Asynchronous Controlled Single-Channel EOG-Based Puzzle Solver Robot

Abstract

Electrooculography (EOG)-based human–computer interface (HCI) systems have a wide range of applications due to their usability in inferring user's intention through eye movements. Because of limited eye activities, these systems generate limited commands, such as looking up, down, left, and right. The challenge is to utilize EOG signals in strategy-based applications, such as game-playing robots. This article presents a novel asynchronous controlled single-channel EOG-based HCI system that uses eyeblink signals to control a robotic manipulator in solving Guarini's puzzle. A puzzle board and three control buttons are presented in a graphical user interface. The user navigates to a target through a single eyeblink and selects it through a double eyeblink. Two data analysis algorithms, specifically logistic regression model and eyeblink detection module, are used to detect eyeblinks. Two online experiments were conducted with ten healthy subjects. In the screen-based puzzle-solving experiment, we achieved an average accuracy of 95.19% with a short response time (RT) of 0.96 s and an information transfer rate (ITR) of 268.14 bits/min. In the robot-assisted experiment, the proposed system achieved an average accuracy of 92.7%, with an RT of 0.98 s and an ITR of 252.92 bits/min. In both experiments, during the decision (idle) state, the average false positive rate (FPR) is found to be 0.02 events/min. This system generates sufficient commands to control a robotic manipulator in solving the puzzle on the physical puzzle board. In comparison to existing EOG-based gaming systems, the proposed system achieves high accuracy, low RT, lower FPR, and high ITR with fewer electrodes.