A Room to Roam: Real-Time Reset Prediction for Redirected Walking Based on Environment Layouts.

Abstract

Redirected Walking (RDW) allows users to explore large virtual environments by using overt resets to reorient users and prevent collisions. However, frequent resets increase the risk of cybersickness and reduce presence. Real physical environments are usually cluttered, and the complexity of their layouts affects the reset frequency. Physical spaces usually contain various objects, some fixed (e.g., built-ins) and some movable (e.g., furniture), creating opportunities to reduce the need for resets by rearranging movable objects. Systematically evaluating alternative layouts is challenging because repeated user testing is costly, and simulation-based approaches are often too slow for interactive design. We introduce a deep-learning predictor that estimates the expected number of resets directly from top view layout maps of physical and virtual environments. Trained on large-scale simulation data, the model generalizes to unseen layouts and provides interactive predictions at a rate of 105 milliseconds per layout. We embedded the predictor in a layout-editing interface and compared three interfaces (intuition-driven, simulation-based, and prediction-based) in a user study. Participants reached the pre-specified reset target with all three interfaces. With the prediction-based interface, they reached it in less time, with lower workload and higher usability. Additionally, consultations with four RDW experts emphasized effort, sequencing constraints, and object semantics, and recommended localized readouts showing where resets occur. These results suggest that continuous reset estimates reduce the time and workload needed to prepare a cluttered space for RDW.