Google DeepMind has a new AI model that can direct robotic tasks it was never trained to perform.
Named RT-2, the model learns from web and robotics data.
It then turns this information into simple instructions for machines.
In other words, RT-2 can speak robot.
40% off TNW Conference!
It also has an improved semantic and visual understanding of robotic data that wasnt previously encountered.
Notably, the model can use rudimentary reasoning to follow new user commands.
Impressively, it can evenperform multi-stage semantic reasoning.
In another evaluation, the model was commanded to push a bottle of ketchup towards a blue cube.
There were several items in the scene, but the only one in the training dataset was the cube.
Nonetheless, RT-2 successfully pushed the ketchup towards the specified destination.
DeepMind has heralded RT-2 as a breakthrough inartificial intelligence.
The Londonlab says the model brings us closer to a future of helpfulrobots.
it’s possible for you to read the RT-2 study paperhere.
Story byThomas Macaulay
Thomas is the managing editor of TNW.
He leads our coverage of European tech and oversees our talented team of writers.
Away from work, he e(show all)Thomas is the managing editor of TNW.
He leads our coverage of European tech and oversees our talented team of writers.
Away from work, he enjoys playing chess (badly) and the guitar (even worse).
