This work assesses the accuracy of mono and stereo vision-based marker tracking on the Microsoft HoloLens as a representative of current generation AR devices. This is motivated by the need to employ object tracking in industrial AR applications. We integrate mono and stereo vision-based marker tracking with the HoloLens. A calibration procedure is developed that allows users to assess the accuracy of the calibration alignments by walking around the virtual calibration target. This can be generally applied when calibrating additional tracking systems with ready-made AR systems. Finally, the accuracy that can be achieved with the developed system is evaluated (comparing the influence of different parameters).

No abstract

No abstract

This paper analyses the usability of Augmented Reality (AR) in the commissioning and programming of industrial robots. Conducting two individual studies with a total of 31 participants we analysed the three dimensions of usability: effectiveness, efficiency, and user satisfaction by comparing our developed AR system with the conventional Teach-In programming method during the commissioning and modification of offline created robot programs. The results indicate that, while less accurate and hence effective, the AR system is more efficient and has a higher user satisfaction. Beyond that a posture analysis indicates that during a timeframe of 30 min the additional weight of the AR device does not significantly worsen the posture of a worker. Complemented by the positive result of the System Usability Score (SUS) that rates the analysed AR system with a good usability, the overall results indicate that while still limited by its achievable accuracy AR is an intuitive medium to conduct robot programming and commissioning.