AI-assisted AR guidance improved first-trial task success from 20% unassisted to 70% in a 12-participant, 144-session human study, alongside a new multimodal dataset and evaluation framework.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards Effective Human-in-the-Loop Assistive AI Agents
AI-assisted AR guidance improved first-trial task success from 20% unassisted to 70% in a 12-participant, 144-session human study, alongside a new multimodal dataset and evaluation framework.