FlowCorrect: Efficient Interactive Correction of Generative Flow Policies for Robotic Manipulation
This addresses the problem of catastrophic failures in robotic manipulation for real-world deployment, though it appears incremental as it builds on existing generative policy frameworks.
The paper tackles the problem of generative manipulation policies failing under deployment-time distribution shift by presenting FlowCorrect, a framework that converts near-miss failures into successes using sparse human nudges without full policy retraining. The result shows an 85% improvement in success on hard cases with a low correction budget while preserving performance on previously solved scenarios.
Generative manipulation policies can fail catastrophically under deployment-time distribution shift, yet many failures are near-misses: the robot reaches almost-correct poses and would succeed with a small corrective motion. We present FlowCorrect, a deployment-time correction framework that converts near-miss failures into successes using sparse human nudges, without full policy retraining. During execution, a human provides brief corrective pose nudges via a lightweight VR interface. FlowCorrect uses these sparse corrections to locally adapt the policy, improving actions without retraining the backbone while preserving the model performance on previously learned scenarios. We evaluate on a real-world robot across three tabletop tasks: pick-and-place, pouring, and cup uprighting. With a low correction budget, FlowCorrect improves success on hard cases by 85\% while preserving performance on previously solved scenarios. The results demonstrate clearly that FlowCorrect learns only with very few demonstrations and enables fast and sample-efficient incremental, human-in-the-loop corrections of generative visuomotor policies at deployment time in real-world robotics.