用图结构整合动作示范，让机器人零样本泛化到新任务
Zero-Shot Generalization from Motion Demonstrations to New Tasks
- 将动作基元转为图节点，通过图搜索实现跨任务动作组合
- 在仿真和真实机器人上成功泛化到未见过的任务，基线方法失败
- 适合需要快速适应新动作的机器人控制场景
从专家示范学习运动策略是现代机器人学的核心范式。尽管端到端模型追求广泛泛化，但需大量数据且推理成本高；而动态系统（DS）学习可实现快速、响应灵敏且可证明稳定的控制，仅需极少示范。然而，现有方法通常针对单一任务建模，难以复用示范以生成新行为。本文提出在共享工作空间中融合孤立示范，实现对未见任务的零样本泛化。引入高斯图（Gaussian Graph），将学习到的动作基元的空间成分重新解释为离散顶点及其连接关系，从而打通连续控制与离散图搜索的桥梁。基于该图，提出两种框架：Stitching用于构建时间不变的动态系统，Chaining则提供序列化动态系统以实现复杂运动，同时保持收敛性保证。仿真与真实机器人实验表明，该方法在基线方法失败的新任务上仍能成功泛化。
原文摘要 · Abstract (English)
Learning motion policies from expert demonstrations is an essential paradigm in modern robotics. While end-to-end models aim for broad generalization, they require large datasets and computationally heavy inference. Conversely, learning dynamical systems (DS) provides fast, reactive, and provably stable control from very few demonstrations. However, existing DS learning methods typically model isolated tasks and struggle to reuse demonstrations for novel behaviors. In this work, we formalize the problem of combining isolated demonstrations within a shared workspace to enable generalization to unseen tasks. The Gaussian Graph is introduced, which reinterprets spatial components of learned motion primitives as discrete vertices with connections to one another. This formulation allows us to bridge continuous control with discrete graph search. We propose two frameworks leveraging this graph: Stitching, for constructing time-invariant DSs, and Chaining, giving a sequence-based DS for complex motions while retaining convergence guarantees. Simulations and real-robot experiments show that these methods successfully generalize to new tasks where baseline methods fail.
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。