发表机构
Ocean University of China; University of Chinese Academy of Sciences; Chinese Academy of Sciences（中国海洋大学; 中国科学院大学; 中国科学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
CHOREO将异构人形技能统一表示为可执行轨迹，通过免训练组合实现高成功率的多动作序列执行。
AI 中文摘要
近期人形机器人领域的进展通过强化学习、运动模仿和生成建模产生了多种技能。然而，这些能力因基于不兼容的表示、接口和控制器而彼此孤立。我们提出CHOREO，一个用于异构人形技能免训练组合的框架。我们的关键观察是，无论技能如何学习，它最终都可以表示为可执行的运动轨迹。基于此观察，CHOREO将每种能力转换为SkillMotion，一种结合运动状态、接触、语义和边界条件的统一表示。技能通过直接延续、三次Hermite混合或经过验证的桥接运动进行组合，无需重新训练源模型或在测试时更新模型。在MuJoCo中的Unitree G1上，CHOREO整理了来自异构来源的2,950个被接纳的SkillMotion资产，并在130个多动作任务中实现了95.4%的序列成功率，包括在八动作序列上93.8%的成功率。这些结果表明，可执行轨迹为积累和组合预训练人形能力提供了可扩展的接口。
英文摘要
Recent advances in humanoid robotics have produced diverse skills through reinforcement learning, motion imitation, and generative modeling. Yet these capabilities remain siloed because they are built around incompatible representations, interfaces, and controllers. We present CHOREO, a framework for training-free composition of heterogeneous humanoid skills. Our key observation is that, regardless of how a skill is learned, it can ultimately be expressed as an executable motion trajectory. Based on this observation, CHOREO converts each capability into SkillMotion, a unified representation that combines motion states, contacts, semantics, and boundary conditions. Skills are composed through direct continuation, cubic Hermite blending, or validated bridge motions, without retraining source models or updating models at test time. On Unitree G1 in MuJoCo, CHOREO organizes 2,950 admitted SkillMotion assets derived from heterogeneous sources and achieves 95.4\% sequence success across 130 multi-action tasks, including 93.8\% success on eight-action sequences. These results demonstrate that executable trajectories provide a scalable interface for accumulating and composing pretrained humanoid capabilities.
