Connected Simulation for Work Zone Safety Applications

Balali, Vahid · 2022 · ROSA P / San Jose State University. College of Business. Mineta Transportation Institute

archive: archived pipeline: cataloged verified

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

Summary

This research addresses the persistent safety crisis in highway work zones, where over 60,000 crashes occur annually in the United States, resulting in thousands of fatalities and significant economic losses. Despite existing safety management practices, injury rates remain unacceptably high. The study aims to unveil high-risk behavioral and environmental precursors to accidents, identify effective interventions, and develop training methods for drivers, workers, and equipment operators. To achieve this, the authors developed a system architecture for a "connected virtual environment," a hyper-realistic simulation where multiple agents operate independent simulators but share a unified, interactive experience. This approach allows for the modeling of complex, dynamic interactions among all work zone actors, which traditional single-user simulators cannot capture. The methodology involved a three-phase process. First, the team conducted an in-depth analysis of historical work zone injury reports and consulted with an expert panel to identify common causal factors, including human error, design characteristics, and environmental conditions. Second, they designed and implemented the connected virtual environment to simulate these identified scenarios. This system integrated technology-driven innovations, including vision-based activity recognition sensors, eye-tracking technology to measure attention allocation, and computer-vision-based asset recognition for providing warnings. Third, the researchers defined and tested specific hypotheses regarding driver and worker behavior under various conditions, such as the presence of flaggers, lane widths, and barrier types. Key findings include the development of a detailed threat zone model for hazard identification. The study defined distinct "alert" and "warning" areas for workers, vehicles, and equipment based on stopping distances, reaction times, and movement patterns. For workers on foot, alert areas were set at 1 meter and warning areas at 1.5 meters, with adjustments for proximity to the work zone border and road curvature. For example, warning areas for workers increased linearly as they approached the traffic lane, and additional buffer zones were added in curved sections to account for centripetal force risks. The research also established a database of equipment dimensions and worker activity patterns, using supervised learning in MATLAB to classify activities like jackhammering, walking, and guiding based on speed, static time, and direction. The significance of this work lies in its contribution to smart behavioral safety analysis and the creation of a robust testbed for evaluating work zone safety interventions. By enabling the simulation of multi-agent interactions, the connected virtual environment provides a safe platform to study complex behavioral patterns and test the efficacy of engineering controls and administrative methods. The study concludes that this approach offers a novel way to understand and mitigate high-risk behaviors, potentially leading to improved training programs and safer work zone designs. Future work suggests integrating probe vehicle data and advanced computer vision techniques to further enhance model accuracy and data collection capabilities.

Key finding

A connected virtual simulation environment effectively captures complex behavioral interactions and high-risk patterns in work zones, and a developed neural network model accurately estimates traffic volumes in sensor-limited areas.

Methodology

simulator

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. Discovered via bulk_ingest_rosap on 2026-05-23 (6 acquisition events logged).

Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.

Topics

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

• work zones
• emergency work zone conspicuity

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: crash risk outcomes