FoldBack：可自我纠错的衣物折叠机器人策略
FoldBack: Self-Correcting Masked Generative Policy for Long-Horizon Garment Folding
机器人叠衣服老是在抓错后硬着头皮做下去，FoldBack 能检测失败、回滚重试，33 件衣服测试成功率 75.2%，比之前最好的基线高出一大截。
FoldBack 是一个面向长程衣物折叠任务的掩码生成策略，围绕三个推理时决策设计恢复机制：何时细化与验证抓取、如何回滚、在哪里以及如何重试。该策略将抓取验证与放置事件对齐，在保留成功抓取的前提下让机器人回到可重试的预抓取姿态，并选择性重新生成失败片段。在 33 件真实衣物、六个类别的测试中，FoldBack 取得 75.2% 的折叠成功率和 0.837 的最终掩码 IoU，最强基线为 45.7% 和 0.689。它是首个无需恢复演示或基座策略重训即可编辑完整轨迹的策略。
FoldBack: Self-Correcting Masked Generative Policy for Long-Horizon Garment Folding
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.
