Embodied AI in Mobile Robot Simulation with EyeSim: Coverage Path Planning with Large Language Models

Xiangrui Kong, Wenxiao Zhang, Jin Hong, Thomas Bräunl

2025

Abstract

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities in understanding and solving mathematical problems, leading to advancements in various fields. We propose an LLM-embodied path planning framework for mobile agents, focusing on solving high-level coverage path planning issues and low-level control. Our proposed multi-layer architecture uses prompted LLMs in the path planning phase and integrates them with the mobile agents’ low-level actuators. To evaluate the performance of various LLMs, we propose a coverage-weighted path planning metric to assess the performance of the embodied models. Our experiments show that the proposed framework improves LLMs’ spatial inference abilities. We demonstrate that the proposed multi-layer framework significantly enhances the efficiency and accuracy of these tasks by leveraging the natural language understanding and generative capabilities of LLMs. Experiments conducted in our EyeSim simulation demonstrate that this framework enhances LLMs’ 2D plane reasoning abilities and enables the completion of coverage path planning tasks. We also tested three LLM kernels: gpt-4o, gemini-1.5-flash, and claude-3.5-sonnet. The experimental results show that claude-3.5 can complete the coverage planning task in different scenarios, and its indicators are better than those of the other models. We have made our experimental simulation platform, EyeSim, freely available at https://roblab.org/eyesim/.

Paper Citation

in Harvard Style

Kong X., Zhang W., Hong J. and Bräunl T. (2025). Embodied AI in Mobile Robot Simulation with EyeSim: Coverage Path Planning with Large Language Models. In Proceedings of the 15th International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: SIMULTECH; ISBN 978-989-758-759-7, SciTePress, pages 185-192. DOI: 10.5220/0013455100003970

in Bibtex Style

@conference{simultech25,
author={Xiangrui Kong and Wenxiao Zhang and Jin Hong and Thomas Bräunl},
title={Embodied AI in Mobile Robot Simulation with EyeSim: Coverage Path Planning with Large Language Models},
booktitle={Proceedings of the 15th International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: SIMULTECH},
year={2025},
pages={185-192},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013455100003970},
isbn={978-989-758-759-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: SIMULTECH
TI - Embodied AI in Mobile Robot Simulation with EyeSim: Coverage Path Planning with Large Language Models
SN - 978-989-758-759-7
AU - Kong X.
AU - Zhang W.
AU - Hong J.
AU - Bräunl T.
PY - 2025
SP - 185
EP - 192
DO - 10.5220/0013455100003970
PB - SciTePress