Modular augment reality platform for smart operator in production environment

Jumyung Um, Jens Popper, Martin Ruskowski



The trend of mass customization requires highly flexible production systems, which pose a new challenge for workers. Numerous concepts using augmented reality technologies have been developed to offer support in manual assembly processes. Newer AR devices are equipped with more and more functions, such as microphones, speakers or multiple camera systems, which can be used to help workers. However, wearable devices offer only limited computational power and limited flexibility of their interface platform. This poses a challenge to heavy data transactions from various different sources and restrict the use for real-time responses, which are often necessary for applications in a factory. To overcome this limitation, the author of this paper proposes a combination of wearable devices with edge devices located on the shop floor. An augmented reality platform was constructed with modularized services by using the digital twin of the machine components and machine learning algorithms for object recognition. This is integrated in the factory environment to synchronize real machine components withtheir digital twin.

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence