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
