AI in psychomotor ITS is used predominantly for feedback construction rather than for task recommendation or adaptation¶

Claim · All claims
Evidence · 1 study · review r3 · q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? The predominant AI use is constructing feedback (pose estimation, gesture recognition, classification, rule-based pose checking), while recommendation/adaptation use cases are comparatively few. → Gianluca Romano 2025

Evidence¶

Gianluca Romano 2025¶

Gianluca Romano, Jan Schneider, Daniele Di Mitri, Hendrik Drachsler. (2025). Through the Telescope: A Systematic Review of Intelligent Tutoring Systems and Their Applications in Psychomotor Skill Learning. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-025-00526-1

q2 · i? · review · r3

Qualitative synthesis of AI usage across the reviewed ITS. Camera/sensor systems retrieve skeleton representations for gesture recognition (dance, yoga, badminton), rule-based systems discern correct from incorrect poses via angles or distance-based metrics, and neural networks classify behavior such as CPR compression.

"However, the number of AI use cases for recommendations is low compared to those for feedback construction."

Discussion¶

Related Claims¶

• Existing ITS for psychomotor skills predominantly target fine, closed, internally paced, discrete, individual, and simple skills — related
• AI is implemented in SRL research primarily as an intervention, most often through adaptive systems and personalization — related