发表机构
Federal University of Santa Catarina (UFSC)（圣卡塔琳娜联邦大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对干摩擦与静摩擦下的质点系统开环控制，研究动作扩散方法，基于条件1D U-Net生成控制序列，实验显示其在低样本场景下可降低终端误差与停滞步骤，性能优于多种基准方法。
AI 中文摘要
扩散模型近期已成为用于规划与控制的高表达生成先验。本文研究动作扩散（Action Diffusion），这是一种动作序列扩散形式，用作具有干摩擦与静摩擦的质点系统的开环提议分布。在该基准中，仅当施加的输入超过静摩擦阈值时运动才会启动，因此有效控制量占据动作序列空间中一个小且具有时间结构的子集。紧凑的条件一维U-Net（1D U-Net）根据初始状态和目标状态生成有界控制序列。我们将其与均匀随机射击（uniform random shooting）、来自同一结构化数据集先验的随机射击以及交叉熵方法（Cross-Entropy Method, CEM）进行比较。结果表明，动作扩散可降低终端误差和停滞步骤，尤其在低样本 regime 中。这些结果表明，条件扩散提供了一种有效机制，用于生成时间连贯的控制序列，该机制通过对训练先验中的结构化控制原语进行条件化和重组，克服静摩擦，实现状态到状态的开环控制。
英文摘要
Diffusion models have recently emerged as expressive generative priors for planning and control. This paper studies Action Diffusion, an action-sequence diffusion formulation used as an open-loop proposal distribution for a point-mass system with dry friction and stiction. In this benchmark, motion starts only when the applied input exceeds a static-friction threshold, so effective controls occupy a small and temporally structured subset of the action-sequence space. A compact conditional 1D U-Net generates bounded control sequences conditioned on initial and target states. We compare it with uniform random shooting, random shooting from the same structured dataset prior, and the Cross-Entropy Method (CEM). Results show that Action Diffusion reduces terminal error and stuck steps, especially in low-sample regimes. These results indicate that conditional diffusion provides an effective mechanism for generating temporally coherent control sequences that overcome stiction by conditioning and recombining structured control primitives from the training prior for state-to-state open-loop control.
