人形Hanoi：探究基于共享全身控制的技能型方块重组
Humanoid Hanoi: Investigating Shared Whole-Body Control for Skill-Based Box Rearrangement
AI总结：
本文提出了一种基于共享全身控制器的技能型方块重组框架，通过数据聚合提升长时域鲁棒性，并在Humanoid Hanoi基准上验证了其有效性。
摘要：
我们研究了一个基于技能的框架，用于人形机器人的方块重组，该框架通过在任务层面序列化可重用的技能，实现了长时间范围的执行。在我们的架构中，所有技能都通过一个共享的、任务无关的全身控制器（WBC）执行，为技能组合提供了一致的闭环接口，与使用每个技能单独低层控制器的非共享设计形成对比。我们发现，简单地重用预训练的相同WBC可能会在长时间范围内降低鲁棒性，因为新的技能及其组合会诱导状态和命令分布的偏移。我们通过一个简单的数据聚合过程来解决这个问题，该过程通过在域随机化下闭环技能执行的rollouts来增强共享WBC训练。为了评估该方法，我们引入了Humanoid Hanoi，一个长时间范围的塔罗克方块重组基准，我们在仿真和Digit V3人形机器人上报告了结果，展示了在长时间范围内完全自主的方块重组，并量化了共享WBC方法相对于非共享基线的优势。项目页面：https://osudrl.github.io/Humanoid_Hanoi/
英文摘要：
We introduce \emph{Humanoid Hanoi}, a challenge problem for long-horizon humanoid skill composition that requires a robot to repeatedly sequence pickup, locomotion, and placement skills to rearrange stacked boxes in simulation and on hardware. This symbolically simple task exposes a weakness in a common modular humanoid architecture, where reusable high-level skills are learned on top of a shared, task-agnostic whole-body controller (WBC). While such a WBC provides a unified low-level interface for skill composition, it may not be sufficiently hardened to execute the full collection of learned skills under domain randomization and long-horizon closed-loop execution. We compare strategies for addressing this issue, including skill-specific WBC fine-tuning, residual low-level adaptation, and task-driven data aggregation that expands the shared-WBC training distribution with closed-loop trajectories induced by learned skills while preserving its original tracking objective. In our evaluated system, the shared-WBC approach achieves the strongest long-horizon robustness. A direct transition-smoothing intervention further shows that low-level controller handoffs account for a substantial part of the composition loss observed with non-shared controllers. Project page: https://osudrl.github.io/Humanoid_Hanoi/
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。
