Skill-Adaptive Ghost Instructors: Enhancing Retention and Reducing Over-Reliance in VR Piano Learning

要旨

Motor-skill learning systems in XR rely on persistent cues. However, constant cueing can induce overreliance and erode memorization and skill transfer. We introduce a skill-adaptive, dynamically transparent ghost instructor whose opacity adapts in real time to learner performance. From a first-person perspective, users observe a ghost hand executing piano fingering with either static or performance-adaptive transparency in a VR piano training. We conducted a within-subjects study (N=30), where learners practiced with traditional Static (fixed-transparency) and our proposed Dynamic (performance-adaptive) modes and were tested without guidance immediately and after a 10-minute retention interval. Relative to Static, the Dynamic mode yielded higher pitch and fingering accuracy and limited error increases. These findings suggest adaptive transparency helps learners internalize fingerings, reducing dependency on external cues and improving short-term skill retention in immersive learning. We discuss design implications for motor-skill learning and outline extensions of this approach to long-term retention and complex tasks.

著者
Tzu-Hsin Hsieh
Delft University of Technology, Delft, Netherlands
Cassandra Michelle Stefanie. Visser
Delft University of Technology, Delft, Zuid-Holland, Netherlands
Elmar Eisemann
Delft University of Technology, Delft, Netherlands
Ricardo Marroquim
TU Delft, Delft, Netherlands

会議: CHI 2026

ACM CHI Conference on Human Factors in Computing Systems

セッション: Learning, Training, and Self-Development with AI

P1 - Room 125
7 件の発表
2026-04-13 20:15:00
2026-04-13 21:45:00