Patents by Inventor Gregory Dudek

Gregory Dudek 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).

  • Patent number: 11036232
    Abstract: A method and apparatus for generating adversarial scenarios and training an autonomous driving agent for an autonomous vehicle, using one or more sets of parameters, each set of parameters defining a respective driving scenario. A new set of parameters is generated by changing one or more parameters of one of the sets of parameters to define a new driving scenario, and performance of the autonomous driving agent is evaluated on the new driving scenario. The generating and evaluating is repeated until the autonomous driving agent fails to satisfy a predefined performance threshold for the new driving scenario. Each instance of changing the one or more parameters is based on a prior evaluated performance of the autonomous driving agent. The autonomous driving agent is trained to update a learned policy of the autonomous driving agent using at least one set of parameters, including the new set of parameters.
    Type: Grant
    Filed: March 11, 2019
    Date of Patent: June 15, 2021
    Assignees: HUAWEI TECHNOLOGIES CO., LTD, THE ROYAL INSTITUTION FOR THE ADVANCEMENT OF LEARNING/MCGILL UNIVERSITY
    Inventors: Florian Shkurti, Gregory Dudek, Yasasa Abeysirigoonawardena, Elmira Amirloo Abolfathi, Jun Luo
  • Publication number: 20200089247
    Abstract: A method and apparatus for generating adversarial scenarios and training an autonomous driving agent for an autonomous vehicle, using one or more sets of parameters, each set of parameters defining a respective driving scenario. A new set of parameters is generated by changing one or more parameters of one of the sets of parameters to define a new driving scenario, and performance of the autonomous driving agent is evaluated on the new driving scenario. The generating and evaluating is repeated until the autonomous driving agent fails to satisfy a predefined performance threshold for the new driving scenario. Each instance of changing the one or more parameters is based on a prior evaluated performance of the autonomous driving agent. The autonomous driving agent is trained to update a learned policy of the autonomous driving agent using at least one set of parameters, including the new set of parameters.
    Type: Application
    Filed: March 11, 2019
    Publication date: March 19, 2020
    Inventors: Florian Shkurti, Gregory Dudek, Yasasa Abeysirigoonawardena, Elmira Amirloo Abolfathi, Jun Luo
  • Patent number: 8025235
    Abstract: There is described a synthetic marker encoding data, the synthetic marker comprising an information payload represented by bits encoded along a spectrum, each of the bits having a priority level assigned thereto ranging from high to low, bits having lower priority levels being encoded along an end of the spectrum which is successively lost with progressively degrading marker viewing conditions compared to bits having higher priority levels.
    Type: Grant
    Filed: May 16, 2008
    Date of Patent: September 27, 2011
    Assignee: The Royal Institution for the Advancement of Learning/McGill University
    Inventor: Gregory Dudek
  • Publication number: 20080300722
    Abstract: A robotic device for navigating in at least a liquid medium, includes a legged propulsion system having a series of legs external of a body of the robotic device, each of the legs being independently driven and mounted to the body for pivotal movement about a respective transverse axis. The legs oscillating relative to the body about the respective transverse axis such that interaction between the legs and the liquid medium produces propulsive forces that displace the robotic device within the liquid medium. A control system is operatively connected to the legged propulsion system for autonomous control and operation of the robotic device based on information received from at least one sensor providing data about an environment of the device.
    Type: Application
    Filed: August 15, 2008
    Publication date: December 4, 2008
    Inventors: Gregory DUDEK, Chris Prahacs, Shane Saunderson, Phillppe Giguere, Junaed Sattar, Michael Jenkin
  • Publication number: 20080296390
    Abstract: There is described a synthetic marker encoding data, the synthetic marker comprising an information payload represented by bits encoded along a spectrum, each of the bits having a priority level assigned thereto ranging from high to low, bits having lower priority levels being encoded along an end of the spectrum which is successively lost with progressively degrading marker viewing conditions compared to bits having higher priority levels.
    Type: Application
    Filed: May 16, 2008
    Publication date: December 4, 2008
    Inventor: Gregory DUDEK
  • Publication number: 20080032571
    Abstract: A control system for a robotic device maneuverable in at least a liquid medium, the system having at least one visual sensor retrieving an image of the device's environment, an image analyzing module receiving the image, determining a presence of an object of a given type therein and analyzing at least one property of the object, a motion calculator determining a desired motion of the device based on the property, and a controller operating a propulsion system of the device to obtain the desired motion. Also, a legged robotic device having a control system including at least one sensor providing data about an environment of the device, the control system using sensor data to determine a desired motion of the device, determining a corresponding required leg motion of each of the legs to produce the desired motion and actuating the legs in accordance with the corresponding required leg motion.
    Type: Application
    Filed: August 2, 2006
    Publication date: February 7, 2008
    Inventors: Gregory Dudek, Chris Prahacs, Shane Saunderson, Philippe Giguere, Junaed Sattar, Michael Jenkin