MUMBAI, India, July 5 -- Intellectual Property India has published a patent application (202517056942 A) filed by Google Llc, Mountain View, U.S.A., on June 13, for 'real-world robot control using transformer neural networks.'
Inventor(s) include P G, Keerthana; Hausman, Karol; Ibarz, Julian; Ichter, Brian; Irpan, Alexander; Kalashnikov, Dmitry; Lu, Yao; Rao, Kanury Kanishka; Ryoo, Michael Sahngwon; Stone, Austin Charles; Xiao, Teddey Ming; Vuong, Quan Ho; Sontakke, Sumedh Anand; Lee, Kuang-Huei; and Nachum, Ofir.
The application for the patent was published on July 4, under issue no. 27/2025.
According to the abstract released by the Intellectual Property India: "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 a natural language text sequence that characterizes a task to be performed by the agent in the environment; generating an encoded representation of the natural language text sequence; and at each of a plurality of time steps: obtaining an observation image characterizing a state of the environment at the time step; processing the observation image to generate an encoded representation of the observation image; generating a sequence of input tokens; processing the sequence of input tokens to generate a policy output that defines an action to be performed by the agent in response to the observation image; selecting an action to be performed by the agent using the policy output; and causing the agent to perform the selected action."
The patent application was internationally filed on Dec. 13, 2023, under International application No.PCT/US2023/083895.
Disclaimer: Curated by HT Syndication.
