Remote Steering of a Mobile Robotic Car by Means of VR-Based SSVEP BCI

Abstract

Brain-computer interface (BCI) technology, including applications based on the steady-state visual evoked potentials (SSVEPs) have proven to provide reliable and accurate control. In this paper, we present and evaluate remote steering of a previously developed and successfully tested mobile robotic car (MRC) utilizing the SSVEP-based BCI system. The visual stimulations were presented inside the head-mounted virtual reality (VR) glasses, here, the Oculus Go. The live video feedback from the MRCs point of view was displayed inside the custom made app of the VR environment. The three visual stimuli were located on both sides and above the video stream of the MRC camera. The task of this study was to steer the MRC through a 8 m long path (in the real world) with 6 turns. Seven participants took part in the experiment reaching on average an accuracy of 98.1 (standard deviation: 5.04)%, an information transfer rate (ITR) of 10.71 (2.78) bits/min with an average command classification time of 3.95 (2.3) seconds. For classification, the minimum energy combination method (MEC) with 16 EEG electrodes as well as a filter bank decomposing method were utilized. All participants successfully completed the task, almost all subjects stated that the presented VR-based SSVEP-BCI was a highly immersive experience.