Robotic link position control using brain computer interface

Abstract

Brain computer interfacing is a new paradigm to provide an alternative path of communication for those, who have lost their sensory, motor and autonomous function limb movement from spinal cord injury or other neuronal disorder. To increase living standard of them, a thought controlled robot or robotic arm can be of great importance for their better communication to external world. This paper proposes a novel approach towards electroencephalogram based random order control of a robot manipulator. Here steady state visual evoked potential has been used to select the desired robot link and motor imagery signal has been used to control the motion of robot link. Left and Right hand motor imagery signal has been used in this purpose. Event related error potential is used for feedback purpose and to correct the positional error of link created by motor imagery. The robot link here is realigned by experimental offset. Power spectral density, common spatial pattern and moving average, have been used as feature extractor and support vector machine with linear kernel function has been used as the classifier. At first, the subject has been trained in offline experiment and then online session performance has been evaluated.