Patents by Inventor Nicholas Watters

Nicholas Watters 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).

  • Making object-level predictions of the future state of a physical system
    Patent number: 11388424
    Abstract: A system implemented by one or more computers comprises a visual encoder component configured to receive as input data representing a sequence of image frames, in particular representing objects in a scene of the sequence, and to output a sequence of corresponding state codes, each state code comprising vectors, one for each of the objects. Each vector represents a respective position and velocity of its corresponding object. The system also comprises a dynamic predictor component configured to take as input a sequence of state codes, for example from the visual encoder, and predict a state code for a next unobserved frame. The system further comprises a state decoder component configured to convert the predicted state code, to a state, the state comprising a respective position and velocity vector for each object in the scene. This state may represent a predicted position and velocity vector for each of the objects.
    Type: Grant
    Filed: December 29, 2020
    Date of Patent: July 12, 2022
    Assignee: DeepMind Technologies Limited
    Inventors: Nicholas Watters, Razvan Pascanu, Peter William Battaglia, Daniel Zorn, Theophane Guillaume Weber
  • MAKING OBJECT-LEVEL PREDICTIONS OF THE FUTURE STATE OF A PHYSICAL SYSTEM
    Publication number: 20210152835
    Abstract: A system implemented by one or more computers comprises a visual encoder component configured to receive as input data representing a sequence of image frames, in particular representing objects in a scene of the sequence, and to output a sequence of corresponding state codes, each state code comprising vectors, one for each of the objects. Each vector represents a respective position and velocity of its corresponding object. The system also comprises a dynamic predictor component configured to take as input a sequence of state codes, for example from the visual encoder, and predict a state code for a next unobserved frame. The system further comprises a state decoder component configured to convert the predicted state code, to a state, the state comprising a respective position and velocity vector for each object in the scene. This state may represent a predicted position and velocity vector for each of the objects.
    Type: Application
    Filed: December 29, 2020
    Publication date: May 20, 2021
    Inventors: Nicholas Watters, Razvan Pascanu, Peter William Battaglia, Daniel Zorn, Theophane Guillaume Weber
  • Making object-level predictions of the future state of a physical system
    Patent number: 10887607
    Abstract: A system implemented by one or more computers comprises a visual encoder component configured to receive as input data representing a sequence of image frames, in particular representing objects in a scene of the sequence, and to output a sequence of corresponding state codes, each state code comprising vectors, one for each of the objects. Each vector represents a respective position and velocity of its corresponding object. The system also comprises a dynamic predictor component configured to take as input a sequence of state codes, for example from the visual encoder, and predict a state code for a next unobserved frame. The system further comprises a state decoder component configured to convert the predicted state code, to a state, the state comprising a respective position and velocity vector for each object in the scene. This state may represent a predicted position and velocity vector for each of the objects.
    Type: Grant
    Filed: November 18, 2019
    Date of Patent: January 5, 2021
    Assignee: DeepMind Technologies Limited
    Inventors: Nicholas Watters, Razvan Pascanu, Peter William Battaglia, Daniel Zorn, Theophane Guillaume Weber
  • MAKING OBJECT-LEVEL PREDICTIONS OF THE FUTURE STATE OF A PHYSICAL SYSTEM
    Publication number: 20200092565
    Abstract: A system implemented by one or more computers comprises a visual encoder component configured to receive as input data representing a sequence of image frames, in particular representing objects in a scene of the sequence, and to output a sequence of corresponding state codes, each state code comprising vectors, one for each of the objects. Each vector represents a respective position and velocity of its corresponding object. The system also comprises a dynamic predictor component configured to take as input a sequence of state codes, for example from the visual encoder, and predict a state code for a next unobserved frame. The system further comprises a state decoder component configured to convert the predicted state code, to a state, the state comprising a respective position and velocity vector for each object in the scene. This state may represent a predicted position and velocity vector for each of the objects.
    Type: Application
    Filed: November 18, 2019
    Publication date: March 19, 2020
    Inventors: Nicholas Watters, Razvan Pascanu, Peter William Battaglia, Daniel Zorn, Theophane Guillaume Weber