SkillAR: omnipresent in-situ feedback for motor skill training using AR
Open accessPublished version of a preprint
Abstract
We present a novel technique called SkillAR to display augmented reality feedback for motor skill learning on a head-mounted display (HMD). SkillAR allows the user to consider movement corrections independent of the head position. Therefore, the user can receive motor feedback comfortably without risking an incorrect exercise performance. Head-mounted displays represent versatile technologies for providing motor feedback regarding skill training. In contrast to room-mounted displays, HMDs are easily portable and wearable. That allows for in-situ feedback in many situations where this would otherwise not be possible. However, the spatial positioning of the 3D feedback is not trivial. On the one hand, the user needs to understand the relation between the body and the suggested corrections in the space. On the other hand, certain exercises demand a specific head positioning to minimize errors and injuries. Depending on the exercise and the type of feedback, these two aspects can be highly conflicting. The paper at hand presents a solution for augmented reality headsets, that provides continuous and omnipresent motor feedback comfortably while facilitating a correct exercise performance. In an in-subject user study with 39 participants, we could not detect a significant disadvantage to SkillAR compared to conventional feedback methods found in the literature regarding identification and execution time as well as identification accuracy, in addition to the apparent major advantages for user health and usability. Furthermore, we found that the users could identify the feedback on the HMD more accurately.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
A mobile AR intervention in elementary school children produced significant differences in gross motor development measured by TGMD-2.
“Diller et al., 2025) conducted a mobile AR intervention on elementary school children and found significant differences in gross motor development with the Test of Gross Motor Development-Second Edition (TGMD-2).”
From Real-time feedback enhances motor learning and motivation in youth team sports through augmented reality tools (2025) · cites this paper as Diller et al., 2025
Section 4.1 reports 32 participants aged 22–61, not elementary-school children. Section 4.4 says the study assessed comprehension of AR feedback rather than motor development, and Section 6 reports no significant difference in pose-imitation accuracy. The cited paper therefore does not report a significant TGMD-2 difference in children. (LLM, conf=0.90)
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredA head-worn AR system with ongoing spatial feedback (SkillAR) improved movement patterns with orientation-free corrections.
“Diller et al. (2025) introduced SkillAR, a head-worn AR-based system with ongoing spatial feedback that showed success in improving movement patterns with orientation-free corrections.”
From Real-time feedback enhances motor learning and motivation in youth team sports through augmented reality tools (2025) · cites this paper as Diller et al. (2025)
The Abstract and System overview describe SkillAR as a head-worn AR system that provides continuous feedback and lets users consider movement corrections independently of head position. However, the Discussion reports no significant difference from a room-mounted display in pose-imitation accuracy; the study showed better identification of corrections, not an improvement in movement patterns. (LLM, conf=0.86)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Hattie, J., & Timperley, H. (2007) · Review of Educational Research · doi:10.3102/003465430298487 · Cited by 12,905 · see citing works
Flagged first, then by citations
Research works printed but not linked: 31
- PCA, Leite H (2023) Virtual reality applied to physiotherapy: a review of current knowledge. Virt Real 27(1):71-95. h t t p s : / / d o i . o r / 1 0 . 1 0 0 7 / s 1 0 0 5 5 -0 2 2 -0 0 6 5 4 -2 · DOI
- Campo-Prieto P, Cancela JM, Rodríguez-Fuentes G (2021) Immersive virtual reality as physical therapy in older adults: present or future (systematic review). Virt Real 25(3):801-817. h t t p s : / / d o i . o r g / 1 0 . 1 0 0 7 / s 1 0 0 5 5 -0 2 0 -0 0 4 9 -x · DOI
- Diller F, Scheuermann G, Wiebel A (2024) Visual cue based corrective feedback for motor skill training in mixed reality: A survey. IEEE Trans Visual Comput Gr 30(7):3121-3134. h t t p s : / / d o i . o r g / 1 0 . 1 1 0 9 / T V C G . 2 0 2 2 . 3 2 2 7 9 9 9 · DOI
- Online as early access since 2022) · DOI
- Lysakowski RS, Walberg HJ (1982) Instructional effects of cues, par- ticipation, and corrective feedback: a quantitative synthesis. Am Educ Res J 19(4):559-572. h t t p s : / / d o i . o r g / 1 0 . 3 1 0 2 / 0 0 0 2 8 3 1 2 0 1 9 0 0 4 · DOI
- Rymal AM, Ste-Marie DM (2009) Does self-modeling affect imagery ability or vividness? J Imag Res Sport Phys Act. h t t p s : / / d o i . o r g / 1 0 . 2 2 0 2 / 1 9 3 2 -0 1 9 1 . 1 0 · DOI
- White A, Hardy L (1998) An in-depth analysis of the uses of imagery by high-level slalom canoeists and artistic gymnasts. Sport Psy- chol 12(4):387-403. h t t p s : / / d o i . o r g / 1 0 . 1 1 2 3 / t s p . 1 2 . 4 . 3 8 · DOI
- Desmond, J.C.: Meaning in Motion: New Cultural Studies of Dance. Duke University Press, Durham (1997). h t t p s : / / d o i . o r / 1 0 . 2 3 0 7 / . 2 4 . 1 · DOI
- Kim, S., Seo, D., Lee, S., Kim, Y., Kang, H.W., Choi, Y.-S., Jung, J.-W.: Real-Time Motion Feedback System based on Smart Mir- ror Vision. 2020 Joint 11th international conference on soft com- puting and intelligent systems and 21st international symposium on advanced intelligent systems (SCIS-ISIS) 00, 1-4 (2020) h t t p s : / / d o i . o r / 1 0 . 1 1 0 9 / s c i s i s i s 5 0 0 6 4 . 2 0 2 0 . 9 3 2 2 7 · DOI
- Park HS, Lee GA, Seo B-K, Billinghurst M (2021) User experience design for a smart-mirror-based personalized training system. Multimedia Tools Appl 80(20):31159-31181. h t t p s : / / d o i . o / 0 0 7 / s 1 1 0 4 2 -0 2 0 -1 0 1 4 8 -5 · DOI
- Waltemate, T., Senna, I., Hülsmann, F., Rohde, M., Kopp, S., Ernst, M., Botsch, M.: The impact of latency on perceptual judgments and motor performance in closed-loop interaction in virtual real- ity. Proceedings of the 22nd ACM Conference on Virtual Reality Software and Technology, 27-35 (2016) h t t p s : / / d o i . o r g / 1 0 . 1 1 4 5 / 2 9 9 3 3 6 9 . 2 9 9 3 3 · DOI
- Hülsmann F, Frank C, Senna I, Ernst MO, Schack T, Botsch M (2019) Superimposed skilled performance in a virtual mirror improves motor performance and cognitive representation of a full body motor action. Front Robot AI 6:43. h t t p s : / / d o i . o r g / 1 0 . 3 3 8 9 / f r o b t . 2 0 1 9 . 0 0 0 4 · DOI
- Inoue Y, Kitazaki M (2021) Virtual mirror and beyond: the psycho- logical basis for avatar embodiment via a mirror. J Robot Mech 33(5):1004-1012
- González-Franco, M., Pérez-Marcos, D., Spanlang, B., Slater, M.: The contribution of real-time mirror reflections of motor actions on virtual body ownership in an immersive virtual environment. In: 2010 IEEE Virtual Reality Conference (VR), pp. 111-114 (2010). h t t p s : / / d o i . o r g / 1 0 . 1 1 0 9 / V R . 2 0 1 0 . 5 4 4 4 8 0 · DOI
- Anderson, F., Grossman, T., Matejka, J., Fitzmaurice, G.: Youmove: enhancing movement training with an augmented reality mirror. In: Proceedings of the 26th Annual ACM Symposium on User Interface Software and Technology. UIST '13, pp. 311-320. Association for Computing Machinery, New York, NY, USA (2013). h t t p s : / / d o i . o r g / 1 0 . 1 1 4 5 / 2 5 0 1 9 8 8 . 2 5 0 2 0 · DOI
- Trajkova M, Cafaro F (2018) Takes Tutu to ballet: designing visual and verbal feedback for augmented mirrors. Proc ACM Interactive, Mobile, Wearable Ubiquitous Technol 2(1):1-30. h t t p s : / / d o i . o r / 1 0 . 1 1 4 5 / 3 1 9 1 7 · DOI
- Treede RD, Rief W, Barke A, Aziz Q, Bennett MI, Benoliel R, Cohen M, Evers S, Finnerup NB, First MB, Giamberardino MA, Kaasa S, Kosek E, Lavand'homme P, Nicholas M, Perrot S, Scholz J, Schug S, Smith BH, Svensson P, Vlaeyen JWS, Wang SJ (2015) A classification of chronic pain for ICD-11. Pain 156(6):1003- 1007. h t t p s : / / d o i . o r g / 1 0 . 1 0 9 7 / j . p a i n . 0 0 0 0 0 0 0 0 0 0 0 0 0 1 6 0 1 3 on -CHIuXiD'19, 1-8 (2019) h t t p s : / / d o i . o r g / 1 0 . 1 1 4 5 / 3 3 2 8 2 4 3 . 3 3 2 8 2 · DOI
- L'Yi S, Jo J, Seo J (2021) Comparative layouts revisited: Design space, guidelines, and future directions. IEEE Trans Visual Comput Gr 27(2):1525-1535. h t t p s : / / d o i . o r g / 1 0 . 1 1 0 9 / T V C G . 2 0 2 0 . 3 0 3 0 4 1 · DOI
- Hoang, T.N., Reinoso, M., Vetere, F., Tanin, E.: Onebody: Remote posture guidance system using first person view in virtual environment. In: Proceedings of the 9th Nordic Conference on Human-Computer Interaction. NordiCHI '16. Association for Computing Machinery, New York, NY, USA (2016). h t t p s : / / d o i . o r / 1 0 . 1 1 4 5 / 2 9 7 1 4 8 5 . 2 9 7 1 5 · DOI
- Le Naour T, Hamon L, Bresciani J-P (2019) Superimposing 3d vir- tual self + expert modeling for motor learning: Application to the throw in American football. Front ICT. h t t p s : / / d o i . o r g / 1 0 . 3 3 8 9 / fi c t . 2 0 1 9 . 0 0 0 1 · DOI
- Raffe, W.L., Garcia, J.A.: Combining skeletal tracking and virtual reality for game-based fall prevention training for the elderly. In: 2018 IEEE 6th International Conference on Serious Games and Applications for Health (SeGAH), pp. 1-7 (2018). h t t p s : / / d o i . o r g / 1 0 . 1 1 0 9 / S e G A H . 2 0 1 8 . 8 4 0 1 3 7 · DOI
- United Nations, Department of Economic and Social Affairs, Popula- tion Division: World Population Prospects 2022, Online Edition. Accessed 2024/12/16 (2023). h t t p s : / / p o p
- Diller, F., Wiebel, A., Scheuermann, G.: Automatic viewpoint selec- tion for interactive motor feedback using principle component analysis. In: VISIGRAPP: GRAPP, HUCAPP, IVAPP, pp. 350- 361 (2024). h t t p s : / / d o i . o r / 1 0 . 5 2 2 0 / 0 0 1 2 3 0 8 7 0 0 0 0 3 · DOI
- Publisher's Note Springer Nature remains neutral with regard to juris- dictional claims in published maps and institutional affiliations.
- Chua, P.T., Crivella, R., Daly, B., Hu, N., Schaaf, R., Ventura, D., Camill, T., Hodgins, J., Pausch, R.: Training for Physical Tasks in Virtual Environments: Tai Chi. IEEE Virtual Reality, 2003. Pro- ceedings, 87-94 (2003) h t t p s : / / d o i . o r g / 1 0 . 1 1 0 9 / v r . 2 0 0 3 . 1 1 9 1 1 · DOI · Paper page
- Han, P.-H., Chen, Y.-S., Zhong, Y., Wang, H.-L., Hung, Y.-P.: My Tai-Chi Coaches: An Augmented-Learning Tool for Practicing Tai-Chi Chuan. Proceedings of the 8th Augmented Human Inter- national Conference, 1-4 (2017) h t t p s : / / d o i . o r g / 1 0 . 1 1 4 5 / 3 0 4 1 1 6 4 . 3 0 4 1 1 · DOI
- Yan, S., Ding, G., Guan, Z., Sun, N., Li, H., Zhang, L.: OutsideMe: augmenting dancer's external self-image by using a mixed real- ity system. proceedings of the 33rd annual ACM conference extended abstracts on human factors in computing systems, 965- 970 (2015) h t t p s : / / d o i . o r g / 1 0 . 1 1 4 5 / 2 7 0 2 6 1 3 . 2 7 3 2 7 5 · DOI
- Kawasaki, H., Iizuka, H., Okamoto, S., Ando, H., Maeda, T.: Col- laboration and skill transmission by first-person perspective view sharing system. 19th international symposium in robot and human interactive communication, 125-131 (2010) h t t p s : / / d o i . o r / 1 0 . 1 1 0 9 / r o m a n . 2 0 1 0 . 5 5 9 8 6 · DOI
- Kasahara, S., Ando, M., Suganuma, K., Rekimoto, J.: Parallel Eyes: Exploring Human Capability and Behaviors with Paralleled First Person View Sharing. Proceedings of the 2016 CHI conference on human factors in computing systems, 1561-1572 (2016) h t t p s : / / d o i . o r g / 1 0 . 1 1 4 5 / 2 8 5 8 0 3 6 . 2 8 5 8 4 · DOI
- Ikeda, A., Hwang, D.H., Koike, H.: AR based self-sports learning sys- tem using decayed dynamic time warping algorithm. eurograph- ics symposium on virtual environments (2018) (2018) h t t p s : / / d o i . o r g / 1 0 . 2 3 1 2 / e g v e . 2 0 1 8 1 3 · DOI
- Hamanishi, N., Miyaki, T., Rekimoto, J.: Assisting viewpoint to under- stand own posture as an avatar in-situation. Proceedings of the 5th International ACM In-Cooperation HCI and UX Conference
Cited by
Sorted by citations
He, X., & Wei, L. (2025) · Frontiers in Psychology · doi:10.3389/fpsyg.2025.1661936 · Cited by 11 · see citing works
- Authors
- Diller, F., Henkel, N., Scheuermann, G., & Wiebel, A.
- Affiliations
- University of Applied Sciences Worms (DE)
- Leipzig University (DE)
- Corresponding author
- Diller, Florian
- Scheuermann, Gerik
- Venue
- Virtual Reality
- Published
- 2025-02-04
- Volume
- 29
- Issue
- 1
- ISSN
- 1359-4338 (ISSN-L)
- 1434-9957
- OpenAlex
- W4407143739
- Cited by
- 7
- References
- 1
- Citations by year
- 2026: 5 · 2025: 2
- FWCI
- 2.47
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- Virtual Reality (publishedVersion, cc-by)
- Research Square (acceptedVersion, cc-by)
- Funders
- Hochschule Worms
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Augmented Reality Applications
- Physical Sciences › Computer Science › Human-Computer Interaction › Virtual Reality Applications and Impacts
- Physical Sciences › Computer Science › Human-Computer Interaction › Interactive and Immersive Displays
- Keywords
- motor skill training, head-mounted displays, motion correction, exercise performance, usability
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review