用扩散模型生成可迁移的自动驾驶危险场景，提升测试真实性和泛化能力。
AdvDiffuser: Generating Adversarial Safety-Critical Driving Scenarios via Guided Diffusion
- 基于扩散模型捕捉车辆群体行为，结合轻量引导模型生成对抗性场景。
- 在nuScenes数据集上仅需少量预热数据即可适配不同系统，性能优于现有方法。
- 适合自动驾驶系统测试与验证，尤其关注场景多样性与跨系统通用性。
安全关键场景在自然驾驶环境中罕见，但对自动驾驶系统的训练与测试至关重要。当前方法通常通过在仿真中引入对抗性调整来自动生成此类场景，但这些调整往往针对特定系统设计，缺乏跨系统可迁移性。本文提出AdvDiffuser，一种通过引导扩散生成对抗性安全关键驾驶场景的框架。该方法利用扩散模型捕捉背景车辆的合理集体行为，并结合轻量级引导模型高效处理对抗性情境，从而实现场景生成的可迁移性。在nuScenes数据集上的实验表明，仅需少量离线驾驶日志训练，AdvDiffuser即可在极小预热样本下适配多种测试系统，在真实性、多样性及对抗性能方面均优于现有方法。
原文摘要 · Abstract (English)
Safety-critical scenarios are infrequent in natural driving environments but hold significant importance for the training and testing of autonomous driving systems. The prevailing approach involves generating safety-critical scenarios automatically in simulation by introducing adversarial adjustments to natural environments. These adjustments are often tailored to specific tested systems, thereby disregarding their transferability across different systems. In this paper, we propose AdvDiffuser, an adversarial framework for generating safety-critical driving scenarios through guided diffusion. By incorporating a diffusion model to capture plausible collective behaviors of background vehicles and a lightweight guide model to effectively handle adversarial scenarios, AdvDiffuser facilitates transferability. Experimental results on the nuScenes dataset demonstrate that AdvDiffuser, trained on offline driving logs, can be applied to various tested systems with minimal warm-up episode data and outperform other existing methods in terms of realism, diversity, and adversarial performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。