Diffusion-based policies have recently achieved remarkable success in robotics by formulating action prediction as a conditional denoising process. However, the standard practice of sampling from random Gaussian noise often requires multiple iterative steps to produce clean actions, leading to high inference latency that incurs a major bottleneck for real-time control. In this paper, we challenge the necessity of uninformed noise sampling and propose Action-to-Action flow matching (A2A), a novel policy paradigm that shifts from random sampling to initialization informed by the previous action. Unlike existing methods that treat proprioceptive action feedback as static conditions, A2A leverages historical proprioceptive sequences, embedding them into a high-dimensional latent space as the starting point for action generation. This design bypasses costly iterative denoising while effectively capturing the robot's physical dynamics and temporal continuity. Extensive experiments demonstrate that A2A exhibits high training efficiency, fast inference speed, and improved generalization. Notably, A2A enables high-quality action generation in as few as a single inference step (0.56 ms latency), and exhibits superior robustness to visual perturbations and enhanced generalization to unseen configurations. Lastly, we also extend A2A to video generation, demonstrating its broader versatility in temporal modeling. Project site: https://lorenzo-0-0.github.io/A2A_Flow_Matching.

翻译：基于扩散的策略最近在机器人学中取得了显著成功，其将动作预测建模为一个条件去噪过程。然而，从随机高斯噪声采样的标准实践通常需要多次迭代步骤来生成清晰的动作，导致较高的推理延迟，这成为实时控制的主要瓶颈。在本文中，我们挑战了无信息噪声采样的必要性，并提出动作到动作流匹配（A2A），这是一种新颖的策略范式，将从随机采样转向由先前动作信息化的初始化。与将本体感觉动作反馈视为静态条件的现有方法不同，A2A利用历史本体感觉序列，将其嵌入高维潜在空间作为动作生成的起点。这种设计绕过了昂贵的迭代去噪过程，同时有效捕捉了机器人的物理动力学和时间连续性。大量实验表明，A2A展现出高训练效率、快速推理速度和改进的泛化能力。值得注意的是，A2A能够在少至单个推理步骤（0.56毫秒延迟）内实现高质量动作生成，并对视觉扰动表现出卓越的鲁棒性，以及对未见配置的增强泛化能力。最后，我们还将A2A扩展到视频生成，展示了其在时间建模方面更广泛的通用性。项目网站：https://lorenzo-0-0.github.io/A2A_Flow_Matching。