FOCI Policy: Focus on Object-Centric Interactions for Relational Manipulation Policies

2026-09-08

AI Summary

为解决现有方法难以有效学习物体间交互的问题，提出FOCI Policy，通过自动提取紧凑的交互片段和表示任务相关物体间的相对运动，提高了操作策略的学习效率与泛化能力。

Abstract

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/}.

Problem

• object-centric manipulation
• interaction dynamics
• relative motion
• learning efficiency

Innovation

• object-centric manipulation
• interaction-centric framework
• relative SE(3) motion
• compact interaction segments