Hybrid Electroencephalography-Induced Robot Navigation for Rehabilitative Platform

Abstract

Decoding upper limb movement from electroencephalography (EEG) signals is an emerging field of research that has the potential to enhance the quality of life for individuals with motor impairments. This paper provides an informative overview of EEG-based upper limb movement decoding and addresses the limitations found in existing studies by proposing a novel rehabilitative robotics framework. The framework utilizes three types of EEG signals: motor imagery, error-related potential, and P300 signals, to navigate an OpenManipulatorX robotic arm. The novelty of this research lies in the utilization of a phase-sensitive Common Spatial Pattern approach for feature extraction, as well as the successful recognition of commands for robot control using Linear Discriminant Analysis. The proposed method achieves an impressive average success rate of 95% for target reaching, making it suitable for the design of prosthetics in real-time rehabilitative platforms.