公开(公告)号：US12223428B2

公开(公告)日：2025-02-11

申请号：US18459954

申请日：2023-09-01

Applicant: Tesla, Inc.

Inventor： Ashok Kumar Elluswamy ,  Matthew Bauch ,  Christopher Payne ,  Andrej Karpathy ,  Joseph Polin

IPC: G06N3/08 ,  G05D1/00 ,  G06F18/28 ,  G06V20/56 ,  G16Y20/10 ,  G06N3/04

Abstract: Sensor data, including a group of time series elements, is received. A training data set is determined, including by determining for at least a selected time series element in the group of time series elements a corresponding ground truth. The corresponding ground truth is based on a plurality of time series elements in the group of time series elements. A processor is used to train a machine learning model using the training dataset.

公开(公告)号：US20200265247A1

公开(公告)日：2020-08-20

申请号：US16279657

申请日：2019-02-19

Applicant: Tesla, Inc.

Inventor： James Anthony Musk ,  Swupnil Kumar Sahai ,  Ashok Kumar Elluswamy

IPC: G06K9/00 ,  G06T7/70 ,  G06N20/00

Abstract: A system is comprised of one or more processors coupled to memory. The one or more processors are configured to receive image data based on an image captured using a camera of a vehicle and to utilize the image data as a basis of an input to a trained machine learning model to at least in part identify a distance of an object from the vehicle. The trained machine learning model has been trained using a training image and a correlated output of an emitting distance sensor.

公开(公告)号：US20240304003A1

公开(公告)日：2024-09-12

申请号：US18666598

申请日：2024-05-16

Applicant: Tesla, Inc.

Inventor： Ashok Kumar Elluswamy ,  Matthew Bauch ,  Christopher Payne ,  Andrej Karpathy ,  Dhaval Shroff ,  Arvind Ramanandan ,  James Robert Howard Hakewill

IPC: G06V20/56 ,  G06F18/214 ,  G06N20/00 ,  G06T7/20 ,  G06V10/764 ,  G06V10/82

CPC classification number: G06V20/588 ,  G06F18/214 ,  G06N20/00 ,  G06T7/20 ,  G06V10/764 ,  G06V10/82 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30241 ,  G06T2207/30256 ,  G06V2201/10

Abstract: A processor coupled to memory is configured to receive image data based on an image captured by a camera of a vehicle. The image data is used as a basis of an input to a trained machine learning model trained to predict a three-dimensional trajectory of a machine learning feature. The three-dimensional trajectory of the machine learning feature is provided for automatically controlling the vehicle.

公开(公告)号：US20240127599A1

公开(公告)日：2024-04-18

申请号：US18473059

申请日：2023-09-22

Applicant: Tesla, Inc.

Inventor： James Anthony Musk ,  Swupnil Kumar Sahai ,  Ashok Kumar Elluswamy

IPC: G06V20/58 ,  G06N20/00 ,  G06T7/70 ,  G06V10/80

CPC classification number: G06V20/58 ,  G06N20/00 ,  G06T7/70 ,  G06V10/803 ,  G06V20/584 ,  G06T2207/20081 ,  G06T2207/30261

Abstract: A system is comprised of one or more processors coupled to memory. The one or more processors are configured to receive image data based on an image captured using a camera of a vehicle and to utilize the image data as a basis of an input to a trained machine learning model to at least in part identify a distance of an object from the vehicle. The trained machine learning model has been trained using a training image and a correlated output of an emitting distance sensor.

公开(公告)号：US11748620B2

公开(公告)日：2023-09-05

申请号：US17301965

申请日：2021-04-20

Applicant: Tesla, Inc.

Inventor： Ashok Kumar Elluswamy ,  Matthew Bauch ,  Christopher Payne ,  Andrej Karpathy ,  Joseph Polin

IPC: G06N3/08 ,  G05D1/02 ,  G06V20/56 ,  G06F18/28 ,  G16Y20/10 ,  G06N3/04

CPC classification number: G06N3/08 ,  G05D1/0221 ,  G06F18/28 ,  G06V20/588 ,  G16Y20/10 ,  G06N3/04

Abstract: Sensor data, including a group of time series elements, is received. A training data set is determined, including by determining for at least a selected time series element in the group of time series elements a corresponding ground truth. The corresponding ground truth is based on a plurality of time series elements in the group of time series elements. A processor is used to train a machine learning model using the training dataset.

公开(公告)号：US20250124286A1

公开(公告)日：2025-04-17

申请号：US18991094

申请日：2024-12-20

Applicant: Tesla, Inc.

Inventor： Ashok Kumar Elluswamy ,  Matthew Bauch ,  Christopher Payne ,  Andrej Karpathy ,  Joseph Polin

IPC: G06N3/08 ,  G06F18/28 ,  G06N3/04 ,  G06V20/56 ,  G16Y20/10

Abstract: Sensor data, including a group of time series elements, is received. A training data set is determined, including by determining for at least a selected time series element in the group of time series elements a corresponding ground truth. The corresponding ground truth is based on a plurality of time series elements in the group of time series elements. A processor is used to train a machine learning model using the training dataset.

公开(公告)号：US12236689B2

公开(公告)日：2025-02-25

申请号：US18473059

申请日：2023-09-22

Applicant: Tesla, Inc.

Inventor： James Anthony Musk ,  Swupnil Kumar Sahai ,  Ashok Kumar Elluswamy

IPC: G06V20/58 ,  G06N20/00 ,  G06T7/70 ,  G06V10/80

Abstract: A system is comprised of one or more processors coupled to memory. The one or more processors are configured to receive image data based on an image captured using a camera of a vehicle and to utilize the image data as a basis of an input to a trained machine learning model to at least in part identify a distance of an object from the vehicle. The trained machine learning model has been trained using a training image and a correlated output of an emitting distance sensor.

公开(公告)号：US20240070460A1

公开(公告)日：2024-02-29

申请号：US18459954

申请日：2023-09-01

Applicant: Tesla, Inc.

Inventor： Ashok Kumar Elluswamy ,  Matthew Bauch ,  Christopher Payne ,  Andrej Karpathy ,  Joseph Polin

IPC: G06N3/08 ,  G05D1/02 ,  G06F18/28 ,  G06V20/56 ,  G16Y20/10

CPC classification number: G06N3/08 ,  G05D1/0221 ,  G06F18/28 ,  G06V20/588 ,  G16Y20/10 ,  G06N3/04

Abstract: Sensor data, including a group of time series elements, is received. A training data set is determined, including by determining for at least a selected time series element in the group of time series elements a corresponding ground truth. The corresponding ground truth is based on a plurality of time series elements in the group of time series elements. A processor is used to train a machine learning model using the training dataset.

公开(公告)号：US20220107651A1

公开(公告)日：2022-04-07

申请号：US17450914

申请日：2021-10-14

Applicant: Tesla, Inc.

Inventor： Ashok Kumar Elluswamy ,  Matthew Bauch ,  Christopher Payne ,  Andrej Karpathy ,  Dhaval Shroff ,  Arvind Ramanandan ,  James Robert Howard Hakewill

IPC: G05D1/02 ,  G06N20/00 ,  G06K9/00 ,  G06K9/62 ,  G06T7/20

Abstract: A processor coupled to memory is configured to receive image data based on an image captured by a camera of a vehicle. The image data is used as a basis of an input to a trained machine learning model trained to predict a three-dimensional trajectory of a machine learning feature. The three-dimensional trajectory of the machine learning feature is provided for automatically controlling the vehicle.

公开(公告)号：US20200249685A1

公开(公告)日：2020-08-06

申请号：US16265720

申请日：2019-02-01

Applicant: Tesla, Inc.

Inventor： Ashok Kumar Elluswamy ,  Matthew Bauch ,  Christopher Payne ,  Andrej Karpathy ,  Dhaval Shroff ,  Arvind Ramanandan ,  James Robert Howard Hakewill

IPC: G05D1/02 ,  G06K9/00 ,  G06T7/20 ,  G06K9/62 ,  G06N20/00

Abstract: A processor coupled to memory is configured to receive image data based on an image captured by a camera of a vehicle. The image data is used as a basis of an input to a trained machine learning model trained to predict a three-dimensional trajectory of a machine learning feature. The three-dimensional trajectory of the machine learning feature is provided for automatically controlling the vehicle.