Google Deepmind has introduced three new robotic training tools, AutoRT, SARA-RT, and RT-Trajectory, aimed at improving real-world robot data collection, speed, and generalization. These tools integrate large foundation models, including a Visual Language Model (VLM), to enhance robotic training. The introduction of these tools is seen as an innovative step in the field of robotics, although some have raised concerns about the cost and sophistication of the robots. The announcement from DeepMind has created anticipation for the upcoming CES shows.
Google’s DeepMind shares advanced systems and models for autonomous robot training https://t.co/x4BpUxQ7B8
Foreshadowing CES shows yet to come, Google’s DeepMind has introduced three new robotic training tools: AutoRT, SARA-RT, and RT-Trajectory. AutoRT is a system that enhances robotic training by integrating large foundation models, specifically a Visual Language Model (VLM) and a… https://t.co/0yCCd176hZ
Google Deepmind introduces AutoRT, SARA-RT and RT-Trajectory to improve real-world robot data collection, speed, and generalization. https://t.co/JdgWTsgYkW
This is the week of robotics :) Here is the latest from Deep Mind. This robot seems rudimentary and, TBH, 10 times more expensive than the Aloha videos released yesterday, but still, there are some innovative concepts they write about in a blog post. They introduce AutoRT,… https://t.co/MqphjFKAUD
Google Deepmind introduces AutoRT, SARA-RT and RT-Trajectory to improve real-world robot data collection, speed, and generalization blog: https://t.co/QbyUQvjB4M https://t.co/WtFyrW9b1q