Papers › Leveraging Large (Visual) Language Models for Robot 3D Scene Understanding

Leveraging Large (Visual) Language Models for Robot 3D Scene Understanding

12 Sep 2022arXiv:2209.05629archive 2025-07-28

William Chen, Siyi Hu, Rajat Talak, Luca Carlone

Abstract semantic 3D scene understanding is a problem of critical importance in robotics. As robots still lack the common-sense knowledge about household objects and locations of an average human, we investigate the use of pre-trained language models to impart common sense for scene understanding. We introduce and compare a wide range of scene classification paradigms that leverage language only (zero-shot, embedding-based, and structured-language) or vision and language (zero-shot and fine-tuned). We find that the best approaches in both categories yield ∼70% room classification accuracy, exceeding the performance of pure-vision and graph classifiers. We also find such methods demonstrate notable generalization and transfer capabilities stemming from their use of language.

PaperPDFCode

Code

mit-spark/llm_scene_understanding officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Common Sense ReasoningScene ClassificationScene Understanding

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections