Patents by Inventor Kevin Johnsrude

Kevin Johnsrude 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: 10830755
    Abstract: A method of board lumber grading is performed in an industrial environment on a machine learning framework configured as an interface to a machine learning-based deep convolutional network that is trained end-to-end, pixels-to-pixels on semantic segmentation. The method uses deep learning techniques that are applied to semantic segmentation to delineate board lumber characteristics, including their sizes and boundaries.
    Type: Grant
    Filed: February 21, 2020
    Date of Patent: November 10, 2020
    Assignee: LUCIDYNE TECHNOLOGIES, INC.
    Inventors: Revathy Priyanga Narasimhan, Patrick Freeman, Hayden Michael Aronson, Kevin Johnsrude, Chris Mosbrucker, Dan Robin, Ryan T. Shear, Joseph H. Weintraub, Eric N. Mortensen
  • Patent number: 10731936
    Abstract: A modular grip panel system for a firearm has a frame to support a pair of grip panels and a backstrap. The system includes a left and right grip panels having pockets, and a backstrap having a boss. The frame has a grip disposed at its rear end having a left and right side bosses to engage the pockets of the grip panels, and a rear surface pocket to receive the backstrap boss. The grip panels are disposed on the side surfaces of the pistol-style grip by insertion of the bosses into the pockets. The backstrap is disposed on the rear surface of grip by insertion of the backstrap boss into the rear surface pocket. When the backstrap is secured to the frame, the boss of grip panels are held in a forwardmost position. The backstrap prevents movement of the left and right grip panels towards the rear end of the frame.
    Type: Grant
    Filed: March 19, 2019
    Date of Patent: August 4, 2020
    Assignee: Kimber IP, LLC
    Inventors: Daniel Edward Sapio, Lucio Ditrolio, Ronald Richard Dudzic, Jr., Kevin Johnsrud
  • Patent number: 10731935
    Abstract: A takedown mechanism for disassembly of a striker-fired pistol, including a takedown release comprising a spring and a pin disposed in the pistol frame adjacent its rear end, the spring to bias the pin towards the barrel end of the frame and disposed against a hard stop on the frame; a takedown bar having a sear contact surface and movable along the longitudinal axis of the frame from a first position to a second position, wherein the takedown release biases the takedown bar towards the barrel end of the frame, wherein, in the first position, the takedown bar is disposed between the takedown release and the slide stop, wherein longitudinal movement of the takedown bar towards the barrel end is limited by the slide stop, wherein, in the second position, the takedown bar is disposed in a forward position toward the barrel end of the frame to cause the sear contact surface on the takedown bar to contact the second leg of the sear to cause the sear to rotate away from the tab of the pistol striker such that the f
    Type: Grant
    Filed: March 19, 2019
    Date of Patent: August 4, 2020
    Assignee: Kimber IP, LLC
    Inventors: Daniel Edward Sapio, Lucio Ditrolio, Ronald Richard Dudzic, Jr., Kevin Johnsrud
  • Publication number: 20200191765
    Abstract: A method of board lumber grading is performed in an industrial environment on a machine learning framework configured as an interface to a machine learning-based deep convolutional network that is trained end-to-end, pixels-to-pixels on semantic segmentation. The method uses deep learning techniques that are applied to semantic segmentation to delineate board lumber characteristics, including their sizes and boundaries.
    Type: Application
    Filed: February 21, 2020
    Publication date: June 18, 2020
    Inventors: Revathy Priyanga Narasimhan, Patrick Freeman, Hayden Michael Aronson, Kevin Johnsrude, Chris Mosbrucker, Dan Robin, Ryan T. Shear, Joseph H. Weintraub, Eric N. Mortensen
  • Patent number: 10571454
    Abstract: A method of board lumber grading is performed in an industrial environment on a machine learning framework configured as an interface to a machine learning-based deep convolutional network that is trained end-to-end, pixels-to-pixels on semantic segmentation. The method uses deep learning techniques that are applied to semantic segmentation to delineate board lumber characteristics, including their sizes and boundaries.
    Type: Grant
    Filed: March 5, 2018
    Date of Patent: February 25, 2020
    Assignee: Lucidyne Technologies, Inc.
    Inventors: Revathy Narasimhan, Patrick Freeman, Hayden Michael Aronson, Kevin Johnsrude, Chris Mosbrucker, Dan Robin, Ryan T. Shear, Joseph H. Weintraub, Eric N. Mortensen
  • Publication number: 20190227049
    Abstract: A method of board lumber (Table 2) grading is performed in an industrial environment on a machine learning framework (12) configured as an interface to a machine learning-based deep convolutional network (20) that is trained end-to-end, pixels-to-pixels on semantic segmentation. The method uses deep learning techniques that are applied to semantic segmentation to delineate board lumber characteristics (Table 1), including their sizes and boundaries.
    Type: Application
    Filed: March 5, 2018
    Publication date: July 25, 2019
    Inventors: Revathy Narasimhan, Patrick Freeman, Hayden Michael Aronson, Kevin Johnsrude, Chris Mosbrucker, Dan Robin, Ryan T. Shear, Joseph H. Weintraub, Eric N. Mortensen
  • Patent number: 8919047
    Abstract: A handle assembly for a door of a vehicle includes a housing, and a grab bar moveably supported by the housing. The grab bar is linearly moveable along a linear path between a retracted position and an extended position. The linear path is disposed on a plane. A motor is attached to the housing, and includes an output rotatable about a rotation axis. The rotation axis is perpendicular to the plane. A scotch yoke mechanism interconnects the output of the motor and the grab bar. The scotch yoke mechanism translates rotational movement of the output into the linear movement of the grab bar to move the grab bar between the extended position and the retracted position.
    Type: Grant
    Filed: August 15, 2012
    Date of Patent: December 30, 2014
    Assignee: GM Global Technology Operations LLC
    Inventors: Kevin Johnsrud, William A. Kokemor, Andrew Ondo, Tony Trinh
  • Publication number: 20140047773
    Abstract: A handle assembly for a door of a vehicle includes a housing, and a grab bar moveably supported by the housing. The grab bar is linearly moveable along a linear path between a retracted position and an extended position. The linear path is disposed on a plane. A motor is attached to the housing, and includes an output rotatable about a rotation axis. The rotation axis is perpendicular to the plane. A scotch yoke mechanism interconnects the output of the motor and the grab bar. The scotch yoke mechanism translates rotational movement of the output into the linear movement of the grab bar to move the grab bar between the extended position and the retracted position.
    Type: Application
    Filed: August 15, 2012
    Publication date: February 20, 2014
    Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC
    Inventors: Kevin Johnsrud, William A. Kokemor, Andrew Ondo, Tony Trinh