2018/11/02 by Stefan W. Hell, Hell, Stefan, Vasileios Argyriou +1 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #Image and Video Quality Assessment #Virtual Reality Applications and Impacts
paper · pdf · doi:10.48550/arxiv.1811.01106
openalex publication_date 2018/11/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Virtual Reality (VR) can cause an unprecedented immersion and feeling of\npresence yet a lot of users experience motion sickness when moving through a\nvirtual environment. Rollercoaster rides are popular in Virtual Reality but\nhave to be well designed to limit the amount of nausea the user may feel. This\npaper describes a novel framework to get automated ratings on motion sickness\nusing Neural Networks. An application that lets users create rollercoasters\ndirectly in VR, share them with other users and ride and rate them is used to\ngather real-time data related to the in-game behaviour of the player, the track\nitself and users' ratings based on a Simulator Sickness Questionnaire (SSQ)\nintegrated into the application. Machine learning architectures based on deep\nneural networks are trained using this data aiming to predict motion sickness\nlevels. While this paper focuses on rollercoasters this framework could help to\nrate any VR application on motion sickness and intensity that involves camera\nmovement. A new well defined dataset is provided in this paper and the\nperformance of the proposed architectures are evaluated in a comparative study.\n