发表机构
Airbus SAS; IRT Saint-Exupery（空中客车公司; 圣埃克苏佩里技术研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对自主位姿估计的几何扰动鲁棒性验证问题，提出基于全局利普希茨优化（GLO）的方法，在YOLOv8-Pose模型上验证其可高效定位失效模式并剪枝80%以上搜索空间，为鲁棒自主感知验证提供了新途径。
AI 中文摘要
将自主系统部署到安全关键领域，要求其具备对抗物理上可行的几何扰动的鲁棒性，而非仅对抗抽象的像素级噪声。在基于视觉的导航和自主着陆场景中，机器学习组件需要在相机旋转、光照变化等动态运行条件下接受严格验证。受分类任务中一阶空间攻击存在失效现象的研究启发，本文表明基于梯度的标准启发式方法（如APGD）在姿态估计任务中同样失效，其表现往往差于简单的随机采样基线。为克服这些优化瓶颈，本文在全局利普希茨优化（Global Lipschitzian Optimization, GLO）框架内重新构建了位姿估计鲁棒性问题。本文认为GLO提供了一种原则性的鲁棒验证方法，可有效定位全局最优解并具备强理论收敛保证。本文在YOLOv8-Pose关键点检测器结合透视-n-点（Perspective-n-Point, PnP）求解器的模型上，针对旋转和对比度扰动开展评估。评估结果显示，GLO能够成功分离出位置偏差超出安全运行极限的关键失效模式，同时可将搜索空间快速剪枝超过80%。据本文所知，这是首个将几何鲁棒性验证扩展到连续关键点回归和深度目标检测的研究，为实现鲁棒自主感知的可验证性迈出了实用的一步。
英文摘要
Deploying autonomous systems in safety-critical domains demands guaranteed robustness against physically plausible geometric perturbations rather than abstract pixel-wise noise. In vision-based navigation and autonomous landing, machine learning components require rigorous validation under dynamic operational conditions such as camera rotations and lighting shifts. Extending findings on the failure of first-order spatial attacks in classification, we show that standard gradient-based heuristics (e.g. APGD) similarly fail on for pose estimation, often performing worse than a simple random sampling baseline. To overcome these optimization bottlenecks, we reformulate pose estimation robustness within the framework of Global Lipschitzian Optimization (GLO). We argue that GLO offers a principled approach to robust validation, effectively localizing global optima with strong theoretical convergence guarantees. We evaluate this framework on a YOLOv8-Pose keypoint detector with a Perspective-n-Point (PnP) solver against rotation and contrast. In our evaluations, GLO successfully isolates critical failure modes where position deviations exceed safe operational limits, while rapidly pruning the search space by over 80%. To the best of our knowledge, this is the first study to extend geometric robustness validation to continuous keypoint regression and deep object detection, establishing a practical step toward certifying robust autonomous perception.
Comments15 pages, 7 figures
