NeuroGaze: a hybrid EEG and eye-tracking brain-computer interface for hands-free interaction in virtual reality

Abstract

Brain-Computer Interfaces (BCIs) have traditionally been studied in clinical and laboratory contexts, but the rise of consumer-grade devices now allows exploration of their use in daily activities. Virtual reality (VR) provides a particularly relevant domain, where existing input methods often force trade-offs between speed, accuracy, and physical effort. This study introduces NeuroGaze, a hybrid interface combining electroencephalography (EEG) with eye tracking to enable hands-free interaction in immersive VR. Twenty participants completed a 360° cube-selection task using three different input methods: VR controllers, gaze combined with a pinch gesture, and NeuroGaze. Performance was measured by task completion time and error rate, while workload was evaluated using the NASA Task Load Index (NASA-TLX). NeuroGaze successfully supported target selection with off-the-shelf hardware, producing fewer errors than the alternative methods but requiring longer completion times, reflecting a classic speed-accuracy tradeoff. Workload analysis indicated reduced physical demand for NeuroGaze compared to controllers, though overall ratings and user preferences were mixed. While the differing confirmation pipelines limit direct comparison of throughput metrics, NeuroGaze is positioned as a feasibility study illustrating trade-offs between speed, accuracy, and accessibility. It highlights the potential of consumer-grade BCIs for long-duration use and emphasizes the need for improved EEG signal processing and adaptive multimodal integration to enhance future performance.