Augmented reality based on edge computing using the example of remote live support

Abstract

Augmented Reality (AR) introduces vast opportunities to the industry in terms of time and therefore cost reduction when utilized in various tasks. The biggest obstacle for a comprehensive deployment of mobile AR is that current devices still leave much to be desired concerning computational and graphical performance. To improve this situation in this paper we introduce an AR Edge Computing architecture with the aim to offload the demanding AR algorithms over the local network to a high-end PC considering the real-time requirements of AR. As an example use case we implemented an AR Remote Live Support application. Applications like this on the one hand are strongly demanded in the industry at present, on the other hand by now mostly do not implement a satisfying tracking algorithm lacking computational resources. In our work we lay the focus on both, the possibilities our architecture offers regarding improvements of tracking and the challenges it implies in respect of real-time. We found that offloading AR algorithms in real-time is possible with available WiFi making use of standard compression techniques like JPEG. However it can be improved by future radio solutions offering higher bandwidth to avoid additional latency contributed by the coding.