利用谓词层级结构提升少样本状态分类性能
Predicate Hierarchies Improve Few-Shot State Classification
- 通过谓词层级与超球距离建模关系结构
- 在少样本下比现有方法准确率显著更高
- 适合需要快速适应新环境的机器人任务
物体及其关系的状态分类是机器人长期任务中的核心问题，尤其在规划与操作中。然而，物体-谓词组合的组合爆炸以及对新现实环境的适应需求，使得模型需在极少样本下实现泛化。为此，我们提出PHIER，利用谓词层级结构，在少样本场景中实现有效泛化。PHIER采用以物体为中心的场景编码器、自监督损失函数来推断谓词间的语义关系，并使用双曲距离度量捕捉层次结构；其学习到的图像-谓词对结构化潜在空间可指导状态分类推理。我们在CALVIN和BEHAVIOR机器人环境中评估，结果表明：在少样本、分布外状态下，PHIER显著优于现有方法，并在从模拟到真实任务间展现出强大的零样本与少样本泛化能力。结果证明，利用谓词层级能有效提升有限数据下的状态分类性能。
原文摘要 · Abstract (English)
State classification of objects and their relations is core to many long-horizon tasks, particularly in robot planning and manipulation. However, the combinatorial explosion of possible object-predicate combinations, coupled with the need to adapt to novel real-world environments, makes it a desideratum for state classification models to generalize to novel queries with few examples. To this end, we propose PHIER, which leverages predicate hierarchies to generalize effectively in few-shot scenarios. PHIER uses an object-centric scene encoder, self-supervised losses that infer semantic relations between predicates, and a hyperbolic distance metric that captures hierarchical structure; it learns a structured latent space of image-predicate pairs that guides reasoning over state classification queries. We evaluate PHIER in the CALVIN and BEHAVIOR robotic environments and show that PHIER significantly outperforms existing methods in few-shot, out-of-distribution state classification, and demonstrates strong zero- and few-shot generalization from simulated to real-world tasks. Our results demonstrate that leveraging predicate hierarchies improves performance on state classification tasks with limited data.
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。