Reimagining service delivery in the agentic era with Google Public Sector
cloud.google.com·19h ago
AI Research
arXiv CS.AI·Jun 9·5 min read
From USD Scenes to Knowledge Graphs: Zero-Shot Ontology Grounding with LLMs
TL;DR
Grounding objects in 3D simulation scenes to formal ontology classes is challenging due to reliance on brittle, manually curated dictionaries. This research explores using large language models (LLMs) to automate this grounding process for Universal Scene Description (USD) scenes without prior training.
✦ Why It Matters
Engineers can leverage LLMs for efficient ontology grounding in robotic applications, reducing manual effort and improving scalability.
Key Takeaways
- Explore LLMs for automating object grounding in 3D scenes.
- Utilize context-augmented prompting to improve accuracy.
- Focus on semantic cues in scene graphs for better results.
- Evaluate the effectiveness of LLMs against traditional methods.
How It Works
LLMs automate the grounding process by interpreting semantic cues from the scene graph, such as relationships between objects. This allows them to match scene objects to ontology classes without needing prior training, achieving high accuracy even with limited information.