AI RESEARCH
Lost in Fog: Sensor Perturbations Expose Reasoning Fragility in Driving VLAs
arXiv CS.AI
•
ArXi:2605.21446v1 Announce Type: cross Interpretable autonomous driving planners depend not only on generating explanations, but also on those explanations remaining reliable under real-world sensor degradation. In this paper we present a controlled perturbation study of Vision-Language-Action (VLA) robustness in autonomous driving, evaluating Alpamayo R1 (10B parameters) across 1,996 scenarios under eight sensor perturbations (Gaussian noise at four intensities, two lighting extremes, and two fog levels; ${\sim}18{,}000$ inference trials.