FlowCorrect: Efficient Interactive Correction of Generative Flow Policies for Robotic Manipulation

TL;DR

FlowCorrect is presented, a deployment-time correction framework that converts near-miss failures into successes using sparse human nudges, without full policy retraining, without full policy retraining.

Abstract

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.

Figures (6)

• Figure 1: Overview of our interactive FlowCorrect framework: A flow matching visuomotor policy is trained from offline demonstrations. During deployment, the frozen base policy runs the robot while a human provides occasional relative corrections. These sparse corrections are used to train our proposed lightweight FlowCorrect module that locally steers the policy’s flow field, yielding an adapted policy without retraining the original backbone.
• Figure 2: (a) Overview of FlowCorrect module that is attached to the DiTX-Transformer from Maniflow yan2025maniflow: we extend an existing flow matching policy $\pi_{\theta}$ based on DiTX-Transformer with our FlowCorrect module. Our lightweight FlowCorrect module consists of LoRA adapters (parametrized by $\Delta\theta$) injected into the transformer, and a gating module $g_{\psi}$ that outputs a signal to steer the vector flow field towards the corrected action. (b) Intuition: across N=4 integration steps, FlowCorrect iteratively adjusts the predicted velocities from $v_{n,t}$ to $v_{n,t}^*$, steering the rollout from a base action $\hat{\boldsymbol{a}}_t^{\text{base}}$ toward a corrected action $\boldsymbol{a}_t^{\text{corr}}$.
• Figure 3: Pipeline of the interactive correction interface.
• Figure 4: Hardware setup and representative real-world tasks used in the experiments.
• Figure 5: Top row: Selected ID-hard and OOD-hard initial conditions for the three tasks (left to right): Pouring, Cup Uprighting, and Pick-and-Place. The green regions indicate the workspace areas covered by the demonstrations. Middle row: Representative failure cases of the base policy under these conditions. Bottom row: Qualitative examples of successful executions after FlowCorrect fine-tuning on conditions that previously failed.