Using Head Tracking Data for Robust Short Term Path Prediction of Human Locomotion

Modern interactive environments like virtual reality simulators or augmented reality systems often require reliable information about a user’s future intention in order to increase their immersion and usefulness. For many of such systems, where human locomotion is an essential way of interaction, knowing a user’s future walking direction provides relevant information. This paper explains how head tracking data can be used to retrieve a person’s intended direction of walking. The goal is to provide a reliable and stable path prediction of human locomotion that holds for a few seconds. Using 6 degrees of freedom head tracking data, the head orientation and the head’s movement direction can be derived. Within a user study it is shown that such raw tracking data provides poor prediction results mainly due to noise from gait oscillations. Hence, smoothing filters have to be applied to the data to increase the reliability and robustness of a predictor. Results of the user study show that double exponential smoothing of a person’s walking direction data in combination with an initialization using the head orientation provides a reliable short term path predictor with high robustness.