Patents by Inventor John George Karvounis
John George Karvounis 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: 11960011Abstract: A computer implemented method of validating an output from a GNSS at a receiver including a fusion system comprising location sensors. A location estimate and a location error estimate are computed. A navigation update including a sensor location estimate and sensor location error estimate is also computed with the fusion system based on sensor measurements from the location sensors. A determination is made as to whether or not GNSS filters should be applied based at least on the location estimate, the sensor location estimate, and the sensor location error estimate. When GNSS filters should be applied, the location estimate and/or the location error estimate may be adjusted or rejected and a new navigation update may be computed with the fusion system based on the adjustment or rejection. When the GNSS filters should not be applied, the new navigation update is computed with the location estimate and the location error estimate.Type: GrantFiled: February 3, 2021Date of Patent: April 16, 2024Assignee: TRX SYSTEMS, INC.Inventors: John George Karvounis, Benjamin Edward Funk, Jonathan Morton Fetter-Degges, Carole Ann Teolis
-
Patent number: 11140379Abstract: LK-SURF, Robust Kalman Filter, HAR-SLAM, and Landmark Promotion SLAM methods are disclosed. LK-SURF is an image processing technique that combines Lucas-Kanade feature tracking with Speeded-Up Robust Features to perform spatial and temporal tracking using stereo images to produce 3D features can be tracked and identified. The Robust Kalman Filter is an extension of the Kalman Filter algorithm that improves the ability to remove erroneous observations using Principal Component Analysis and the X84 outlier rejection rule. Hierarchical Active Ripple SLAM is a new SLAM architecture that breaks the traditional state space of SLAM into a chain of smaller state spaces, allowing multiple tracked objects, multiple sensors, and multiple updates to occur in linear time with linear storage with respect to the number of tracked objects, landmarks, and estimated object locations. In Landmark Promotion SLAM, only reliable mapped landmarks are promoted through various layers of SLAM to generate larger maps.Type: GrantFiled: September 2, 2020Date of Patent: October 5, 2021Assignee: TRX SYSTEMS, INC.Inventor: John George Karvounis
-
Publication number: 20210239848Abstract: A computer implemented method of validating an output from a GNSS at a receiver including a fusion system comprising location sensors. A location estimate and a location error estimate are computed. A navigation update including a sensor location estimate and sensor location error estimate is also computed with the fusion system based on sensor measurements from the location sensors. A determination is made as to whether or not GNSS filters should be applied based at least on the location estimate, the sensor location estimate, and the sensor location error estimate. When GNSS filters should be applied, the location estimate and/or the location error estimate may be adjusted or rejected and a new navigation update may be computed with the fusion system based on the adjustment or rejection. When the GNSS filters should not be applied, the new navigation update is computed with the location estimate and the location error estimate.Type: ApplicationFiled: February 3, 2021Publication date: August 5, 2021Inventors: John George Karvounis, Benjamin Edward Funk, Jonathan Morton Fetter-Degges, Carole Ann Teolis
-
Publication number: 20200404245Abstract: LK-SURF, Robust Kalman Filter, HAR-SLAM, and Landmark Promotion SLAM methods are disclosed. LK-SURF is an image processing technique that combines Lucas-Kanade feature tracking with Speeded-Up Robust Features to perform spatial and temporal tracking using stereo images to produce 3D features can be tracked and identified. The Robust Kalman Filter is an extension of the Kalman Filter algorithm that improves the ability to remove erroneous observations using Principal Component Analysis and the X84 outlier rejection rule. Hierarchical Active Ripple SLAM is a new SLAM architecture that breaks the traditional state space of SLAM into a chain of smaller state spaces, allowing multiple tracked objects, multiple sensors, and multiple updates to occur in linear time with linear storage with respect to the number of tracked objects, landmarks, and estimated object locations. In Landmark Promotion SLAM, only reliable mapped landmarks are promoted through various layers of SLAM to generate larger maps.Type: ApplicationFiled: September 2, 2020Publication date: December 24, 2020Inventor: John George Karvounis
-
Patent number: 10805595Abstract: The present invention relates to LK-SURF, Robust Kalman Filter, HAR-SLAM, and Landmark Promotion SLAM methods. LK-SURF is an image processing technique that combines Lucas-Kanade feature tracking with Speeded-Up Robust Features to perform spatial and temporal tracking using stereo images to produce 3D features can be tracked and identified. The Robust Kalman Filter is an extension of the Kalman Filter algorithm that improves the ability to remove erroneous observations using Principal Component Analysis and the X84 outlier rejection rule. Hierarchical Active Ripple SLAM is a new SLAM architecture that breaks the traditional state space of SLAM into a chain of smaller state spaces, allowing multiple tracked objects, multiple sensors, and multiple updates to occur in linear time with linear storage with respect to the number of tracked objects, landmarks, and estimated object locations.Type: GrantFiled: June 14, 2018Date of Patent: October 13, 2020Assignee: TRX SYSTEMS, INC.Inventor: John George Karvounis
-
Patent number: 10750155Abstract: LK-SURF, Robust Kalman Filter, HAR-SLAM, and Landmark Promotion SLAM methods are disclosed. LK-SURF is an image processing technique that combines Lucas-Kanade feature tracking with Speeded-Up Robust Features to perform spatial and temporal tracking using stereo images to produce 3D features can be tracked and identified. The Robust Kalman Filter is an extension of the Kalman Filter algorithm that improves the ability to remove erroneous observations using Principal Component Analysis and the X84 outlier rejection rule. Hierarchical Active Ripple SLAM is a new SLAM architecture that breaks the traditional state space of SLAM into a chain of smaller state spaces, allowing multiple tracked objects, multiple sensors, and multiple updates to occur in linear time with linear storage with respect to the number of tracked objects, landmarks, and estimated object locations. In Landmark Promotion SLAM, only reliable mapped landmarks are promoted through various layers of SLAM to generate larger maps.Type: GrantFiled: June 14, 2018Date of Patent: August 18, 2020Assignee: TRX SYSTEMS, INC.Inventor: John George Karvounis
-
Publication number: 20190007674Abstract: LK-SURF, Robust Kalman Filter, HAR-SLAM, and Landmark Promotion SLAM methods are disclosed. LK-SURF is an image processing technique that combines Lucas-Kanade feature tracking with Speeded-Up Robust Features to perform spatial and temporal tracking using stereo images to produce 3D features can be tracked and identified. The Robust Kalman Filter is an extension of the Kalman Filter algorithm that improves the ability to remove erroneous observations using Principal Component Analysis and the X84 outlier rejection rule. Hierarchical Active Ripple SLAM is a new SLAM architecture that breaks the traditional state space of SLAM into a chain of smaller state spaces, allowing multiple tracked objects, multiple sensors, and multiple updates to occur in linear time with linear storage with respect to the number of tracked objects, landmarks, and estimated object locations. In Landmark Promotion SLAM, only reliable mapped landmarks are promoted through various layers of SLAM to generate larger maps.Type: ApplicationFiled: June 14, 2018Publication date: January 3, 2019Inventor: John George Karvounis
-
Publication number: 20190007673Abstract: LK-SURF, Robust Kalman Filter, HAR-SLAM, and Landmark Promotion SLAM methods are disclosed. LK-SURF is an image processing technique that combines Lucas-Kanade feature tracking with Speeded-Up Robust Features to perform spatial and temporal tracking using stereo images to produce 3D features can be tracked and identified. The Robust Kalman Filter is an extension of the Kalman Filter algorithm that improves the ability to remove erroneous observations using Principal Component Analysis and the X84 outlier rejection rule. Hierarchical Active Ripple SLAM is a new SLAM architecture that breaks the traditional state space of SLAM into a chain of smaller state spaces, allowing multiple tracked objects, multiple sensors, and multiple updates to occur in linear time with linear storage with respect to the number of tracked objects, landmarks, and estimated object locations. In Landmark Promotion SLAM, only reliable mapped landmarks are promoted through various layers of SLAM to generate larger maps.Type: ApplicationFiled: June 14, 2018Publication date: January 3, 2019Inventor: John George Karvounis
-
Patent number: 10027952Abstract: LK-SURF, Robust Kalman Filter, HAR-SLAM, and Landmark Promotion SLAM methods are disclosed. LK-SURF is an image processing technique that combines Lucas-Kanade feature tracking with Speeded-Up Robust Features to perform spatial and temporal tracking using stereo images to produce 3D features can be tracked and identified. The Robust Kalman Filter is an extension of the Kalman Filter algorithm that improves the ability to remove erroneous observations using Principal Component Analysis and the X84 outlier rejection rule. Hierarchical Active Ripple SLAM is a new SLAM architecture that breaks the traditional state space of SLAM into a chain of smaller state spaces, allowing multiple tracked objects, multiple sensors, and multiple updates to occur in linear time with linear storage with respect to the number of tracked objects, landmarks, and estimated object locations. In Landmark Promotion SLAM, only reliable mapped landmarks are promoted through various layers of SLAM to generate larger maps.Type: GrantFiled: August 3, 2012Date of Patent: July 17, 2018Assignee: TRX SYSTEMS, INC.Inventor: John George Karvounis
-
Publication number: 20150304634Abstract: LK-SURF, Robust Kalman Filter, HAR-SLAM, and Landmark Promotion SLAM methods are disclosed. LK-SURF is an image processing technique that combines Lucas-Kanade feature tracking with Speeded-Up Robust Features to perform spatial and temporal tracking using stereo images to produce 3D features can be tracked and identified. The Robust Kalman Filter is an extension of the Kalman Filter algorithm that improves the ability to remove erroneous observations using Principal Component Analysis and the X84 outlier rejection rule. Hierarchical Active Ripple SLAM is a new SLAM architecture that breaks the traditional state space of SLAM into a chain of smaller state spaces, allowing multiple tracked objects, multiple sensors, and multiple updates to occur in linear time with linear storage with respect to the number of tracked objects, landmarks, and estimated object locations. In Landmark Promotion SLAM, only reliable mapped landmarks are promoted through various layers of SLAM to generate larger maps.Type: ApplicationFiled: August 3, 2012Publication date: October 22, 2015Inventor: John George Karvounis