Diverse Human Driving Vehicle Simulation in Background Traffic for Autonomous Driving Tests

Realistic background traffic is critical to the simulation platforms for autonomous driving (AD) testing. Given most of vehicles in reality are driven by human beings, introducing human driving (HD) vehicles to the background traffic is necessary and able to discover more problems of tested AD vehicle in the simulation stage. However, existing methods rely on ad-hoc rules or data-driven trainings to mimic partial human driver behaviors, which is not comprehensive and lack of transparency. In this work, we design a smart human driving vehicle simulator HDSim which is empowered by cognitively inspired modeling and AI models. HDSim enables diverse, realistic and scalable HD traffic simulation on AD testing platforms like Carla in a non-intrusive measure. There are two novel components in HDSim. First, we introduce a formalized model to guide the generation of diverse human driving styles by using different combinations of latent cognitive factors in a hierarchy. Second, we design a Perception-Mediated Behavior Influence (PMBI) mechanism to uses LLM-assisted perceptual transformations to indirectly fuse driving actions with driving styles. Experiments show that HDSim traffic can help simulation platforms like Carla to reveal 68% more failures of tested AD vehicles, and the explainability of reported accidents is also improved.