Language-Grounded Dynamic Scene Graphs for Interactive Object Search with Mobile Manipulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Honerkamp, Daniel, Büchner, Martin, Despinoy, Fabien, Welschehold, Tim, Valada, Abhinav
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916366883225600
author Honerkamp, Daniel
Büchner, Martin
Despinoy, Fabien
Welschehold, Tim
Valada, Abhinav
author_facet Honerkamp, Daniel
Büchner, Martin
Despinoy, Fabien
Welschehold, Tim
Valada, Abhinav
contents To fully leverage the capabilities of mobile manipulation robots, it is imperative that they are able to autonomously execute long-horizon tasks in large unexplored environments. While large language models (LLMs) have shown emergent reasoning skills on arbitrary tasks, existing work primarily concentrates on explored environments, typically focusing on either navigation or manipulation tasks in isolation. In this work, we propose MoMa-LLM, a novel approach that grounds language models within structured representations derived from open-vocabulary scene graphs, dynamically updated as the environment is explored. We tightly interleave these representations with an object-centric action space. Given object detections, the resulting approach is zero-shot, open-vocabulary, and readily extendable to a spectrum of mobile manipulation and household robotic tasks. We demonstrate the effectiveness of MoMa-LLM in a novel semantic interactive search task in large realistic indoor environments. In extensive experiments in both simulation and the real world, we show substantially improved search efficiency compared to conventional baselines and state-of-the-art approaches, as well as its applicability to more abstract tasks. We make the code publicly available at http://moma-llm.cs.uni-freiburg.de.
format Preprint
id arxiv_https___arxiv_org_abs_2403_08605
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Language-Grounded Dynamic Scene Graphs for Interactive Object Search with Mobile Manipulation
Honerkamp, Daniel
Büchner, Martin
Despinoy, Fabien
Welschehold, Tim
Valada, Abhinav
Robotics
To fully leverage the capabilities of mobile manipulation robots, it is imperative that they are able to autonomously execute long-horizon tasks in large unexplored environments. While large language models (LLMs) have shown emergent reasoning skills on arbitrary tasks, existing work primarily concentrates on explored environments, typically focusing on either navigation or manipulation tasks in isolation. In this work, we propose MoMa-LLM, a novel approach that grounds language models within structured representations derived from open-vocabulary scene graphs, dynamically updated as the environment is explored. We tightly interleave these representations with an object-centric action space. Given object detections, the resulting approach is zero-shot, open-vocabulary, and readily extendable to a spectrum of mobile manipulation and household robotic tasks. We demonstrate the effectiveness of MoMa-LLM in a novel semantic interactive search task in large realistic indoor environments. In extensive experiments in both simulation and the real world, we show substantially improved search efficiency compared to conventional baselines and state-of-the-art approaches, as well as its applicability to more abstract tasks. We make the code publicly available at http://moma-llm.cs.uni-freiburg.de.
title Language-Grounded Dynamic Scene Graphs for Interactive Object Search with Mobile Manipulation
topic Robotics
url https://arxiv.org/abs/2403.08605