[論文レビュー] TPIFM: A Task-Aware Model for Evaluating Perceptual Interaction Fluency in Remote AR Collaboration

Jiarun Song, Ninghao Wan+2 more|arXiv (Cornell University)|Mar 10, 2026

Augmented Reality Applications被引用数 0

ひとこと要約

The paper proposes TPIFM, a task-aware model to evaluate perceptual interaction fluency (PIF) in remote AR collaboration under network impairments, considering task-specific JNDs and using subjective experiments to validate the model.

ABSTRACT

Remote Collaborative Augmented Reality (RCAR) enables geographically distributed users to collaborate by integrating virtual and physical environments. However, because RCAR relies on real-time transmission, it is susceptible to delay and stalling impairments under constrained network conditions. Perceptual interaction fluency (PIF), defined as the perceived pace and responsiveness of collaboration, is influenced not only by physical network impairments but also by intrinsic task characteristics. These characteristics can be interpreted as the task-specific just-noticeable difference (JND), i.e., the maximal tolerable temporal responsiveness before PIF degrades. When the average response time (ART), measured as the mean time per operation from receiving collaborator feedback to initiating the next action, falls within the JND, PIF is generally sustained, whereas values exceeding it indicate disruption. Tasks differ in their JNDs, reflecting distinct temporal responsiveness demands and sensitivities to impairments. From the perspective of the Free Energy Principle (FEP), tasks with lower JNDs impose stricter temporal prediction demands, making PIF more vulnerable to impairments, whereas higher JNDs allow greater tolerance. On this basis, we classify RCAR tasks by JND and evaluate their PIF through controlled subjective experiments under delay, stalling, and hybrid conditions. Building on these findings, we propose the Task-Aware Perceptual Interaction Fluency Model (TPIFM). Experimental results show that TPIFM accurately assesses PIF under network impairments, providing guidance for adaptive RCAR design and user experience optimization under network constraints.

研究の動機と目的

• Motivate and define perceptual interaction fluency (PIF) in RCAR and its dependence on network impairments and task characteristics.
• Introduce the concept of task-specific just-noticeable difference (JND) as a measure of temporal responsiveness tolerance.
• Develop a Task-Aware Perceptual Interaction Fluency Model (TPIFM) to assess PIF across delay, stalling, and hybrid conditions.
• Classify RCAR tasks by JND and analyze PIF using controlled subjective experiments to inform adaptive RCAR design.

提案手法

• Define PIF and JND in RCAR contexts and relate JND to Free Energy Principle (FEP) predictions.
• Conduct controlled subjective experiments under delay, stalling, and hybrid impairments to collect PIF data across tasks.
• Develop TPIFM to map observed PIF to task JND and impairment types.
• Evaluate TPIFM's accuracy in assessing PIF under network impairments and derive design guidance for RCAR optimization.

実験結果

リサーチクエスチョン

• RQ1 How do task-specific JNDs influence perceptual interaction fluency in remote AR collaboration under network impairments?
• RQ2 Can TPIFM accurately assess PIF across delay, stall, and hybrid conditions?
• RQ3 How do temporal prediction demands (per FEP) affect PIF vulnerability across tasks with different JNDs?
• RQ4 What guidance can TPIFM provide for adaptive RCAR design under network constraints?

主な発見

• TPIFM successfully assesses PIF under network impairments in controlled experiments.
• Tasks with lower JNDs impose stricter temporal prediction demands and show greater PIF vulnerability.
• Higher-JND tasks exhibit greater tolerance to temporal impairments as predicted by the model.
• The results provide guidance for adaptive RCAR design and user experience optimization under network constraints.