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). We find that reasoning consistency is a high-fidelity indicator of trajectory reliability: when Chain-of-Causation (CoC) explanations change after perturbation, trajectory deviation spikes $5.3{\times}$ (21.8m vs 4.1m), with $r\!=\!0.99$ across attack types and $r_{pb}\!=\!0.53$ per-sample (Cohen's $d\!=\!1.12$). A controlled ablation provides evidence that enabling CoC generation is associated with improved trajectory accuracy (11.8% on average across conditions; $p < 0.0001$) under matched inference settings. Over the tested noise range ($σ\in \{10, 30, 50, 70\}$), degradation is approximately linear ($R^2\!=\!0.957$), while standard input preprocessing defenses provide only marginal relief. Together, these results establish CoC consistency as a quantitative proxy for planning safety and motivate reasoning-based runtime monitoring for safer VLA deployment.

翻译：可解释的自主驾驶规划器不仅依赖于生成解释，还依赖于这些解释在真实世界传感器退化下的可靠性。本文对自主驾驶中视觉-语言-动作（Vision-Language-Action, VLA）模型的鲁棒性进行了受控扰动研究，评估了Alpamayo R1（10B参数）在八种传感器扰动（四种强度的高斯噪声、两种极端光照条件和两种雾等级；约18,000次推理试验）下的1,996个场景。我们发现，推理一致性是轨迹可靠性的高保真指标：当扰动后因果链（Chain-of-Causation, CoC）解释发生变化时，轨迹偏差激增5.3倍（21.8米对4.1米），攻击类型间的相关系数r=0.99，逐样本的点双列相关系数r_pb=0.53（Cohen's d=1.12）。一项受控消融实验表明，在匹配推理设置下，启用CoC生成与轨迹精度提升相关（各条件下平均提升11.8%；p<0.0001）。在测试的噪声范围内（σ∈{10, 30, 50, 70}），退化近似线性（R²=0.957），而标准输入预处理防御仅能提供边际缓解。综合而言，这些结果确立了CoC一致性作为规划安全性的定量代理指标，并推动了基于推理的运行时监控，以实现更安全的VLA部署。