Journal of Visual Computing logo

Articles

Vol. 1 No. 1 (2026)

Field Experiment of Assembly Accuracy with Augmented Reality Overlays in Aircraft Maintenance Training

Submitted
January 7, 2026
Published
January 26, 2026

Abstract

The integration of augmented reality into industrial training protocols represents a significant paradigm shift in how complex spatial tasks are taught and executed. This study presents comprehensive field experiment evidence assessing the impact of augmented reality overlays on assembly accuracy within the highly critical domain of aircraft maintenance training. As modern aviation systems grow increasingly complex, the cognitive demand placed on maintenance technicians escalates, thereby increasing the risk of assembly errors which could lead to catastrophic failures. Traditional training methodologies, which rely heavily on two-dimensional technical manuals and abstract diagrammatic reasoning, often fail to adequately support the spatial cognition required for three-dimensional assembly tasks. To address this gap, we conducted a rigorous field experiment involving novice technicians tasked with assembling a high-fidelity aircraft hydraulic pump mechanism. Participants were divided into a control group utilizing standard interactive electronic technical manuals and an experimental group utilizing head-mounted augmented reality devices that provided context-aware, three-dimensional holographic overlays. The empirical evidence demonstrates a substantial reduction in both critical and non-critical assembly errors among participants trained with augmented reality overlays. Furthermore, the data suggests that augmented reality significantly mitigates extraneous cognitive load by spatially anchoring instructional information directly onto the physical task space. These findings offer robust empirical validation for the adoption of augmented reality in safety-critical maintenance training, highlighting its potential to enhance assembly accuracy, streamline skill acquisition, and ultimately improve the operational reliability of aviation systems.

References

  1. 1. Haghbayan, M.-H.; Farahnakian, F.; Poikonen, J.; Laurinen, M.; Nevalainen, P.; Plosila, J. An efficient multi- sensor fusion approach for object detection in maritime environments. In Proceedings of the 2018 21st International Conference on Intelligent Transportation Systems (ITSC), Maui, HI, USA, 4–7 November 2018; IEEE: New York, NY, USA, 2018.
  2. 2. Huang, L.; Wang, W.; Chen, J.; Wei, X.Y. Attention on attention for image captioning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Pepublic of Korea, 27–28 October 2019; pp. 4634–4643.
  3. 3. Fasbender, A.; Tuia, D.; Bogaert, P.; Kanevski, M. Support-based implementation of Bayesian data fusion for spatial enhancement: Applications to ASTER thermal images. IEEE Geosci. Remote Sens. Lett. 2008, 5, 598–602.
  4. 4. Liu, Y.; Li, Q.; Xu, Y.; Chen, Y.; Men, Y. Comparison of the safety between propylthiouracil and methimazole with hyperthyroidism in pregnancy: A systematic review and meta-analysis. PLoS ONE 2023, 18, e0286097.
  5. 5. Tan, W.; Geng, B.; Bai, X. A study on infrared-visible fusion multimodal object detection algorithm based on cross-modal information bottleneck and minimum redundancy transformation. Sci. Rep. 2026, 16, 12991.
  6. 6. Amazon Web Services, Inc. Elastic Load Balancing. Available online: https://docs.aws.amazon.com/elasticloadbalancing (accessed on 30 March 2026).
  7. 7. Amazon Web Services, Inc. Amazon EC2—Cloud Compute Capacity. Available online: https://aws.amazon.com/ec2 (accessed on 30 March 2026).
  8. 8. Bi, Y.; Hu, Z. Disentangled contour learning for quadrilateral text detection. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Virtual, 5–9 January 2021; pp. 909–918.
  9. 9. Tang, C.; Tian, G.; Boussakta, S.; Wu, J. Feature-supervised compressed sensing for microwave imaging systems. IEEE Trans. Instrum. Meas. 2019, 69, 5287–5297.
  10. 10. Ing, E.; Bondok, M. Oculoplastics and Augmented Intelligence: A Literature Review. J. Clin. Med. 2025, 14, 6875.
  11. 11. Ooi, Y.K.; Ibrahim, H. Deep learning algorithms for single image super-resolution: A systematic review. Electronics 2021, 10, 867.
  12. 12. Busso, C.; Deng, Z.; Yildirim, S.; Bulut, M.; Lee, C.M.; Kazemzadeh, A.; Lee, S.; Neumann, U.; Narayanan, S. Analysis of emotion recognition using facial expressions, speech and multimodal information. In Proceedings of the 6th International Conference on Multimodal Interfaces, New York, NY, USA, 13–15 October 2004.
  13. 13. Swets, J.A. Measuring the accuracy of diagnostic systems. Science 1988, 240, 1285–1293.
  14. 14. Lin, Y.-C.; Chiang, P.-Y.; Miaou, S.-G. Enhancing deep-learning object detection performance based on fusion of infrared and visible images in advanced driver assistance systems. IEEE Access 2022, 10, 105214–105231.
  15. 15. Küng, R.; Jung, P. Robust nonnegative sparse recovery and 0/1-Bernoulli measurements. In Proceedings of the 2016 IEEE Information Theory Workshop (ITW); IEEE: Piscataway, NJ, USA, 2016; pp. 260–264.
  16. 16. Wagner, J.; Andre, E.; Lingenfelser, F.; Kim, J. Exploring fusion methods for multimodal emotion recognition with missing data. IEEE Trans. Affect. Comput. 2011, 2, 206–218.