose a wheelchair framework that enables the user to issue the command via a multi-input hands free interface (HFI), which subsequently assists him/her to overcome difficult circumstances using a multimodal control strategy. Initially the HFI inputs are analysed to infer the desired control mode and the user command. Then environmental information is perceived using a combination of laser and Kinect sensors for determining all possible obstacle locations and outputting a safety map around the wheelchair's vicinity. Eventually, the user's command is validated with the safety map to moderate the final motion, which is collision free and the best for the user's preference. The proposed method can reduce the burden of severe impairment users when controlling wheelchairs by continuously monitoring the surroundings and can make them move easily according to the users' intention.