分层控制让人形机器人更稳更灵活，实测表现优于现有方法。
JAEGER: Dual-Level Humanoid Whole-Body Controller
- 上下半身分开控制，降低复杂度并提升容错性。
- 支持粗粒度根部速度与细粒度关节角度追踪，动作更稳定。
- 基于人体数据训练，适合需要复杂运动的机器人研发者。
本文提出JAEGER，一种双层级人形机器人全身控制器，旨在解决训练更鲁棒、多功能策略的挑战。与传统单控制器方法不同，JAEGER将上半身和下半身控制分离为两个独立控制器，使各部分能更专注地完成特定任务。该设计缓解了维度灾难问题，并提升了系统容错能力。JAEGER同时支持根部速度跟踪（粗粒度控制）和局部关节角度跟踪（细粒度控制），实现多样化且稳定的运动。为训练控制器，我们采用人体运动数据集AMASS，通过高效重定向网络将人体姿态映射至人形机器人姿态，并结合课程学习策略：先进行监督学习初始化，再通过强化学习进一步探索。我们在两种人形机器人平台上进行实验，在仿真与真实环境中均证明该方法优于当前先进方法。
原文摘要 · Abstract (English)
This paper presents JAEGER, a dual-level whole-body controller for humanoid robots that addresses the challenges of training a more robust and versatile policy. Unlike traditional single-controller approaches, JAEGER separates the control of the upper and lower bodies into two independent controllers, so that they can better focus on their distinct tasks. This separation alleviates the dimensionality curse and improves fault tolerance. JAEGER supports both root velocity tracking (coarse-grained control) and local joint angle tracking (fine-grained control), enabling versatile and stable movements. To train the controller, we utilize a human motion dataset (AMASS), retargeting human poses to humanoid poses through an efficient retargeting network, and employ a curriculum learning approach. This method performs supervised learning for initialization, followed by reinforcement learning for further exploration. We conduct our experiments on two humanoid platforms and demonstrate the superiority of our approach against state-of-the-art methods in both simulation and real environments.
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。