基于10次演示学习可泛化的3D操作
Learning Generalizable 3D Manipulation With 10 Demonstrations
AI总结：
提出一种仅需10次演示即可学习3D操作技能的框架，通过SGP和SGD模块及空间等变训练策略，在物体姿态和相机视角变化下成功率提升60%。
摘要：
从演示中学习鲁棒且可泛化的操作技能仍然是机器人学中的一个关键挑战，在工业自动化和服务机器人中具有广泛的应用。虽然最近的模仿学习方法取得了令人瞩目的成果，但它们通常需要大量的演示数据，并且难以在不同的空间变体之间进行泛化。在这项工作中，我们提出了一个新颖的框架，该框架仅从10次演示中学习操作技能，但仍能泛化到不同的空间变体，例如不同的初始物体位置和相机视角。我们的框架由两个关键模块组成：Semantic Guided Perception (SGP)（语义引导感知），它从RGB-D输入中构建以任务为中心、具有空间感知的3D点云表示；以及Spatial Generalized Decision (SGD)（空间泛化决策），这是一个高效的基于扩散的决策模块，通过去噪生成动作。为了有效地从有限数据中学习泛化能力，我们引入了一种关键的空间等变训练策略，该策略捕获嵌入在专家演示中的空间知识。我们通过在模拟基准和真实世界机器人系统上的大量实验验证了我们的框架。我们的方法在一系列具有挑战性的任务上，成功率比最先进的方法提高了60%，即使在物体姿态和相机视角存在显著变化的情况下也是如此。这项工作展示了在现实应用中推进高效、可泛化操作技能学习的巨大潜力。
英文摘要：
Learning robust and generalizable manipulation skills from demonstrations remains a key challenge in robotics, with broad applications in industrial automation and service robotics. While recent imitation learning methods have achieved impressive results, they often require large amounts of demonstration data and struggle to generalize across different spatial variants. In this work, we present a novel framework that learns manipulation skills from as few as 10 demonstrations, yet still generalizes to spatial variants such as different initial object positions and camera viewpoints. Our framework consists of two key modules: Semantic Guided Perception (SGP), which constructs task-focused, spatially aware 3D point cloud representations from RGB-D inputs; and Spatial Generalized Decision (SGD), an efficient diffusion-based decision-making module that generates actions via denoising. To effectively learn generalization ability from limited data, we introduce a critical spatially equivariant training strategy that captures the spatial knowledge embedded in expert demonstrations. We validate our framework through extensive experiments on both simulation benchmarks and real-world robotic systems. Our method demonstrates a 60 percent improvement in success rates over state-of-the-art approaches on a series of challenging tasks, even with substantial variations in object poses and camera viewpoints. This work shows significant potential for advancing efficient, generalizable manipulation skill learning in real-world applications.
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。
