MICROLOCATIONS USING TAGGED DATA
    11.
    发明申请

    公开(公告)号:US20220394101A1

    公开(公告)日:2022-12-08

    申请号:US17496479

    申请日:2021-10-07

    Applicant: Apple Inc.

    Abstract: A semi-supervised machine learning model can provide for classifying an input data point as associated with a particular target location or a particular action. Each data point comprises one or more sensor values from one or more signals emitted by one or more signal sources located within a physical area. A tagged sample set and an untagged sample set are combined to train the machine learning model. Each tagged sample includes a respective data point and a label representing a respective location/action. Each untagged sample includes a data point, but is unlabeled. Once trained, given a current data point, the machine learning model can classify the current data point as associated with a particular location/action, after which a target object (e.g., other device or application to be used) can be predicted.

    Error vector magnitude requirement negotiation for ranging operation

    公开(公告)号:US11265100B2

    公开(公告)日:2022-03-01

    申请号:US16662582

    申请日:2019-10-24

    Applicant: Apple Inc.

    Abstract: Some embodiments of this disclosure include apparatuses and methods for implementing a requirement negotiation for an error vector magnitude (EVM) (or other metrics for measuring transmission signal quality) for ranging and/or positioning operation(s). Some embodiments relate to an electronic device including a transceiver and one or more processors communicatively coupled to the transceiver. The one or more processors transmit, during a negotiation phase of a ranging operation, an initial request frame to a second electronic device, wherein the initial request frame comprises a first indication of an error vector magnitude (EVM) requirement. The one or more processors receive an initial response frame from the second electronic device and determine a second indication of the EVM requirement based at least in part on the received initial response frame. The one or more processors implement a measurement phase of the ranging operation in accordance with the second indication of the EVM requirement.

    Dielectric-loading detection apparatus

    公开(公告)号:US11152970B1

    公开(公告)日:2021-10-19

    申请号:US17028879

    申请日:2020-09-22

    Applicant: Apple Inc.

    Abstract: An apparatus for detecting worn and/or unworn status of a wearable host device includes one or more first antennas, a second antenna, and a radio-frequency (RF) circuit to measure a dielectric loading based on an RF isolation. The second antenna is placed within a portion of the wearable host device that is substantially in contact with the skin of a user, and the RF isolation is between at least one of the one or more first antennas and the second antenna.

    Power saving for non-trigger-based ranging

    公开(公告)号:US11057829B2

    公开(公告)日:2021-07-06

    申请号:US16550508

    申请日:2019-08-26

    Applicant: Apple Inc.

    Abstract: Methods for performing a ranging procedure according to the non-trigger-based protocol may include negotiating timing parameters associated with the ranging procedure, performing a ranging measurement, and transmitting/receiving, after completion of the ranging measurement, a message announcing initiation of another ranging measurement. The timing parameters may indicate a time window in which an initiating device can initiate a subsequent ranging measurement and the message announcing initiation of the second ranging measurement may be received during the time range specified. Timing parameters may indicate a responding device's required minimum and maximum time between ranging measurements. Additional parameters may indicate an initiating device's required minimum and maximum time between ranging measurements. A power savings mode may be entered after the first ranging measurement and during at least a portion of a time period specified by the parameters.

    Time of flight estimation using a convolutional neural network

    公开(公告)号:US10051423B1

    公开(公告)日:2018-08-14

    申请号:US15612553

    申请日:2017-06-02

    Applicant: Apple Inc.

    Abstract: Embodiments herein relate to using a convolutional neural network (CNN) for time-of-flight estimation in a wireless communication system. A wireless device may receive, from a remote device, wireless communications including a first transmission time value associated with the transmission of the wireless communications. The wireless device may perform a coarse time-of-arrival (TOA) estimation on the wireless communications received from the remote device. The coarse TOA estimation may be used to generate an estimated impulse response, which may be input to a CNN associated with the wireless device to calculate a line-of-sight estimate. The wireless device may determine a range between the wireless device and the remote device based on the transmission time value and the line-of-sight estimate.

Patent Agency Ranking