Assessing the Impact of AR-Assisted Warnings on Roadway Worker Stress Under Different Workload Conditions

Banani Ardecani, Fatemeh; Kumar, Amit; Shoghli, Omidreza · 2024 · Crossref

DOI: 10.22260/isarc2024/0065

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This study addresses the rising number of fatal crashes in roadway work zones by investigating how Augmented Reality (AR)-assisted warnings impact worker stress under varying workload conditions. While previous research focused on external safety factors, this work examines the internal physiological responses of workers, specifically how light- versus medium-intensity activities affect stress levels when receiving multi-sensory warnings. The research aims to bridge the gap in understanding how these factors influence worker stress, thereby informing the development of improved warning systems and resource allocation strategies in construction settings. The researchers conducted an experiment using a high-fidelity Virtual Reality (VR) environment to simulate a roadway work zone, allowing for safe testing of high-risk scenarios. Eighteen participants performed two routine maintenance tasks: a light-intensity activity (inspecting and photographing a clogged stormwater inlet) and a medium-intensity activity (clearing debris with a leaf blower). During these tasks, participants received simultaneous haptic, audio, and visual AR warnings. Physiological data, including photoplethysmography (PPG), electrodermal activity (EDA), and skin temperature, were collected using a wristband sensor. The study analyzed heart rate (HR), heart rate variability (HRV) metrics (such as HF, RMSSD, NN50, and pNN50), and skin conductance responses (SCR) to assess stress levels. The results indicated significant physiological differences between the two activity levels. Participants exhibited higher mean heart rates and reduced heart rate variability during medium-intensity tasks compared to light-intensity tasks, suggesting increased stress and reduced autonomic nervous system adaptability. Specifically, moderate activity resulted in lower mean NN50 and pNN50 values, indicating decreased parasympathetic activity and higher workload. Additionally, HF-HRV showed a significant difference between the two conditions, with lower values associated with the moderate activity. However, no significant difference was found in the number of SCR peaks between the light and moderate scenarios, implying that physical activity intensity did not significantly impact this specific cognitive stress indicator in the controlled environment. The study concludes that moderate-intensity tasks induce higher physiological stress markers than light-intensity tasks when workers are exposed to AR-assisted warnings. These findings highlight the importance of considering physical workload when designing safety systems, as stress indicators can be confounded by physical exertion. The research contributes a model for continuous, non-invasive stress monitoring using wearable sensors, which can enhance safety and productivity in construction sites. Future research should expand the sample size, explore demographic variables, and include heavy-intensity tasks to further validate these findings.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.

Summary generated by qwen3.6-27b-nvidia on 2026-08-10; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• workload measurement
• emergency work zone conspicuity
• stress driving

Information type

What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).

• Empirical Findings: physiological data