发表机构
Norwegian University of Science and Technology (NTNU)（挪威科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出自适应均值流（AMF），一种基于流的模仿学习方法，通过加速流匹配和利用上一步轨迹的损坏版本，实现平滑且响应式的全闭环机器人控制，在模拟和真实任务中性能显著优于基线。
AI 中文摘要
基于扩散和流的机器人策略近年来在机器人模仿学习（IL）中变得广泛，因为它们具有高性能和建模连续及多模态分布的能力。然而，这些模型使用的迭代去噪过程引入了显著的预测延迟，阻碍了高频闭环机器人控制，并在频繁更新机器人动作预测时导致抖动和不稳定的运动。因此，通常的做法是训练模型预测动作块，这些动作块可以在没有反馈的情况下顺序执行，即使这会降低响应性并可能意味着最新的状态信息未被使用。在本文中，我们提出了自适应均值流（AMF），一种基于流的IL方法，能够实现平滑且响应式的全闭环机器人控制。AMF使用均值流（Mean Flow），这是流匹配（FM）的一种加速形式，以最小化预测延迟。为了确保预测之间的平滑性和一致性，AMF在预测新机器人动作时使用来自上一步轨迹的损坏版本，信噪比随轨迹的时间参数增加而增加。这阻止了预测从一步到下一步的大变化，同时允许自由调整未来步骤的预测。我们在广泛的模拟和真实机器人任务上评估了AMF，并展示了与基线相比显著改进的性能。代码：此https URL。
英文摘要
Diffusion- and flow-based robot policies have recently become widespread in robotic Imitation Learning (IL) due to their high performance and ability to model continuous and multimodal distributions. However, the iterative denoising procedure used by these models introduces significant prediction latency, hindering high-frequency closed-loop robot control and leading to jittery, unstable motion when frequent updates to the robot's action predictions are used. Therefore, it is common practice to train models to predict chunks of actions that can be executed sequentially without feedback, even when this reduces responsiveness and may mean the most recent state information is not used. In this article, we present Adaptive Mean Flow (AMF), a flow-based IL method that enables smooth and responsive, fully closed-loop robot control. AMF uses Mean Flow, which is an accelerated form of Flow Matching (FM), to minimize prediction latency. To ensure smoothness and consistency across predictions, AMF uses a corrupted version of the trajectory from the previous step when predicting new robot actions, with the signal-to-noise ratio increasing over the time parameter of the trajectory. This discourages large changes in the prediction from one step to the next, while allowing freedom to adapt the predictions for future steps. We evaluate AMF across a wide range of simulated and real robot tasks and demonstrate significantly improved performance compared with baselines. Code: https://github.com/akselva/Adaptive-mean-flow-RoboticIL.
Comments8 pages, 7 figures
Journal refIEEE Robotics and Automation Letters, vol. 11, no. 11, pp. 12935-12942, Nov. 2026
