EEG-gesture based artificial limb movement for rehabilitative applications

Abstract

Due to damage in parietal and/or motor cortex regions of a rehabilitative patient (subject), there can be failure while performing day-to-day basic task. Thus this chapter focuses on directing an artificial limb based on brain signals and body gesture to assist the subject. This research finds tremendous applications in rehabilitative aid for the disable persons. To concretize our goal we have developed an experimental setup, where the target subject is asked to catch a ball while his/her brain (occipital, parietal and motor cortex) signals electroencephalography (EEG) sensor and body gestures using Kinect sensor are simultaneously acquired. These two data are mapped using cascade correlation learning architecture to train Jaco robot arm to move accordingly. When a rehabilitative patient is unable to catch the ball, then in that scenario, the artificial limb is helpful for assisting the patient to catch the ball. The proposed system can be implemented not only in ball catching experiment but also in several application areas where an artificial limb needs to perform a locomotive task based on EEG and body gesture.