Sensor-enabled Calibration of VR-Integrated Co-Simulation Platforms for Enhanced Accuracy in Multi-modal Mobility Models

Ergan, Semiha; Ozbay, Kaan; Zhang, Shuo; Zuo, Fan · 2024 · ROSA P / Connected Communities for Smart Mobility Toward Accessible and Resilient Transportation for Equitably Reducing Congestion (C2SMARTER) Tier-1 University Transportation Center (UTC)

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 paper addresses the critical safety challenges in roadway work zones, where over 140 fatalities and 40,000 injuries occur annually in the U.S. due to vehicle-related incidents. Existing research often isolates driver behavior or static work zone design, failing to capture the dynamic interactions between drivers and workers. Furthermore, real-world testing of safety interventions is hazardous and costly. To bridge this gap, the authors introduce VR-WISE, a high-fidelity co-simulation platform designed to study vehicle-work zone interactions in a controlled, immersive environment. The platform aims to enhance the accuracy of multi-modal mobility models by integrating realistic worker animations with driver behavioral data, thereby facilitating the calibration of simulation outcomes against real-world observations. The methodology involves a multi-component system integrating Virtual Reality (VR) with micro-traffic simulators. The platform combines CARLA, a driving simulator, with SUMO, a traffic flow simulator, to create a holistic urban mobility environment. Realistic worker movements are generated using Sony Mocopi 3D motion capture sensors and mapped into Maya for full-body animation, which are then rendered in Unreal Engine. Drivers navigate these scenarios using a VR headset (Meta Quest Pro) equipped with eye-tracking and a racing wheel (Logitech G29) for haptic feedback. Biometric data, including heart rate, blood volume pulse, and electrodermal activity, are collected via Empatica E4 wristbands. The research also establishes a comprehensive vocabulary of calibration metrics for both VR fidelity (e.g., visual and auditory system quality) and SUMO traffic dynamics (e.g., vehicle speed, density, and acceleration) to ensure synchronization between simulation environments and real-world conditions. The study presents findings from user experiments involving four distinct work zone scenarios. Data collection focused on drivers’ situational awareness, measured through gaze duration, fixation ratios, and physiological stress responses. The results demonstrate the platform’s capability to capture detailed behavioral and biometric data, revealing how drivers respond to dynamic worker presence and varying work zone configurations. Statistical analyses, including ANOVA, were used to compare awareness levels across different scenario types. The integration of SUMO and CARLA allowed for the simultaneous analysis of macro-level traffic flow and micro-level vehicle dynamics, providing a robust dataset for calibrating multi-modal models. The developed calibration vocabulary successfully linked simulation parameters to observable real-world metrics, validating the platform’s utility for accurate modeling. The significance of this work lies in its contribution to work zone safety research and the development of autonomous vehicle technologies. By providing a safe, cost-effective, and high-fidelity environment for studying human-vehicle interactions, VR-WISE enables the evaluation of safety interventions that are impractical to test in real life. The platform’s ability to integrate biometric and behavioral data with traffic simulation offers a nuanced understanding of situational awareness, which is crucial for designing effective safety measures. Ultimately, this research supports the creation of more resilient transportation systems by bridging the gap between simulation and reality, offering a scalable tool for future studies in traffic safety, autonomous driving, and urban planning.

Key finding

The VR-WISE platform successfully integrates biometric and eye-tracking data within a co-simulation environment to accurately capture driver situational awareness and physiological responses during interactions with simulated roadway workers.

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
• simulator validity fidelity
• simulator sickness
• situational awareness

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).

• Methodological Resource: tool software, validation psychometrics
• Theoretical Contribution: computational model