Google's DeepMind AI enables robots to perform novel tasks

Source: IANS

Google has demonstrated its first vision-language-action (VLA) model for robot control that showed improved generalization capabilities and semantic (the understanding of words and sentences), and visual understanding beyond the robotic data it was exposed to.

This includes interpreting new commands and responding to user commands by performing beginner-level reasoning, such as reasoning about object categories or high-level descriptions.

The Robotic Transformer 2 (RT-2) is a novel vision-language-action (VLA) model that learns from both web and robotics data, and translates this knowledge into generalized instructions for robotic control, according to Google DeepMind, the tech giant's artificial intelligence subsidiary.

A robot that can perform multiple tasks

A traditional robot can pick up a ball and stumble when picking up a cube. RT-2's flexible approach enables a robot to train on picking up a ball and can figure out how to adjust its extremities to pick up a cube or another toy it's never seen before.

"We also show that incorporating chain-of-thought reasoning allows RT-2 to perform multi-stage semantic reasoning, like deciding which object could be used as an improvised hammer (a rock), or which type of drink is best for a tired person (an energy drink),” said the team behind it.

The latest model builds upon Robotic Transformer 1 (RT-1) that was trained on multi-task demonstrations.

The team performed a series of qualitative and quantitative experiments on RT-2 models, on over 6,000 robotic trials.

The potential of vision-language models

The RT-2 model shows that vision-language models (VLMs) can be transformed into powerful vision-language-action (VLA) models, which can directly control a robot by combining VLM pre-training with robotic data.

"RT-2 is not only a simple and effective modification over existing VLM models, but also shows the promise of building a general-purpose physical robot that can reason, problem solve, and interpret information for performing a diverse range of tasks in the real -world,” said Google DeepMind.

(Source: IANS)

-Edited for style

For more such updates and news on the go, follow us on

Instagram | YouTube | Facebook

Comments

Popular posts from this blog

The lines written by the left, are now decreasing!

Darkness will be the enemy of Chandrayaan! How the lander and rover on the moon will work at night, this time is the most challenging

Heart rate was 110 beats per minute before Neil Armstrong set foot on the moon.

NGT orders report on health impact of microplastics in human blood

ISRO launches 'Navik' satellite, will keep an eye on enemies with enhanced security

A major change in the method of syncing contacts in smartphones

Facebook launches dating app to find a partner, find out what's special about it

400 howitzer guns will be bought for Indian Army, know the strength of Made in India guns

For the first time in the history of medical science, an HIV patient recovered automatically

BharatOS for the people of India, of the people of India, by the people of India!