US-12628110-B2 - Bandwidth aggregation for radio frequency fingerprint positioning

Abstract

In an aspect, a method of wireless communication performed by a user equipment (UE) includes measuring a plurality of different bandwidth segments of a reference signal (RS) over a corresponding plurality of different RS occasions during a positioning session to obtain a plurality of radio frequency fingerprint positioning (RFFP) measurements corresponding to the plurality of different bandwidth segments; aggregating the plurality of RFFP measurements to provide at least one aggregated RFFP measurement; and applying a positioning model to the at least one aggregated RFFP measurement to obtain an estimate of one or more positioning parameters associated with a location of the UE.

Inventors

• Mohammed Ali Mohammed Hirzallah
• Marwen Zorgui
• Srinivas Yerramalli

Assignees

• QUALCOMM INCORPORATED

Dates

Publication Date

20260512

Application Date

20221014

Claims (17)

1. 1 . A method of wireless communication performed by a user equipment (UE), comprising: measuring a plurality of different bandwidth segments of a reference signal (RS) over a corresponding plurality of different RS occasions during a positioning session to obtain a plurality of radio frequency fingerprint positioning (RFFP) measurements corresponding to the plurality of different bandwidth segments; and applying a latent feature machine learning (ML) model to each of the plurality of RFFP measurements to obtain a plurality of latent feature representations corresponding to the plurality of RFFP measurements, wherein the UE stores a plurality of latent feature ML models, and at least two or more of the latent feature ML models of the plurality of latent feature ML models provide latent feature representations having different dimensionalities.
2. 2 . The method of claim 1 , wherein: the latent feature ML model compresses each RFFP measurement to provide a corresponding latent feature representation of reduced dimensionality.
3. 3 . The method of claim 1 , further comprising: applying a positioning model to the plurality of latent feature representations to obtain one or more positioning parameters associated with a location of the UE.
4. 4 . The method of claim 3 , wherein the one or more positioning parameters comprise: the location of the UE; one or more positioning coordinates associated with the location of the UE; one or more positioning measurements associated with the location of the UE; or any combination thereof.
5. 5 . The method of claim 3 , wherein: the positioning model fuses the plurality of latent feature representations to obtain the one or more positioning parameters.
6. 6 . The method of claim 1 , further comprising: transmitting, to a network server, an indication of a latent feature model identifier corresponding to the latent feature ML model applied to each of the plurality of RFFP measurements; a data size associated with individual latent feature representations provided by the latent feature ML model; a dimensionality associated with individual latent feature representations provided by the latent feature ML model; a bandwidth size associated with individual bandwidth segments used to measure the plurality of different bandwidth segments; one or more timestamps corresponding to measurements of the plurality of different bandwidth segments; one or more timestamps corresponding to obtaining the plurality of latent feature representations; the plurality of latent feature representations; or any combination thereof.
7. 7 . The method of claim 1 , further comprising: receiving, from a network server, assistance data including an indication of a latent feature model of the plurality of latent feature ML models that is to be applied, during the positioning session, as the latent feature model to the plurality of RFFP measurements.
8. 8 . The method of claim 1 , further comprising: transmitting, to a network server, a capability of the UE to provide latent feature representations having different data dimensionalities.
9. 9 . The method of claim 1 , further comprising: receiving, from a network server, assistance data including an indication of a maximum time gap allowable between measurements of successive bandwidth segments of the plurality of different bandwidth segments; an indication of RS occasions during which the plurality of different bandwidth segments of the RS are transmitted during the positioning session; an indication of a maximum time gap allowable between successive RS measured by the UE; or any combination thereof.
10. 10 . The method of claim 9 , wherein the assistance data includes the indication of the maximum time gap allowable between measurements of successive bandwidth segments, the method further comprising: measuring the plurality of different bandwidth segments during less than all of the indicated RS occasions based on successive RS occasions being measured by the UE within the maximum time gap.
11. 11 . The method of claim 1 , further comprising: transmitting, to a network server, a capability message including an indication of a bandwidth of a largest bandwidth segment of the RS that the UE can measure during a single RS occasion; an indication of a largest dimensionality of a latent feature representation that may be processed at the UE; an indication of a number of latent feature representations that may be stored at the UE for a given dimensionality of the latent feature representations; an indication of a buffer size available for storage of latent feature representations; or any combination thereof.
12. 12 . A user equipment (UE), comprising: a memory; at least one transceiver; and at least one processor communicatively coupled to the memory and the at least one transceiver, the at least one processor configured to: measure a plurality of different bandwidth segments of a reference signal (RS) over a corresponding plurality of different RS occasions during a positioning session to obtain a plurality of radio frequency fingerprint positioning (RFFP) measurements corresponding to the plurality of different bandwidth segments; and apply a latent feature machine learning (ML) model to each of the plurality of RFFP measurements to obtain a plurality of latent feature representations corresponding to the plurality of RFFP measurements, wherein the UE stores a plurality of latent feature ML models, and at least two or more of the latent feature ML models of the plurality of latent feature ML models provide latent feature representations having different dimensionalities.
13. 13 . The UE of claim 12 , wherein: the latent feature ML model compresses each RFFP measurement to provide a corresponding latent feature representation of reduced dimensionality.
14. 14 . The UE of claim 12 , wherein the at least one processor is further configured to: apply a positioning model to the plurality of latent feature representations to obtain one or more positioning parameters associated with a location of the UE.
15. 15 . The UE of claim 14 , wherein the one or more positioning parameters comprise: the location of the UE; one or more positioning coordinates associated with the location of the UE; one or more positioning measurements associated with the location of the UE; or any combination thereof.
16. 16 . The UE of claim 14 , wherein: the positioning model fuses the plurality of latent feature representations to obtain the one or more positioning parameters.
17. 17 . The UE of claim 12 , wherein the at least one processor is further configured to: transmit, to a network server, an indication of a latent feature model identifier corresponding to the latent feature ML model applied to each of the plurality of RFFP measurements; a data size associated with individual latent feature representations provided by the latent feature ML model; a dimensionality associated with individual latent feature representations provided by the latent feature ML model; a bandwidth size associated with individual bandwidth segments used to measure the plurality of different bandwidth segments; one or more timestamps corresponding to measurements of the plurality of different bandwidth segments; one or more timestamps corresponding to obtaining the plurality of latent feature representations; the plurality of latent feature representations; or any combination thereof.

Description

BACKGROUND OF THE DISCLOSURE 1. Field of the Disclosure Aspects of the disclosure relate generally to wireless communications. 2. Description of the Related Art Wireless communication systems have developed through various generations, including a first-generation analog wireless phone service (1G), a second-generation (2G) digital wireless phone service (including interim 2.5G and 2.75G networks), a third-generation (3G) high speed data, Internet-capable wireless service and a fourth-generation (4G) service (e.g., Long Term Evolution (LTE) or WiMax). There are presently many different types of wireless communication systems in use, including cellular and personal communications service (PCS) systems. Examples of known cellular systems include the cellular analog advanced mobile phone system (AMPS), and digital cellular systems based on code division multiple access (CDMA), frequency division multiple access (FDMA), time division multiple access (TDMA), the Global System for Mobile communications (GSM), etc. A fifth generation (5G) wireless standard, referred to as New Radio (NR), enables higher data transfer speeds, greater numbers of connections, and better coverage, among other improvements. The 5G standard, according to the Next Generation Mobile Networks Alliance, is designed to provide higher data rates as compared to previous standards, more accurate positioning (e.g., based on reference signals for positioning (RS-P), such as downlink, uplink, or sidelink positioning reference signals (PRS)), and other technical enhancements. These enhancements, as well as the use of higher frequency bands, advances in PRS processes and technology, and high-density deployments for 5G, enable highly accurate 5G-based positioning. SUMMARY The following presents a simplified summary relating to one or more aspects disclosed herein. Thus, the following summary should not be considered an extensive overview relating to all contemplated aspects, nor should the following summary be considered to identify key or critical elements relating to all contemplated aspects or to delineate the scope associated with any particular aspect. Accordingly, the following summary has the sole purpose to present certain concepts relating to one or more aspects relating to the mechanisms disclosed herein in a simplified form to precede the detailed description presented below. In an aspect, a method of wireless communication performed by a user equipment (UE) includes measuring a plurality of different bandwidth segments of a reference signal (RS) over a corresponding plurality of different RS occasions during a positioning session to obtain a plurality of radio frequency fingerprint positioning (RFFP) measurements corresponding to the plurality of different bandwidth segments; aggregating the plurality of RFFP measurements to provide at least one aggregated RFFP measurement; and applying a positioning model to the at least one aggregated RFFP measurement to obtain an estimate of one or more positioning parameters associated with a location of the UE. In an aspect, a method of wireless communication performed by a user equipment (UE) includes measuring a plurality of different bandwidth segments of a reference signal (RS) over a corresponding plurality of different RS occasions during a positioning session to obtain a plurality of radio frequency fingerprint positioning (RFFP) measurements corresponding to the plurality of different bandwidth segments; and applying a latent feature machine learning (ML) model to each of the plurality of RFFP measurements to obtain a plurality of latent feature representations corresponding to the plurality of RFFP measurements. In an aspect, a method of wireless communication performed by a network server includes receiving, from a user equipment (UE), a plurality of latent feature representations corresponding to a plurality of radio frequency fingerprint positioning (RFFP) measurements obtained by the UE during a positioning session, wherein the plurality of latent feature representations are based on measurements, by the UE, of a plurality of different bandwidth segments of a reference signal (RS) over a corresponding plurality of different RS occasions during the positioning session; and applying a positioning model to the plurality of latent feature representations to obtain one or more positioning parameters associated with a location of the UE. In an aspect, a user equipment (UE) includes a memory; at least one transceiver; and at least one processor communicatively coupled to the memory and the at least one transceiver, the at least one processor configured to: measure a plurality of different bandwidth segments of a reference signal (RS) over a corresponding plurality of different RS occasions during a positioning session to obtain a plurality of radio frequency fingerprint positioning (RFFP) measurements corresponding to the plurality of different bandwidth segments; aggregate the plurality of RFFP