Personalized Robotic Object Rearrangement from Scene Context

TL;DR

This paper introduces PARSEC, a large benchmark dataset for personalized robotic object rearrangement, and proposes ContextSortLM, a model that leverages scene context to better align with user preferences in object placement.

Contribution

The paper presents a new benchmark dataset PARSEC and a novel LLM-based model ContextSortLM for personalized object rearrangement in household environments.

Findings

ContextSortLM outperforms existing models in replicating user preferences.

Models leveraging multiple scene context sources perform better than single-source models.

Evaluation reveals challenges in modeling environment semantics across different categories.

Abstract

Object rearrangement is a key task for household robots requiring personalization without explicit instructions, meaningful object placement in environments occupied with objects, and generalization to unseen objects and new environments. To facilitate research addressing these challenges, we introduce PARSEC, an object rearrangement benchmark for learning user organizational preferences from observed scene context to place objects in a partially arranged environment. PARSEC is built upon a novel dataset of 110K rearrangement examples crowdsourced from 72 users, featuring 93 object categories and 15 environments. To better align with real-world organizational habits, we propose ContextSortLM, an LLM-based personalized rearrangement model that handles flexible user preferences by explicitly accounting for objects with multiple valid placement locations when placing items in partially arranged environments. We evaluate ContextSortLM and existing personalized rearrangement approaches on the PARSEC benchmark and complement these findings with a crowdsourced evaluation of 108 online raters ranking model predictions based on alignment with user preferences. Our results indicate that personalized rearrangement models leveraging multiple scene context sources perform better than models relying on a single context source. Moreover, ContextSortLM outperforms other models in placing objects to replicate the target user's arrangement and ranks among the top two in all three environment categories, as rated by online evaluators. Importantly, our evaluation highlights challenges associated with modeling environment semantics across different environment categories and provides recommendations for future work.