AILGROMar 4, 2025

DriveGen: Towards Infinite Diverse Traffic Scenarios with Large Models

arXiv:2503.05808v19 citationsh-index: 9IROS
Originality Highly original
AI Analysis

This addresses the problem of insufficient scenario diversity for autonomous driving training and testing, offering a novel method to enhance algorithm robustness without retraining.

The paper tackles the limited diversity in microscopic traffic simulation by proposing DriveGen, a framework that uses large models to generate diverse and realistic traffic scenarios, achieving superior performance over state-of-the-art baselines and improving downstream driving algorithm optimization.

Microscopic traffic simulation has become an important tool for autonomous driving training and testing. Although recent data-driven approaches advance realistic behavior generation, their learning still relies primarily on a single real-world dataset, which limits their diversity and thereby hinders downstream algorithm optimization. In this paper, we propose DriveGen, a novel traffic simulation framework with large models for more diverse traffic generation that supports further customized designs. DriveGen consists of two internal stages: the initialization stage uses large language model and retrieval technique to generate map and vehicle assets; the rollout stage outputs trajectories with selected waypoint goals from visual language model and a specific designed diffusion planner. Through this two-staged process, DriveGen fully utilizes large models' high-level cognition and reasoning of driving behavior, obtaining greater diversity beyond datasets while maintaining high realism. To support effective downstream optimization, we additionally develop DriveGen-CS, an automatic corner case generation pipeline that uses failures of the driving algorithm as additional prompt knowledge for large models without the need for retraining or fine-tuning. Experiments show that our generated scenarios and corner cases have a superior performance compared to state-of-the-art baselines. Downstream experiments further verify that the synthesized traffic of DriveGen provides better optimization of the performance of typical driving algorithms, demonstrating the effectiveness of our framework.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes