Home > Technology peripherals > AI > body text

Google launches RT-2 visual language action model to enable robots to master garbage disposal skills

王林
Release: 2023-08-03 17:49:03
forward
1290 people have browsed it

News on July 28, Google today launched a new artificial intelligence (AI) model Robotics Transformer2 (RT-2) , which can help train robots to understand tasks such as throwing away garbage.

Google launches RT-2 visual language action model to enable robots to master garbage disposal skills

This sentence cannot be rewritten because it is not a complete sentence, but a label. Please provide a complete sentence and I will be happy to help you rewrite it

According to Google, RT-2 is a visual language capable of converting information and images from the Internet into actions that robots can understand Action models, which help improve the robot's learning ability

Although tasks such as picking up trash may seem simple to humans, robots need to master a range of knowledge in order to learn. For example, a robot must first learn to identify what items trash is made of, and then understand how to pick it up and dispose of it

RT-2 enables robots to use knowledge from the network to understand how tasks are completed, rather than Programming guides robots to complete specific tasks. Even if the robot has not undergone explicit training steps, it can learn and complete new tasks through RT-2

According to the New York Times report, Google currently has no plans to release or sell robots using this new technology. But eventually this technology may be applied to warehousing logistics or home assistant robots

IT Home attaches a detailed description of the RT-2 model:Click here to go

The above is the detailed content of Google launches RT-2 visual language action model to enable robots to master garbage disposal skills. For more information, please follow other related articles on the PHP Chinese website!

Related labels:
source:51cto.com
Statement of this Website
The content of this article is voluntarily contributed by netizens, and the copyright belongs to the original author. This site does not assume corresponding legal responsibility. If you find any content suspected of plagiarism or infringement, please contact admin@php.cn
Popular Tutorials
More>
Latest Downloads
More>
Web Effects
Website Source Code
Website Materials
Front End Template