基于流匹配世界建模的外科机器人模仿策略故障检测
Failure Detection for Surgical Robot Imitation Policies via Flow-Matching World Modeling
- Georgia Institute of Technology（佐治亚理工学院）
- Emory University（埃默里大学）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
该研究针对外科机器人模仿策略的故障检测难题，提出FoMo-FD方法，利用流匹配世界模型实现无故障演示的视觉-动作不一致性窗口级检测，在dVRK的模拟与真实实验中表现优于基线方法。
中文摘要 AI 辅助
模仿学习在自主外科手术中展现出日益增长的应用前景，但由于外科任务的安全关键属性以及手术环境的复杂性与多变性，安全部署仍具挑战性。故障检测因此成为必不可少的安全保障，但受限于故障数据稀缺、操作动力学高度多变，以及漏检与破坏性误报的平衡需求，其开发工作仍存在困难。为应对这些挑战，我们提出FoMo-FD（用于故障检测的流匹配世界模型），该故障检测方法通过带动作条件的流匹配世界模型学习标称短 horizon 视觉动力学。FoMo-FD对观测到的终点隐变量的逆传输不一致性进行评分，无需故障演示即可实现视觉-动作不一致性的窗口级检测。检测阈值通过对成功执行的保形校准获得，可生成任务特定的警报，且无需假设未来故障类型。我们在模拟环境和使用达芬奇研究套件（dVRK）的真实世界实验中，针对四个与外科相关的操作任务、二十种故障模式对FoMo-FD进行评估。结果显示，FoMo-FD的性能优于观测级异常基线及同一世界模型的预测误差变体，其中腕部相机视图实现了最强性能，包括在1.3%误报率（FAR）下达到96.6%的故障检测率（FDR）。
英文摘要
Imitation learning has shown increasing promise for autonomous robotic surgery, yet safe deployment remains challenging due to the safety-critical nature of surgical tasks and the complexity and variability of surgical environments. Failure detection is therefore an essential safeguard, but its development remains difficult due to the challenges of scarce failure data, highly variable manipulation dynamics, and the need to balance missed detections against disruptive false alarms. To address these challenges, we introduce FoMo-FD (Flow-Matching World Model for Failure Detection), a failure detection method that learns nominal short-horizon visual dynamics with an action-conditioned flow-matching world model. FoMo-FD scores the inverse-transport nonconformity of observed endpoint latents, enabling window-level detection of visual-action inconsistencies without requiring failure demonstrations. Detection thresholds are obtained by conformal calibration on successful executions, yielding task-specific alarms without assuming future failure types. We evaluate FoMo-FD on four surgically relevant manipulation tasks with twenty failure modes across simulation and real-world experiments using the da Vinci Research Kit (dVRK). Results show that FoMo-FD outperforms observation-level anomaly baselines and a prediction-error variant of the same world model, with the wrist-camera view achieving the strongest performance, including a 96.6% failure detection rate (FDR) at a 1.3% false alarm rate (FAR).
