Household Task Planning with Multi-Objects State and Relationship Using Large Language Models Based Preconditions Verification

Jin Aoyama, Jin Aoyama, Sudesna Chakraborty, Takeshi Morita, Takeshi Morita, Shusaku Egami, Takanori Ugai, Takanori Ugai, Ken Fukuda

2025

Abstract

We propose a novel approach to household task planning that leverages Large Language Models (LLMs) to comprehend and consider environmental states. Unlike previous methods that depend primarily on commonsense reasoning or visual inputs, our approach focuses on understanding object states and relationships within the environment. To evaluate the capability, we developed a specialized dataset of household tasks that specifically tests LLMs’ ability to reason about object states, identifiers, and relationships. Our method combines simulator-derived environmental state information with an LLM-based planning to generate executable action sequences. A key feature in our system is the LLM-driven verification mechanism that assesses whether environmental preconditions are met before each action executes, automatically reformulating action steps when prerequisites are not satisfied. Experimental results using GPT-4o demonstrate strong performance, achieving 89.4% success rate on state change tasks and 81.6% on placement tasks. Ablation studies confirm the precondition check’s significant contribution to task success. This study establishes both a new methodology for embodied AI reasoning and a benchmark for future work in environment-aware task planning.

Paper Citation

in Harvard Style

Aoyama J., Chakraborty S., Morita T., Egami S., Ugai T. and Fukuda K. (2025). Household Task Planning with Multi-Objects State and Relationship Using Large Language Models Based Preconditions Verification. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 472-483. DOI: 10.5220/0013188400003890

in Bibtex Style

@conference{icaart25,
author={Jin Aoyama and Sudesna Chakraborty and Takeshi Morita and Shusaku Egami and Takanori Ugai and Ken Fukuda},
title={Household Task Planning with Multi-Objects State and Relationship Using Large Language Models Based Preconditions Verification},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2025},
pages={472-483},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013188400003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - Household Task Planning with Multi-Objects State and Relationship Using Large Language Models Based Preconditions Verification
SN - 978-989-758-737-5
AU - Aoyama J.
AU - Chakraborty S.
AU - Morita T.
AU - Egami S.
AU - Ugai T.
AU - Fukuda K.
PY - 2025
SP - 472
EP - 483
DO - 10.5220/0013188400003890
PB - SciTePress