Вторник, 30 Апреля +19...+18 Температура воды в море онлайн |
Курсы валют в банках Актау
|
|
How could robotics soon help us in our daily lives?
— Google DeepMind (@GoogleDeepMind) January 4, 2024
Today, we’re announcing a suite of research advances that enable robots to make decisions faster as well as better understand and navigate their environments.
Here's a snapshot of the work. https://t.co/rqOnzDDMDI pic.twitter.com/satbbGyltI
The system first uses a VLM to understand its surroundings. Next, an LLM proposes creative tasks for each robot and selects which one they should perform.
— Google DeepMind (@GoogleDeepMind) January 4, 2024
In evaluations over 7 months, AutoRT safely orchestrated as many as 20 robots simultaneously across various offices. pic.twitter.com/6IKNqEOIS5
1️⃣ Our new system SARA-RT converts Robotics Transformer models into more efficient versions using a novel method: “up-training.”
— Google DeepMind (@GoogleDeepMind) January 4, 2024
This can reduce the computational requirements needed for on-robot deployment, increasing speed while preserving quality. https://t.co/rqOnzDDMDI pic.twitter.com/wCzrSf6oBl
2️⃣ The RT-Trajectory model learns how to follow instructions by automatically adding visual outlines that describe robot motions to its training.
— Google DeepMind (@GoogleDeepMind) January 4, 2024
It takes videos in a dataset and overlays it with a 2D trajectory sketch of the robot arm’s gripper as it performs the task. pic.twitter.com/9robOqkMij
Комментарии ( 0 )
Содержание комментариев не имеет отношения к редакционной политике Лада.kz.
Редакция не несет ответственность за форму и характер комментариев, оставляемых пользователями сайта.
Оставьте свой комментарий первым.