Probzbilistic scan mode of a robot manipulator workspace using EEG signals. Part I

Abstract

In this paper a probabilistic-based workspace scan mode of a manipulator robot is presented. The scan mode is governed by a Brain Computer Interface (BCI) based on Event Related Potentials (Synchronization and Dessynchronization events). The user is capable to select a specific position at the robot's workspace, which should be reached by the manipulator. The robot workspace is divided into cells. Each cell has a probability value associated with it. Once the robot reaches a cell, its probability value is updated. The mode the scan is made is determined by the probability of all cells at the workspace. Finally, the manipulator is teleoperated via TCP/IP. © 2007 IOP Publishing Ltd.