Patents by Inventor James Robert FERLEZ

James Robert FERLEZ 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).

  • Safely scheduling offloading of computing tasks for an autonomous vehicle
    Patent number: 12565232
    Abstract: A local computing device of a vehicle receives a stream of sensor data from one or sensors of the vehicle. If a remote computing device is estimated to process the stream of sensor data and provide driving instructions within a maximum acceptable wait time, then the local computing device sends a request to the remote computing device to process the stream of sensor data and provide driving instructions. If the processing is estimated to meet or exceed the maximum acceptable wait time, then the local computing device uses a locally executed neural network to determine driving instructions. The driving instructions received either from the remote computing or from the local neural network are sent to an autonomous driving system of the vehicle. Offloading processing the sensor data to the remote computing device may result in the local computing device consuming less energy.
    Type: Grant
    Filed: April 30, 2024
    Date of Patent: March 3, 2026
    Assignee: The Regents of the University of California
    Inventors: Mohammad Abdullah Al Faruque, Yasser Shoukry Ahmed Sakr, Mohanad Mohamed Abdelmagid Abdelkhale Odema, James Robert Ferlez
  • SAFELY SCHEDULING OFFLOADING OF COMPUTING TASKS FOR AN AUTONOMOUS VEHICLE
    Publication number: 20240367678
    Abstract: A local computing device of a vehicle receives a stream of sensor data from one or sensors of the vehicle. If a remote computing device is estimated to process the stream of sensor data and provide driving instructions within a maximum acceptable wait time, then the local computing device sends a request to the remote computing device to process the stream of sensor data and provide driving instructions. If the processing is estimated to meet or exceed the maximum acceptable wait time, then the local computing device uses a locally executed neural network to determine driving instructions. The driving instructions received either from the remote computing or from the local neural network are sent to an autonomous driving system of the vehicle. Offloading processing the sensor data to the remote computing device may result in the local computing device consuming less energy.
    Type: Application
    Filed: April 30, 2024
    Publication date: November 7, 2024
    Applicant: University of California Irvine
    Inventors: Mohammad Abdullah Al Faruque, Yasser Shoukry Ahmed SAKR, Mohanad Mohamed Abdelmagid Abdelkhalek Odema, James Robert FERLEZ