MR-HVIL: A Mixed-Reality-Based Human--Vehicle-In-the-Loop On-Road Validation Platform for Mixed Traffic Testing
- 1 May 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (7) , 7936-7949
Abstract
This paper introduces MR-HVIL, a novel mixed-reality-based platform designed for on-road human-vehicle-in-the-loop validation in vehicle research. MR-HVIL leverages an optical see-through mixed reality framework to seamlessly integrate real-world driving environments with virtual traffic scenarios. Unlike traditional vehicle-in-the-loop and driving simulators, our platform enhances driver experience by combining real-world physical vehicle dynamic motions with optimized virtual content overlay, ensuring a realistic and immersive validation environment. To address the challenges of synchronization and localization in outdoor environments, we develop a real-time virtual object localization and correction algorithm that integrates vehicle sensor data, enhancing mixed reality accuracy and stability. Experimental validation demonstrates the platform’s efficacy in comparing human responses to real and virtual autonomous vehicles, offering new opportunities for human-centric validation in mixed traffic scenarios. MR-HVIL paves the way for safer, more versatile, and naturalistic testing of mixed traffic systems.Keywords
Funding Information
- U.S. Department of Energy (DOE) Vehicle Technologies Office (VTO) under the Energy Efficient Mobility Systems (EEMS) Program
This publication has 31 references indexed in Scilit:
- Segment Anything2023
- Dense reinforcement learning for safety validation of autonomous vehiclesNature, 2023
- Driver Behavior Modeling Toward Autonomous Vehicles: Comprehensive ReviewIEEE Access, 2023
- Energy and flow effects of optimal automated driving in mixed traffic: Vehicle-in-the-loop experimental resultsTransportation Research Part C: Emerging Technologies, 2021
- Distributed Microscopic Traffic Simulation with Human-in-the-Loop Enabled by Virtual Reality TechnologiesAdvances in Engineering Software, 2021
- Next Generation X-in-the-Loop Validation Methodology for Automated Vehicle SystemsIEEE Access, 2021
- You Only Look Once: Unified, Real-Time Object Detection2016
- Microscopic Traffic Flow Simulator VISSIM2010
- A New Approach to Linear Filtering and Prediction Problems2009
- Congested traffic states in empirical observations and microscopic simulationsPhysical Review E, 2000