Robust Validation to Geometric Perturbations for Autonomous Pose Estimation

arXiv:2608.21066v1 Announce Type: new Abstract: 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.

Related

• Perception with Guarantees: Certified Pose Estimation via Reachability Analysis
• Adversarial Attacks on Robot Localization Systems via Deep Feature Perturbation
• SeFaR: Semantic Feature-aware Robustness Testing of Deep Neural Networks
• Detectors Learn the Wrong Thing: Shortcut-Resistant Adversarial Training Against Physically Realizable Attacks

Source: arXiv cs.CV | 2026-08-24