ITSC 2025 Paper Abstract

Paper TH-LM-T29.1

Xu, Zheng (Monash University), Xiao, Dong (Monash University), Zheng, Nan (Monash University)

Analyzing Riders’ Intervention Behavior During Autonomous Driving: A VR-Based Exploratory Study

Scheduled for presentation during the Regular Session "S29a-Human Factors and Human Machine Interaction in Automated Driving" (TH-LM-T29), Thursday, November 20, 2025, 10:30−10:50, Currumbin

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Keywords Autonomous Vehicle Safety and Performance Testing, Driver Behavior Monitoring and Feedback Systems for Semi-autonomous Vehicles, Human-Machine Interaction Systems for Enhanced Driver Assistance and Safety

Abstract

As Intelligent Transportation Systems (ITS) technologies rapidly evolve, the future of mobility increasingly leans towards vehicular autonomy. Despite the advancements of autonomous vehicle (AV) technologies, the way to full automation remains challenging. The intricate balance between vehicular autonomy and human input presents a significant challenge for road safety in the realm of autonomous driving. This study illuminates the intervention behaviors of human riders in AV operations, leveraging this insight to enhance the understanding of critical driving scenarios. Virtual reality (VR) and traffic microsimulation are combined to create experimental environments, conducting tests across various traffic situations, such as freeway merging and navigating signalized urban intersections. Key performance indicators, including intervention probability and accident rates, are defined to measure and compare risk levels. This research contributes novel perspectives on rider intervention behavior, aiding in the enhancement of autonomous driving systems in similar situations. Additionally, the development of such an integrated, immersive tool for studying autonomous driving is a significant contribution to research on trust between humans and automation.