回到熟悉的未来：通过预想里程碑选择实现VLA策略的故障恢复
Back to the Familiar Future: Failure Recovery for VLA Policies via Pre-Imagined Milestone Selection
AI总结：
提出B2FF框架，通过预生成熟悉未来状态里程碑并选择恢复目标，使VLA策略在偏离轨迹时无需微调即可稳健恢复，成功率从56.3%提升至74.0%。
摘要：
视觉-语言-动作（VLA）策略在操作过程中可能偏离标称轨迹，即使任务在物理上仍然可行。从这些偏离中恢复具有挑战性，因为它们将策略推入陌生的状态空间，直接重新规划常常会破坏动作序列的稳定性。我们提出“回到熟悉的未来”（B2FF），一种面向预见性VLA的恢复框架，利用未来视觉条件作为恢复接口。在执行前，VLA基于干净的初始观察生成一个由熟悉未来状态组成的里程碑库。在恢复时，一个可恢复性感知的选择器从该库中选择一个恢复里程碑，并将其强制作为固定的视觉目标。这使得VLA能够将偏离轨迹的观察稳健地映射回熟悉的未来。在注入故障的LIBERO数据集上，在受控的恢复时间与注入故障对齐的情况下，B2FF将基线VLA的平均成功率从56.3%提升至74.0%，证明预想里程碑可以在不微调底层动作生成器的情况下指导恢复。
英文摘要：
Vision-language-action (VLA) policies can deviate from nominal trajectories during manipulation, even when tasks remain physically feasible. Recovering from these deviations is challenging, as they push the policy into unfamiliar state spaces where direct re-planning frequently destabilizes action sequences. We propose Back to the Familiar Future (B2FF), a recovery framework for foresight-driven VLAs that leverages future visual conditioning as a recovery interface. Before execution, the VLA generates a milestone bank of familiar future states conditioned on the clean initial observation. At recovery time, a recoverability-aware selector selects a recovery milestone from this bank and enforces it as a fixed visual goal. This enables the VLA to robustly map off-trajectory observations back to a familiar future. On failure-injected LIBERO, under controlled recovery timing aligned with the injected failure, B2FF increases the average success rate of a baseline VLA from 56.3% to 74.0%, demonstrating that pre-imagined milestones can guide recovery without fine-tuning the low-level action generator.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
