实测12项设计对人形机器人运动追踪的影响，找出真正关键因素。
What Matters in Humanoid General Motion Tracking? An Empirical Study
- 构建可控实验框架YAHMP，系统对比不同建模与训练配置
- 发现动作表示和训练方法显著影响追踪精度，其余多影响能耗或交互能力
- 零样本部署到真实Unitree G1，实现平衡追踪与有力交互
人形机器人通用运动追踪需在保持平衡的同时复现多样全身动作。现有方法涉及众多设计选择，其独立影响常难以评估。本文通过实证研究，分析近期人形运动模仿流水线中的常见建模与训练因素。为保证实验可控可复现，我们开发了YAHMP——一个开源模块化框架，用于在Unitree G1上训练、评估与部署全身运动追踪策略。在YAHMP中，我们定义基准配置，并对比不同变体：动作指令表示、观测历史、动作表示、执行方式、训练中手部受力随机化及训练方法。在重定向人类动作的测试集上评估策略，并与在同一动作集上训练的外部基线TWIST2进行比较。结果区分出对追踪效果有明显影响的选择，以及仅改变执行努力、训练复杂度或物理交互能力的选择。最终，我们将YAHMP策略零样本部署至真实Unitree G1，验证了多样全身运动追踪、外力扰动下的平衡维持及有力交互能力。
原文摘要 · Abstract (English)
Humanoid general motion tracking requires policies that can follow diverse whole-body references while maintaining balance. Building such policies involves many practical design choices, and their individual effects are often hard to assess. We address this issue with an empirical study of common modeling and training factors used in recent humanoid motion-imitation pipelines. To make the study controlled and reproducible, we developed YAHMP, an open-source modular framework for training, evaluating, and deploying whole-body motion tracking policies on the Unitree G1. Within YAHMP, we define a nominal configuration and compare variants that differ in motion-command representation, observation history, action representation, actuation profile, hand-force randomization during training, and training approach. We evaluate the resulting policies on a test set of retargeted human motions and compare the nominal policy with TWIST2 as an external baseline trained on the same motion set. The results distinguish choices with clear tracking effects from choices that mainly change actuation effort, training complexity, or physical interaction capability. Finally, we deploy YAHMP policies zero-shot on the real Unitree G1, demonstrating diverse whole-body motion tracking, balance under external perturbations, and forceful interaction.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。