[2K5-OS-20a] OS-20

[2K5-OS-20a-03] Proposal for LLM-based Knowledge Graph Construction Method for Affordance Acquisition

〇Kazuma Arii¹, Reo Abe¹, Reo Kobayashi¹, Akifumi Ito¹, Kazuki Sasada¹, Satoshi Kurihara¹ (1. Keio University)

Keywords:Affordance, Knowledge Graph, Large Language Model

Large Language Model (LLM), which is evolving rapidly, learns human writing. Since GPT4-class LLMs are constructed with scaled resources, they are expected to contain information on common sense and affordances. For development of autonomous agent behavior, it plays important role to make affordances available mechanically. In this study, we propose a Knowledge Graph Construction Method for Affordance Acquisition based on LLM. This method is divided into three part: method for knowledge extraction from LLM, method for knowledge graph construction, and method for affordance calculation. This enables affordance acquisition under various conditions, such as when multiple objects are observed and in certain situations. Also, in the process, it is determined automatically what object use as tool. The result shows the method enables the appropriate affordance acquiring for the situation.