aiqbench analysis
This research introduces FoMo-FD, a flow-matching world model designed to detect failures in autonomous surgical robots by learning nominal visual dynamics without requiring explicit failure demonstrations. By leveraging conformal calibration on successful executions, the method achieves high detection rates while minimizing false alarms across diverse manipulation tasks and real-world hardware like the da Vinci Research Kit. The work addresses critical safety challenges in robotic surgery through advanced machine learning techniques that generalize well to unseen failure modes.
Failure Detection for Surgical Robot Imitation Policies via Flow-Matching World Modeling
arXiv:2607.27511v1 Announce Type: new Abstract: 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).
Abstract: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).
9 pages, 6 figures. Submitted to IEEE Robotics and Automation Letters (RA-L)
Robotics (cs.RO)
arXiv:2607.27511 [cs.RO]
(or arXiv:2607.27511v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2607.27511 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 301 words
Related coverage
Rewind-IL: Online Failure Detection and State Respawning for Imitation Learning
arXiv · Oct 2, 2026
LeRobot v0.6.0: Imagine, Evaluate, Improve
Hugging Face · Jul 7, 2026
Uncertainty Quantification for Flow-Based Generalist Robot Policies
arXiv · Oct 5, 2026
Build a Physical AI model factory with NVIDIA Cosmos 3 on SageMaker HyperPod
AWS · Sep 4, 2026