This paper presents a novel reference software architecture and supporting pattern language for an augmented reality authoring and training system. Industry-based augmented reality training is considered an essential element of the next techno-industrial revolution. These next generation learning environments allow a trainee to offload complexity and giving them live (or on-demand) feedback on their progress and performance through workplace augmentation is already being taken up by industry forerunners. This reference architecture-for wearable experience for knowledge intensive training-incorporates head-mounted augmented vision, an array of wearable sensors that monitor movement and physiological signals, a data-layer managing sensor data and a cloud-based repository for storing information about the activity and workplace. Moreover, this architecture has been tested in a range of knowledge intensive workplaces, in the aeronautic, medical and space industries. Two iterations of the architecture were developed and validated, together with over 500 participants, producing datasets on activity performance, physiological state and assessment of the platform. The components and links of the architecture are presented here as generalizable design patterns to support wider development. We then propose a pattern language for augmented reality training applications.
|Publication status||Published - Dec 2019|
|MoE publication type||Not Eligible|
|Event||IEEE International Conference on Engineering, Technology and Education, IEEE TALE 2019: Creative & Innovative Education to Enhance the Quality of Life - Yogyakarta, Indonesia|
Duration: 10 Dec 2019 → 13 Dec 2019
|Conference||IEEE International Conference on Engineering, Technology and Education, IEEE TALE 2019|
|Abbreviated title||IEEE TALE 2019|
|Period||10/12/19 → 13/12/19|
Guest, W., Wild, F., Di Mitri, D., Klemke, R., Karjalainen, J., & Helin, K. (2019). Architecture and Design Patterns for Distributed, Scalable Augmented Reality and Wearable Technology Systems. Paper presented at IEEE International Conference on Engineering, Technology and Education, IEEE TALE 2019, Yogyakarta, Indonesia.