轨迹中的捉迷藏：发现VLA运行时监测的失效信号

摘要

视觉-语言-动作（VLA）模型使机器人能够遵循自然语言指令并在多样化任务中泛化，但在实际部署时仍易受执行失败影响，从而损害系统可靠性。因此，在执行过程中检测此类失败对于具身系统的鲁棒部署至关重要。现有失败检测方法要么依赖昂贵的动作重采样或外部模型，要么将轨迹级标签均匀传播至每个时间步，模糊了局部化失败信号。本文提出Hide-and-Seek框架，将VLA失败检测建模为粗监督学习问题。通过结合轨迹间和轨迹内对比目标，Hide-and-Seek能够仅从轨迹级监督中定位指示失败的动作，并诱导出具有时间结构的失败信号，无需任何步骤级标注。我们在LIBERO、VLABench及真实机器人平台上，对三种代表性VLA策略（OpenVLA、π_0和π_{0.5}）进行了评估。该方法在多任务失败检测中达到了最先进性能，并在共形预测框架下实现了实用的准确率-及时性权衡，且能良好泛化至已见和未见任务。

English

Vision-Language-Action (VLA) models enable robots to follow natural language instructions and generalize across diverse tasks, but they remain vulnerable to execution failures that compromise reliability in real-world deployment. Detecting such failures during execution is therefore critical for the robust deployment of embodied systems. Existing failure detection methods either rely on expensive action resampling or external models, while alternatives propagate trajectory-level labels uniformly across every timestep, obscuring localized failure signals. In this paper, we propose Hide-and-Seek, a framework that formulates VLA failure detection as a coarsely supervised learning problem. By combining inter-trajectory and intra-trajectory contrastive objectives, Hide-and-Seek localizes failure-indicative actions and induces temporally structured failure signals from trajectory-level supervision alone, without any step-level annotation. We evaluate Hide-and-Seek on LIBERO, VLABench, and a real-world robotic platform across three representative VLA policies: OpenVLA, π_0, and π_{0.5}.Our method achieves state-of-the-art multi-task failure detection performance with a practical accuracy--timeliness trade-off under conformal prediction, and generalizes well to both seen and unseen tasks.