用动态条件聚合指令，让机器人更稳地复现复杂动作。
Robust and Generalized Humanoid Motion Tracking
- 通过时序编码器融合本体感知，动态选择动作指令上下文。
- 仅需3.5小时数据训练，实现零样本迁移与真实机器人稳定运行。
- 适合追求高鲁棒性的仿人机器人运动控制研究者。
学习通用的仿人机器人全身控制器极具挑战，因为实际参考动作在转移到机器人后常含噪声和不一致，闭环执行可能放大局部缺陷，导致高动态、接触频繁行为中的漂移或失败。本文提出一种动态条件命令聚合框架，采用因果时序编码器总结近期本体感知信息，并通过多头交叉注意力编码器基于当前动态有选择性地聚合上下文窗口。进一步引入跌倒恢复训练策略，结合随机不稳定的初始化及逐渐增强的向上助力力，提升鲁棒性和抗干扰能力。所提策略仅需约3.5小时运动数据，支持单阶段端到端训练，无需知识蒸馏。在多种参考输入和挑战性运动场景下评估，表现出对未见动作的零样本迁移能力，以及在物理仿人机器人上的稳健仿真到现实迁移效果。
原文摘要 · Abstract (English)
Learning a general humanoid whole-body controller is challenging because practical reference motions can exhibit noise and inconsistencies after being transferred to the robot domain, and local defects may be amplified by closed-loop execution, causing drift or failure in highly dynamic and contact-rich behaviors. We propose a dynamics-conditioned command aggregation framework that uses a causal temporal encoder to summarize recent proprioception and a multi-head cross-attention command encoder to selectively aggregate a context window based on the current dynamics. We further integrate a fall recovery curriculum with random unstable initialization and an annealed upward assistance force to improve robustness and disturbance rejection. The resulting policy requires only about 3.5 hours of motion data and supports single-stage end-to-end training without distillation. The proposed method is evaluated under diverse reference inputs and challenging motion regimes, demonstrating zero-shot transfer to unseen motions as well as robust sim-to-real transfer on a physical humanoid robot.
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。