From USD Scenes to Knowledge Graphs: Zero-Shot Ontology Grounding with LLMs 事件

From USD Scenes to Knowledge Graphs: Zero-Shot Ontology Grounding with LLMs arXiv:2606.09134v1 Announce Type: cross Abstract: 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 Sce