FlowCorrect: Efficient Interactive Correction of Generative Flow Policies for Robotic Manipulation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908864699432960 |
|---|---|
| author | Welte, Edgar Shi, Yitian Wolf, Rosa Gilles, Maximillian Rayyes, Rania |
| author_facet | Welte, Edgar Shi, Yitian Wolf, Rosa Gilles, Maximillian Rayyes, Rania |
| contents | 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 propose FlowCorrect, a modular interactive imitation learning approach that enables deployment-time adaptation of flow-matching manipulation policies from sparse, relative human corrections without 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 four tabletop tasks: pick-and-place, pouring, cup uprighting, and insertion. With a low correction budget, FlowCorrect achieves an 80% success rate on previously failed cases while preserving performance on previously solved scenarios. The results clearly demonstrate that FlowCorrect learns from very few demonstrations and enables fast, sample-efficient, incremental, human-in-the-loop corrections of generative visuomotor policies at deployment time in real-world robotics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_22056 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FlowCorrect: Efficient Interactive Correction of Generative Flow Policies for Robotic Manipulation Welte, Edgar Shi, Yitian Wolf, Rosa Gilles, Maximillian Rayyes, Rania Robotics Machine Learning 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 propose FlowCorrect, a modular interactive imitation learning approach that enables deployment-time adaptation of flow-matching manipulation policies from sparse, relative human corrections without 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 four tabletop tasks: pick-and-place, pouring, cup uprighting, and insertion. With a low correction budget, FlowCorrect achieves an 80% success rate on previously failed cases while preserving performance on previously solved scenarios. The results clearly demonstrate that FlowCorrect learns from very few demonstrations and enables fast, sample-efficient, incremental, human-in-the-loop corrections of generative visuomotor policies at deployment time in real-world robotics. |
| title | FlowCorrect: Efficient Interactive Correction of Generative Flow Policies for Robotic Manipulation |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2602.22056 |