LLM-based Human-like Traffic Simulation for Self-driving Tests
This work addresses the need for more realistic and diverse human-like traffic simulations to improve the reliability testing of self-driving systems, representing a novel method for a known bottleneck in the field.
The paper tackled the problem of generating realistic traffic dynamics for self-driving system tests by introducing HDSim, a framework that combines cognitive theory with LLM assistance, resulting in up to a 68% improvement in detecting safety-critical failures and enhanced accident interpretability.
Ensuring realistic traffic dynamics is a prerequisite for simulation platforms to evaluate the reliability of self-driving systems before deployment in the real world. Because most road users are human drivers, reproducing their diverse behaviors within simulators is vital. Existing solutions, however, typically rely on either handcrafted heuristics or narrow data-driven models, which capture only fragments of real driving behaviors and offer limited driving style diversity and interpretability. To address this gap, we introduce HDSim, an HD traffic generation framework that combines cognitive theory with large language model (LLM) assistance to produce scalable and realistic traffic scenarios within simulation platforms. The framework advances the state of the art in two ways: (i) it introduces a hierarchical driver model that represents diverse driving style traits, and (ii) it develops a Perception-Mediated Behavior Influence strategy, where LLMs guide perception to indirectly shape driver actions. Experiments reveal that embedding HDSim into simulation improves detection of safety-critical failures in self-driving systems by up to 68% and yields realism-consistent accident interpretability.