English

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

Robotics 2023-11-09 v2 Computation and Language Computer Vision and Pattern Recognition Machine Learning

Abstract

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%\sim 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.

Keywords

Cite

@article{arxiv.2209.05629,
  title  = {Leveraging Large (Visual) Language Models for Robot 3D Scene Understanding},
  author = {William Chen and Siyi Hu and Rajat Talak and Luca Carlone},
  journal= {arXiv preprint arXiv:2209.05629},
  year   = {2023}
}

Comments

arXiv admin note: text overlap with arXiv:2206.04585

R2 v1 2026-06-28T01:10:18.251Z