HumanTracker：面向全面且與人類對齊的運動追蹤基準

摘要

人形機器人運動追蹤是遙操作與全身模仿的核心技術，然而其評估結果往往與人們在影片中的感知不一致。運動學誤差雖能平均逐幀姿態差異，卻忽略了最關鍵的物理偽影，特別是不穩定的支撐以及錯誤的接觸，例如腳部滑步與時機不當的觸地。此外，目前廣泛使用的測試套件規模偏小，缺乏足夠的多樣性來充分考驗接觸密集且長時間跨度的行為。我們提出HumanTracker，使人形機器人追蹤評估兼具感知對齊性與可擴展性。HumanTracker基準包含來自多位專業表演者的約153小時光學運動軌跡，組織為四個動作族類，並附有文字標註以支持細粒度診斷。我們進一步提出HumanScore，這是一個基於偏好對齊的指標，在包含24K個動作的12K組動作配對上訓練而成。在具代表性的最新追蹤方法上，HumanScore能更準確地預測人類偏好，並揭露運動學指標經常遺漏的接觸與穩定性失敗。

English

Humanoid motion tracking is central to teleoperation and whole-body imitation, yet evaluation often disagrees with what people perceive in videos. Kinematic errors average per-frame pose differences but miss the physical artifacts that matter most, particularly unstable support and incorrect contacts such as foot skating and mistimed touch-downs. Meanwhile, widely used test suites are small and lack the diversity needed to stress contact-rich, long-horizon behaviors. We introduce HumanTracker to make humanoid tracking evaluation both perceptually aligned and scalable. The HumanTracker benchmark contains approximately 153 hours of optical motion trajectories from multiple professional performers, organized into four motion families with text labels for fine-grained diagnosis. We further propose HumanScore, a preference-aligned metric trained on 12K motion pairs containing 24K motions. Across representative state-of-the-art trackers, HumanScore better predicts human preferences and reveals contact and stability failures that kinematic metrics often miss.