Towards Environment- and Task-Independent Locomotion Prediction for Haptic VR

Abstract

The use of robots presenting physical props has significantly enhanced the haptic experience in virtual reality. Autonomous mobile robots made haptic interaction in large walkable virtual environments feasible but brought new challenges. For effective operation, a mobile robot must not only track the user but also predict her future position for the next several seconds to be able to plan and navigate in the common space safely and timely. This paper presents a novel environment- and taskindependent concept for locomotion-based prediction of the user position within a chosen range. Our approach supports the dynamic placement of haptic content with minimum restrictions. We validate it based on a real use case by making predictions within a range of 2 m to 4 m or 2 s to 5 s. We also discuss the adaptation to arbitrary space sizes and configurations with minimal real data collection. Finally, we suggest optimal utilization strategies and discuss the limitations of our approach.