ITSC 2025 Paper Abstract

Paper VP-VP.75

Hu, Xinyue (University of California, Irvine), Dees, Laporsha (Toyota Research Institute), Edakkattil Gopinath, Deepak (Toyota Research Institute), Silva, Andrew (Toyota Research Institute), DeCastro, Jonathan (Toyota Research Institute), Rosman, Guy (Toyota Research Institute (TRI)), Sumner, Emily (Toyota Research Institute)

Enhancing Trust Repair in Driving: The Role of AI Emotional Expression and Perceived Control

Scheduled for presentation during the Video Session "On-Demand Video Presentations" (VP-VP), Saturday, November 22, 2025, 08:00−18:00, On-Demand Platform

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 April 2, 2026

Keywords Human-Machine Interaction Systems for Enhanced Driver Assistance and Safety, Trust, Acceptance, and Public Perception of Autonomous Transportation Technologies, Driver Behavior Monitoring and Feedback Systems for Semi-autonomous Vehicles

Abstract

As autonomous agents become increasingly integrated into daily life, particularly in high-risk environments like driving, maintaining user trust is crucial. Driving presents unique challenges due to heightened perception of risk and driver’s individual preferences. Therefore, we focus on studying trust in AI-assisted driving tasks to understand how it can be maintained and repaired in complex, real-world scenarios. Using a shared-control driving algorithm that suggests when and how participants should pass a vehicle, we conducted two experiments (n = 660). Study 1 examined high-risk, performance-driving scenarios where participants experienced trust violations caused by the in-vehicle agent’s mistakes. We evaluated three trust repair strategies—apology, denial, and promise—and compared emotional versus neutral expressions in restoring trust. Study 2 extended this investigation to lower-risk urban and video game contexts to explore how perceived risk and perceived vehicle control influence trust recovery. Results reveal that traditional trust repair methods are inadequate for restoring trust in high- risk scenarios. Contrary to prior findings, emotional expressions were shown to be ineffective. Our findings underscore the challenges of repairing trust in driving scenarios and highlight how perceived helpfulness and driver control influence trust recovery. This study advances the understanding of trust dynamics in AI- assisted driving systems.