MORE: Mobile Manipulation Rearrangement Through Grounded Language Reasoning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mohammadi, Mohammad, Honerkamp, Daniel, Büchner, Martin, Cassinelli, Matteo, Welschehold, Tim, Despinoy, Fabien, Gilitschenski, Igor, Valada, Abhinav
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916721864998912
author Mohammadi, Mohammad
Honerkamp, Daniel
Büchner, Martin
Cassinelli, Matteo
Welschehold, Tim
Despinoy, Fabien
Gilitschenski, Igor
Valada, Abhinav
author_facet Mohammadi, Mohammad
Honerkamp, Daniel
Büchner, Martin
Cassinelli, Matteo
Welschehold, Tim
Despinoy, Fabien
Gilitschenski, Igor
Valada, Abhinav
contents Autonomous long-horizon mobile manipulation encompasses a multitude of challenges, including scene dynamics, unexplored areas, and error recovery. Recent works have leveraged foundation models for scene-level robotic reasoning and planning. However, the performance of these methods degrades when dealing with a large number of objects and large-scale environments. To address these limitations, we propose MORE, a novel approach for enhancing the capabilities of language models to solve zero-shot mobile manipulation planning for rearrangement tasks. MORE leverages scene graphs to represent environments, incorporates instance differentiation, and introduces an active filtering scheme that extracts task-relevant subgraphs of object and region instances. These steps yield a bounded planning problem, effectively mitigating hallucinations and improving reliability. Additionally, we introduce several enhancements that enable planning across both indoor and outdoor environments. We evaluate MORE on 81 diverse rearrangement tasks from the BEHAVIOR-1K benchmark, where it becomes the first approach to successfully solve a significant share of the benchmark, outperforming recent foundation model-based approaches. Furthermore, we demonstrate the capabilities of our approach in several complex real-world tasks, mimicking everyday activities. We make the code publicly available at https://more-model.cs.uni-freiburg.de.
format Preprint
id arxiv_https___arxiv_org_abs_2505_03035
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MORE: Mobile Manipulation Rearrangement Through Grounded Language Reasoning
Mohammadi, Mohammad
Honerkamp, Daniel
Büchner, Martin
Cassinelli, Matteo
Welschehold, Tim
Despinoy, Fabien
Gilitschenski, Igor
Valada, Abhinav
Robotics
Artificial Intelligence
Autonomous long-horizon mobile manipulation encompasses a multitude of challenges, including scene dynamics, unexplored areas, and error recovery. Recent works have leveraged foundation models for scene-level robotic reasoning and planning. However, the performance of these methods degrades when dealing with a large number of objects and large-scale environments. To address these limitations, we propose MORE, a novel approach for enhancing the capabilities of language models to solve zero-shot mobile manipulation planning for rearrangement tasks. MORE leverages scene graphs to represent environments, incorporates instance differentiation, and introduces an active filtering scheme that extracts task-relevant subgraphs of object and region instances. These steps yield a bounded planning problem, effectively mitigating hallucinations and improving reliability. Additionally, we introduce several enhancements that enable planning across both indoor and outdoor environments. We evaluate MORE on 81 diverse rearrangement tasks from the BEHAVIOR-1K benchmark, where it becomes the first approach to successfully solve a significant share of the benchmark, outperforming recent foundation model-based approaches. Furthermore, we demonstrate the capabilities of our approach in several complex real-world tasks, mimicking everyday activities. We make the code publicly available at https://more-model.cs.uni-freiburg.de.
title MORE: Mobile Manipulation Rearrangement Through Grounded Language Reasoning
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2505.03035