Eye On A.I. cover image

#173 Vincent Vanhoucke: How Is AI Helping Advance Robotics?

Eye On A.I.

00:00

RT2 is a Multimodal Model Trained on Language and Image Data

RT2 operates as a multimodal model capable of processing both language and image inputs. It has been specifically trained on robotics data, which consists of paired images and robotic actions, allowing it to interpret and generate outputs in both natural language and robotic commands. This approach essentially enables the model to 'speak' in the language of robotics, thereby expanding its communicative abilities beyond traditional language processing.

Play episode from 06:47
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app