In this paper, we demonstrate how a human
computer interface (HCI) system based on electrooculography
(EOG) can be used to control a mobile robot. Such systems can
be particularly useful for people with limited mobility or when
the user needs to execute multiple tasks simultaneously. We use
an autonomic system that does not require a user to execute
every action. The operator issues high-level commands, which
the system uses to achieve a certain goal. A total of six different
events are acquired and classified into desired commands. We
demonstrate our approach by controlling a mobile robot that
wirelessly receives high-level commands such as “move forward”
or “turn left at the next intersection”. During our experiments,
the users were watching a live video feed from the perspective of
the robot, and were able to simultaneously control it and execute
other tasks, such as typing or carrying out a conversation.