Performance and Latency Analysis of EEG Signal for Control System of Robotic Arm Movements Based on Sliding Mode Controller

The integration of brain-computer interfaces (BCIs) in robotics presents a novel approach to enable intuitive control of robotic systems. This paper proposes a real-time control methodology for a two-link robot arm utilizing synthetic electroencephalography (EEG) signals combined with a sliding mode control (SMC) strategy. The objective is to achieve precise manipulation of the robotic arm in response to the classified EEG signals, simulating brain activities that indicate movement intentions. We first generate a synthetic EEG dataset to represent brain signals indicative of left and right arm movements. This dataset serves as the input for a classification algorithm that determines the desired motion of the robotic arm. The proposed control framework leverages SMC, known for its robustness against system uncertainties and external disturbances, ensuring stable performance even in dynamic environments. The dynamics of the two-link robot arm are modeled, incorporating the non-linarites associated with joint movements. The control law is designed to achieve the desired angles through a sliding surface that adapts to the specified EEG signals. Simulation results demonstrate the efficacy of the control approach, showing rapid convergence of the robot arm to the target positions based on the EEG-derived commands. Moreover, the paper presents comprehensive performance metrics, including the trajectory tracking accuracy and response time of the robotic arm. Visualizations illustrate the arm's motion during the execution of left and right movements, providing a clear understanding of the system's dynamics in action. This research highlights the potential of EEG-driven control in enhancing human-robot interaction, paving the way for future developments in assistive technologies and rehabilitation robotics. The findings indicate a promising direction for integrating BCIs in robotic systems, contributing to advancements in intelligent automation.