提出混合生成策略，让机器人抓取更快更准。
HybridFlow: A Two-Step Generative Policy for Robotic Manipulation
- 分三阶段生成：先快速跳步，再调分布，最后精细修正。
- 比16步扩散模型成功率高15%~25%，推理速度提升8倍。
- 适合需要低延迟交互的机器人操作场景。
受限于推理延迟，现有机器人操作策略缺乏足够的实时环境交互能力。尽管更快的流匹配方法正逐步替代扩散模型，研究者仍在追求更适合交互式机器人控制的极速生成方案。作为流匹配的一步变体，均值流（MeanFlow）在图像生成中表现优异，但在动作生成精度上无法满足机器人操作的严苛要求。为此，我们提出**HybridFlow**，一种**3阶段、2-NFE**的方法：首先在均值流模式下进行全局跳步，接着通过重噪声（ReNoise）实现分布对齐，最后在重流（ReFlow）模式下进行局部精修。该方法通过利用均值流的快速生成优势，同时以最少生成步骤保证动作精度，平衡了推理速度与生成质量。真实世界实验表明，HybridFlow相较于16步扩散策略成功率提升15%~25%，推理时间从152ms降至19ms（**8×加速**，**约52Hz**）；在未见颜色的分布外（OOD）抓取任务中达到70.0%成功率，在可变形物体折叠任务中达66.3%。我们期望HybridFlow成为提升机器人操作策略实时交互能力的实用低延迟方法。
原文摘要 · Abstract (English)
Limited by inference latency, existing robot manipulation policies lack sufficient real-time interaction capability with the environment. Although faster generation methods such as flow matching are gradually replacing diffusion methods, researchers are pursuing even faster generation suitable for interactive robot control. MeanFlow, as a one-step variant of flow matching, has shown strong potential in image generation, but its precision in action generation does not meet the stringent requirements of robotic manipulation. We therefore propose \textbf{HybridFlow}, a \textbf{3-stage method} with \textbf{2-NFE}: Global Jump in MeanFlow mode, ReNoise for distribution alignment, and Local Refine in ReFlow mode. This method balances inference speed and generation quality by leveraging the rapid advantage of MeanFlow one-step generation while ensuring action precision with minimal generation steps. Through real-world experiments, HybridFlow outperforms the 16-step Diffusion Policy by \textbf{15--25\%} in success rate while reducing inference time from 152ms to 19ms (\textbf{8$\times$ speedup}, \textbf{$\sim$52Hz}); it also achieves 70.0\% success on unseen-color OOD grasping and 66.3\% on deformable object folding. We envision HybridFlow as a practical low-latency method to enhance real-world interaction capabilities of robotic manipulation policies.
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。