PFM-HR：面向人形机器人的姿态流匹配
PFM-HR: Pose Flow Matching for Humanoid Robots
浏览论文内容
中文总结 AI 辅助
本文提出PFM-HR，一种在大规模无序姿态数据上训练的可复用流匹配先验，通过引入PGS调节跟踪奖励提升人形机器人运动跟踪性能，尤其适用于高动态运动。
中文摘要 AI 辅助
运动先验可提升基于物理的人形机器人跟踪的强化学习效果，但时间先验需要有序的运动片段，而姿态先验对策略诱导的姿态转换的指导有限。本文提出面向人形机器人的姿态流匹配（Pose Flow Matching for Humanoid Robots，PFM-HR），这是一种直接在大规模无序姿态数据上训练的可复用流匹配先验。PFM-HR引入姿态几何得分（Pose Geometry Score，PGS），用于量化执行过程中关节坐标变化与先验捕获的姿态变化局部几何的对齐程度。通过PGS调节跟踪奖励，可引导策略向结构化姿态变化方向探索，同时在跟踪任务中保持先验冻结。实验表明，PFM-HR在单一运动和通用运动跟踪中均有提升，尤其对高动态运动效果显著。
英文摘要
Motion priors improve reinforcement learning for physics-based humanoid tracking, but temporal priors require ordered motion clips, while pose priors provide limited guidance for policy-induced pose transitions. We present Pose Flow Matching for Humanoid Robots (PFM-HR), a reusable flow matching prior trained directly on large scale unordered pose data. PFM-HR introduces the Pose Geometry Score (PGS), which quantifies how joint coordinate changes during rollouts align with the local geometry of pose variation captured by the prior. Using PGS to modulate the tracking reward guides policy exploration toward structured pose changes while keeping the prior frozen across tracking tasks. Experiments demonstrate that PFM-HR improves both single motion and general motion tracking, especially for highly dynamic motions.
