用几何变换建模视觉不确定性，提升感知控制系统的安全验证能力
Verification of Visual Controllers via Compositional Geometric Transformations
- 通过显式建模几何扰动，构建状态到图像的可计算映射
- 在基准控制环境中实现对可达集的外逼近，保障系统安全性
- 适合关注自动驾驶、机器人等视觉驱动系统的安全验证者
基于感知的神经网络控制器在依赖视觉输入的自主系统中应用日益广泛，但其在不确定环境下的安全性验证极具挑战。现有验证方法通常仅关注像素空间中的Lp有界扰动，难以捕捉真实世界中许多低维视觉效应。本文提出一种新型验证框架，通过显式建模几何扰动来生成感知控制器可达集的外逼近。该方法构建了从状态到图像的可界定映射，使基于状态的验证工具可在考虑感知不确定性的情况下使用。我们提供了方法正确性的理论保证，并在多个基准控制环境中验证了其有效性。本工作为在现实视觉扰动下认证感知驱动控制系统安全性提供了系统性框架。
原文摘要 · Abstract (English)
Perception-based neural network controllers are increasingly used in autonomous systems that rely on visual inputs to operate in the real world. Ensuring the safety of such systems under uncertainty is challenging. Existing verification techniques typically focus on Lp-bounded perturbations in the pixel space, which fails to capture the low-dimensional structure of many real-world effects. In this work, we introduce a novel verification framework for perception-based controllers that can generate outer-approximations of reachable sets through explicitly modeling uncertain observations with geometric perturbations. Our approach constructs a boundable mapping from states to images, enabling the use of state-based verification tools while accounting for uncertainty in perception. We provide theoretical guarantees on the soundness of our method and demonstrate its effectiveness across benchmark control environments. This work provides a principled framework for certifying the safety of perception-driven control systems under realistic visual perturbations.
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。