A recurrent neural network approach to virtual environment latency reduction

One of the most notable problems facing current virtual environment applications is the perceptible latency that is experienced by the user as a result of head-tracking device lag. Such perceptible latency has been shown to have undesirable effects on users of virtual environments, including a lack of accuracy during tracking tasks, motion sickness, and loss of immersion. In this paper, we present a recurrent neural network system designed to predict future angular velocity of the human head from current angular velocity data. These predictions can be used to supplement head tracking in virtual environments to reduce latency and increase tracking accuracy, thus enhancing the user's performance and comfort. We demonstrate that the recurrent neural network system is capable of predicting future angular velocity with a high degree of accuracy. In addition, when compared with the current extrapolation methods built into head-tracking devices, we show that the neural network system tends to produce increased accuracy.