公开(公告)号：US20200160172A1

公开(公告)日：2020-05-21

申请号：US16602702

申请日：2019-11-20

Applicant: Google LLC

Inventor： Kuan Fang ,  Alexander Toshkov Toshev

IPC: G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling an agent. One of the methods includes receiving a current observation characterizing a current state of the environment as of the time step; generating an embedding of the current observation; processing scene memory data comprising embeddings of prior observations received at prior time steps using an encoder neural network, wherein the encoder neural network is configured to apply an encoder self-attention mechanism to the scene memory data to generate an encoded representation of the scene memory data; processing the encoded representation of the scene memory data and the embedding of the current observation using a decoder neural network to generate an action selection output; and causing the agent to perform the selected action.

公开(公告)号：US20240220799A1

公开(公告)日：2024-07-04

申请号：US18536074

申请日：2023-12-11

Applicant: Google LLC

Inventor： Kuan Fang ,  Alexander Toshkov Toshev

IPC: G06N3/08 ,  G06N3/045

CPC classification number: G06N3/08 ,  G06N3/045

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling an agent. One of the methods includes receiving a current observation characterizing a current state of the environment as of the time step; generating an embedding of the current observation; processing scene memory data comprising embeddings of prior observations received at prior time steps using an encoder neural network, wherein the encoder neural network is configured to apply an encoder self-attention mechanism to the scene memory data to generate an encoded representation of the scene memory data; processing the encoded representation of the scene memory data and the embedding of the current observation using a decoder neural network to generate an action selection output; and causing the agent to perform the selected action.

公开(公告)号：US11842277B2

公开(公告)日：2023-12-12

申请号：US17953222

申请日：2022-09-26

Applicant: Google LLC

Inventor： Kuan Fang ,  Alexander Toshkov Toshev

IPC: G06N3/08 ,  G06N3/045

CPC classification number: G06N3/08 ,  G06N3/045

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling an agent. One of the methods includes receiving a current observation characterizing a current state of the environment as of the time step; generating an embedding of the current observation; processing scene memory data comprising embeddings of prior observations received at prior time steps using an encoder neural network, wherein the encoder neural network is configured to apply an encoder self-attention mechanism to the scene memory data to generate an encoded representation of the scene memory data; processing the encoded representation of the scene memory data and the embedding of the current observation using a decoder neural network to generate an action selection output; and causing the agent to perform the selected action.

公开(公告)号：US12248875B2

公开(公告)日：2025-03-11

申请号：US18536074

申请日：2023-12-11

Applicant: Google LLC

Inventor： Kuan Fang ,  Alexander Toshkov Toshev

IPC: G06N3/08 ,  G06N3/045

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling an agent. One of the methods includes receiving a current observation characterizing a current state of the environment as of the time step; generating an embedding of the current observation; processing scene memory data comprising embeddings of prior observations received at prior time steps using an encoder neural network, wherein the encoder neural network is configured to apply an encoder self-attention mechanism to the scene memory data to generate an encoded representation of the scene memory data; processing the encoded representation of the scene memory data and the embedding of the current observation using a decoder neural network to generate an action selection output; and causing the agent to perform the selected action.

公开(公告)号：US20250033201A1

公开(公告)日：2025-01-30

申请号：US18918590

申请日：2024-10-17

Applicant: GOOGLE LLC

Inventor： Yunfei Bai ,  Kuan Fang ,  Stefan Hinterstoisser ,  Mrinal Kalakrishnan

IPC: B25J9/16

Abstract: Implementations are directed to training a machine learning model that, once trained, is used in performance of robotic grasping and/or other manipulation task(s) by a robot. The model can be trained using simulated training examples that are based on simulated data that is based on simulated robot(s) attempting simulated manipulations of various simulated objects. Portion(s) of the model can also be trained based on real training examples that are based on data from real-world physical robots attempting manipulations of various objects. The simulated training examples can be utilized to train the model to predict an output that can be utilized in a particular task—and the real training examples used to adapt at least a portion of the model to the real-world domain can be tailored to a distinct task. In some implementations, domain-adversarial similarity losses are determined during training, and utilized to regularize at least portion(s) of the model.

公开(公告)号：US20230090658A1

公开(公告)日：2023-03-23

申请号：US17953222

申请日：2022-09-26

Applicant: Google LLC

Inventor： Kuan Fang ,  Alexander Toshkov Toshev

IPC: G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling an agent. One of the methods includes receiving a current observation characterizing a current state of the environment as of the time step; generating an embedding of the current observation; processing scene memory data comprising embeddings of prior observations received at prior time steps using an encoder neural network, wherein the encoder neural network is configured to apply an encoder self-attention mechanism to the scene memory data to generate an encoded representation of the scene memory data; processing the encoded representation of the scene memory data and the embedding of the current observation using a decoder neural network to generate an action selection output; and causing the agent to perform the selected action.

公开(公告)号：US12138793B2

公开(公告)日：2024-11-12

申请号：US16987771

申请日：2020-08-07

Applicant: GOOGLE LLC

Inventor： Yunfei Bai ,  Kuan Fang ,  Stefan Hinterstoisser ,  Mrinal Kalakrishnan

IPC: B25J9/16

Abstract: Implementations are directed to training a machine learning model that, once trained, is used in performance of robotic grasping and/or other manipulation task(s) by a robot. The model can be trained using simulated training examples that are based on simulated data that is based on simulated robot(s) attempting simulated manipulations of various simulated objects. Portion(s) of the model can also be trained based on real training examples that are based on data from real-world physical robots attempting manipulations of various objects. The simulated training examples can be utilized to train the model to predict an output that can be utilized in a particular task—and the real training examples used to adapt at least a portion of the model to the real-world domain can be tailored to a distinct task. In some implementations, domain-adversarial similarity losses are determined during training, and utilized to regularize at least portion(s) of the model.

公开(公告)号：US11455530B2

公开(公告)日：2022-09-27

申请号：US16602702

申请日：2019-11-20

Applicant: Google LLC

Inventor： Kuan Fang ,  Alexander Toshkov Toshev

IPC: G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling an agent. One of the methods includes receiving a current observation characterizing a current state of the environment as of the time step; generating an embedding of the current observation; processing scene memory data comprising embeddings of prior observations received at prior time steps using an encoder neural network, wherein the encoder neural network is configured to apply an encoder self-attention mechanism to the scene memory data to generate an encoded representation of the scene memory data; processing the encoded representation of the scene memory data and the embedding of the current observation using a decoder neural network to generate an action selection output; and causing the agent to perform the selected action.