仅用一次演示，实现零样本物体操作迁移
GRAFT: Graph-Based Affordance Transfer via Part Correspondence
- 基于部件图表示物体，兼顾语义与几何相似性
- 通过部件对应关系，精准传递接触点位置
- 适合少样本或无新数据的机器人操作场景
将机器人操作泛化至未见过的物体仍具挑战，因学习方法需大量示范且在少样本场景下表现不佳。以往工作依赖语义检索传递功能，但忽视几何相似性——这对操作至关重要。本文提出GRAFT，一种基于几何对齐的零样本操作迁移框架，仅需每类物体一个示范。物体以部件级图结构表示：部件级描述符支持全局实例检索与功能部件对齐，顶点级描述符实现细粒度接触点匹配。对于未知物体，先从示范库中检索功能与几何最相似的实例，并对齐功能部件；最后通过点级对应关系传播接触点。
原文摘要 · Abstract (English)
Generalizing robotic manipulation to unseen objects remains challenging, as learning-based approaches require many demonstrations and fail in few-shot settings. Prior work transfers affordances through semantic retrieval, but semantics alone neglect geometric similarity, which is critical for manipulation. We propose GRAFT, a geometry-aware correspondence framework for zero-shot manipulation transfer using only one demonstration per object. Objects are represented as part-based graphs, where part-level descriptors support global instance retrieval and part correspondence, and vertex-level descriptors enable fine-grained contact point matching. For an unseen object, our method first retrieves the most functionally and geometrically similar instance from the demonstration buffer with aligned functional parts, and finally propagates the contact points through point-wise correspondence.
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。