Augmented Reality Multistation Warning System Using Wearable Artificial Intelligence
Akhmetov T. Moger G.D. Varol H.A.
2025Institute of Electrical and Electronics Engineers Inc.
Proceedings of the Annual International Conference on Control, Automation and Robotics, ICCAR
2025Issue 2025483 - 492 pp.
This study presents an innovative augmented reality (AR)-based warning system aimed at enhancing safety and productivity in small-batch production environments by mitigating distractions that can lead to accidents, injuries, and costly production downtime. Deployed on wearable AR glasses with optical see-through technology, the system uses an on-device computer vision model to track the positions of multiple stations, eliminating the need for cloud or remote server processing. The system is designed to improve situational awareness in environments where operator vigilance is crucial for maintaining productivity and safety, particularly in operations involving CNC machines, drilling machines, and 3D printers. Vigilance is especially critical for automated machines like CNCs, where emergencies can escalate into severe hazards such as fires, and for drilling machines, where mishandling can cause injuries or damage. While 3D printer failures are less hazardous, they can still lead to significant downtime and require operator intervention for tasks like adjusting print models or replacing filament. Unlike traditional machine alert systems that rely on audible or visual signals from individual machines, the AR-based system consolidates and contextualizes alerts to minimize distractions caused by overlapping or ambiguous notifications. To evaluate its effectiveness, experiments were conducted with 16 participants, testing three hypotheses: does the system reduce inattention compared to standard systems (H1), is it user-friendly (H2), and does it lower cognitive and physical workload (H3)? Results show that the AR system significantly reduces inattention and mental effort, and offers a positive user experience, particularly in visual warning mode. The study also discusses current limitations of wearable devices and suggests improvements for enhancing usability and ergonomics, paving the way for safer and more efficient industrial operations.
artificial intelligence , augmented reality , eye tracking , industrial safety , warning system
Text of the article Перейти на текст статьи
Nazarbayev University, Institute of Smart Systems and Ai, Astana, 010000, Kazakhstan
Nazarbayev University
10 лет помогаем публиковать статьи Международный издатель
Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026