面向人形机器人视频模仿学习的直接动态重定向
Direct Dynamic Retargeting for Humanoid Imitation Learning from Videos
AI总结：
提出直接动态重定向（DDR）框架，直接从专家视频生成高保真、动态可行的轨迹，通过任务空间建模和基于采样的模型预测控制求解器，绕过几何偏差，提升演示跟踪精度并加速强化学习训练。
摘要：
从单目视频演示中进行模仿学习为向人形机器人教授复杂技能提供了一种可扩展的方法。然而，将人体运动转化为类人运动需要克服显著的形态不匹配。标准方法依赖于几何重定向或间接动态重定向流程。我们发现这些中间运动学投影引入了几何偏差，限制了搜索空间并产生了次优的动态行为。在本文中，我们提出了直接动态重定向（DDR），一种新颖的单阶段框架，可直接从专家视频生成高保真、动态可行的轨迹。通过将问题在任务空间中建模，并在物理模拟器中利用基于采样的模型预测控制求解器，DDR 在缓解输入漂移的同时原生优化复杂的接触序列。我们的实验表明，绕过几何偏差使 DDR 在演示跟踪精度上优于最先进的基线方法。此外，我们证实，向强化学习智能体提供此类物理可行的参考可加速训练收敛，并增强敏捷和平衡行为的最终执行。源代码将公开发布。
英文摘要：
Imitation Learning from monocular video demonstrations provides a scalable approach for teaching complex skills to humanoid robots. However, translating human motion to humanoids requires overcoming significant morphological mismatches. Standard approaches rely on Geometric Retargeting or Indirect Dynamic Retargeting pipelines. We identify that these intermediate kinematic projections introduce a geometric bias, restricting the search space and yielding suboptimal dynamic behaviors. In this paper, we propose Direct Dynamic Retargeting (DDR), a novel single-stage framework that generates high-fidelity, dynamically feasible trajectories directly from expert videos. By formulating the problem in the task space and leveraging a sampling-based Model Predictive Control solver within a physics simulator, DDR natively optimizes over complex contact sequences while mitigating input drift. Our experiments demonstrate that bypassing the geometric bias allows DDR to outperform state-of-the-art baselines in demonstration tracking accuracy. Furthermore, we establish that providing such physically viable references to RL agents accelerates training convergence and enhances the final execution of agile and balancing behaviors. Source code will be made publicly available.
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。
