This paper shows and evaluates a novel approach to integrate a non-invasiveBrain-Computer Interface (BCI) with the Robot Operating System (ROS) tomentally drive a telepresence robot. Controlling a mobile device by using humanbrain signals might improve the quality of life of people suffering from severephysical disabilities or elderly people who cannot move anymore. Thus, the BCIuser is able to actively interact with relatives and friends located indifferent rooms thanks to a video streaming connection to the robot. Tofacilitate the control of the robot via BCI, we explore new ROS-basedalgorithms for navigation and obstacle avoidance, making the system safer andmore reliable. In this regard, the robot can exploit two maps of theenvironment, one for localization and one for navigation, and both can be usedalso by the BCI user to watch the position of the robot while it is moving. Asdemonstrated by the experimental results, the user's cognitive workload isreduced, decreasing the number of commands necessary to complete the task andhelping him/her to keep attention for longer periods of time.
展开▼
