The prediction of human locomotion behavior is a complex task based on data from the given environment and the user. In this study, we trained multiple machine learning models to investigate if data from contemporary virtual reality hardware enables long-and short-term locomotion predictions. To create our data set, 18 participants walked through a virtual environment with different tasks. The recorded positional, orientation-and eye-tracking data was used to train an LSTM model predicting the future walking target. We distinguished between short-term predictions of 50ms and longterm predictions of 2.5 seconds. Moreover, we evaluated GRUs, sequence-to-sequence prediction, and Bayesian model weights. Our results showed that the best short-term model was the LSTM using positional and orientation data with a mean error of 5.14 mm. The best long-term model was the LSTM using positional, orientation and eye-tracking data with a mean error of 65.73 cm. Gaze data offered the greatest predictive utility for long-term predictions of short distances. Our findings indicate that an LSTM model can be used to predict walking paths in VR. Moreover, our results suggest that eye-tracking data provides an advantage for this task.

Figure 1: User perspective of the experiment while walking to a target and avoiding an obstacle.

In many applications of human–computer interaction, a prediction of the human’s next intended action is highly valuable. To control direction and orientation of the body when walking towards a goal, a walking person relies on visual input obtained by eye and head movements. The analysis of these parameters might allow us to infer the intended goal of the walker. However, such a prediction of human locomotion intentions is a challenging task, since interactions between these parameters are nonlinear and highly dynamic. We employed machine learning models to investigate if walk and gaze data can be used for locomotor prediction. We collected training data for the models in a virtual reality experiment in which 18 participants walked freely through a virtual environment while performing various tasks (walking in a curve, avoiding obstacles and searching for a target). The recorded position, orientation- and eye-tracking data was used to train an LSTM model to predict the future position of the walker on two different time scales, short-term predictions of 50[Formula: see text]ms and long-term predictions of 2.5[Formula: see text]s. The trained LSTM model predicted free walking paths with a mean error of 5.14[Formula: see text]mm for the short-term prediction and 65.73[Formula: see text]cm for the long-term prediction. We then investigated how much the different features (direction and orientation of the head and body and direction of gaze) contributed to the prediction quality. For short-term predictions, position was the most important feature while orientation and gaze did not provide a substantial benefit. In long-term predictions, gaze and orientation of the head and body provided significant contributions. Gaze offered the greatest predictive utility in situations in which participants were walking short distances or in which participants changed their walking speed.