HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark
2026-08-13 • Robotics
RoboticsArtificial IntelligenceComputer Vision and Pattern Recognition
AI summaryⓘ
The authors point out that current ways to check how well robots mimic human movements often miss important problems people notice, like shaky balance or slipping feet. To fix this, they created HumanTracker, a large and varied collection of real human motion data with detailed labels to help test these motions better. They also made HumanScore, a new scoring system trained on many pairs of motions that better matches what people actually prefer when judging robot movements. Their method finds issues that old scoring methods usually overlook, making humanoid motion tracking evaluation more accurate and useful.
humanoid motion trackingteleoperationwhole-body imitationkinematic errorsfoot skatingmotion benchmarksHumanTrackerHumanScoremotion evaluationperceptual alignment
Authors
Dairu Liu, Zekun Qi, Jiayu Zeng, Ruixi Yu, Yu Guan, Yintianrun Zhang, Xuchuan Chen, Sikai Liang, Zekai Li, Chenghuai Lin, Xinqiang Yu, Wenyao Zhang, He Wang, Li Yi
Abstract
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.