This work presents the development of a robotic wheelchair that can be commanded by users in a supervised way or by a fully automatic unsupervised navigation system. It provides flexibility to choose different modalities to command the wheelchair, in addition to be suitable for people with different levels of disabilities. Users can command the wheelchair based on their eye blinks, eye movements, head movements, by sip-and-puff and through brain signals. The wheelchair can also operate like an auto-guided vehicle, following metallic tapes, or in an autonomous way. The system is provided with an easy to use and flexible graphical user interface onboard a personal digital assistant, which is used to allow users to choose commands to be sent to the robotic wheelchair. Several experiments were carried out with people with disabilities, and the results validate the developed system as an assistive tool for people with distinct levels of disability.
This paper proposes an exponential interpolation to merge a part-of-speech-based language model and a word-based $n$ -gram language model to accomplish word prediction tasks. In order to find a set of mathematical equations to properly describe the language modeling, a model based on partial differential equations is proposed. With the appropriate initial conditions, it was found an interpolation model similar to the traditional maximum entropy language model. Improvements in keystroke saved and perplexity over the word-based $n$ -gram language model and two other traditional interpolation models is obtained, considering three different languages. The proposed interpolation model also provides additional improvement in hit rate parameter.
This work presents a multi-modal interface that can be used for communication of people with disabilities. The interface is installed onboard a robotic wheelchair, and provides flexibility to choose different modalities for communication by people with different levels of disabilities. Users can use the interface through eye blinks, eye movements, head movements, by blowing or sucking a straw, and through brain signals. The interface is easy to use and has a flexible graphical user interface running on a personal digital assistant or tablet. Several experiments were carried out with healthy people and people with disabilities, and the results validate the developed interface as an assistive tool to allow communication of people with distinct levels of disability.