通过显式匹配物体对应关系，实现少样本下跨对象的稳定机器人策略泛化。
MatchingPolicy: Correspondence-Aware Policy Enables Cross-Object In-Context Learning
- 用视觉基础模型+两阶段匹配算法动态建立物体间语义对应关系
- 在RLBench和真实任务中实现少样本下对未见物体的可靠泛化
- 适合需要快速适应新物体的机器人操作场景
上下文模仿学习虽能实现少样本策略泛化，但在未见物体和新场景中性能下降。为此，我们提出MatchingPolicy，一种以对应关系驱动的框架，显式分离演示到场景的匹配与策略学习。核心是基于扩散模型的对应关系感知策略，直接以密集语义对应关系为条件生成机器人动作。该架构分离有效缓解了对应关系识别与动作适应之间的内在冲突，实现鲁棒的分布外迁移。框架融合视觉基础模型与新型两阶段匹配算法，动态建立可靠对应关系。在RLBench及真实世界操作任务上的大量实验表明，MatchingPolicy在少样本条件下表现优异，能可靠地跨未见物体实例和语义类别泛化。
原文摘要 · Abstract (English)
In-context imitation learning enables few-shot policy generalization but struggles to maintain performance on unseen objects and novel scenarios. To address this, we introduce MatchingPolicy, a correspondence-driven framework that explicitly decouples demonstration-to-scene matching from policy learning. Central to our method is a correspondence-aware diffusion policy that conditions robotic actions directly on dense semantic correspondences. This architectural separation resolves the inherent conflict between correspondence identification and action adaptation, enabling robust out-of-distribution transfer. Our framework integrates vision foundation models with a novel two-stage matching algorithm to dynamically establish reliable correspondences. Extensive evaluations on RLBench and real-world manipulation tasks confirm that MatchingPolicy achieves superior few-shot performance, generalizing reliably across unseen object instances and semantic categories.
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。