Lightweight Cybersickness Detection based on User-Specific Eye and Head Tracking Data in Virtual Reality

2026-04-18

AI Summary

This study addresses key challenges in motion sickness detection within virtual reality, including poor cross-user generalization, high model complexity, and insufficient personalization. To overcome these limitations, the authors propose a lightweight ensemble learning framework that integrates user-specific eye-tracking and head-movement data, comprising 23 engineered features. By constructing customized training sets and applying tailored feature engineering, the method achieves efficient and accurate detection. Evaluated on the Simulation 2021 dataset, the approach attains 93% accuracy in cross-user settings and 88% under personalized configurations. The solution maintains high precision while substantially reducing computational overhead, enabling real-time deployment. These results underscore the critical importance of personalized modeling and lightweight design for effective motion sickness detection in immersive environments.

Technology Category

• Computer Vision: Motion & Tracking
• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters
• Machine Learning: Ensemble Methods

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

The occurrence of cybersickness in virtual reality (VR) significantly impairs users' perception and sense of immersion. Therefore, timely detection of cybersickness and the application of appropriate intervention strategies are crucial for enhancing the user experience. However, existing cybersickness detection methods often suffer from issues such as poor detection reliability across different levels of cybersickness and unnecessary model complexity. Furthermore, while cybersickness exhibits significant inter-user variability, most existing approaches aggregate all data from users and lack user-specific solutions. In this paper, we investigate a lightweight approach for cybersickness detection incorporating an ensemble learning model and user-specific eye and head tracking data. Our experiments using the open-source dataset Simulation 2021 demonstrate that feature engineering and training set construction are critical for determining detection performance. Models trained with data from similar-content segments achieve the best results, attaining detection accuracies of 93% in the cross-user setting and 88% in the user-personalized setting, using only 23-dimensional eye and head features. Moreover, by using user-specific data, well-tuned ensemble learning models with shorter training and inference times can be feasibly applied to real-world cybersickness detection, offering superior time efficiency and outstanding detection performance. This work offers useful evidence toward the development of lightweight and user-adaptive cybersickness detection models for VR applications.

Problem

• cybersickness
• virtual reality
• user-specific
• lightweight detection
• inter-user variability

Innovation

• lightweight detection
• user-specific modeling
• eye and head tracking
• ensemble learning
• cybersickness