发表机构
Georgia Institute of Technology（佐治亚理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出谱技能表示，通过预测性学习紧凑编码运动片段，在29自由度人形机器人上降低62%跟踪误差，并支持技能链接与组合。
AI 中文摘要
机器人基础模型为通用人形机器人控制提供了一条有前景的路径，通常采用分层架构。然而，其有效性取决于规划器与控制器之间的命令接口，该接口必须支持精确执行，同时保持易于预测，并理想情况下允许从先前行为中组合出新行为。在本工作中，我们引入了谱技能（spectral skills），一种满足这些要求的接口潜在表示，通过预测性表示学习实现。设计上，谱技能紧凑地编码短运动片段，并通过预测后续运动而非重建编码器输入来学习。在29自由度人形机器人上，基于谱技能的条件控制器相对于现有技术水平将全局跟踪误差降低了62%。同一冻结控制器能够链接独立编码的技能，而无需单独的过渡策略。它还能通过向任何兼容的基础技能添加正交方向来组合新行为，产生训练数据中未见过的组合。我们在Unitree G1硬件上演示了跟踪、链接和组合，以及通过语言条件规划器的控制。项目页面：此https URL。
英文摘要
Robotic foundation models offer a promising path toward general-purpose humanoid robot control, often through hierarchical architectures. However, their effectiveness depends on the command interface between the planner and the controller, which must support accurate execution while remaining easy to predict, and ideally allow new behaviors to be composed from prior ones. In this work, we introduce spectral skills, a latent representation of this interface that meets these requirements through predictive representation learning. By design, spectral skills compactly encode short motion segments and are learned by predicting subsequent motion rather than reconstructing the encoder input. On a 29-DoF humanoid, a controller conditioned on spectral skills reduces global tracking error by 62\% relative to the state of the art. The same frozen controller chains independently encoded skills without a separate transition policy. It also composes new behaviors by adding orthogonal directions to any compatible base skill, producing combinations unseen in the training data. We demonstrate tracking, chaining, and composition, as well as control through a language-conditioned planner, on Unitree G1 hardware. Project page: https://spectral-skill.github.io
