Pluto: Motion Detection for Navigation in a VR Headset
This is an incremental improvement for VR systems to enhance robustness in challenging environments.
The paper tackled the problem of tracking failure in VR navigation due to poor illumination or low saliency by detecting motion and stillness states from accelerometer data, achieving 87% accuracy and a 40% reduction in navigation drift in failure scenarios.
Untethered, inside-out tracking is considered a new goalpost for virtual reality, which became attainable with advent of machine learning in SLAM. Yet computer vision-based navigation is always at risk of a tracking failure due to poor illumination or saliency of the environment. An extension for a navigation system is proposed, which recognizes agents motion and stillness states with 87% accuracy from accelerometer data. 40% reduction in navigation drift is demonstrated in a repeated tracking failure scenario on a challenging dataset.