RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control ​

← Back to topic

Authors: Anthony Brohan, Noah Brown, Justice Carbajal, Yevgen Chebotar, Joseph Dabis, et al.
Year: 2022
Journal: CoRL
DOI: 10.48550/arXiv.2307.15818
Publisher: https://arxiv.org/abs/2307.15818

Keywords: rt-2, vla

Abstract ​

We present RT-2 a vision-language-action model that transfers web knowledge to robotic control.

Cite this paper ​

@misc{rt22022,
  title  = {RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control},
  author = {Anthony Brohan, Noah Brown, Justice Carbajal, Yevgen Chebotar, Joseph Dabis, et al.},
  year   = {2022},
  journal = {CoRL},
  doi    = {10.48550/arXiv.2307.15818},
  url    = {https://doi.org/10.48550/arXiv.2307.15818},
}

Source files ​

• metadata.json
• paper.bib