公开(公告)号：US20210334599A1

公开(公告)日：2021-10-28

申请号：US17279924

申请日：2019-09-27

Applicant: Google LLC

Inventor： Soeren Pirk ,  Yunfei Bai ,  Pierre Sermanet ,  Seyed Mohammad Khansari Zadeh ,  Harrison Lynch

IPC: G06K9/62 ,  G06K9/00 ,  G10L15/22 ,  G06K9/20 ,  G05B13/02 ,  G06N3/08 ,  B25J9/16 ,  B25J13/00

Abstract: Training a machine learning model (e.g., a neural network model such as a convolutional neural network (CNN) model) so that, when trained, the model can be utilized in processing vision data (e.g., from a vision component of a robot), that captures an object, to generate a rich object-centric embedding for the vision data. The generated embedding can enable differentiation of even subtle variations of attributes of the object captured by the vision data.

公开(公告)号：US20230150127A1

公开(公告)日：2023-05-18

申请号：US18157919

申请日：2023-01-23

Applicant: Google LLC

Inventor： YEVGEN CHEBOTAR ,  Pierre Sermanet ,  Harrison Lynch

IPC: B25J9/16 ,  G06N20/00 ,  G05B13/02 ,  G06N3/084

CPC classification number: B25J9/163 ,  G06N20/00 ,  B25J9/1664 ,  B25J9/1697 ,  G05B13/0205 ,  G05B13/027 ,  G06N3/084

Abstract: There are provided systems, methods, and apparatus, for optimizing a policy controller to control a robotic agent that interacts with an environment to perform a robotic task. One of the methods includes optimizing the policy controller using a neural network that generates numeric embeddings of images of the environment and a demonstration sequence of demonstration images of another agent performing a version of the robotic task.

公开(公告)号：US11887363B2

公开(公告)日：2024-01-30

申请号：US17279924

申请日：2019-09-27

Applicant: Google LLC

Inventor： Soeren Pirk ,  Yunfei Bai ,  Pierre Sermanet ,  Seyed Mohammad Khansari Zadeh ,  Harrison Lynch

IPC: G06V20/10 ,  B25J9/16 ,  B25J13/00 ,  G05B13/02 ,  G06N3/08 ,  G10L15/22 ,  G06F18/21 ,  G06F18/2413 ,  G06V10/764 ,  G06V10/70 ,  G06V10/776 ,  G06V10/82

CPC classification number: G06V20/10 ,  B25J9/1697 ,  B25J13/003 ,  G05B13/027 ,  G06F18/217 ,  G06F18/2413 ,  G06N3/08 ,  G06V10/764 ,  G06V10/768 ,  G06V10/776 ,  G06V10/82 ,  G10L15/22

Abstract: Training a machine learning model (e.g., a neural network model such as a convolutional neural network (CNN) model) so that, when trained, the model can be utilized in processing vision data (e.g., from a vision component of a robot), that captures an object, to generate a rich object-centric embedding for the vision data. The generated embedding can enable differentiation of even subtle variations of attributes of the object captured by the vision data.

公开(公告)号：US12240117B2

公开(公告)日：2025-03-04

申请号：US18157919

申请日：2023-01-23

Applicant: Google LLC

Inventor： Yevgen Chebotar ,  Pierre Sermanet ,  Harrison Lynch

IPC: B25J9/16 ,  G05B13/02 ,  G06N3/084 ,  G06N20/00

Abstract: There are provided systems, methods, and apparatus, for optimizing a policy controller to control a robotic agent that interacts with an environment to perform a robotic task. One of the methods includes optimizing the policy controller using a neural network that generates numeric embeddings of images of the environment and a demonstration sequence of demonstration images of another agent performing a version of the robotic task.

公开(公告)号：US11559887B2

公开(公告)日：2023-01-24

申请号：US16649596

申请日：2018-09-20

Applicant: GOOGLE LLC

Inventor： Yevgen Chebotar ,  Pierre Sermanet ,  Harrison Lynch

IPC: G06N20/00 ,  G05B13/02 ,  G06N3/08 ,  B25J9/16

Abstract: There are provided systems, methods, and apparatus, for optimizing a policy controller to control a robotic agent that interacts with an environment to perform a robotic task. One of the methods includes optimizing the policy controller using a neural network that generates numeric embeddings of images of the environment and a demonstration sequence of demonstration images of another agent performing a version of the robotic task.

公开(公告)号：US20200276703A1

公开(公告)日：2020-09-03

申请号：US16649596

申请日：2018-09-20

Applicant: GOOGLE LLC

Inventor： Yevgen Chebotar ,  Pierre Sermanet ,  Harrison Lynch

IPC: B25J9/16 ,  G05B13/02 ,  G06N3/08 ,  G06N20/00

Abstract: There are provided systems, methods, and apparatus, for optimizing a policy controller to control a robotic agent that interacts with an environment to perform a robotic task. One of the methods includes optimizing the policy controller using a neural network that generates numeric embeddings of images of the environment and a demonstration sequence of demonstration images of another agent performing a version of the robotic task.