MACHINE LEARNING ASSISTED SATELLITE BASED POSITIONING

    公开(公告)号:US20230184961A1

    公开(公告)日:2023-06-15

    申请号:US18107496

    申请日:2023-02-08

    Applicant: Apple Inc.

    CPC classification number: G01S19/428 G06N20/00 G01S19/393

    Abstract: A device implementing a system for estimating device location includes at least one processor configured to receive an estimated position based on a positioning system comprising a Global Navigation Satellite System (GNSS) satellite, and receive a set of parameters associated with the estimated position. The processor is further configured to apply the set of parameters and the estimated position to a machine learning model, the machine learning model having been trained based at least on a position of a receiving device relative to the GNSS satellite. The processor is further configured to provide the estimated position and an output of the machine learning model to a Kalman filter, and provide an estimated device location based on an output of the Kalman filter.

    MODIFYING DEVICE SECURITY STATE WITH SECURE RANGING

    公开(公告)号:US20240406735A1

    公开(公告)日:2024-12-05

    申请号:US18509220

    申请日:2023-11-14

    Applicant: Apple Inc.

    Abstract: The subject technology provides a framework for a trusted device to modify a security state of a target device (e.g., not fully unlocking the target device by activating biometric authentication at the target device) based on a secure ranging operation. The subject technology enables the trusted device to establish a secure and authenticated connection with the target device that is used to activate biometric authentication at the target device. The biometric authentication may fully unlock the target device. The trusted device may be able to activate the biometric authentication at the target device when the trusted device is in an unlocked state, or even when the trusted device is in a locked state so long as less than a threshold amount of time has passed since the trusted device was last unlocked.

    RELOCALIZATION FOR DEVICE FINDING
    4.
    发明公开

    公开(公告)号:US20230394111A1

    公开(公告)日:2023-12-07

    申请号:US18080730

    申请日:2022-12-13

    Applicant: Apple Inc.

    CPC classification number: G06F18/20 G06T7/70

    Abstract: A method is provided that includes at each position of a plurality of positions along a trajectory of a first electronic device within an area: determining a range value corresponding to a distance between the first electronic device and a second electronic device, determining a pose of the first electronic device with respect to a reference coordinate system, and setting and storing an anchor point corresponding to the determined range value and pose. An update to an anchor point set for a current position of the first electronic device is received and the determined pose corresponding to one or more of the set anchor points is updated based on the update to the anchor point set for the current position of the first electronic device. A location of the second electronic device is estimated based on the range values and poses corresponding to the set anchor points.

    MACHINE LEARNING ASSISTED SATELLITE BASED POSITIONING

    公开(公告)号:US20200049837A1

    公开(公告)日:2020-02-13

    申请号:US16536234

    申请日:2019-08-08

    Applicant: Apple Inc.

    Abstract: A device implementing a system for estimating device location includes at least one processor configured to receive an estimated position based on a positioning system comprising a Global Navigation Satellite System (GNSS) satellite, and receive a set of parameters associated with the estimated position. The processor is further configured to apply the set of parameters and the estimated position to a machine learning model, the machine learning model having been trained based at least on a position of a receiving device relative to the GNSS satellite. The processor is further configured to provide the estimated position and an output of the machine learning model to a Kalman filter, and provide an estimated device location based on an output of the Kalman filter.

Patent Agency Ranking