Null-space-based shared control of a mobile robot using motor imagery based brain-computer interface.

The paper presents a shared control architecture for non-holonomic mobile robots commanded through a motor imagery based Brain-Computer Interface (BCI). The overall system is aimed at assisting people to teleoperate a mobile robot in a simulated house-like scenario by resorting to two motor imagery commands. The developed architecture is structured in such a way that the user can drive the mobile robot while safety tasks, e.g. obstacle avoidance, are autonomously achieved, leaving complete autonomy to the mobile robot to let the latter adjust its configuration, e.g. aligning itself with a narrow passage. The overall architecture has been realized by developing control modules with the ROS environment, while the OpenVibe framework has been adopted to process the EEG signals. The effectiveness of the proposed architecture has been validated through experiments where a healthy user, wearing a Unicorn g.tec BCI, performs an assisted teleoperation task through motor imagery sessions with a Turtlebot robot.