How hard is your brain working in VR? This paper presents a machine learning system that predicts cognitive load in real time using behavioral and physiological signals collected through VR headsets. Trained on data from 738 participants across various VR experiences, the model achieves remarkably low error (MAE of 0.11) in predicting mental workload. The system analyzes markers like eye movements, head motion, and physiological responses to infer how cognitively demanding a VR experience is for users. This has significant implications for adaptive VR systems that could automatically adjust difficulty, pacing, or complexity based on the user's mental state. The researchers also release a test dataset from 100 participants to enable further research in this area.
Jishang Wei, Erika Siegel, Prahalathan Sundaramoorthy, Antônio Gomes, Shibo Zhang, Mithra Vankipuram, Kevin Smathers, Sarthak Ghosh, Hiroshi Horii, Jeremy Bailenson, and Rafael Ballagas. 2025. Cognitive Load Inference Using Physiological Markers in Virtual Reality. In 2025 IEEE Conference Virtual Reality and 3D User Interfaces (VR), Saint Malo, France. IEEE. https://doi.org/10.1109/VR59515.2025.00098
Podden och tillhörande omslagsbild på den här sidan tillhör
Kai Kunze. Innehållet i podden är skapat av Kai Kunze och inte av,
eller tillsammans med, Poddtoppen.
