发表机构
University of Glasgow（格拉斯哥大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
FoldBack提出一种自校正掩码生成策略，通过三个推理时决策（细化验证、回滚、重试）实现长时程衣物折叠中的失败检测与修复，在33件真实衣物上达到75.2%成功率，优于基线。
AI 中文摘要
我们提出了FoldBack，一种用于长时程衣物折叠的自校正掩码生成策略。现有的长轨迹策略在抓取失败或滑脱后可能会继续执行，即使衣物尚未达到预期构型。我们将FoldBack的恢复机制构建在三个推理时决策之上：何时进行细化与验证、如何回滚、以及在何处以及如何重试。FoldBack将细化与抓取验证与拾放事件对齐，在保留成功抓取的同时将机器人返回到可重试的预抓取构型，并有选择地重新生成失败片段及选定的未来动作，同时避开之前失败的抓取位置。据我们所知，FoldBack是首个统一这些决策的可编辑全轨迹策略，使得失败交互能够在执行继续之前被检测、撤销和修复，而无需恢复演示或对基础策略进行重新训练。在来自六个类别的33件真实衣物上，FoldBack实现了75.2%的最终折叠成功率和0.837的最终掩码IoU，而最强先前基线的对应数值分别为45.7%和0.689。
英文摘要
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.
