发表机构
Technical University of Munich; Mercedes Benz AG（慕尼黑工业大学; 梅赛德斯-奔驰股份公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对自动驾驶生成式场景模型缺乏物理一致性保证的问题，提出一种五层评估协议，从内部表示到输出动力学约束全面检验模型，并在VAE及多种生成模型上验证其有效性。
AI 中文摘要
生成式人工智能模型越来越多地用于自动驾驶中的场景生成。虽然它们能够生成视觉上逼真的场景，但通常对其学习到的表示以及与真实车辆动力学的一致性提供的透明度有限。这种缺乏正式保证的情况限制了它们在安全关键验证和认证工作流程中的使用。为了解决这一问题，我们引入了一种分层评估协议，通过五个层面对模型进行评估，以补充现有方法。前四个层面通过运动学对齐、统计基线比较、潜在可控性和激活分析来检查内部表示和网络层。第五个层面根据车辆动力学约束（如横向加速度变化率阈值）评估模型输出。我们在一个基于变分自编码器（VAE）的场景生成器上演示了该协议。尽管标准的输出级指标和可视化表明生成的场景是逼真的，但我们的协议提供了更深入的洞察，揭示了模型潜在空间与运动学特征对齐的程度，以及视觉上合理的轨迹是否满足车辆动力学约束。我们进一步将该协议应用于其他生成模型，证明了其超越VAE架构的适用性。
英文摘要
Generative AI models are increasingly used for scenario generation in autonomous driving. While they can generate realistic-looking scenarios, they often provide limited transparency into learned representations and consistency with real-world vehicle dynamics. This lack of formal assurance limits their use in safety-critical validation and certification workflows. To address this aspect, we introduce a layered evaluation protocol that complements existing methods by assessing models across five layers. The first four layers inspect internal representations and network layers through kinematic alignment, statistical baseline comparison, latent controllability, and activation analysis. The fifth layer evaluates model outputs against vehicle dynamics constraints such as lateral jerk thresholds. We demonstrate the protocol on a Variational Autoencoder (VAE)-based scenario generator. Although standard output-level metrics and visualizations suggest that the generated scenarios are realistic, our protocol provides deeper insight into the extent to which the model's latent space aligns with kinematic features and whether visually plausible trajectories satisfy vehicle-dynamics constraints. We further apply the protocol to additional generative models, demonstrating its applicability beyond the VAE architecture.
