US Patent Issued to Google on March 17 for "Controlling robots using multi-modal language models" (German, American Inventors)

ALEXANDRIA, Va., March 17 -- United States Patent no. 12,576,523, issued on March 17, was assigned to Google LLC (Mountain View, Calif.).

"Controlling robots using multi-modal language models" was invented by Peter Raymond Florence (San Francisco), Danny Michael Driess (Berlin), Igor Mordatch (Oakland, Calif.), Andy Zeng (Stanford, Calif.), Seyed Mohammad Mehdi Sajjadi (Berlin) and Klaus Greff (Berlin).

According to the abstract* released by the U.S. Patent & Trademark Office: "Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling an agent interacting with an environment. In one aspect, a method comprises: receiving one or more observations of an environment; receiving an input ...