让跟踪变得容易：用于双足机器人全身控制的神经运动重定向
Make Tracking Easy: Neural Motion Retargeting for Humanoid Whole-body Control
AI总结：
本文提出NMR框架，通过学习数据分布而非优化最优解，解决传统重定向方法的非凸性问题，提升双足机器人在复杂环境中的运动能力。
摘要：
双足机器人需要多样化的运动技能以适应复杂环境，但从人类数据中弥合运动学和动力学的具身体验差距仍是重大瓶颈。通过Hessian分析，我们证明传统基于优化的重定向本质上非凸且易陷入局部最优，导致物理伪影如关节跳跃和自穿透。为此，我们将重定向问题重新表述为学习数据分布而非优化最优解，提出NMR神经运动重定向框架，将静态几何映射转化为动态感知的学习过程。我们首先提出分层专家物理细化（CEPR），通过基于VAE的运动聚类将异构运动分组为潜在动机。此策略显著降低了大规模并行强化学习专家的计算开销，这些专家将嘈杂的人类示范投影并修复到机器人可行运动流形上。所获得的高保真数据监督非自回归的CNN-Transformer架构，通过全局时间上下文推理以抑制重建噪声并绕过几何陷阱。在Unitree G1双足机器人上进行的实验表明，NMR消除了关节跳跃并显著减少了自碰撞，相比最先进的基线方法。此外，NMR生成的参考加速了下游全身控制策略的收敛，建立了弥合人类-机器人具身体验差距的可扩展路径。
英文摘要：
Humanoid robots require diverse motor skills to integrate into complex environments, but bridging the kinematic and dynamic embodiment gap from human data remains a major bottleneck. We demonstrate through Hessian analysis that traditional optimization-based retargeting is inherently non-convex and prone to local optima, leading to physical artifacts like joint jumps and self-penetration. To address this, we reformulate the targeting problem as learning data distribution rather than optimizing optimal solutions, where we propose NMR, a Neural Motion Retargeting framework that transforms static geometric mapping into a dynamics-aware learned process. We first propose Clustered-Expert Physics Refinement (CEPR), a hierarchical data pipeline that leverages VAE-based motion clustering to group heterogeneous movements into latent motifs. This strategy significantly reduces the computational overhead of massively parallel reinforcement learning experts, which project and repair noisy human demonstrations onto the robot's feasible motion manifold. The resulting high-fidelity data supervises a non-autoregressive CNN-Transformer architecture that reasons over global temporal context to suppress reconstruction noise and bypass geometric traps. Experiments on the Unitree G1 humanoid across diverse dynamic tasks (e.g., martial arts, dancing) show that NMR eliminates joint jumps and significantly reduces self-collisions compared to state-of-the-art baselines. Furthermore, NMR-generated references accelerate the convergence of downstream whole-body control policies, establishing a scalable path for bridging the human-robot embodiment gap.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
