A Survey of Robotic Language Grounding: Tradeoffs between Symbols and Embeddings

IJCAI 2024

Vanya Cohen1, Jason Xinyu Liu2, Raymond Mooney1, Stefanie Tellex2,3, David Watkins3
1 UT Austin, 2 Brown University, 3 RAI Institute
arXiv IJCAI Slides Poster

We reviewed and situated recent robotic language grounding papers into a spectrum with two poles, discussed the benefits and tradeoffs of each approach, and provided directions for future work.

Abstract

With large language models, robots can understand language more flexibly and more capable than ever before. This survey reviews and situates recent literature into a spectrum with two poles: 1) mapping between language and some manually defined formal representation of meaning, and 2) mapping between language and high-dimensional vector spaces that translate directly to low-level robot policy.

Using a formal representation allows the meaning of the language to be precisely represented, limits the size of the learning problem, and leads to a framework for interpretability and formal safety guarantees. Methods that embed language and perceptual data into high-dimensional spaces avoid this manually specified symbolic structure and thus have the potential to be more general when fed enough data but require more data and computing to train.

We discuss the benefits and tradeoffs of each approach and finish by providing directions for future work that achieves the best of both worlds.

Spectrum

BibTeX

@inproceedings{cohen2024roblanggroundsurvey,
  title     = {A Survey of Robotic Language Grounding: Tradeoffs between Symbols and Embeddings},
  author    = {Cohen, Vanya and Liu, Jason Xinyu and Mooney, Raymond and Tellex, Stefanie and Watkins, David},
  booktitle = {International Joint Conference on Artificial Intelligence (IJCAI)},
  year      = {2024}
}