Patents by Inventor Matthew Bauch

Matthew Bauch has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • GENERATING GROUND TRUTH FOR MACHINE LEARNING FROM TIME SERIES ELEMENTS
    Publication number: 20240070460
    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.
    Type: Application
    Filed: September 1, 2023
    Publication date: February 29, 2024
    Inventors: Ashok Kumar Elluswamy, Matthew Bauch, Christopher Payne, Andrej Karpathy, Joseph Polin
  • Generating ground truth for machine learning from time series elements
    Patent number: 11748620
    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.
    Type: Grant
    Filed: April 20, 2021
    Date of Patent: September 5, 2023
    Assignee: Tesla, Inc.
    Inventors: Ashok Kumar Elluswamy, Matthew Bauch, Christopher Payne, Andrej Karpathy, Joseph Polin
  • PREDICTING THREE-DIMENSIONAL FEATURES FOR AUTONOMOUS DRIVING
    Publication number: 20220107651
    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.
    Type: Application
    Filed: October 14, 2021
    Publication date: April 7, 2022
    Inventors: Ashok Kumar Elluswamy, Matthew Bauch, Christopher Payne, Andrej Karpathy, Dhaval Shroff, Arvind Ramanandan, James Robert Howard Hakewill
  • GENERATING GROUND TRUTH FOR MACHINE LEARNING FROM TIME SERIES ELEMENTS
    Publication number: 20210342637
    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.
    Type: Application
    Filed: April 20, 2021
    Publication date: November 4, 2021
    Inventors: Ashok Kumar Elluswamy, Matthew Bauch, Christopher Payne, Andrej Karpathy, Joseph Polin
  • Predicting three-dimensional features for autonomous driving
    Patent number: 11150664
    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.
    Type: Grant
    Filed: February 1, 2019
    Date of Patent: October 19, 2021
    Assignee: Tesla, Inc.
    Inventors: Ashok Kumar Elluswamy, Matthew Bauch, Christopher Payne, Andrej Karpathy, Dhaval Shroff, Arvind Ramanandan, James Robert Howard Hakewill
  • Generating ground truth for machine learning from time series elements
    Patent number: 10997461
    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.
    Type: Grant
    Filed: February 1, 2019
    Date of Patent: May 4, 2021
    Assignee: Tesla, Inc.
    Inventors: Ashok Kumar Elluswamy, Matthew Bauch, Christopher Payne, Andrej Karpathy, Joseph Polin
  • PREDICTING THREE-DIMENSIONAL FEATURES FOR AUTONOMOUS DRIVING
    Publication number: 20200249685
    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.
    Type: Application
    Filed: February 1, 2019
    Publication date: August 6, 2020
    Inventors: Ashok Kumar Elluswamy, Matthew Bauch, Christopher Payne, Andrej Karpathy, Dhaval Shroff, Arvind Ramanandan, James Robert Howard Hakewill
  • GENERATING GROUND TRUTH FOR MACHINE LEARNING FROM TIME SERIES ELEMENTS
    Publication number: 20200250473
    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.
    Type: Application
    Filed: February 1, 2019
    Publication date: August 6, 2020
    Inventors: Ashok Kumar Elluswamy, Matthew Bauch, Christopher Payne, Andrej Karpathy, Joseph Polin