Learning Discrete Abstractions for Visual Rearrangement Tasks Using Vision-Guided Graph Coloring

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ajith, Abhiroop, Chamzas, Constantinos
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910060973654016
author Ajith, Abhiroop
Chamzas, Constantinos
author_facet Ajith, Abhiroop
Chamzas, Constantinos
contents Learning abstractions directly from data is a core challenge in robotics. Humans naturally operate at an abstract level, reasoning over high-level subgoals while delegating execution to low-level motor skills -- an ability that enables efficient problem solving in complex environments. In robotics, abstractions and hierarchical reasoning have long been central to planning, yet they are typically hand-engineered, demanding significant human effort and limiting scalability. Automating the discovery of useful abstractions directly from visual data would make planning frameworks more scalable and more applicable to real-world robotic domains. In this work, we focus on rearrangement tasks where the state is represented with raw images, and propose a method to induce discrete, graph-structured abstractions by combining structural constraints with an attention-guided visual distance. Our approach leverages the inherent bipartite structure of rearrangement problems, integrating structural constraints and visual embeddings into a unified framework. This enables the autonomous discovery of abstractions from vision alone, which can subsequently support high-level planning. We evaluate our method on two rearrangement tasks in simulation and show that it consistently identifies meaningful abstractions that facilitate effective planning and outperform existing approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2509_14460
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Discrete Abstractions for Visual Rearrangement Tasks Using Vision-Guided Graph Coloring
Ajith, Abhiroop
Chamzas, Constantinos
Robotics
Learning abstractions directly from data is a core challenge in robotics. Humans naturally operate at an abstract level, reasoning over high-level subgoals while delegating execution to low-level motor skills -- an ability that enables efficient problem solving in complex environments. In robotics, abstractions and hierarchical reasoning have long been central to planning, yet they are typically hand-engineered, demanding significant human effort and limiting scalability. Automating the discovery of useful abstractions directly from visual data would make planning frameworks more scalable and more applicable to real-world robotic domains. In this work, we focus on rearrangement tasks where the state is represented with raw images, and propose a method to induce discrete, graph-structured abstractions by combining structural constraints with an attention-guided visual distance. Our approach leverages the inherent bipartite structure of rearrangement problems, integrating structural constraints and visual embeddings into a unified framework. This enables the autonomous discovery of abstractions from vision alone, which can subsequently support high-level planning. We evaluate our method on two rearrangement tasks in simulation and show that it consistently identifies meaningful abstractions that facilitate effective planning and outperform existing approaches.
title Learning Discrete Abstractions for Visual Rearrangement Tasks Using Vision-Guided Graph Coloring
topic Robotics
url https://arxiv.org/abs/2509.14460