LOCALIZATION VIA MACHINE LEARNING BASED ON PERCEIVED CHANNEL PROPERTIES AND INERTIAL MEASUREMENT UNIT SUPERVISION

    公开(公告)号:US20240372636A1

    公开(公告)日:2024-11-07

    申请号:US18481655

    申请日:2023-10-05

    Abstract: Certain aspects of the present disclosure provide techniques and apparatus for improved machine learning. A sequence of data records is accessed, each data record comprising wireless channel measurements and inertial measurement unit (IMU) data. Known position information corresponding to at least a first data record is accessed. A first sequence of positions is determined by processing the sets of IMU data and known position information using a forward operation. A second sequence of positions is determined by processing the sets of IMU data and known position information using a backward operation. An IMU adjustment parameter is generated using the first and second sequences of positions. A pseudo-label is generated for a second data record using the IMU adjustment parameter and the sets of IMU data. A machine learning model is trained, using the second data record and the pseudo-label, to predict positions using one or more wireless channel measurements.

    ASSISTANCE DATA SELECTION
    12.
    发明公开

    公开(公告)号:US20240361422A1

    公开(公告)日:2024-10-31

    申请号:US18684326

    申请日:2022-09-19

    CPC classification number: G01S5/0236 G01S5/06

    Abstract: An assistance data selection and use method includes: obtaining, at a user equipment, a plurality of assistance data sets each indicating a respective plurality of positioning reference signal resources; selecting, at the user equipment, a desired assistance data set from the plurality of assistance data sets based on positioning performance information; and either: transmitting, from the user equipment, a first positioning reference signal in accordance with the desired assistance data set; or receiving, by the user equipment, a second positioning reference signal in accordance with the desired assistance data set.

    DATA COLLECTION AND TRAINING FOR A NETWORK POSITIONING MODEL

    公开(公告)号:US20240337721A1

    公开(公告)日:2024-10-10

    申请号:US18295817

    申请日:2023-04-04

    CPC classification number: G01S5/02524 G01S5/0236 H04L5/0048 H04W64/00

    Abstract: A network node may receive a set of sounding reference signals (SRSs) from a wireless device. The network node may measure the set of SRSs. The network node may output at least one of a set of estimated positioning labels, training associated information, or labeling assistance information associated with the set of measured SRSs for a positioning model. In one example, the network node may output the data by training the positioning model based on at least one of the set of estimated positioning labels, the training associated information, the labeling assistance information, or the set of measured SRSs. In another example, the network node may output the data by transmitting, for a network entity, at least one of the set of estimated positioning labels, the training associated information, or the set of measured SRSs for training the positioning model.

    MULTI-HYPOTHESIS MEASUREMENT CONFIGURATION IN RF SENSING

    公开(公告)号:US20240323709A1

    公开(公告)日:2024-09-26

    申请号:US18186692

    申请日:2023-03-20

    CPC classification number: H04W24/02 H04W24/10

    Abstract: Apparatuses and methods for multi-hypothesis measurement configuration in RF sensing are described. An apparatus is configured to receive, from a sensing entity, a sensing configuration, wherein the sensing configuration indicates a total number of sensing hypotheses and at least a first sensing hypothesis and a second sensing hypothesis that is different from the first sensing hypothesis; The apparatus is also configured to measure a first set of sensing measurement data associated with the first sensing hypothesis and a second set of sensing measurement data associated with the second sensing hypothesis. The apparatus is further configured to transmit, for the sensing entity, at least one of: (1) the first set of sensing measurement data and the second set of sensing measurement data, or (2) an indication of the first sensing hypothesis and the second sensing hypothesis.

    MAP INFORMATION SIGNALING FOR POSITIONING AND RADIO FREQUENCY SENSING

    公开(公告)号:US20240276419A1

    公开(公告)日:2024-08-15

    申请号:US18169770

    申请日:2023-02-15

    CPC classification number: H04W64/00 G01S7/006 G01S13/003

    Abstract: In an aspect, a UE may transmit, for a network node, a request for map information for at least one of a positioning session or an RF sensing session. The UE may receive, from the network node, a response including the map information. The UE may perform a set of measurements for at least one of the positioning session or the RF sensing session based on the map information. In another aspect, a first network node may receive at least one of a set of positioning measurements or a set of sensing measurements. The first network node may receive map information from a second network node. The first network node may calculate at least one of a first positioning state of a target entity or a first sensing state based on the map information and at least one of the set of positioning measurements or the set of sensing measurements.

Patent Agency Ranking