从单次示范到通用的接触密集操纵策略
From a Single Demonstration to a General Policy for Contact-Rich Manipulation
AI总结：
本文提出了一种学习从示范（LfD）框架，通过利用环境约束作为归纳偏差，实现多阶段、接触密集任务的一次性泛化。该方法将示范表示为利用环境约束的行为序列，将任务通用结构（约束类型及其转换）与实例特定细节（精确示范轨迹、姿态和局部几何）分离。四阶段流程在该表示上构建完整策略：机器人首先将单次示范抽象为环境约束原语，然后通过自我引导探索进行歧义消除，接着整合针对人类修正以处理超出分布的变化，最后通过合规交互在线恢复抽象掉的细节。由于最终策略遵循约束而非模仿轨迹，它在物体姿态、局部几何和未建模接触动力学上实现了泛化。我们在七个现实世界多阶段接触密集操纵任务上验证了该方法，成功率达到90%以上。这些广泛实验结果确立了环境约束作为学习从示范中高效泛化基本构建块的重要性。
摘要：
我们提出了一种学习从示范（LfD）框架，实现多阶段、接触密集任务的一次性泛化。我们的方法核心是利用环境约束作为归纳偏差。通过将示范表示为利用环境约束的行为序列，机器人将任务通用结构——约束类型及其转换——与实例特定细节（如精确示范轨迹、姿态和局部几何）分离。我们的四阶段流程在该表示上构建完整策略：机器人首先将单次示范抽象为环境约束原语，然后通过自我引导探索进行歧义消除，接着整合针对人类修正以处理超出分布的变化，最后通过合规交互在线恢复抽象掉的细节。由于最终策略遵循约束而非模仿轨迹，它在物体姿态、局部几何和未建模接触动力学上实现了泛化。我们在七个现实世界多阶段接触密集操纵任务上验证了该方法，成功率达到90%以上。这些广泛实验结果确立了环境约束作为学习从示范中高效泛化基本构建块的重要性。
英文摘要：
We present a Learning from Demonstration (LfD) framework that achieves one-shot generalization in multi-stage, contact-rich manipulation tasks. Central to our approach is the utilization of environmental constraints as the inductive bias. By representing a demonstration as a sequence of behaviors that exploit environmental constraints, the robot separates task-general structure -- the constraint types and their transitions -- from instance-specific details such as exact demonstration trajectories, poses, and local geometries. Our four-stage pipeline builds a complete policy on this representation: the robot first abstracts a single demonstration into environmental-constraint primitives, then disambiguates them through self-guided exploration, next assimilates targeted human corrections that handle out-of-distribution variations, and finally recovers the abstracted-away details online through compliant interaction. Because the resulting policy follows constraints rather than mimics trajectories, it generalizes across object poses, local geometries, and unmodeled contact dynamics. We validate our approach on seven real-world multi-stage contact-rich manipulation tasks and achieve over 90% success. These extensive experimental results establish environmental constraints as fundamental building blocks for efficient generalization in learning from demonstration.
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。
