Tag: google
-
Robotic Transformer 2 (RT-2): Advancing Vision-Language-Action Models in Robotics
Introduction Robotic Transformer 2 (RT-2) is a groundbreaking vision-language-action (VLA) model that represents a significant advancement in the field of robotics. By learning from both web and robotics data, RT-2 translates this knowledge into generalised instructions for controlling robots, while retaining the web-scale capabilities of high-capacity vision-language models (VLMs). This article explores the development and…