有目的的流动：潜在动作引导的流匹配策略用于机器人操作
Flowing With Purpose: Latent Action Guided Flow Matching Policies For Robotic Manipulation
AI总结：
提出潜在动作引导流匹配（LAFM）框架，通过自适应先验分布库替代固定高斯分布，利用潜在动作模型选择结构对齐的初始化，解决流匹配策略中向量场纠缠问题，在真实机器人部署中成功率提升23.4%。
摘要：
流匹配最近已成为机器人操作中行为克隆的新标准。然而，最先进的流匹配策略存在系统性的结构不匹配：尽管机器人动作空间具有强烈的碎片化和异方差结构，它们仍依赖于全局固定的各向同性源分布。这种不可知的初始化迫使模型学习高度纠缠的向量场，成为训练效率的瓶颈并限制整体策略性能。为解决这一局限，我们引入了潜在动作引导流匹配（LAFM），一种新颖的框架，用自适应学习先验分布库替代单一高斯分布。通过使用潜在动作模型来锚定这些分布，LAFM将当前观测映射到离散运动基元，选择专门的基分布，为去噪过程提供信息丰富、结构对齐的初始化。这种动态自适应性自然地适应人类演示中的异方差性，并使传输轨迹更短、纠缠更少。实验表明，LAFM显著优于标准流匹配公式，在真实机器人部署中任务成功率提高23.4%，在LIBERO-90基准上提高10.4%。此外，我们证明LAFM达到了最先进的结果，在利用显著更小架构的同时超越了大规模预训练的视觉-语言-动作模型。
英文摘要：
Flow matching has recently become a new standard for behavior cloning in robotic manipulation. However, state-of-the-art flow matching policies suffer from a systematic structural mismatch: they rely on a globally fixed isotropic source distribution despite the strongly fragmented and heteroscedastic structure of robotic action spaces. This agnostic initialization forces the model to learn highly entangled vector fields, bottlenecking training efficiency and limiting overall policy performance. To address this limitation, we introduce Latent Action Guided Flow Matching (LAFM), a novel framework that replaces the monolithic Gaussian with an adaptive library of learned prior distributions. By grounding these distributions using a latent action model, LAFM maps current observations to discrete motion primitives, selecting a specialized base distribution that provides an informed, structurally aligned initialization for the denoising process. This dynamic adaptivity naturally accommodates heteroscedasticity in human demonstrations and makes transport trajectories shorter and less entangled. Empirically, LAFM substantially outperforms standard flow matching formulations, increasing task success rates by 23.4% in real-world robotic deployments and by 10.4% on the LIBERO-90 benchmark. Furthermore, we demonstrate that LAFM achieves state-of-the-art results, surpassing massively pre-trained vision-language-action models while utilizing significantly smaller architectures.
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。
