RT-2: New models translate vision and language into action

the study Published July 28, 2023 Evgen Chebotar, Tianhe Yu Robotic Transformer 2 (RT-2) is a new Vision Language Action (VLA) model that learns from both web and robot data and converts this knowledge into generalized instructions for robot control. Because large-capacity visual language models (VLMs) are trained on web-scale datasets, these systems are very [...]

The post RT-2: New models translate vision and language into action first appeared on Versa AI hub.

from Blog - Versa AI hub https://versaaihub.com/rt-2-new-models-translate-vision-and-language-into-action/?utm_source=rss&utm_medium=rss&utm_campaign=rt-2-new-models-translate-vision-and-language-into-action
via IFTTT