USDシーンから知識グラフへ：LLMによるゼロショットオントロジー接地
From USD Scenes to Knowledge Graphs: Zero-Shot Ontology Grounding with LLMs
3Dシミュレーションシーンから知識グラフを構築する際の物体とオントロジークラスの対応付けを、大規模言語モデルを用いてゼロショットで自動化する手法を提案・評価した論文。
著者: Jiangtao Shuai, Zongxiong Chen, Manfred Hauswirth, Sonja Schimmler
分類: cs.RO, cs.AI, cs.CL, cs.CV, cs.GR
原文アブストラクト
Constructing knowledge graphs from 3D simulation scenes is essential for robot task reasoning, but the key bottleneck, grounding scene objects to formal ontology classes, still relies on manually curated dictionaries that are brittle and do not generalize across assets. We investigate whether large language models (LLMs) can automate this grounding step for Universal Scene Description (USD) scenes as a zero-shot, training-free alternative. On a kitchen scene (125 objects) with SOMA-HOME Ontology, LLMs achieve 90-96% exact-match accuracy with descriptive names and 49-89% with abbreviated names, substantially outperforming dictionary and embedding baselines. Under fully opaque names, context-augmented prompting recovers up to 48%. Feature ablation reveals that LLMs primarily exploit semantic cues in the scene graph (sibling names and parent paths); anonymizing these cues reduces accuracy to 0-6%, while geometry alone yields only 4-17%.