FOCI策略：聚焦于关系操作策略的以对象为中心的交互
FOCI Policy: Focus on Object-Centric Interactions for Relational Manipulation Policies
- KU Leuven（鲁汶大学）
- Flanders Make（佛兰德斯制造研究院）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
FOCI策略通过提取紧凑交互片段并建模对象间相对SE(3)运动，以少量数据实现高效的关系操作泛化。
中文摘要 AI 辅助
以对象为中心的操作策略通过建模对象运动而非直接预测机器人动作来提高泛化能力。然而，现有方法常常受限于表示方式，这些表示要么过于简单而无法捕捉交互动态，要么过于密集而难以高效学习。我们观察到，许多刚性关系操作任务由短暂的交互阶段主导，在这些阶段中，任务相关对象之间的相对运动受到严格约束。基于这一观察，我们提出了FOCI策略，一个以交互为中心的框架，实现了双重抽象：（1）在时间上，通过自动从示范中提取紧凑的交互片段；（2）在空间上，通过将技能表示为任务相关对象之间的相对SE(3)运动，从而对场景配置和机器人本体具有不变性。在RLBench、COLOSSEUM和真实世界任务上的实验表明，FOCI策略在显著少于先前以对象为中心和以动作为中心的策略的训练数据下实现了强劲性能。这些结果表明，建模对象-对象交互为刚性关系操作提供了一个简单而高效的归纳偏置。项目页面：此https URL。
英文摘要
Object-centric manipulation policies improve generalization by modeling object motion instead of directly predicting robot actions. However, existing methods are often limited by representations which are either too simplistic to capture interaction dynamics or too dense to learn efficiently. We observe that many rigid relational manipulation tasks are governed by short interaction phases where the relative motion between task-relevant objects is tightly constrained. Based on this observation, we propose \textsc{Foci Policy}, an interaction-centric framework that achieves a two-fold abstraction: (1) temporally, by automatically extracting compact interaction segments from demonstrations;(2) spatially, by representing skills as relative $SE(3)$ motion between task-relevant objects, yielding invariance to scene configurations and robot embodiment. Experiments on RLBench, COLOSSEUM, and real-world tasks show that \textsc{Foci Policy} achieves strong performance with substantially less training data than prior object-centric and action-centric policies. These results suggest that modeling object-object interactions provides a simple and efficient inductive bias for rigid relational manipulation. Project page: \href{https://fitz0401.github.io/foci-page/}{fitz0401.github.io/foci-page/}.
