Research

My research sits at the intersection of traffic safety, human factors, and autonomous systems. It covers three topics:

Autonomous vehicle safety evaluation

Most pedestrian and vehicle models used in AV simulation are conservative and rule-following. I develop RL-trained adversarial agents whose behavior is constrained to remain behaviorally realistic while still stressing AV decision logic, yielding sharper, more informative safety evaluation than either purely random or purely worst-case scenarios.

Conceptual framework for behaviorally realistic AV safety evaluation.

Aggressiveness-Calibrated Adversarial Scenario Generation for Highway Autonomous Vehicle Safety Evaluation

Park, H., Oh, T., Liu, Y., & Kim, I.*

Accident Analysis & Prevention, 2026. (Under review.)

Beyond Collision Rate: SUT-Invariant Adversarial Evaluation of Autonomous Driving via Item Response Theory

Park, H., & Kim, I.*

In preparation, 2026.

V2X-aware humanoid drivers

I am training humanoid robots to drive ordinary vehicles through world-model–based reinforcement learning. Instead of making the vehicle intelligent, as conventional autonomous driving does, this line of work leaves the vehicle as it is and replaces the driver: the robot learns a world model that captures its own joint control and the vehicle's response together, and acquires driving skills by rehearsing inside that model before ever touching a real car. The learned policy is then transferred to a physical humanoid and validated on a real vehicle in a V2X testbed, where the robot itself receives and acts on cooperative messages from the infrastructure, the way a human driver would follow guidance rather than a controller consuming a signal.

Conceptual framework for embodied autonomous driving.

Human-centric traffic safety research

A long-running line of work using immersive VR experiments to measure how drivers, pedestrians, and evacuees actually decide, attend, and move in safety-critical mobility situations.

Human factors research using immersive VR experiments.

Micromobility safety and driver behavior

Drivers share roads with bicycles and e-scooters in increasingly mixed traffic. I study how a driver's own prior riding experience shapes overtaking maneuvers, lateral distance, and risk-taking, using VR-based driving simulators that reproduce realistic urban roadways.

Micro Mobility Safety Challenges: A Study on Drivers Overtaking Bicycles and E-Scooters according to Road Conditions and Prior Riding Experience

Park, H., Oh, T., Lim, J., & Kim, I.*

Transportation Research Part F: Traffic Psychology and Behaviour, 2026.

Pedestrian safety and ADAS

How does the way safety information is presented to a driver (a real-time count of crossing pedestrians, or a UWB-based pedestrian tag) change braking behavior, cognitive load, and the safety margins drivers leave under uncertainty? I design and analyze ADAS warning systems with the driver's perception in the loop.

Effects of Driver's Braking Behavior by the Real-Time Pedestrian Scale Warning System

Park, H., Oh, T., & Kim, I.*

Accident Analysis & Prevention, vol. 205, 107685, 2024.

Human-Centric Evaluation of UWB-based V2P ADAS: How Pedestrian Tag Adoption Rates Influence Driver Cognitive Load and Safety Performance in School Zones

Park, H., Tamakloe, R., Kim, E. M., Lim, J., & Kim, I.*

In preparation, 2026.

Underground and rail safety

Underground and rail environments place people under poor visibility, conflicting cues, and varying perceptual ability. Using VR, I study three settings: how visibility and permissibility signals shape pedestrian evacuation route choice during subway-station fires; how in-tunnel information design affects driver behavior in road tunnels; and how age-related perceptual constraints reshape transport disadvantage in railway information systems.

From Passive Visibility to Active Permissibility: A Virtual Reality Study on Overcoming Track Avoidance Bias in Subway Station Fires

Park, H., Oh, T., Kim, J., Kim, J., & Kim, I.*

Underground Space, 2026. (Under review, R1.)

The Impact of Information Delivery Systems in Tunnels Depending on Lighting Intensity and Speed Limit

Lim, J., Park, H., Oh, T., & Kim, I.*

Tunnelling and Underground Space Technology, vol. 157, 106365, 2025.

How Age-Related Constraints Reshape Transport Disadvantage in Railway Information Systems: Evidence from Virtual Aging Simulation

Baek, J., Kim, J., Park, H., & Kim, I.*

Journal of Urban Mobility, 2026. (Under review, R1.)