Presentations at IE2024
Three research presentations and Best Short Paper Award at IE2024
Publications & Talks Awards
International Conference · 2024
Generating Human Daily Activities with LLM for Smart Home Simulator Agents
Abstract
This paper presents a novel approach to smart home simulation by integrating Large Language Models (LLMs) for generating human daily schedules and activities of smart home simulator agents. The use of LLMs aims to reduce the complexity of user settings and increase the variety and generality of generated activities. This study explores the potential of LLMs to simulate human-like activity-generating by exploiting their experiential knowledge and adaptability. In addition, this paper discusses fine-tuning techniques for LLMs to optimize their performance within a simulator. By utilizing LoRA and task-specific fine-tuning datasets, while maintaining the ability to generate proper activities, we achieve as much as 4.3% performance improvement about the number of queries. Overall, the integration of LLMs into smart home simulators offers promising opportunities for enhancing the intelligence and adaptability of virtual agents in smart home environments.
Research Note
This research proposes a method for simulating residents' decision-making and daily activities in a smart home environment using a Large Language Model (LLM). In recent years, Digital Twins and Agent-Based Modeling (ABM) have gained attention for real-world applications. However, existing agents often have simplified behavioral patterns, making it difficult to fully replicate the diversity of human behavior. By leveraging LLMs, this study aims to develop a more human-centric and flexible approach to modeling decision-making processes.
Published Paper
- 米倉晴紀, 田中福治, 水本旭洋, 山口弘純. (2023). スマートホームシミュレータにおける大規模言語モデルを用いた生活行動の自動生成に関する検討. 研究報告モバイルコンピューティングと新社会システム (MBL), 2023(28), 1-8. https://ipsj.ixsq.nii.ac.jp/records/228980
- H. Yonekura, F. Tanaka, T. Mizumoto and H. Yamaguchi, "Generating Human Daily Activities with LLM for Smart Home Simulator Agents," 2024 International Conference on Intelligent Environments (IE), Ljubljana, Slovenia, 2024, pp. 93-96, https://ieeexplore.ieee.org/document/10599909
Related Lab Activities
Related Projects
A Platform for Digitalizing Knowledge of Regional Communities
Japan Science and Technology Agency (JST) CREST
「基礎理論とシステム基盤技術の融合によるSociety 5.0のための基盤ソフトウェアの創出」領域
