Control of a 2-DoF robotic arm using a P300-based brain-computer interface

TL;DR

This paper presents a novel P300-based brain-computer interface system that enables a 2-DoF robotic arm to accurately perform target tracking and letter writing tasks in a simulated environment, demonstrating high recognition accuracy.

Contribution

It develops a real-time control algorithm for a P300 BCI to operate a robotic arm, achieving high accuracy without pre-channel selection, and compares favorably with BCI Competition datasets.

Findings

Recognition rate of 97% with multi-class SVM

Effective control of robotic arm in 2D space

System successfully performs target tracking and letter writing

Abstract

In this study, a novel control algorithm for a P-300 based brain-computer interface is fully developed to control a 2-DoF robotic arm. Eight subjects including 5 men and 3 women, perform a 2-dimensional target tracking task in a simulated environment. Their EEG signals from visual cortex are recorded and P-300 components are extracted and evaluated to perform a real-time BCI based controller. The volunteer's intention is recognized and will be decoded as an appropriate command to control the cursor. The final goal of the system is to control a simulated robotic arm in a 2-dimensional space for writing some English letters. The results show that the system allows the robot end-effector to move between arbitrary positions in a point-to-point session with the desired accuracy. This model is tested on and compared with Dataset II of the BCI Competition. The best result is obtained with a multi-class SVM solution as the classifier, with a recognition rate of 97 percent, without pre-channel selection.