motion-tracking

MimicX introduces policy-in-the-loop supervision refinement for video-driven humanoid motion tracking, enabling robots to execute human motions (tennis, football juggling, dance, kung fu, parkour) captured from ordinary video demonstrations, including in collision scenes.

BRACE 提出一种全身人形机器人运动跟踪器，通过变换参考轨迹并将教师策略蒸馏为纯本体感知的 flow-matching 策略，使其在倾斜地形上能够施加和补偿手部指令力，实现在仿真与 Unitree-G1 真机上的力控与地形适应。

CrossBFM proposes a unified encoder architecture to distill a shared latent behavior space across humanoid embodiments, enabling efficient training and cross-embodiment generalization for motion tracking, goal reaching, and reward optimization.

Philips has launched a new smart toothbrush with AI motion-tracking and a touchscreen to help users improve their brushing technique, available in Europe and the US with a global rollout expected in 2027.

SceneBot is a unified motion tracking framework that conditions a single humanoid policy on both reference motions and per-link contact labels, enabling free-space locomotion, terrain traversal, and whole-body manipulation in contact-rich environments.

This paper introduces LIMMT, a data-centric study showing that training with high-quality, minimal subsets of motion data (under 3% of AMASS) outperforms using the full dataset for physics-based humanoid motion tracking, defining motion data quality through physics feasibility, diversity, and complexity.

Humanoid-GPT is a GPT-style Transformer pre-trained on a billion-scale motion corpus, achieving zero-shot generalization for whole-body motion tracking across unseen motions and tasks.