Several of the neurological diseases that human beings can result in severe disabilities. In some
cases, people who suffer from such deficiencies lose any chance of communication with their
environment, being the only possible alternative to give the brain a new channel not based on
muscular activity, allowing these people to send messages and commands to the external world.
The systems that allows the latter is what is known as Brain-Computer Interfaces (BCI). Their
common feature is to process the brain’s electrical activity for extracting information that can be
used to command an external device, as for example, a wheelchair to provide them some mobility.
One of the most important limitations of these brain controlled wheelchair is to guarantee that a
person can, through his mental activity, safely control the variety of navigation commands that
provide control of the wheelchair: advance, turn, move back, and stop. The vast majority of the
mobile robot navigation applications that are controlled via a BCI demand that the user performs
as many different mental tasks as there are different control commands, worsening the classification
accuracy. In order to enable an effective and autonomous wheelchair navigation with a BCI system
without worsening user performance, the Brain–Computer Interface (BCI) group of the University
of Málaga (UMA-BCI) proposed and later developed a new paradigm based on the discrimination
of only two classes (one active mental task versus any other mental activity), which enabled the
selection of four commands: move forwards, turn right, move backward and turn left. The final
aim of this contribution is to show how to control a robotic wheelchair through the use of only
two mental tasks. The mapping of these two mental tasks into several navigation commands allows the Brain-Controlled Wheelchair to be moved and turned in order to achieve effective navigation.
