Patents by Inventor Vedran Skarica
Vedran Skarica 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: 11721235Abstract: A method of simulating a quadcopter includes recording camera output for one or more video cameras under constant conditions and subtracting a constant signal from the recorded camera output to obtain a camera noise recording. Simulated camera noise is generated from the camera noise recording and is added to a plurality of simulated camera outputs of a quadcopter simulator to generate noise-added simulated camera outputs. The noise-added simulated camera outputs are sent to an Artificial Intelligence (AI) controller coupled to the quadcopter simulator for the AI controller to use to pilot a simulated quadcopter of the quadcopter simulator.Type: GrantFiled: March 21, 2019Date of Patent: August 8, 2023Assignee: Performance Drone Works LLCInventor: Vedran Skarica
-
Patent number: 11455336Abstract: A method of simulating a quadcopter includes testing a plurality of quadcopter components at a plurality of operating conditions to generate one or more lookup tables for characteristics of the quadcopter components. The lookup tables are stored for quadcopter component simulation in a quadcopter simulator. When a simulated input value for a simulated quadcopter component is received in the simulator lookup table, entries corresponding to the simulated input value are read from the lookup table and simulated quadcopter component output is generated. Simulated quadcopter output to a flight controller is generated according to the simulated quadcopter component output from one or more entries of one or more lookup tables.Type: GrantFiled: March 21, 2019Date of Patent: September 27, 2022Assignee: Performance Drone Works LLCInventors: Vedran Skarica, Ryan Gury, Eduardo Dias da Costa
-
Patent number: 11409291Abstract: An autonomous quadcopter has four motors, each motor coupled to a corresponding propeller and a flight controller coupled to the four motors to provide input to the four motors to control flight. The autonomous quadcopter also has a plurality of cameras and an Artificial Intelligence (AI) controller coupled to the plurality of cameras to receive input from the plurality of cameras, determine a flightpath for the autonomous quadcopter according to the input from the plurality of cameras, and provide commands to the flight controller to direct the flight controller to follow the flightpath.Type: GrantFiled: March 21, 2019Date of Patent: August 9, 2022Assignee: Performance Drone Works LLCInventors: Jordan Restifo, Ryan Gury, Vedran Skarica
-
Patent number: 11312506Abstract: A method of debugging quadcopter piloting code includes coupling an Artificial Intelligence (AI) controller configured with AI piloting code to a workstation having a quadcopter simulator and initiating piloting of a simulated quadcopter of the quadcopter simulator by the AI piloting code of the AI controller. Operations of the quadcopter simulator are logged, and communications timestamped. Subsequently, in response to an AI piloting code event at an event time, the event time is determined from a timestamped communication and a logged operation of the quadcopter simulator having a timestamp corresponding to the event time is found. The quadcopter simulator is rewound to at least the logged operation and one or more operations of the quadcopter simulator and the AI piloting code are stepped through to identify AI piloting code errors relating to the AI piloting code event.Type: GrantFiled: March 21, 2019Date of Patent: April 26, 2022Assignee: Performance Drone Works LLCInventors: Jordan Restifo, Vedran Skarica
-
Publication number: 20200302822Abstract: A method of simulating a quadcopter includes recording camera output for one or more video cameras under constant conditions and subtracting a constant signal from the recorded camera output to obtain a camera noise recording. Simulated camera noise is generated from the camera noise recording and is added to a plurality of simulated camera outputs of a quadcopter simulator to generate noise-added simulated camera outputs. The noise-added simulated camera outputs are sent to an Artificial Intelligence (AI) controller coupled to the quadcopter simulator for the AI controller to use to pilot a simulated quadcopter of the quadcopter simulator.Type: ApplicationFiled: March 21, 2019Publication date: September 24, 2020Applicant: DRONE RACING LEAGUE, INC.Inventor: Vedran Skarica
-
Publication number: 20200302026Abstract: An apparatus includes a quadcopter simulator coupled to an Artificial Intelligence (AI) controller. The quadcopter controller is configured to receive quadcopter flight control commands and to generate simulated sensor output and simulated camera output for a plurality of stereoscopic cameras of a simulated quadcopter. The AI controller is configured to receive the simulated sensor and camera output from the quadcopter simulator, determine a flight path for the simulated quadcopter according to the simulated sensor and camera output, generate the quadcopter flight control commands according to the flight path, and provide the quadcopter flight control commands to the quadcopter simulator.Type: ApplicationFiled: March 21, 2019Publication date: September 24, 2020Applicant: DRONE RACING LEAGUE, INC.Inventors: Jordan Restifo, Vedran Skarica, Chris Miller
-
Publication number: 20200301971Abstract: A method of simulating a quadcopter includes testing a plurality of quadcopter components at a plurality of operating conditions to generate one or more lookup tables for characteristics of the quadcopter components. The lookup tables are stored for quadcopter component simulation in a quadcopter simulator. When a simulated input value for a simulated quadcopter component is received in the simulator lookup table, entries corresponding to the simulated input value are read from the lookup table and simulated quadcopter component output is generated. Simulated quadcopter output to a flight controller is generated according to the simulated quadcopter component output from one or more entries of one or more lookup tables.Type: ApplicationFiled: March 21, 2019Publication date: September 24, 2020Applicant: DRONE RACING LEAGUE, INC.Inventors: Vedran Skarica, Ryan Gury, Eduardo Dias da Costa
-
Publication number: 20200301427Abstract: An autonomous quadcopter has four motors, each motor coupled to a corresponding propeller and a flight controller coupled to the four motors to provide input to the four motors to control flight. The autonomous quadcopter also has a plurality of cameras and an Artificial Intelligence (AI) controller coupled to the plurality of cameras to receive input from the plurality of cameras, determine a flightpath for the autonomous quadcopter according to the input from the plurality of cameras, and provide commands to the flight controller to direct the flight controller to follow the flightpath.Type: ApplicationFiled: March 21, 2019Publication date: September 24, 2020Applicant: DRONE RACING LEAGUE, INC.Inventors: Jordan Restifo, Ryan Gury, Vedran Skarica
-
Publication number: 20200299001Abstract: A method of debugging quadcopter piloting code includes coupling an Artificial Intelligence (AI) controller configured with AI piloting code to a workstation having a quadcopter simulator and initiating piloting of a simulated quadcopter of the quadcopter simulator by the AI piloting code of the AI controller. Operations of the quadcopter simulator are logged, and communications timestamped. Subsequently, in response to an AI piloting code event at an event time, the event time is determined from a timestamped communication and a logged operation of the quadcopter simulator having a timestamp corresponding to the event time is found. The quadcopter simulator is rewound to at least the logged operation and one or more operations of the quadcopter simulator and the AI piloting code are stepped through to identify AI piloting code errors relating to the AI piloting code event.Type: ApplicationFiled: March 21, 2019Publication date: September 24, 2020Applicant: DRONE RACING LEAGUE, INC.Inventors: Jordan Restifo, Vedran Skarica