A novel context-aware augmented reality framework for maintenance systems

Augmented Reality (AR) bridges the gap between the real and the virtual world by bringing virtual information to a real environment as seamlessly as possible. The need for better perception of knowledge-intensive complex maintenance tasks and access to large amounts of documents and data makes the use of AR technology promising in a maintenance domain. Context-awareness enhances the usability of such AR applications, i.e. the output and behavior of the system will be adapted according to different contexts, such as the user location, preferences, devices, etc. to afford a higher level of personalization. The adaptation needs to be efficient in terms of performance and speed. This paper presents an optimized framework which combines context-awareness and AR for training and assisting technicians in maintaining equipment in an industrial context to improve field workers effectiveness. Ontology is used to model a maintenance context, and Semantic Web Rule Language (SWRL) provides logical reasoning. This optimized framework utilizes a behavior network to select a collection of suitable actions based on the current step of an ongoing task, and applies context-based inferred information from the ontology to each member of this collection. Evaluation results comparing the performance of the proposed framework with conventional ontology alone in a maintenance domain confirmed that the proposed framework in this research provides the same results as the ontology in terms of content, but it runs much faster in terms of run-time and performance. The proposed context-aware framework is quite valuable especially in terms of response time and performance for maintenance systems with a large number of maintenance activities.