通过子频率流形遍历的频率引导动作扩散
Frequency-Guided Action Diffusion via Sub-Frequency Manifold Traversal
AI总结：
提出频率引导算子（FGO），通过子频率流形逐步引导扩散策略生成平滑动作，在15个机器人操作任务上提升了动作平滑性和时间一致性。
摘要：
通过行为克隆学习视觉运动策略通常涉及模仿人类操作员收集的专家演示。然而，自然的人类演示固有地包含高频噪声，例如间歇性抖动、暂停和动作抖动。训练策略直接模仿这些原始轨迹不可避免地会导致模型继承这些次优行为。这种病理在基于扩散的策略中尤为明显，其中迭代去噪步骤可能无意中放大高频伪影而牺牲有意义的细粒度细节。为了解决这些限制，我们提出了一种新颖的基于频率的算法，该算法能够实现隐式频谱操控和平滑动作生成。我们的方法，频率引导算子（FGO），通过逐步将噪声样本通过具有扩展频谱带的中间子频率流形驱动，来引导扩散策略的生成过程。在来自5个基准测试的15个机器人操作任务上验证，FGO在增强动作平滑性和时间一致性方面取得了优越性能，同时保留了成功执行任务所需的细节。项目网站：https://henrywjl.github.io/frequency-guidance-operator/
英文摘要：
Learning visuomotor policies via behavior cloning typically involves mimicking expert demonstrations collected by human operators. However, natural human demonstrations inherently contain high-frequency noise, such as intermittent jerks, pauses, and action jitter. Training policies to directly imitate these raw trajectories inevitably causes the model to inherit these suboptimal behaviors. This pathology is particularly pronounced in diffusion-based policies, where iterative denoising steps can inadvertently amplify high-frequency artifacts at the expense of meaningful fine-grained details. To address these limitations, we present a novel frequency-based algorithm that enables implicit spectral maneuvering and smooth action generation. Our method, Frequency Guidance Operator (FGO), steers the generation process of diffusion polices by progressively driving the noisy samples through intermediate sub-frequency manifolds with expanding spectral bands. Validated on 15 robotic manipulation tasks from 5 benchmarks, FGO achieves superior performance in enhancing action smoothness and temporal consistency while preserving the details necessary for successful task execution. Project website: https://henrywjl.github.io/frequency-guidance-operator/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
