A Deep Learning Approach for Robotic Arm Control using Brain-Computer Interface

Abstract

Brain-Computer Interface (BCI) is atechnology that enables a human to communicate with anexternal stratagem to achieve the desired result. This paperpresents a Motor Imagery (MI) – Electroencephalography(EEG) signal based robotic hand movements of lifting anddropping of an external robotic arm. The MI-EEG signalswere extracted using a 3-channel electrode system with theAD8232 amplifier. The electrodes were placed on threelocations, namely, C3, C4, and right mastoid. Signalprocessing methods namely, Butterworth filter and Sym-9Wavelet Packet Decomposition (WPD) were applied on theextracted EEG signals to de-noise the raw EEG signal.Statistical features like entropy, variance, standarddeviation, covariance, and spectral centroid were extractedfrom the de-noised signals. The statistical features werethen applied to train a Multi-Layer Perceptron (MLP) -Deep Neural Network (DNN) to classify the hand movementinto two classes; ‘No Hand Movement’ and ’HandMovement’. The resultant k-fold cross-validated accuracyachieved was 85.41% and other classification metrics, suchas precision, recall sensitivity, specificity, and F1 Score werealso calculated. The trained model was interfaced withArduino to move the robotic arm according to the classpredicted by the DNN model in a real-time environment.The proposed end to end low-cost deep learning frameworkprovides a substantial improvement in real-time BCI.