Project Grant 2616182

The National Science Foundation Division of Computing and Communication Foundations awarded Duke University $500,000 on October 1, 2026, under the Computer and Information Science and Engineering program to develop automated evaluation and monitoring methods for augmented reality guidance in pervasive AR and human-robot collaboration applications.

The project will create foundations for detecting and preventing five categories of AR guidance failures: poor legibility, inaccurate spatial alignment, incorrect guidance, unsafe guidance, and contextually inappropriate guidance. The research team will collect and annotate large datasets of AR guidance examples across varied physical environments, lighting conditions, tasks, and robotic collaboration settings, then develop evaluation methods combining AR device data and other inputs to automatically assess whether AR systems are clear, correct, safe, and appropriate for their physical context. The work spans navigation, training, maintenance, healthcare, warehouse operations, and human-robot collaboration environments.

Duke University's Office of Research Administration will execute the work in Durham, North Carolina. The period of performance runs from October 1, 2026, through September 30, 2030. The project includes education and workforce development components training students in augmented reality, robotics, artificial intelligence, edge computing, and human-centered system design, with plans to share datasets, software, and demonstrations with researchers, industry, and the public.