Causeway：恢复VLA策略中指令切换的任务可达性

中文摘要 AI 辅助

视觉-语言-动作（VLA）策略能够从标准初始状态执行许多任务，然而在另一个任务改变了机器人的物理状态后，新的指令可能会失败。我们研究指令切换，即在执行一个任务期间或之后发出新任务的情况。我们观察到，一个从标准初始状态能够可靠完成的目标任务，可能从前序任务产生的状态变得不可达。我们将这种状态称为任务孤岛。我们提出Causeway，一种无需训练的推理时干预方法。给定当前状态和目标任务的重新进入位姿，Causeway通过冻结的解码计算进行反向传播，并在动作流表示中应用状态导向的写入。VLA自行解码返回运动，无需参数更新、新的动作头或外部动作生成。在LIBERO-Goal上的71个跨物体对、三种切换时机和三种VLA架构中，Causeway将裸切换成功率从3-26%提高到47-65%，并将到达交接邻域的比例提高了42-72个百分点。在LIBERO-Object和真实xArm平台上的额外实验表明，该恢复方法超越了主要的LIBERO-Goal设置，在仿真和机器人上均有效。

英文摘要

Vision-language-action (VLA) policies can execute many tasks from standard initial states, yet a new instruction may fail after another task has altered the robot's physical state. We study instruction switching, where a new task is issued during or after the execution of a different one. We observe that a target task that is reliably completed from its standard initial states can become inaccessible from states produced by a preceding task. We call such states task islands. We propose Causeway, a training-free inference-time intervention. Given the current state and a re-entry pose for the target task, Causeway back-propagates through the frozen decoding computation and applies a state-directed write within the action-stream representation. The VLA decodes the return motion itself, without parameter updates, a new action head, or external action generation. Across 71 cross-object pairs, three switch timings, and three VLA architectures on LIBERO-Goal, Causeway raises bare-switch success from 3-26% to 47-65% and increases the rate of reaching the handoff neighborhood by 42-72 percentage points across models. Additional experiments on LIBERO-Object and a real xArm platform show that the recovery extends beyond the main LIBERO-Goal setting, both in simulation and on a robot.

发表机构

• University of Maryland（马里兰大学）
• University of Southern California（南加州大学）

机构由 AI 辅助整理，请以论文原文为准。