公开(公告)号：WO2019010136A3

公开(公告)日：2019-01-10

申请号：PCT/US2018/040641

申请日：2018-07-02

Applicant: X DEVELOPMENT LLC

Inventor： HUDSON, Nicolas ,  YAMPARALA, Devesh

IPC: B25J9/16 ,  G05B13/02 ,  G06N3/08 ,  G06N3/04 ,  G06N20/00

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.

公开(公告)号：WO2019133081A1

公开(公告)日：2019-07-04

申请号：PCT/US2018/050868

申请日：2018-09-13

Applicant: X DEVELOPMENT LLC

Inventor： RAJKUMAR, Nareshkumar ,  LEGER, Patrick ,  HUDSON, Nicolas ,  SHANKAR, Krishna ,  HESSMER, Rainer

IPC: B25J9/00 ,  B25J9/16

CPC classification number: G06N3/08 ,  B25J9/0003 ,  B25J9/1671 ,  G05B2219/45108 ,  H04L67/12 ,  H04L67/2842

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：WO2019010136A2

公开(公告)日：2019-01-10

申请号：PCT/US2018/040641

申请日：2018-07-02

Applicant: X DEVELOPMENT LLC

Inventor： HUDSON, Nicolas ,  YAMPARALA, Devesh

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.

公开(公告)号：WO2019010137A1

公开(公告)日：2019-01-10

申请号：PCT/US2018/040644

申请日：2018-07-02

Applicant: X DEVELOPMENT LLC

Inventor： SHANKAR, Krishna ,  HUDSON, Nicolas ,  TOSHEV, Alexander

IPC: G06N3/00 ,  G06K9/62 ,  G06N3/08

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：EP3713719A1

公开(公告)日：2020-09-30

申请号：EP18779545.5

申请日：2018-09-13

Applicant: X Development LLC

Inventor： RAJKUMAR, Nareshkumar ,  LEGER, Patrick ,  HUDSON, Nicolas ,  SHANKAR, Krishna ,  HESSMER, Rainer

IPC: B25J9/00 ,  B25J9/16

公开(公告)号：EP3628031A2

公开(公告)日：2020-04-01

申请号：EP18749662.5

申请日：2018-07-02

Applicant: X Development LLC

Inventor： HUDSON, Nicolas ,  YAMPARALA, Devesh

IPC: B25J9/16 ,  G05B13/02 ,  G06N3/08 ,  G06N3/04 ,  G06N20/00

公开(公告)号：EP3625730A1

公开(公告)日：2020-03-25

申请号：EP18743369.3

申请日：2018-07-02

Applicant: X Development LLC

Inventor： SHANKAR, Krishna ,  HUDSON, Nicolas ,  TOSHEV, Alexander

IPC: G06N3/00 ,  G06K9/62 ,  G06N3/08

公开(公告)号：EP4219088A1

公开(公告)日：2023-08-02

申请号：EP23175880.6

申请日：2018-07-02

Applicant: X Development LLC

Inventor： HUDSON, Nicolas ,  YAMPARALA, Devesh

IPC: B25J9/16 ,  G05B13/02 ,  G06N3/08 ,  G06N3/04 ,  G06N20/00 ,  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). 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.