LLM-enhanced Scene Graph Learning for Household Rearrangement

TL;DR

This paper introduces an LLM-enhanced scene graph learning approach that improves household object rearrangement by identifying misplaced items and planning their proper placement using an affordance-enhanced graph representation.

Contribution

It proposes a novel method to mine object functionality and user preferences directly from scenes using LLM-enhanced scene graphs, enabling better rearrangement planning without human intervention.

Findings

Achieves state-of-the-art performance in misplacement detection.

Effective in task planning for household object rearrangement.

Validated on a new benchmark with extensive evaluations.

Abstract

The household rearrangement task involves spotting misplaced objects in a scene and accommodate them with proper places. It depends both on common-sense knowledge on the objective side and human user preference on the subjective side. In achieving such task, we propose to mine object functionality with user preference alignment directly from the scene itself, without relying on human intervention. To do so, we work with scene graph representation and propose LLM-enhanced scene graph learning which transforms the input scene graph into an affordance-enhanced graph (AEG) with information-enhanced nodes and newly discovered edges (relations). In AEG, the nodes corresponding to the receptacle objects are augmented with context-induced affordance which encodes what kind of carriable objects can be placed on it. New edges are discovered with newly discovered non-local relations. With AEG, we perform task planning for scene rearrangement by detecting misplaced carriables and determining a proper placement for each of them. We test our method by implementing a tiding robot in simulator and perform evaluation on a new benchmark we build. Extensive evaluations demonstrate that our method achieves state-of-the-art performance on misplacement detection and the following rearrangement planning.