Using Nonlinear Kinematic Parameters as a Means of Predicting Motion Sickness in Real-Time in Virtual Environments.

Objective: This article presents two studies (one simulation and one pilot) that assess a custom computer algorithm designed to predict motion sickness in real-time.

Background: Virtual reality has a wide range of applications; however, many users experience visually induced motion sickness. Previous research has demonstrated that changes in kinematic (behavioral) parameters are predictive of motion sickness. However, there has not been research demonstrating that these measures can be utilized in real-time applications.

Method: Two studies were performed to assess an algorithm designed to predict motion sickness in real-time. Study 1 was a simulation study that used data from Smart et al. (2014). Study 2 employed the algorithm on 28 new participants' motion while exposed to virtual motion.

Results: Study 1 revealed that the algorithm was able to classify motion sick participants with 100% accuracy. Study 2 revealed that the algorithm could predict if a participant would become motion sick with 57% accuracy.

Conclusion: The results of the present study suggest that the motion sickness prediction algorithm can predict if an individual will experience motion sickness but needs further refinement to improve performance.

Application: The algorithm could be used for a wide array of VR devices to predict likelihood of motion sickness with enough time to intervene.