FoldBack: Self-Correcting Masked Generative Policy for Long-Horizon Garment Folding
cs.RO, cs.AI
Submitted: 2026-10-07
Updated: 2026-10-07
License: http://creativecommons.org/licenses/by/4.0/
The gist: We present FoldBack, a self-correcting masked generative policy for long-horizon garment folding.
Terminology
Abstract
We present FoldBack, a self-correcting masked generative policy for long-horizon garment folding. Existing long-trajectory policies may continue after a missed or slipped grasp even when the garment has not reached the intended configuration. We structure FoldBack's recovery mechanisms around three inference-time decisions: when to refine and verify, how to roll back, and where and how to retry. FoldBack aligns refinement and grasp verification with pick-and-place events, returns the robot to a retryable pre-grasp configuration while preserving successful grasps, and selectively regenerates the failed segment and selected future actions while avoiding previous failed grasp locations. To our knowledge, FoldBack is the first editable full-trajectory policy to unify these decisions, enabling failed interactions to be detected, undone, and repaired before execution continues, without recovery demonstrations or base-policy retraining. Across 33 real garments from six categories, FoldBack achieves 75.2% final folding success and 0.837 final-mask IoU, versus 45.7% and 0.689 for the strongest prior baseline.
Sources
- Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and Progress
- Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policies
- REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction
- CycleVLA: Proactive Self-Correcting Vision-Language-Action Models via Subtask Backtracking and Minimum Bayes Risk Decoding
- FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement
- 3D Diffuser Actor: Policy Diffusion with 3D Scene Representations
- Behavior Transformers: Cloning $k$ modes with one stone
- Behavior Generation with Latent Actions
- Training-Time Action Conditioning for Efficient Real-Time Chunking
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies