# Short-Term Trajectory Prediction for Full-Immersive Multiuser Virtual Reality with Redirected Walking

arXiv: https://arxiv.org/abs/2207.07520 · HTML: https://mlsanity.com/paper/2207.07520/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 17 references that are in the map.
- First posted on arXiv 15 Jul 2022.

## Builds on (most cited first, 5 of 5)

- [Context-Aware Trajectory Prediction](https://mlsanity.com/paper/1705.02503/) (2017)
- [Towards Low-Latency and Ultra-Reliable Virtual Reality](https://mlsanity.com/paper/1801.07587/) (2018)
- [Learning-based Prediction, Rendering and Transmission for Interactive Virtual Reality in RIS-Assisted Terahertz Networks](https://mlsanity.com/paper/2107.12943/) (2021)
- [Towards Ultra-Low-Latency mmWave Wi-Fi for Multi-User Interactive Virtual Reality](https://mlsanity.com/paper/2008.12086/) (2020)
- [Millimeter-Wave Beamforming with Continuous Coverage for Mobile Interactive Virtual Reality](https://mlsanity.com/paper/2105.11793/) (2021)

## Built on by (most cited first, 1 of 1)

- [F-RDW: Redirected Walking with Forecasting Future Position](https://mlsanity.com/paper/2304.03497/) (2023)

## Abstract (arXiv)

Full-immersive multiuser Virtual Reality (VR) envisions supporting unconstrained mobility of the users in the virtual worlds, while at the same time constraining their physical movements inside VR setups through redirected walking. For enabling delivery of high data rate video content in real-time, the supporting wireless networks will leverage highly directional communication links that will "track" the users for maintaining the Line-of-Sight (LoS) connectivity. Recurrent Neural Networks (RNNs) and in particular Long Short-Term Memory (LSTM) networks have historically presented themselves as a suitable candidate for near-term movement trajectory prediction for natural human mobility, and have also recently been shown as applicable in predicting VR users' mobility under the constraints of redirected walking. In this work, we extend these initial findings by showing that Gated Recurrent Unit (GRU) networks, another candidate from the RNN family, generally outperform the traditionally utilized LSTMs. Second, we show that context from a virtual world can enhance the accuracy of the prediction if used as an additional input feature in comparison to the more traditional utilization of solely the historical physical movements of the VR users. Finally, we show that the prediction system trained on a static number of coexisting VR users be scaled to a multi-user system without significant accuracy degradation.