通过选对初始噪声，让机器人动作块无缝衔接。
Start Right, Arrive Right: Asynchronous Execution via Initial Noise Selection
- 用反向欧拉法找合适初始噪声，不改模型也能生成连贯动作。
- 12个仿真+6个真实任务中，动作衔接更稳定，性能提升显著。
- 无需训练或梯度，适合想快速部署的机器人开发者。
动作分块使机器人策略产生时间一致的行为，但基于流模型的多步动作序列生成存在延迟，无法满足实时控制需求。异步执行时，机器人在执行当前动作块的同时生成下一动作块，微小延迟也会导致动作块边界不一致。现有方法通过引导生成过程以匹配已执行的动作前缀来解决此问题。本文提出新思路：通过在生成前选择合适的初始噪声，即可让未修改的流微分方程自然生成连贯的下一动作块，将异步推理重构为噪声选择问题。我们提出 extbf{PAINT}，一种无需训练的方法，通过反向欧拉反演寻找初始噪声，并利用重绘规则构建最终动作块。 exttt{PAINT} 不需要梯度、重训练或策略修改；在 extit{12 个仿真基准} 和 extit{6 个真实世界操作任务} 上，覆盖单臂、双臂和人形机器人，均提升了执行一致性与任务表现。
原文摘要 · Abstract (English)
Action chunking enables robot policies to produce temporally coherent behavior, but generating multi-step action sequences with flow-based policies incurs latency that is incompatible with real-time control. Under asynchronous execution, the robot continues executing the current chunk while the next one is generated, causing even minor delays to create inconsistencies at chunk boundaries. Existing methods address this problem by steering generation toward the already executed action prefix. We instead show that prefix consistency can be achieved by selecting an appropriate initial noise before generation begins, allowing the unmodified flow ODE to produce a coherent next chunk. This reframes asynchronous inference as a noise selection problem rather than a trajectory steering problem. We introduce \textbf{PAINT}, a training-free method that finds this noise via backward Euler inversion and constructs the final chunk through a repainting rule. In summary, \texttt{PAINT} requires no gradients, retraining, or policy modification; yet it improves execution consistency and task performance across \textit{12 simulated benchmarks} and \textit{6 real-world manipulation tasks} spanning single-arm, bimanual, and humanoid embodiments. Website: ~\href{https://paint-action-chunking.github.io}{\texttt{https://paint-action-chunking.github.io}}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。