SafeTSim: Immersive Traffic-Aware Rare Events Simulation for Safe Autonomy

Data for training learning-enabled self-driving cars in the physical world are typically collected in a safe, normal environment. Such data distribution often engenders a strong bias towards safe driving, making self-driving cars unprepared when encountering adversarial scenarios like unexpected accidents. Due to a dearth of such adverse data that is practically unsafe for drivers to collect, autonomous vehicles can perform poorly when experiencing such rare events. This work addresses a much research need by having participants drive a VR vehicle simulator going through simulated traffic with various types of accidental scenarios. It aims to understand human responses and behaviors in simulated accidents, contributing to our understanding of driving dynamics and safety. The simulation framework adopts a robust traffic simulation and is implemented using the Unity Game Engine. Furthermore, the simulation framework is built with low-cost immersive driving simulator hardware, lowering the resource barrier for user studies in autonomous driving research.

Download Appendix