公开(公告)号：US20240189994A1

公开(公告)日：2024-06-13

申请号：US18539171

申请日：2023-12-13

Applicant: Google LLC

Inventor： Keerthana P G ,  Karol Hausman ,  Julian Ibarz ,  Brian Ichter ,  Alexander Irpan ,  Dmitry Kalashnikov ,  Yao Lu ,  Kanury Kanishka Rao ,  Michael Sahngwon Ryoo ,  Austin Charles Stone ,  Teddey Ming Xiao ,  Quan Ho Vuong ,  Sumedh Anand Sontakke

IPC: B25J9/16

CPC classification number: B25J9/163 ,  B25J9/161

Abstract: 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.