您的视觉-语言-动作模型已具备路径偏差检测的注意力头
Your Vision-Language-Action Model Already Has Attention Heads For Path Deviation Detection
AI总结：
本文提出一种无需训练的异常检测框架，通过监控VLA模型中的三个注意力头实时检测路径偏差，并利用轻量级RL策略进行恢复，展示了其在物理机器人上的实际鲁棒性。
摘要：
视觉-语言-动作（VLA）模型在导航任务中预测语义动作表现出强大潜力，能够推理复杂的语言指令和视觉上下文。然而，它们受到视觉推理幻觉的限制，导致轨迹偏移。本文发现，在冻结的VLA模型中监控几个注意力头可以准确检测路径偏移，而无需额外计算开销。这些注意力头本质上捕捉了历史视觉序列与语言指令之间的时空因果性，称为导航头。利用这些头，我们提出了一种直观的异常检测框架，通过监控其信号实时检测幻觉。令人惊讶的是，超过一千个注意力头中，仅用三个组合即可实现44.6%的偏移检测率，且假阳性率仅为11.7%。进一步地，检测到偏移后，我们绕过重型VLA模型，触发轻量级强化学习（RL）策略以安全执行最短路径回滚。通过将整个检测-恢复流水线集成到物理机器人上，我们展示了其实际鲁棒性。所有源代码将公开可用。
英文摘要：
Vision-Language-Action (VLA) models have demonstrated strong potential for predicting semantic actions in navigation tasks, demonstrating the ability to reason over complex linguistic instructions and visual contexts. However, they are fundamentally hindered by visual-reasoning hallucinations that lead to trajectory deviations. Addressing this issue has conventionally required training external critic modules or relying on complex uncertainty heuristics. In this work, we discover that monitoring a few attention heads within a frozen VLA model can accurately detect path deviations without incurring additional computational overhead. We refer to these heads, which inherently capture the spatiotemporal causality between historical visual sequences and linguistic instructions, as Navigation Heads. Using these heads, we propose an intuitive, training-free anomaly-detection framework that monitors their signals to detect hallucinations in real time. Surprisingly, among over a thousand attention heads, a combination of just three is sufficient to achieve a 44.6 % deviation detection rate with a low false-positive rate of 11.7 %. Furthermore, upon detecting a deviation, we bypass the heavy VLA model and trigger a lightweight Reinforcement Learning (RL) policy to safely execute a shortest-path rollback. By integrating this entire detection-to-recovery pipeline onto a physical robot, we demonstrate its practical robustness. All source code will be publicly available.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
