2024-03-13
I'm really excited to be starting a new adventure with multiple amazing friends & colleagues. Our company is called Physical Intelligence (Pi or π, like the policy). A short thread 🧵
Bloomberg
Source: Physical Intelligence, a startup making an AI model for “any robot or physical device”, raised $70M from Thrive, Khosla, Lux, OpenAI, Sequoia, and more
Physical Intelligence (Pi, π, @physical_int). We're focused on bringing the amazing recent breakthroughs of AI and foundation models into the physical world. Ashlee Vance / @ashlee...
2023-07-30
Vision-language ➡️ vision-language-action model By using a pre-trained VLM (e.g. PaLI-X), RT-2 enables robots to generalize to new objects & instructions RT-2 also shows basic reasoning capabilities. (e.g. “place orange in matching bowl") Paper+videos: https://robotics-transformer2.github.io / [image]
New York Times
Google launches RT-2 or Robotics Transformer 2, a “vision-language-action” model trained on text and images from the web that can output robotic actions
Our sneak peek into Google's new robotics model, RT-2, which melds artificial intelligence technology with robots.
2023-07-29
Vision-language ➡️ vision-language-action model By using a pre-trained VLM (e.g. PaLI-X), RT-2 enables robots to generalize to new objects & instructions RT-2 also shows basic reasoning capabilities. (e.g. “place orange in matching bowl") Paper+videos: https://robotics-transformer2.github.io / [image]
New York Times
Google launches RT-2 or Robotics Transformer 2, a “vision-language-action” model trained on text and images from the web that can output robotic actions
Our sneak peek into Google's new robotics model, RT-2, which melds artificial intelligence technology with robots.