Search

Though in their infancy, mixed reality systems have proven to aid humans in mission critical tasks, once performed manually and requiring diverse skilled manpower. Industry 4.0 initiatives have seen mixed reality systems successfully adopted by many aerospace manufacturing environments, however aerospace maintenance and sustainment has been slower to adopt such initiatives, for various reasons. The paper reports about a mixed reality-based aircraft maintenance task that has been performed and compared with a non-mixed reality-based manual task. The data was collected using computer vision and machine learning techniques unobtrusively, generating both qualitative and quantitative measures, and a usability metric was derived. Furthermore, feature selection techniques are employed to determine the accuracy of the machine learning (ML) based usability assessment model. Supervised learning methods are employed for unstructured physiological data, and a usability metric for mixed-reality systems has been assessed based on dynamic features. The preliminary results are encouraging and lay the foundation for deriving data-driven models to predict usability of mixed reality systems when used in complex aircraft maintenance tasks. [ABSTRACT FROM AUTHOR]