EEG Controlled Robotic Arm Using Fuzzy Logic Controller

Abstract

This paper presents an Electroencephalogram (EEG)-controlled robotic arm system designed to establish a direct interface between human brain signals and precise robotic arm movements. The study begins with the derivation of kine-matic models to understand the spatial dynamics of the robotic arm. Following a systematic methodology, the EEG data undergo preprocessing, training using an optimizable KNN model and an optimizable tree model, and integration with a Fuzzy Logic Controller (FLC), addressing uncertainties in neural signal inter-pretation. Simulation results demonstrate the system's efficacy in accurately interpreting neural signals and executing movements based on user intents. The robust integration of machine learning algorithms and a Fuzzy Logic Controller validates the seamless translation of raw EEG data into precise control commands.