公开(公告)号：US20240256865A1

公开(公告)日：2024-08-01

申请号：US18430586

申请日：2024-02-01

Applicant: Google LLC

Inventor： Deepali Jain ,  Krzysztof Marcin Choromanski ,  Sumeet Singh ,  Vikas Sindhwani ,  Tingnan Zhang ,  Jie Tan ,  Kumar Avinava Dubey

IPC: G06N3/08 ,  G06N3/0455

CPC classification number: G06N3/08 ,  G06N3/0455

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training neural networks. One of the methods for training a neural network configured to perform a machine learning task includes performing, at each of a plurality of iterations: performing a training step to obtain respective new gradients of a loss function; for each network parameter: generating an optimizer network input; processing the optimizer network input using an optimizer neural network, wherein the processing comprises, for each cell: generating a cell input for the cell; and processing the cell input for the cell to generate a cell output, wherein the processing comprises: obtaining latent embeddings from the cell input; generating the cell output from the hidden state; and determining an update to the hidden state; and generating an optimizer network output defining an update for the network parameter; and applying the update to the network parameter.

公开(公告)号：US20210182620A1

公开(公告)日：2021-06-17

申请号：US16717471

申请日：2019-12-17

Applicant: Google LLC

Inventor： Jie Tan ,  Sehoon Ha ,  Tingnan Zhang ,  Xinlei Pan ,  Brian Andrew Ichter ,  Aleksandra Faust

IPC: G06K9/62 ,  G05D1/00 ,  G06N3/08 ,  G06N3/04

Abstract: A computer-implemented method is disclosed for training one or more machine-learned models. The method can include inputting a first image frame and a second image frame into a feature disentanglement model and receiving, as an output of the machine-learned feature disentanglement model, a state feature and a perspective feature. The method can include inputting the state feature and the perspective feature into a machine-learned decoder model and receiving, as an output of the machine-learned decoder model, the reconstructed image frame. The method can include comparing the reconstructed image frame with a third image frame corresponding with the location and the perspective orientation. The method can include adjusting one or more parameters of the machine-learned feature disentanglement model based on the comparison of the reconstructed image frame and the third image frame.

公开(公告)号：US12172309B2

公开(公告)日：2024-12-24

申请号：US17047892

申请日：2019-04-22

Applicant: Google LLC

Inventor： Jie Tan ,  Tingnan Zhang ,  Atil Iscen ,  Erwin Coumans ,  Yunfei Bai

IPC: B62D57/032 ,  B25J9/16 ,  G05D1/00 ,  G06N3/042 ,  G06N3/08

Abstract: Training and/or using a machine learning model for locomotion control of a robot, where the model is decoupled. In many implementations, the model is decoupled into an open loop component and a feedback component, where a user can provide a desired reference trajectory (e.g., a symmetric sine curve) as input for the open loop component. In additional and/or alternative implementations, the model is decoupled into a pattern generator component and a feedback component, where a user can provide controlled parameter(s) as input for the pattern generator component to generate pattern generator phase data (e.g., an asymmetric sine curve). The neural network model can be used to generate robot control parameters.

公开(公告)号：US11436441B2

公开(公告)日：2022-09-06

申请号：US16717471

申请日：2019-12-17

Applicant: Google LLC

Inventor： Jie Tan ,  Sehoon Ha ,  Tingnan Zhang ,  Xinlei Pan ,  Brian Andrew Ichter ,  Aleksandra Faust

IPC: G06K9/00 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G05D1/00

Abstract: A computer-implemented method is disclosed for training one or more machine-learned models. The method can include inputting a first image frame and a second image frame into a feature disentanglement model and receiving, as an output of the machine-learned feature disentanglement model, a state feature and a perspective feature. The method can include inputting the state feature and the perspective feature into a machine-learned decoder model and receiving, as an output of the machine-learned decoder model, the reconstructed image frame. The method can include comparing the reconstructed image frame with a third image frame corresponding with the location and the perspective orientation. The method can include adjusting one or more parameters of the machine-learned feature disentanglement model based on the comparison of the reconstructed image frame and the third image frame.

公开(公告)号：US20210162589A1

公开(公告)日：2021-06-03

申请号：US17047892

申请日：2019-04-22

Applicant: Google LLC

Inventor： Jie Tan ,  Tingnan Zhang ,  Atil Iscen ,  Erwin Coumans ,  Yunfei Bai

IPC: B25J9/16 ,  G05D1/08 ,  B62D57/032 ,  G06N3/04 ,  G06N3/08

Abstract: Training and/or using a machine learning model for locomotion control of a robot, where the model is decoupled. In many implementations, the model is decoupled into an open loop component and a feedback component, where a user can provide a desired reference trajectory (e.g., a symmetric sine curve) as input for the open loop component. In additional and/or alternative implementations, the model is decoupled into a pattern generator component and a feedback component, where a user can provide controlled parameter(s) as input for the pattern generator component to generate pattern generator phase data (e.g., an asymmetric sine curve). The neural network model can be used to generate robot control parameters.