公开(公告)号：US12265910B2

公开(公告)日：2025-04-01

申请号：US17930874

申请日：2022-09-09

Applicant: Google LLC

Inventor： Nareshkumar Rajkumar ,  Patrick Leger ,  Nicolas Hudson ,  Krishna Shankar ,  Rainer Hessmer

IPC: G06F13/00 ,  B25J9/00 ,  B25J9/16 ,  G06N3/08 ,  H04L67/12 ,  H04L67/568

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for sharing learned information among robots. In some implementations, a robot obtains sensor data indicating characteristics of an object. The robot determines a classification for the object and generates an embedding for the object using a machine learning model stored by the robot. The robot stores the generated embedding and data indicating the classification for the object. The robot sends the generated embedding and the data indicating the classification to a server system. The robot receives, from the server system, an embedding generated by a second robot and a corresponding classification. The robot stores the received embedding and the corresponding classification in the local cache of the robot. The robot may then use the information in the cache to identify objects.

公开(公告)号：US20230405812A1

公开(公告)日：2023-12-21

申请号：US18239735

申请日：2023-08-29

Applicant: GOOGLE LLC

Inventor： Nicolas Hudson ,  Devesh Yamparala

IPC: B25J9/16 ,  G05B13/02 ,  G06N3/084 ,  G06N3/008 ,  G06N3/045

CPC classification number: B25J9/161 ,  B25J9/163 ,  G05B13/027 ,  B25J9/1656 ,  B25J9/1602 ,  B25J9/1697 ,  G06N3/084 ,  G06N3/008 ,  G06N3/045 ,  G05B2219/33036 ,  G05B2219/33037

Abstract: Methods, apparatus, and computer-readable media for determining and utilizing human corrections to robot actions. In some implementations, in response to determining a human correction of a robot action, a correction instance is generated that includes sensor data, captured by one or more sensors of the robot, that is relevant to the corrected action. The correction instance can further include determined incorrect parameter(s) utilized in performing the robot action and/or correction information that is based on the human correction. The correction instance can be utilized to generate training example(s) for training one or model(s), such as neural network model(s), corresponding to those used in determining the incorrect parameter(s).

公开(公告)号：US20250061302A1

公开(公告)日：2025-02-20

申请号：US18939168

申请日：2024-11-06

Applicant: GOOGLE LLC

Inventor： Krishna Shankar ,  Nicolas Hudson ,  Alexander Toshev

IPC: G06N3/008 ,  B25J9/16 ,  G06F18/40 ,  G06N3/04 ,  G06N3/08 ,  G06N3/084 ,  G06V10/778 ,  G06V10/82

Abstract: Methods, apparatus, and computer-readable media for determining and utilizing corrections to robot actions. Some implementations are directed to updating a local features model of a robot in response to determining a human correction of an action performed by the robot. The local features model is used to determine, based on an embedding generated over a corresponding neural network model, one or more features that are most similar to the generated embedding. Updating the local features model in response to a human correction can include updating a feature embedding, of the local features model, that corresponds to the human correction. Adjustment(s) to the features model can immediately improve robot performance without necessitating retraining of the corresponding neural network model.

公开(公告)号：US12159210B2

公开(公告)日：2024-12-03

申请号：US18140366

申请日：2023-04-27

Applicant: GOOGLE LLC

Inventor： Krishna Shankar ,  Nicolas Hudson ,  Alexander Toshev

IPC: G06N3/008 ,  B25J9/16 ,  G06F18/40 ,  G06N3/04 ,  G06N3/08 ,  G06N3/084 ,  G06V10/778 ,  G06V10/82

Abstract: Methods, apparatus, and computer-readable media for determining and utilizing corrections to robot actions. Some implementations are directed to updating a local features model of a robot in response to determining a human correction of an action performed by the robot. The local features model is used to determine, based on an embedding generated over a corresponding neural network model, one or more features that are most similar to the generated embedding. Updating the local features model in response to a human correction can include updating a feature embedding, of the local features model, that corresponds to the human correction. Adjustment(s) to the features model can immediately improve robot performance without necessitating retraining of the corresponding neural network model.

公开(公告)号：US12064876B2

公开(公告)日：2024-08-20

申请号：US18239735

申请日：2023-08-29

Applicant: GOOGLE LLC

Inventor： Nicolas Hudson ,  Devesh Yamparala

IPC: B25J13/08 ,  B25J9/16 ,  G05B13/02 ,  G06N3/008 ,  G06N3/045 ,  G06N3/084

CPC classification number: B25J9/161 ,  B25J9/1602 ,  B25J9/163 ,  B25J9/1656 ,  B25J9/1697 ,  G05B13/027 ,  G06N3/008 ,  G06N3/045 ,  G06N3/084 ,  G05B2219/33036 ,  G05B2219/33037

Abstract: Methods, apparatus, and computer-readable media for determining and utilizing human corrections to robot actions. In some implementations, in response to determining a human correction of a robot action, a correction instance is generated that includes sensor data, captured by one or more sensors of the robot, that is relevant to the corrected action. The correction instance can further include determined incorrect parameter(s) utilized in performing the robot action and/or correction information that is based on the human correction. The correction instance can be utilized to generate training example(s) for training one or model(s), such as neural network model(s), corresponding to those used in determining the incorrect parameter(s).

公开(公告)号：US20240367313A1

公开(公告)日：2024-11-07

申请号：US18776203

申请日：2024-07-17

Applicant: GOOGLE LLC

Inventor： Nicolas Hudson ,  Devesh Yamparala

IPC: B25J9/16 ,  G05B13/02 ,  G06N3/008 ,  G06N3/045 ,  G06N3/084

Abstract: Methods, apparatus, and computer-readable media for determining and utilizing human corrections to robot actions. In some implementations, in response to determining a human correction of a robot action, a correction instance is generated that includes sensor data, captured by one or more sensors of the robot, that is relevant to the corrected action. The correction instance can further include determined incorrect parameter(s) utilized in performing the robot action and/or correction information that is based on the human correction. The correction instance can be utilized to generate training example(s) for training one or model(s), such as neural network model(s), corresponding to those used in determining the incorrect parameter(s).

公开(公告)号：US20230281422A1

公开(公告)日：2023-09-07

申请号：US18140366

申请日：2023-04-27

Applicant: GOOGLE LLC

Inventor： Krishna Shankar ,  Nicolas Hudson ,  Alexander Toshev

IPC: G06N3/008 ,  G06N3/04 ,  G06N3/08 ,  B25J9/16 ,  G06N3/084 ,  G06F18/40 ,  G06V10/778 ,  G06V10/82

CPC classification number: G06N3/008 ,  B25J9/1605 ,  B25J9/161 ,  B25J9/1671 ,  G06F18/41 ,  G06N3/04 ,  G06N3/08 ,  G06N3/084 ,  G06V10/7788 ,  G06V10/82 ,  Y10S901/03

Abstract: Methods, apparatus, and computer-readable media for determining and utilizing corrections to robot actions. Some implementations are directed to updating a local features model of a robot in response to determining a human correction of an action performed by the robot. The local features model is used to determine, based on an embedding generated over a corresponding neural network model, one or more features that are most similar to the generated embedding. Updating the local features model in response to a human correction can include updating a feature embedding, of the local features model, that corresponds to the human correction. Adjustment(s) to the features model can immediately improve robot performance without necessitating retraining of the corresponding neural network model.

公开(公告)号：US11780083B2

公开(公告)日：2023-10-10

申请号：US17520175

申请日：2021-11-05

Applicant: GOOGLE LLC

Inventor： Nicolas Hudson ,  Devesh Yamparala

IPC: B25J13/08 ,  B25J9/16 ,  G05B13/02 ,  G06N3/084 ,  G06N3/008 ,  G06N3/045

CPC classification number: B25J9/161 ,  B25J9/1602 ,  B25J9/163 ,  B25J9/1656 ,  B25J9/1697 ,  G05B13/027 ,  G06N3/008 ,  G06N3/045 ,  G06N3/084 ,  G05B2219/33036 ,  G05B2219/33037

Abstract: Methods, apparatus, and computer-readable media for determining and utilizing human corrections to robot actions. In some implementations, in response to determining a human correction of a robot action, a correction instance is generated that includes sensor data, captured by one or more sensors of the robot, that is relevant to the corrected action. The correction instance can further include determined incorrect parameter(s) utilized in performing the robot action and/or correction information that is based on the human correction. The correction instance can be utilized to generate training example(s) for training one or model(s), such as neural network model(s), corresponding to those used in determining the incorrect parameter(s). In various implementations, the training is based on correction instances from multiple robots. After a revised version of a model is generated, the revised version can thereafter be utilized by one or more of the multiple robots.