ALEXANDRIA, Va., June 18 -- United States Patent no. 12,327,169, issued on June 10, was assigned to GOOGLE LLC (Mountain View, Calif.).

"Controlling a robot based on free-form natural language input" was invented by Pararth Shah (Sunnyvale, Calif.), Dilek Hakkani-Tur (Los Altos, Calif.), Juliana Kew (San Francisco), Marek Fiser (Mountain View, Calif.) and Aleksandra Faust (Palo Alto, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Implementations relate to using deep reinforcement learning to train a model that can be utilized, at each of a plurality of time steps, to determine a corresponding robotic action for completing a robotic task. Implementations additionally or alternatively relate to utilizat...