Beam-based machine learning-enabled RF Fingerprint (RFFP) positioning

Abstract

Various aspects presented herein may enable an ML module to associate an RF fingerprint with a beam direction and / or a beam characteristic to improve uniqueness of the RF fingerprint. In one aspect, a network entity may receive a plurality of first RF fingerprints from one or more wireless devices, each of the plurality of first RF fingerprints being associated with at least one directional characteristic and a location. The network entity may receive a request to determine a location of the UE based on at least one second RF fingerprint associated with or captured by the UE. The network entity may estimate the location of the UE based at least in part on matching the at least one second RF fingerprint with at least one RF fingerprint of the plurality of first RF fingerprints.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of U.S. patent application serial number 17 / 457,718, filed on December 6, 2021, entitled “BEAM-BASED MACHINE LEARNING-ENABLED RFFP POSITIONING,” which is expressly incorporated herein by reference in its entirety. Technical Field

[0003] The present disclosure relates generally to communication systems and, more particularly, to wireless communications related to positioning. Background Art

[0004] Wireless communication systems are widely deployed to provide a variety of telecommunication services, such as telephony, video, data, messaging, and broadcast. Typical wireless communication systems may employ multiple access technologies capable of supporting communication with multiple users by sharing available system resources. Examples of such multiple access technologies include code division multiple access (CDMA) systems, time division multiple access (TDMA) systems, frequency division multiple access (FDMA) systems, orthogonal frequency division multiple access (OFDMA) systems, single carrier frequency division multiple access (SC-FDMA) systems, and time division synchronous code division multiple access (TD-SCDMA) systems.

[0005] These multiple access technologies have been adopted in various telecommunication standards to provide a common protocol that enables different wireless devices to communicate at city, country, region, and even global levels. An example telecommunication standard is 5G New Radio (NR). 5G NR is part of the continuous mobile broadband evolution promulgated by the Third Generation Partnership Project (3GPP) to meet new requirements associated with latency, reliability, security, scalability (e.g., with the Internet of Things (IoT)) and other requirements. 5G NR includes services associated with enhanced mobile broadband (eMBB), massive machine type communication (mMTC), and ultra-reliable low latency communication (URLLC). Certain aspects of 5G NR may be based on 4G Long Term Evolution (LTE) standards. It is necessary to further improve 5G NR technology. In addition, these improvements may also be applicable to other multiple access technologies and telecommunication standards that employ these technologies.

[0006] Some communication systems may also support a variety of cellular network-based positioning technologies, in which the geographic location of a wireless device may be determined based on measuring radio signals exchanged between the wireless device and other wireless devices. For example, the distance between the wireless device and a transmission reception point (TRP) may be estimated based on the time it takes for a reference signal (e.g., a positioning reference signal (PRS)) transmitted from the TRP to reach the wireless device. Other examples of cellular network-based positioning technologies may include downlink-based, uplink-based, and / or downlink- and uplink-based positioning methods. Summary of the invention

[0007] A simplified summary of one or more aspects is presented below in order to provide a basic understanding of these aspects. This summary is not an extensive overview of all contemplated aspects, and is neither intended to identify key or important elements of all aspects, nor to describe the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to a more detailed description presented later.

[0008] In one aspect of the present disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus receives a plurality of first radio frequency (RF) fingerprints from one or more wireless devices, each of the plurality of first RF fingerprints being associated with at least one directional feature and a location. The apparatus receives a request to determine a location of a user equipment (UE) based on at least one second RF fingerprint associated with the UE or captured by the UE. The apparatus estimates the location of the UE based at least in part on matching the at least one second RF fingerprint with at least one RF fingerprint of the plurality of first RF fingerprints.

[0009] To achieve the foregoing and related ends, one or more aspects include the features fully described below and particularly pointed out in the claims. The following description and the accompanying drawings set forth in detail some illustrative features of one or more aspects. However, these features are merely indicative of some of the various ways in which the principles of the various aspects may be employed, and this specification is intended to include all such aspects and their equivalents. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 is a diagram illustrating an example of a wireless communication system and an access network.

[0011] Figure 2A is a diagram illustrating an example of a first frame according to various aspects of the present disclosure.

[0012] Figure 2B is a diagram illustrating an example of DL channels within a subframe according to various aspects of the present disclosure.

[0013] Figure 2Cis a diagram illustrating an example of a second frame according to various aspects of the present disclosure.

[0014] Figure 2D is a diagram illustrating an example of UL channels within a subframe according to various aspects of the present disclosure.

[0015] Figure 3 is a diagram illustrating an example of a base station and a user equipment (UE) in an access network.

[0016] Figure 4 is a diagram illustrating an example of UE positioning based on reference signal measurement according to various aspects of the present disclosure.

[0017] Figure 5A is a diagram illustrating an example of a downlink positioning reference signal (DL-PRS) transmitted from multiple transmission reception points (TRPs) according to various aspects of the present disclosure.

[0018] Figure 5B is a diagram illustrating an example of an uplink sounding reference signal (UL-SRS) transmitted from a UE according to various aspects of the present disclosure.

[0019] Figure 6 is a diagram illustrating an example of estimating a UE's location based on multiple round trip time (RTT) measurements from multiple TRPs in accordance with various aspects of the present disclosure.

[0020] Figure 7 is a diagram illustrating an example of machine learning (ML) location training and inference for radio frequency fingerprinting (RFFP) in accordance with various aspects of the present disclosure.

[0021] Figure 8 is a diagram illustrating an example ML module according to various aspects of the present disclosure.

[0022] Fig. 9 is a diagram illustrating an example directional radio frequency (RF) fingerprint in accordance with various aspects of the present disclosure.

[0023] Fig.10 is a diagram illustrating example beam pairs in accordance with various aspects of the present disclosure.

[0024] Fig.11A is a diagram illustrating example RF features in accordance with various aspects of the present disclosure.

[0025] Fig. 11B is a diagram illustrating example RF features in accordance with various aspects of the present disclosure.

[0026] Fig. 11C is a diagram illustrating example RF features in accordance with various aspects of the present disclosure.

[0027] Fig.12is a diagram illustrating an example directional RF fingerprint with compression in accordance with various aspects of the present disclosure.

[0028] Fig.13 is a diagram illustrating an example directional RF fingerprint based on the strongest beam pair in accordance with various aspects of the present disclosure.

[0029] Fig.14 is a diagram illustrating an example spherical cover test in accordance with various aspects of the present disclosure.

[0030] Fig.15 is a diagram illustrating an example of extracting beam features based on a graph convolutional network (GCN) according to various aspects of the present disclosure.

[0031] Fig.16 is a diagram illustrating an example of single shot beam based ML module training and inference according to various aspects of the present disclosure.

[0032] Fig.17 is a diagram illustrating an example of beam scanning based ML module training and inference according to various aspects of the present disclosure. In another aspect of the present disclosure.

[0033] Fig.18 is a diagram illustrating an example of ML module training and inference based on multi-TRP single-shot beams according to various aspects of the present disclosure.

[0034] Fig.19 is a diagram illustrating an example of ML module training and inference based on multi-TRP beam scanning according to various aspects of the present disclosure.

[0035] Fig. 20A is a diagram illustrating example RF fingerprint features based on multi-TRP beam scanning according to various aspects of the present disclosure.

[0036] Fig. 20B is a diagram illustrating example RF fingerprint features based on multi-TRP beam scanning according to various aspects of the present disclosure.

[0037] Fig.21 is a communication flow illustrating an example of directional RF fingerprint based ML module training and inference according to various aspects of the present disclosure.

[0038] Fig. 22 is a flow chart of a method of wireless communication in accordance with various aspects presented herein.

[0039] Fig.23 is a flow chart of a method of wireless communication in accordance with various aspects presented herein.

[0040] Fig.24 is a diagram illustrating an example of a hardware implementation for an example device in accordance with various aspects presented herein. DETAILED DESCRIPTION

[0041] The detailed description set forth below in conjunction with the accompanying drawings is intended as a description of various configurations and is not intended to represent the only configurations with which the concepts described herein may be practiced. In order to provide a thorough understanding of the various concepts, the detailed description includes specific details. However, it is apparent to those skilled in the art that these concepts may be practiced without these specific details. In some instances, well-known structures and components are shown in block diagram form to avoid obscuring these concepts.

[0042] Several aspects of telecommunication systems will now be presented with reference to various apparatus and methods. These apparatus and methods will be described in the following detailed description and illustrated in the accompanying drawings by various blocks, components, circuits, processes, algorithms, etc. (collectively referred to as "elements"). These elements may be implemented using electronic hardware, computer software, or any combination thereof. Whether such elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system.

[0043] For example, an element, or any part of an element, or any combination of elements may be implemented as a "processing system", which includes one or more processors. Examples of processors include microprocessors, microcontrollers, graphics processing units (GPUs), central processing units (CPUs), application processors, digital signal processors (DSPs), reduced instruction set computing (RISC) processors, systems on chip (SoCs), baseband processors, field programmable gate arrays (FPGAs), programmable logic devices (PLDs), state machines, gate logic, discrete hardware circuits, and other suitable hardware configured to perform various functionalities described throughout the present disclosure. One or more processors in a processing system may execute software. Whether referred to as software, firmware, middleware, microcode, hardware description language, or other names, software should be broadly understood to mean instructions, instruction sets, codes, code segments, program codes, programs, subroutines, software components, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, processes, functions, etc.

[0044] Therefore, in one or more example embodiments, the described functions can be implemented with hardware, software or any combination thereof. If implemented with software, the function can be stored or encoded on a computer-readable medium as one or more instructions or codes. Computer-readable media include computer storage media. Storage media can be any available medium that can be accessed by a computer. As an example and not limitation, such computer-readable media may include random access memory (RAM), read-only memory (ROM), electrically erasable programmable ROM (EEPROM), optical disk storage device, magnetic disk storage device, other magnetic storage devices, a combination of these types of computer-readable media, or any other medium that can be used to store instructions or data structure forms that can be accessed by a computer.

[0045] Although various aspects and specific implementations are described in this application by the illustration of some examples, it will be understood by those skilled in the art that additional specific implementations and use cases may be generated in many different arrangements and scenarios. The innovation described herein can be implemented across many different platform types, devices, systems, shapes, sizes, and packaging arrangements. For example, specific implementations and / or uses can be generated via integrated chip specific implementations and other devices based on non-module components (e.g., end-user devices, vehicles, communication equipment, computing equipment, industrial equipment, retail / purchase equipment, medical equipment, devices supporting artificial intelligence (AI), etc.). Although some examples may or may not specifically point to use cases or applications, the applicability of various types of described innovations may occur. Specific implementations can range from chip-level or modular components to non-modular, non-chip-level specific implementations, and further to the scope of aggregation, distributed or original equipment manufacturer (OEM) equipment or systems that merge one or more aspects of the described innovation. In some practical environments, the equipment combined with the various aspects and features described may also include additional components and features for specific implementation and practice of the claimed and described aspects. For example, the transmission and reception of wireless signals necessarily include multiple components for analog and digital purposes (e.g., hardware components including antennas, RF chains, power amplifiers, modulators, buffers, processors, interleavers, adders / summers, etc.). The innovations described herein are intended to be practiced in a variety of devices, chip-level components, systems, distributed arrangements, aggregated or disaggregated components, end-user devices, etc., of varying sizes, shapes, and configurations.

[0046] Figure 11 is a diagram 100 showing an example of a wireless communication system and access network. The wireless communication system (which is also referred to as a wireless wide area network (WWAN)) includes a base station 102, a UE 104, an evolved packet core (EPC) 160, and another core network 190 (e.g., a 5G core (5GC)). The base station 102 may include a macro cell (a high-power cellular base station) and / or a small cell (a low-power cellular base station). A macro cell includes a base station. A small cell includes a femto cell, a pico cell, and a micro cell.

[0047] Various aspects presented herein can improve the accuracy of RFFP-based positioning by associating RF fingerprints with beam directions and / or beam characteristics to improve the uniqueness of RF fingerprints. Various aspects presented herein can enable an ML module to map directional RF fingerprints and / or beam characteristic inputs to a device location as an output, wherein the directional RF fingerprint may include RF captured between an antenna pair (e.g., at least one antenna of a transmitter and at least one antenna of a receiver). For the purposes of this disclosure, an RF fingerprint including features associated with a transmission beam and / or a reception beam may be referred to as a directional RF fingerprint or an RF fingerprint with directional features. For example, a directional RF fingerprint may be a CIR captured at one or more antenna pairs (which may also be referred to as a beam pair), a CFR captured at one or more antenna pairs, and / or a normalized histogram of received signal strength measured over a certain time period and / or frequency range captured at one or more antenna pairs, etc.

[0048] In certain aspects, the UE 104 and / or the base station 102 / 180 may include an RF fingerprint recognition component 198 that is configured to associate an RF fingerprint with a beam direction and / or a beam characteristic. In one configuration, the RF fingerprint recognition component 198 may be configured to receive a plurality of first RF fingerprints from one or more wireless devices, each of the plurality of first RF fingerprints being associated with at least one directional characteristic and a location. In this configuration, the RF fingerprint recognition component 198 may receive a request to determine the location of the UE based on at least one second RF fingerprint associated with the UE or captured by the UE. In this configuration, the RF fingerprint recognition component 198 may estimate the location of the UE based at least in part on matching the at least one second RF fingerprint with at least one RF fingerprint of the plurality of first RF fingerprints.

[0049] The base station 102 configured for 4G LTE (which is collectively referred to as the Evolved Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access Network (E-UTRAN)) can interact with the EPC 160 through a first backhaul link 132 (e.g., an S1 interface). The base station 102 configured for 5G NR (which is collectively referred to as the Next Generation RAN (NG-RAN)) can interact with the core network 190 through a second backhaul link 184. Among other functions, the base station 102 can perform one or more of the following functions: transmission of user data, radio channel encryption and decryption, integrity protection, header compression, mobility control functions (e.g., handover, dual connectivity), inter-cell interference coordination, connection establishment and release, load balancing, distribution of non-access stratum (NAS) messages, NAS node selection, synchronization, radio access network (RAN) sharing, multimedia broadcast multicast service (MBMS), subscriber and equipment tracking, RAN information management (RIM), paging, positioning, and delivery of warning messages. The base stations 102 may communicate with each other directly or indirectly (eg, via the EPC 160 or the core network 190) via the third backhaul link 134 (eg, an X2 interface). The first backhaul link 132, the second backhaul link 184, and the third backhaul link 134 may be wired or wireless.

[0050] In some aspects, the base station 102 or 180 may be referred to as a RAN and may include aggregated components or disaggregated components. As an example of a disaggregated RAN, the base station may include a central unit (CU) 103, one or more distributed units (DU) 105, and / or one or more remote units (RU) 109, such as Figure 1As illustrated. The RAN can be decomposed by splitting between RU 109 and aggregated CU / DU. The RAN can be decomposed by splitting between CU 103, DU 105 and RU 109. The RAN can be decomposed by splitting between CU 103 and aggregated DU / RU. CU 103 and one or more DU 105 can be connected via an F1 interface. DU 105 and RU 109 can be connected via a forwarding interface. The connection between CU 103 and DU 105 can be called a mid-haul, and the connection between DU 105 and RU 109 can be called a forwarding. The connection between CU 103 and the core network can be called a backhaul. The RAN can be based on functional splitting between various components of the RAN (e.g., between CU 103, DU 105 or RU 109). The CU can be configured to perform one or more aspects of a wireless communication protocol (e.g., one or more layers of a handling protocol stack), and the DU can be configured to handle other aspects of the wireless communication protocol (e.g., other layers of a protocol stack). In different specific implementations, the split between the layers handled by the CU and the layers handled by the DU may occur at different layers of the protocol stack. As a non-limiting example, the DU 105 may provide a logical node for hosting at least a portion of the radio link control (RLC) layer, the medium access control (MAC) layer, and the physical (PHY) layer based on the functional split. The RU may provide a logical node configured to host at least a portion of the PHY layer and radio frequency (RF) processing. The CU 103 may host, for example, higher layer functions above the RLC layer, such as the service data adaptation protocol (SDAP) layer, the packet data convergence protocol (PDCP) layer. In other specific implementations, the split between the layer functions provided by the CU, DU, or RU may be different.

[0051] The access network may include one or more integrated access and backhaul (IAB) nodes 111, which exchange wireless communications with UE 104 or other IAB nodes 111 to provide access and backhaul to the core network. In an IAB network of multiple IAB nodes, the anchor node may be referred to as an IAB donor. The IAB donor may be a base station 102 or 180 that provides access to the core network 190 or EPC 160 and / or control of one or more IAB nodes 111. The IAB donor may include a CU 103 and a DU 105. The IAB node 111 may include a DU 105 and a mobile terminal (MT) 113. The DU 105 of the IAB node 111 may operate as a parent node, and the MT 113 may operate as a child node.

[0052] Base station 102 can communicate wirelessly with UE 104. Each of base stations 102 can provide communication coverage for a corresponding geographic coverage area 110. There may be overlapping geographic coverage areas 110. For example, a small cell 102' can have a coverage area 110' that overlaps with the coverage area 110 of one or more macro base stations 102. A network including both small cells and macro cells can be referred to as a heterogeneous network. A heterogeneous network can also include a home evolved B node (eNB) (HeNB), which can provide services to a restricted group called a closed subscriber group (CSG). The communication link 120 between base station 102 and UE 104 can include an uplink (UL) (also referred to as a reverse link) transmission from UE 104 to base station 102 and / or a downlink (DL) (also referred to as a forward link) transmission from base station 102 to UE 104. The communication link 120 can use multiple input multiple output (MIMO) antenna technology, including spatial multiplexing, beamforming and / or transmission diversity. The communication link can go through one or more operators. For each carrier allocated in the carrier aggregation for a total of up to Yx MHz (x component carriers) for transmission in each direction, the base station 102 / UE 104 can use spectrum with a bandwidth of up to Y MHz (e.g., 5 MHz, 10 MHz, 15 MHz, 20 MHz, 100 MHz, 400 MHz, etc.). The carriers may or may not be adjacent to each other. The allocation of carriers may be asymmetric with respect to DL and UL (e.g., more or fewer carriers may be allocated for DL ​​compared to UL). The component carrier may include a primary component carrier and one or more secondary component carriers. The primary component carrier may be referred to as a primary cell (PCell) and the secondary component carrier may be referred to as a secondary cell (SCell).

[0053] Some UEs 104 may communicate with each other using a device-to-device (D2D) communication link 158. The D2D communication link 158 may use DL / UL WWAN spectrum. The D2D communication link 158 may use one or more sidelink channels, such as a physical sidelink broadcast channel (PSBCH), a physical sidelink discovery channel (PSDCH), a physical sidelink shared channel (PSSCH), and a physical sidelink control channel (PSCCH). The D2D communication may be through a variety of wireless D2D communication systems, such as, for example, WiMedia, Bluetooth, ZigBee, Wi-Fi based on the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standard, LTE, or NR.

[0054] The wireless communication system may also include a Wi-Fi access point (AP) 150 that communicates with a Wi-Fi station (STA) 152 via a communication link 154, e.g., in a 5 GHz unlicensed spectrum, etc. When communicating in an unlicensed spectrum, the STA 152 / AP 150 may perform a clear channel assessment (CCA) prior to communication to determine whether a channel is available.

[0055] The small cell 102' may operate in a licensed and / or unlicensed spectrum. When operating in an unlicensed spectrum, the small cell 102' may employ NR and use the same unlicensed spectrum (e.g., 5 GHz, etc.) as used by the Wi-Fi AP 150. The small cell 102' employing NR in the unlicensed spectrum may improve the coverage of the access network and / or increase the capacity of the access network.

[0056] The electromagnetic spectrum is typically subdivided into various categories, bands, channels, etc. based on frequency / wavelength. In 5G NR, two initial operating bands have been identified with the frequency range names FR1 (410 MHz-7.125 GHz) and FR2 (24.25 GHz-52.6 GHz). Although a portion of FR1 is greater than 6 GHz, FR1 is often referred to (interchangeably) as the "sub-6 GHz" band in various documents and articles. A similar naming issue sometimes occurs with respect to FR2, which is often (interchangeably) referred to as the "millimeter wave" band in documents and articles, although it is different from the extremely high frequency (EHF) band (30 GHz-300 GHz) identified as the "millimeter wave" band by the International Telecommunication Union (ITU).

[0057] Frequencies between FR1 and FR2 are generally referred to as mid-band frequencies. Recent 5G NR research has identified the operating bands for these mid-band frequencies as frequency range names FR3 (7.125GHz-24.25GHz). The bands falling within FR3 can inherit FR1 characteristics and / or FR2 characteristics, so the features of FR1 and / or FR2 can be effectively extended to mid-band frequencies. In addition, higher frequency bands are currently being explored to extend 5G NR operations to more than 52.6GHz. For example, three higher operating bands have been identified as frequency range names FR2-2 (52.6GHz-71GHz), FR4 (52.6GHz-114.25GHz) and FR5 (114.25GHz-300Ghz). Each of these higher frequency bands falls within the EHF band.

[0058] In view of the above aspects, unless otherwise specifically stated, it should be understood that if used in this article, the term "sub-6 GHz" and the like can be broadly referred to as frequencies that can be less than 6 GHz, can be within FR1, or can include mid-band frequencies. In addition, unless otherwise explicitly stated, it should be understood that if the term "millimeter wave" and the like are used in this article, they can be broadly referred to as frequencies that can include mid-band frequencies, can be within FR2, FR4, FR2-2 and / or FR5, or can be within the EHF band.

[0059] The base station 102, whether a small cell 102' or a large cell (e.g., a macro base station), may include and / or be referred to as an eNB, a gNodeB (gNB), or another type of base station. Some base stations, such as gNB 180, may operate in the traditional sub-6 GHz spectrum, in millimeter wave frequencies, and / or near millimeter wave frequencies to communicate with the UE 104. When the gNB 180 operates in millimeter wave or near millimeter wave frequencies, the gNB 180 may be referred to as a millimeter wave base station. The millimeter wave base station 180 may utilize beamforming 182 with the UE 104 to compensate for path loss and short range. The base station 180 and the UE 104 may each include multiple antennas, such as antenna elements, antenna panels, and / or antenna arrays, to facilitate beamforming.

[0060] Base station 180 may transmit beamformed signals in one or more transmission directions 182' to UE 104. UE 104 may receive beamformed signals from base station 180 in one or more reception directions 182". UE 104 may also transmit beamformed signals to base station 180 in one or more transmission directions. Base station 180 may receive beamformed signals from UE 104 in one or more reception directions. Base station 180 / UE 104 may perform beam training to determine the best reception direction and transmission direction for each of base station 180 / UE 104. The transmission direction and reception direction of base station 180 may be the same or different. The transmission and reception directions of UE 104 may be the same or different.

[0061] The EPC 160 may include a mobility management entity (MME) 162, other MMEs 164, a serving gateway 166, a multimedia broadcast multicast service (MBMS) gateway 168, a broadcast multicast service center (BM-SC) 170, and a packet data network (PDN) gateway 172. The MME 162 may communicate with a home subscriber server (HSS) 174. The MME 162 is a control node that handles signaling between the UE 104 and the EPC 160. Typically, the MME 162 provides bearer and connection management. All user Internet Protocol (IP) packets are transmitted through the serving gateway 166, which itself is connected to the PDN gateway 172. The PDN gateway 172 provides UE IP address allocation and other functions. The PDN gateway 172 and the BM-SC 170 are connected to IP services 176. The IP services 176 may include the Internet, an intranet, an IP multimedia subsystem (IMS), a PS streaming service, and / or other IP services. The BM-SC 170 may provide functionality for MBMS user service provisioning and delivery. The BM-SC 170 may serve as an entry point for content provider MBMS transmissions, may be used to authorize and initiate MBMS bearer services in a public land mobile network (PLMN), and may be used to schedule MBMS transmissions. The MBMS Gateway 168 may be used to distribute MBMS traffic to base stations 102 belonging to a multicast broadcast single frequency network (MBSFN) area that broadcasts a specific service, and may be responsible for session management (start / stop) and collecting eMBMS-related billing information.

[0062] The core network 190 may include an access and mobility management function (AMF) 192, other AMFs 193, a session management function (SMF) 194, and a user plane function (UPF) 195. The AMF 192 may communicate with a unified data management (UDM) 196. The AMF 192 is a control node for processing signaling between the UE 104 and the core network 190. In general, the AMF 192 provides QoS flow and session management. All user Internet Protocol (IP) packets are transmitted through the UPF 195. The UPF 195 provides UE IP address allocation and other functions. The UPF 195 is connected to an IP service 197. The IP service 197 may include the Internet, an intranet, an IP multimedia subsystem (IMS), a packet switching (PS) stream (PSS) service, and / or other IP services.

[0063] Base stations may include and / or be referred to as gNBs, Node Bs, eNBs, access points, base transceivers, radio base stations, radio transceivers, transceiver functions, basic service sets (BSSs), extended service sets (ESSs), transmission reception points (TRPs), or some other suitable terminology. Base stations 102 provide access points to EPC 160 or core network 190 for UEs 104. Examples of UEs 104 include cellular phones, smart phones, session initiation protocol (SIP) phones, laptops, personal digital assistants (PDAs), satellite radios, global positioning systems, multimedia devices, video devices, digital audio players (e.g., MP3 players), cameras, game consoles, tablets, smart devices, wearable devices, vehicles, electric meters, gas pumps, large or small kitchen appliances, healthcare devices, implants, sensors / actuators, displays, or any other similarly functional devices. Some of UEs 104 may be referred to as IoT devices (e.g., parking meters, gas pumps, toasters, vehicles, heart monitors, etc.). UE 104 may also be referred to as a station, mobile station, subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, mobile phone, user agent, mobile client, client or some other appropriate term. In some scenarios, the term UE may also be applied to one or more supporting devices, such as in a device constellation arrangement. One or more of these devices may access the network together and / or individually.

[0064] Figure 2A FIG200 is a diagram showing an example of a first subframe within a 5G NR frame structure. Figure 2B 230 is a diagram showing an example of DL channels within a 5G NR subframe. Figure 2C is a diagram 250 showing an example of a second subframe within a 5G NR frame structure. Figure 2D is a diagram 280 showing an example of UL channels within a 5G NR subframe. The 5G NR frame structure can be frequency division duplex (FDD) (wherein, for a particular set of subcarriers (carrier system bandwidth), subframes within the subcarrier set are dedicated to either DL or UL), or can be time division duplex (TDD) (wherein, for a particular set of subcarriers (carrier system bandwidth), subframes within the subcarrier set are dedicated to both DL and UL). Figure 2A , Figure 2CIn the example provided, the 5GNR frame structure is assumed to be TDD, where subframe 4 is configured with slot format 28 (most of which are DL), where D is DL, U is UL, and F is flexible between DL / UL, and subframe 3 is configured with slot format 1 (all of which are UL). Although subframes 3 and 4 are shown with slot formats 1 and 28, respectively, any particular subframe may be configured with any of the various available slot formats 0-61. Slot formats 0 and 1 are all DL and all UL, respectively. Other slot formats 2-61 include a mix of DL, UL, and flexible symbols. The UE is configured with the slot format (dynamically configured by DL control information (DCI) or semi-statically / statically configured by radio resource control (RRC) signaling) through the received slot format indicator (SFI). Note that the following description also applies to the 5G NR frame structure for TDD.

[0065] FIG. 2A to FIG. 2D The frame structure is shown, and various aspects of the present disclosure are applicable to other wireless communication technologies that may have different frame structures and / or different channels. A frame (10ms) may be divided into 10 subframes (1ms) of the same size. Each subframe may include one or more time slots. A subframe may also include a microslot, which may include 7, 4, or 2 symbols. Each time slot may include 14 or 12 symbols, depending on whether the cyclic prefix (CP) is normal or extended. For a normal CP, each time slot may include 14 symbols, and for an extended CP, each time slot may include 12 symbols. The symbol on the DL may be a CP orthogonal frequency division multiplexing (OFDM) (CP-OFDM) symbol. The symbol on the UL may be a CP-OFDM symbol (for high throughput scenarios) or a discrete Fourier transform (DFT) extended OFDM (DFT-s-OFDM) symbol (also known as a single carrier frequency division multiple access (SC-FDMA) symbol) (for power-limited scenarios; limited to single-stream transmission). The number of slots within a subframe is based on the CP and the parameter set. The parameter set defines the subcarrier spacing (SCS) and effectively defines the symbol length / duration, which is equal to 1 / SCS.

[0066]

[0067] For normal CP (14 symbols / slot), different parameter sets μ0 to 4 allow 1, 2, 4, 8, and 16 slots per subframe, respectively. For extended CP, parameter set 2 allows 4 slots per subframe. Accordingly, for normal CP and parameter set μ, there are 14 symbols / slot and 2 μ timeslots / subframe. The subcarrier spacing can be equal to 2 μ*15kHz, where μ is parameter set 0 to 4. Therefore, the subcarrier spacing for parameter set μ=0 is 15kHz, and the subcarrier spacing for parameter set μ=4 is 240kHz. The symbol length / duration is inversely related to the subcarrier spacing. FIG. 2A to FIG. 2D An example of a parameter set μ=2 with a normal CP of 14 symbols per slot and 4 slots per subframe is provided. The slot duration is 0.25 ms, the subcarrier spacing is 60 kHz, and the symbol duration is about 16.67 ps. Within a frame set, there may be one or more different bandwidth parts (BWPs) that are frequency-division multiplexed (see Figure 2B ). Each BWP can have a specific parameter set and CP (normal or extended).

[0068] A resource grid may be used to represent the frame structure. Each slot includes a resource block (RB) (also called a physical RB (PRB)) extending over 12 consecutive subcarriers. The resource grid is divided into a number of resource elements (REs). The number of bits carried by each RE depends on the modulation scheme.

[0069] like Figure 2A As shown in , some of the REs carry reference (pilot) signals (RS) for the UE. The RS may include a demodulation RS (DM-RS) (indicated as R for a particular configuration, but other DM-RS configurations are possible) and a channel state information reference signal (CSI-RS) for channel estimation at the UE. The RS may also include a beam measurement RS (BRS), a beam refinement RS (BRRS), and a phase tracking RS (PT-RS).

[0070] Figure 2BExamples of various DL channels within a subframe of a frame are shown. A physical downlink control channel (PDCCH) carries DCI within one or more control channel elements (CCEs) (e.g., 1, 2, 4, 8, or 16 CCEs), each CCE including six RE groups (REGs), each REG including 12 consecutive REs in an OFDM symbol of an RB. A PDCCH within a BWP may be referred to as a control resource set (CORESET). The UE is configured to monitor PDCCH candidates in a PDCCH search space (e.g., a common search space, a UE-specific search space) during a PDCCH monitoring opportunity on a CORESET, wherein the PDCCH candidates have different DCI formats and different aggregation levels. Additional BWPs may be located at higher and / or lower frequencies on the channel bandwidth. A primary synchronization signal (PSS) may be within symbol 2 of a particular subframe of a frame. The PSS is used by UE 104 to determine subframe / symbol timing and physical layer identification. A secondary synchronization signal (SSS) may be within symbol 4 of a particular subframe of a frame. The SSS is used by the UE to determine the physical layer cell identity group number and the radio frame timing. Based on the physical layer identity and the physical layer cell identity group number, the UE can determine the physical cell identifier (PCI). Based on the PCI, the UE can determine the location of the DM-RS. The physical broadcast channel (PBCH) carrying the master information block (MIB) can be logically grouped with the PSS and SSS to form a synchronization signal (SS) / PBCH block (also called SS block (SSB)). The MIB provides the number of RBs in the system bandwidth and the system frame number (SFN). The physical downlink shared channel (PDSCH) carries user data, broadcast system information not transmitted via the PBCH (such as the system information block (SIB)), and paging messages.

[0071] like Figure 2C As shown, some of the REs carry DM-RS (indicated as R for a specific configuration, but other DM-RS configurations are possible) for channel estimation at the base station. The UE can transmit the DM-RS of the physical uplink control channel (PUCCH) and the DM-RS of the physical uplink shared channel (PUSCH). The PUSCH DM-RS can be transmitted in the first or first two codewords of the PUSCH. Depending on whether a short PUCCH or a long PUCCH is transmitted and depending on the specific PUCCH format used, the PUCCH DM-RS can be transmitted in different configurations. The UE can transmit a sounding reference signal (SRS). The SRS can be transmitted in the last codeword of the subframe. The SRS can have a comb structure, and the UE can transmit the SRS on one of the combs in the comb. The SRS can be used by the base station for channel quality estimation to achieve frequency-dependent scheduling of the UL.

[0072] Figure 2DExamples of various UL channels within a subframe of a frame are shown. The PUCCH may be located at a position as indicated in one configuration. The PUCCH carries uplink control information (UCI), such as scheduling requests, channel quality indicators (CQI), precoding matrix indicators (PMI), rank indicators (RI), and hybrid automatic repeat request (HARQ) acknowledgement (ACK) (HARQ-ACK) feedback (i.e., one or more HARQ ACK bits indicating one or more ACKs and / or negative ACKs (NACKs)). The PUSCH carries data and may additionally be used to carry buffer status reports (BSRs), power headroom reports (PHRs), and / or UCI.

[0073] Figure 3 3 is a block diagram of a base station 310 in an access network communicating with a UE 350. In the DL, IP packets from the EPC 160 may be provided to a controller / processor 375. The controller / processor 375 implements layer 3 and layer 2 functionality. Layer 3 includes a radio resource control (RRC) layer, and layer 2 includes a service data adaptation protocol (SDAP) layer, a packet data convergence protocol (PDCP) layer, a radio link control (RLC) layer, and a medium access control (MAC) layer. The controller / processor 375 provides RRC layer functionality associated with broadcasting of system information (e.g., MIB, SIB), RRC connection control (e.g., RRC connection paging, RRC connection establishment, RRC connection modification, and RRC connection release), inter-radio access technology (RAT) mobility, and measurement configuration for UE measurement reporting; PDCP layer functionality associated with header compression / decompression, security (encryption, decryption, integrity protection, integrity verification), and handover support functions; RLC layer functionality associated with transmission of upper layer packet data units (PDUs), error correction through ARQ, concatenation, segmentation and reassembly of RLC service data units (SDUs), re-segmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functionality associated with mapping between logical channels and transport channels, multiplexing of MAC SDUs onto transport blocks (TBs), demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction through HARQ, priority handling, and logical channel prioritization.

[0074] The transmission (TX) processor 316 and the reception (RX) processor 370 implement layer 1 functionality associated with various signal processing functions. Layer 1 (which includes the physical (PHY) layer) may include error detection on the transmission channel, forward error correction (FEC) decoding / decoding of the transmission channel, interleaving, rate matching, mapping to the physical channel, modulation / demodulation of the physical channel, and MIMO antenna processing. The TX processor 316 processes the mapping for the signal constellation diagram based on various modulation schemes (e.g., binary phase shift keying (BPSK), quadrature phase shift keying (QPSK), M-order phase shift keying (M-PSK), M-order quadrature amplitude modulation (M-QAM)). The decoded and modulated symbols can then be divided into parallel streams. Subsequently, each stream can be mapped to an OFDM subcarrier, multiplexed with a reference signal (e.g., a pilot) in the time domain and / or frequency domain, and then combined using an inverse fast Fourier transform (IFFT) to generate a physical channel for carrying a time domain OFDM symbol stream. The OFDM stream is spatially pre-coded to generate multiple spatial streams. Channel estimates from a channel estimator 374 may be used to determine the coding and modulation schemes, as well as for spatial processing. Channel estimates may be derived based on reference signals and / or channel condition feedback transmitted by the UE 350. Each spatial stream may then be provided to a different antenna 320 via a separate transmitter 318TX. Each transmitter 318TX may modulate a radio frequency (RF) carrier with a corresponding spatial stream for transmission.

[0075] At the UE 350, each receiver 354RX receives a signal through its corresponding antenna 352. Each receiver 354RX recovers the information modulated onto the RF carrier and provides the information to a receive (RX) processor 356. The TX processor 368 and the RX processor 356 implement layer 1 functionality associated with various signal processing functions. The RX processor 356 can perform spatial processing on the information to recover any spatial stream destined for the UE 350. If multiple spatial streams are destined for the UE 350, they can be combined into a single OFDM symbol stream by the RX processor 356. The RX processor 356 then converts the OFDM symbol stream from the time domain to the frequency domain using a fast Fourier transform (FFT). The frequency domain signal includes a separate OFDM symbol stream for each subcarrier of the OFDM signal. The symbol on each subcarrier is recovered and demodulated by determining the signal constellation point most likely to be transmitted by the base station 310, as well as the reference signal. These soft decisions can be based on the channel estimates calculated by the channel estimator 358. The soft decisions are then decoded and deinterleaved to recover the data and control signals originally transmitted on the physical channel by base station 310. The data and control signals are then provided to controller / processor 359, which implements layer 3 functionality and layer 2 functionality.

[0076] The controller / processor 359 may be associated with a memory 360 that stores program codes and data. The memory 360 may be referred to as a computer readable medium. In the UL, the controller / processor 359 provides demultiplexing between transport and logical channels, packet reassembly, decryption, header decompression, and control signal processing to recover IP packets from the EPC 160. The controller / processor 359 is also responsible for error detection using an ACK and / or NACK protocol to support HARQ operations.

[0077] Similar to the functionality described in conjunction with DL transmissions performed by the base station 310, the controller / processor 359 provides RRC layer functionality associated with system information (e.g., MIB, SIB) acquisition, RRC connection, and measurement reporting; PDCP layer functionality associated with header compression / decompression and security (encryption, decryption, integrity protection, integrity verification); RLC layer functionality associated with transmission of upper layer PDUs, error correction through ARQ, concatenation, segmentation and reassembly of RLC SDUs, resegmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functionality associated with mapping between logical channels and transport channels, multiplexing of MAC SDUs onto TBs, demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction through HARQ, priority handling, and logical channel prioritization.

[0078] The TX processor 368 may use channel estimates derived by the channel estimator 358 from a reference signal or feedback transmitted by the base station 310 to select appropriate coding and modulation schemes and to facilitate spatial processing. The spatial streams generated by the TX processor 368 may be provided to different antennas 352 via separate transmitters 354TX. Each transmitter 354TX may modulate an RF carrier with a corresponding spatial stream for transmission.

[0079] UL transmissions are processed at the base station 310 in a manner similar to that described in conjunction with the receiver functionality at the UE 350. Each receiver 318RX receives a signal through its respective antenna 320. Each receiver 318RX recovers information modulated onto an RF carrier and provides the information to a RX processor 370.

[0080] The controller / processor 375 may be associated with a memory 376 that stores program codes and data. The memory 376 may be referred to as a computer readable medium. In the UL, the controller / processor 375 provides demultiplexing between transport channels and logical channels, packet reassembly, decryption, header decompression, control signal processing to recover IP packets from the UE 350. The IP packets from the controller / processor 375 may be provided to the EPC 160. The controller / processor 375 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operations.

[0081] In some examples, at least one of the TX processor 368, the RX processor 356, and the controller / processor 359 may be configured to perform a combined Figure 1 In other examples, at least one of the TX processor 316, the RX processor 370, and the controller / processor 375 may be configured to perform a combined Figure 1 Various aspects of the RF fingerprint recognition component 198.

[0082] The network may support several cellular network-based positioning techniques, such as downlink-based positioning methods, uplink-based positioning methods, and / or downlink and uplink-based positioning methods. Downlink-based positioning methods may include observed time difference of arrival (OTDOA) (e.g., in LTE), downlink time difference of arrival (DL-TDOA) (e.g., in NR), and / or downlink angle of departure (DL-AoD) (e.g., in NR). During the OTDOA or DL-TDOA positioning process, the UE may measure the difference between each time of arrival (ToA) of a reference signal (e.g., positioning reference signal (PRS)) received from a base station (referred to as reference signal time difference (RSTD) measurement or arrival time difference (TDOA) measurement), and report these differences to a positioning entity (e.g., positioning management function (LMF)). For example, the UE may receive an identifier (ID) of a reference base station (which may also be referred to as a reference cell or reference gNB) and at least one non-reference base station in auxiliary data (AD). The UE may then measure the RSTD between the reference base station and each non-reference base station. Based on the known positioning of the base stations involved and RSTD measurements, the positioning entity can estimate the positioning of the UE. In other words, the position of the UE can be estimated based on measuring reference signals transmitted between the UE and one or more base stations and / or the transmission reception points (TRPs) of one or more base stations. Therefore, the PRS enables the UE to detect and measure adjacent TRPs and perform positioning based on the measurements. For the purposes of this disclosure, the suffixes "based on" and "assisted" may refer to a node responsible for performing positioning calculations (and may also provide measurements) and a node that provides measurements (but may not perform positioning calculations), respectively. For example, an operation in which the UE provides measurements to a base station / positioning entity for use in calculating a position estimate may be described as "UE assisted", "UE assisted positioning" and / or "UE assisted position calculation", while an operation in which the UE calculates its own position may be described as "UE-based", "UE-based positioning" and / or "UE-based position calculation".

[0083] In some examples, the term "TRP" may refer to one or more antennas of a base station, and the term "base station" may refer to a complete unit (e.g., base station 102 / 180) including aggregated or disaggregated components, such as a combination of Figure 1Described. For example, as an example of a decomposed RAN, a base station may include a CU, one or more DUs, one or more RUs, and / or one or more TRPs. One or more decomposed components may be located at different locations. For example, different TRPs may be located at different geographical locations. In another example, a TRP may refer to a geographically co-located set of antennas (e.g., an antenna array (having one or more antenna elements)) that supports transmission point (TP) and / or reception point (RP) functions. Therefore, a base station may transmit signals to other wireless devices (e.g., UE, another base station, etc.) and / or receive signals from the other wireless devices via one or more TRPs. For the purposes of the present disclosure, in some examples, the term "TRP" may be used interchangeably with the term "base station."

[0084] For DL-AoD positioning, the positioning entity can use beam reports from the UE on received signal strength measurements of multiple downlink transmission beams to determine the angle between the UE and the transmitting base station. The positioning entity can then estimate the position of the UE based on the determined angle and the known position of the transmitting base station.

[0085] Uplink-based positioning methods may include UL-TDOA and UL-AoA. UL-TDOA is similar to DL-TDOA, but is based on uplink reference signals (e.g., sounding reference signals (SRS)) transmitted by the UE. For UL-AoA positioning, one or more base stations may measure the received signal strength of one or more uplink reference signals (e.g., SRS) received from the UE on one or more uplink receive beams. The positioning entity may use the signal strength measurement and the angle of the receive beam to determine the angle between the UE and the base station. Based on the determined angle and the known location of the base station, the positioning entity may then estimate the location of the UE.

[0086] Downlink and uplink based positioning methods may include enhanced cell ID (E-CID) positioning and multi-round trip time (RTT) positioning (also referred to as "multi-cell RTT"). During the RTT process, the initiator (base station or UE) transmits an RTT measurement signal (e.g., PRS or SRS) to the responder (UE or base station), and the responder transmits an RTT response signal (e.g., SRS or PRS) back to the initiator. The RTT response signal may include the difference between the ToA of the RTT measurement signal and the transmission time of the RTT response signal (referred to as the receive-transmit (Rx-Tx) time difference). The initiator may calculate the difference between the transmission time of the RTT measurement signal and the ToA of the RTT response signal (referred to as the transmit-receive (Tx-Rx) time difference). The propagation time (also referred to as "flight time") between the initiator and the responder may be calculated using the Tx-Rx and Rx-Tx time differences. Based on the propagation time and the known speed of light, the distance between the initiator and the responder may be determined. For multi-RTT positioning, the UE may perform RTT procedures with multiple base stations so that the UE's position can be determined based on the known positions of the base stations (e.g., using multilateration). RTT and multi-RTT methods may be combined with other positioning techniques (such as UL-AoA and DL-AoD) to improve positioning accuracy.

[0087] The E-CID positioning method can be based on radio resource management (RRM) measurements. In E-CID, the UE can report the serving cell ID, timing advance (TA), and the identifiers, estimated timing, and signal strength of the detected neighboring base stations. The UE's position is then estimated based on this information and the known location of the base stations.

[0088] To assist the positioning operation, a location server (e.g., a location server, LMF, or SLP) may provide assistance data (AD) to the UE. For example, the assistance data may include: an identifier of the base station (or a cell / TRP of a base station) from which the reference signal is measured, reference signal configuration parameters (e.g., the number of consecutive positioning subframes, the periodicity of the positioning subframes, the silent sequence, the frequency hopping sequence, the reference signal identifier, the reference signal bandwidth, etc.), and / or other parameters applicable to a specific positioning method. Alternatively, the assistance data may originate directly from the base station (e.g., in an overhead message broadcast periodically, etc.). In some cases, the UE may be able to detect neighboring network nodes without using assistance data.

[0089] In the case of an OTDOA or DL-TDOA positioning process, the assistance data may also include an expected RSTD value and an associated uncertainty (e.g., a search space window) around the expected RSTD. In some cases, the value range of the expected RSTD may be plus or minus (+ / -) 500 microseconds (μs). In some cases, when any resource used for positioning measurements is in FR1, the value range of the uncertainty of the expected RSTD may be + / -32μs. In other cases, when all resources used for positioning measurements are in FR2, the value range of the uncertainty of the expected RSTD may be + / -8μs. In this context, "RSTD" may refer to one or more measurements indicating the time difference of arrival between a PRS transmitted by a base station (referred to herein as a "neighboring base station" or "measurement base station") and a PRS transmitted by a reference base station. The reference base station may be selected by a location server and / or by a UE to provide a good or sufficient signal strength observed at the UE so that the PRS may be acquired and / or measured more accurately and / or more quickly, such as without any special assistance from a serving base station.

[0090] A positioning estimate may also be referred to as a position estimate, a position fix, a position fix, a position fix, a fix, and the like. A positioning estimate may be geodetic and include coordinates (e.g., latitude, longitude, and possibly altitude), or may be municipal and include a street address, a postal address, or some other verbal description of a position. A position estimate may be further defined relative to some other known location or in absolute terms (e.g., using latitude, longitude, and possibly altitude). A positioning estimate may include an expected error or uncertainty (e.g., by including an area or volume within which the location is expected to be contained with a specified or default confidence level). For purposes of this disclosure, reference signals may include PRS, tracking reference signals (TRS), phase tracking reference signals (PTRS), cell-specific reference signals (CRS), CSI-RS, demodulation reference signals (DMRS), PSS, SSS, SSB, SRS, and the like, depending on whether the illustrated frame structure is for uplink or downlink communication. In some examples, a set of resource elements (REs) used for transmission of PRS is referred to as "PRS resources". A set of resource elements may span multiple PRBs in the frequency domain and one or more consecutive symbols within a time slot in the time domain. In a given OFDM symbol in the time domain, a PRS resource may occupy consecutive PRBs in the frequency domain. In other examples, a "PRS resource set" may refer to a set of PRS resources used for transmission of a PRS signal, wherein each PRS resource may have a PRS resource ID. In addition, the PRS resources in a PRS resource set may be associated with the same TRP. A PRS resource set may be identified by a PRS resource set ID and may be associated with a specific TRP (identified by a TRP ID). In addition, the PRS resources in a PRS resource set may have the same periodicity, a common muting pattern configuration, and / or the same cross-slot repetition factor. The periodicity may be the time from the first repetition of the first PRS resource of the first PRS instance to the same first repetition of the same first PRS resource of the next PRS instance. For example, the periodicity may have a length selected from: 2^μ*{4, 5, 8, 10, 16, 20, 32, 40, 64, 80, 160, 320, 640, 1280, 2560, 5120, 10240} time slots, where μ=0, 1, 2, 3. The repetition factor may have a length selected from {1, 2, 4, 6, 8, 16, 32} time slots. The PRS resource ID in a PRS resource set may be associated with a single beam (or beam ID) transmitted from a single TRP (one TRP may transmit one or more beams). That is, each PRS resource in a PRS resource set may be transmitted on a different beam, and therefore, a "PRS resource" (or simply "resource") may also be referred to as a "beam".In some examples, a "PRS instance" or "PRS opportunity" may be an instance of a periodically repeating time window (such as a group of one or more consecutive time slots) in which a PRS is expected to be transmitted. A PRS opportunity may also be referred to as a "PRS positioning opportunity," "PRS positioning instance," "positioning opportunity," "positioning instance," "positioning repetition," or simply "opportunity," "instance," and / or "repetition," etc.

[0091] A "positioning frequency layer (PFL)" (also referred to as a "frequency layer") may be a set of one or more PRS resource sets with the same values ​​for certain parameters across one or more TRPs. Specifically, the set of PRS resource sets may have the same subcarrier spacing and cyclic prefix (CP) type (e.g., meaning that all parameter sets that support PDSCH also support PRS), the same point A, the same downlink PRS bandwidth value, the same starting PRB (and center frequency) and / or the same comb size, etc. The point A parameter may take the value of the parameter ARFCN-ValueNR (where "ARFCN" stands for "absolute radio frequency channel number") and may be an identifier / code that specifies a physical radio channel pair for transmission and reception. In some examples, the downlink PRS bandwidth may have a granularity of four PRBs, and the minimum value is 24 PRBs and the maximum value is 272 PRBs. In other examples, up to four frequency layers may be configured, and up to two PRS resource sets may be configured per TRP per frequency layer.

[0092] The concept of frequency layer may be similar to component carrier (CC) and BWP, where CC and BWP may be used by one base station (or macro cell base station and small cell base station) to transmit data channels, and frequency layer may be used by multiple (e.g., three or more) base stations to transmit PRS. The UE may indicate the number of frequency layers it can support when the UE sends its positioning capabilities to the network (such as during a positioning protocol session). For example, the UE may indicate whether it can support one or four PFLs.

[0093] Figure 44 is a diagram illustrating an example of UE positioning based on reference signal measurements in accordance with various aspects of the present disclosure. In one example, the position of a UE 404 may be estimated based on multi-cell round trip time (multi-RTT) measurements, where a plurality of TRPs 402 may perform round trip time (RTT) measurements on signals transmitted to and received from the UE 404 to determine an approximate distance of the UE 404 relative to each of the plurality of TRPs 402. Similarly, the UE 404 may perform RTT measurements on signals transmitted to and received from the TRPs 402 to determine an approximate distance of each TRP relative to the UE 404. Then, based at least in part on the approximate distances of the UE 404 relative to the plurality of TRPs 402, a location management function (LMF) associated with the TRPs 402 and / or the UE 404 may estimate the position of the UE 404. For example, the TRP 406 may transmit at least one downlink positioning reference signal (DL-PRS) 410 to the UE 404 and may receive at least one uplink sounding reference signal (UL-SRS) 412 transmitted from the UE 404. Based at least in part on measuring the RTT 414 between the transmitted DL-PRS 410 and the received UL-SRS 412, a serving base station associated with the TRP 406 or an LMF associated with the TRP 406 may identify a location (e.g., distance) of the UE 404 relative to the TRP 406. Similarly, the UE 404 may transmit the UL-SRS 412 to the TRP 406 and may receive the DL-PRS 410 transmitted from the TRP 406. Based at least in part on measuring the RTT 414 between the transmitted UL-SRS 412 and the received DL-PRS 410, the UE 404 or an LMF associated with the UE 404 may identify the location of the TRP 406 relative to the UE 404. The multi-RTT measurement mechanism may be initiated by the LMF associated with the TRP 406 / 408 and / or the UE 404. The TRP may configure the UL-SRS resources to the UE via radio resource control (RRC) signaling. In some examples, the UE and the TRP may report the multi-RTT measurements to the LMF, and the LMF may estimate the location of the UE based on the reported multi-RTT metrics.

[0094] In other examples, the location of the UE may be estimated based on multiple antenna beam measurements, where the downlink angle of departure (DL-AoD) and / or uplink angle of arrival (UL-AoA) of transmissions between the UE and one or more TRPs may be used to estimate the location of the UE and / or the distance of the UE relative to each TRP. For example, referring back to Figure 4, with respect to DL-AoD, UE 404 may perform reference signal received power (RSRP) measurements of a DL-PRS set 416 transmitted from a plurality of transmission beams (e.g., DL-PRS beams) of TRP 408, and UE 404 may provide the DL-PRS beam measurements to a serving base station (or to an LMF associated with a base station). Based on the DL-PRS beam measurements, the serving TRP or LMF may derive a departure azimuth (e.g., Φ) and a departure zenith angle (e.g., θ) of the DL-PRS beam of TRP 408. The serving TRP or LMF may then estimate the positioning of UE 404 relative to TRP 408 based on the departure azimuth and departure zenith angle of the DL-PRS beam. Similarly, with respect to UL-AoA, the positioning of the UE may be estimated based on UL-SRS beam measurements measured at a different TRP (such as at TRP 402). Based on the UL-SRS beam measurement, the serving base station or the LMF associated with the serving base station can derive the arrival azimuth and arrival zenith angle of the UL-SRS beam from the UE, and the serving base station or the LMF can estimate the positioning of the UE and / or the distance of the UE relative to each of the TRPs based on the arrival azimuth and arrival zenith angle of the UL-SRS beam.

[0095] Figure 5A 500A is a diagram illustrating an example of a DL-PRS transmitted from multiple TRPs according to various aspects of the present disclosure. In one example, the serving base station may configure the DL-PRS to be transmitted from one or more TRPs in one time slot or across multiple time slots. If the DL-PRS is configured to be transmitted in one time slot, the serving base station may configure the starting resource element from each of the one or more TRPs in time and frequency. If the DL-PRS is configured to be transmitted across multiple time slots, the serving base station may configure the gap between the DL-PRS time slots, the periodicity of the DL-PRS, and / or the density of the DL-PRS in the time period. The serving base station may also configure the DL-PRS to start at any physical resource block (PRB) in the system bandwidth. In one example, the system bandwidth may be in the range of from 24 to 276 PRBs, with a step size of 4 PRBs (e.g., 24, 28, 32, 36, etc.). The serving base station may transmit the DL-PRS in a PRS beam, where the PRS beam may be referred to as a "PRS resource", and the entire set of PRS beams transmitted from a TRP on the same frequency may be referred to as a "PRS resource set" or a "PRS resource set", such as in conjunction with Figure 4 As described. Figure 5A As shown, DL-PRS transmitted from different TRPs and / or from different PRS beams may be multiplexed across symbols or time slots.

[0096] In some examples, each symbol of the DL-PRS may be configured with a comb structure in frequency, where the DL-PRS from a TRP of a base station may occupy every N subcarriers. The comb value N may be configured to be 2, 4, 6, or 12. The length of the PRS within a slot may be a multiple of N symbols, and the position of the first symbol within a slot may be flexible, as long as the slot consists of at least N PRS symbols. Diagram 500A shows an example of a comb-6 DL-PRS configuration, where the pattern for DL-PRS from different TRPs may be repeated after six (6) symbols.

[0097] Figure 5B 500B is a diagram illustrating an example of a UL-SRS transmitted from a UE according to various aspects of the present disclosure. In one example, the UL-SRS from the UE may be configured with a comb-4 pattern, where the pattern for the UL-SRS may be repeated after four (4) symbols. Similarly, the UL-SRS may be configured in one SRS resource of an SRS resource set, where each SRS resource may correspond to an SRS beam, and the SRS resource set may correspond to a set of SRS resources (e.g., beams) configured for a TRP. In some examples, the SRS resources may span 1, 2, 4, 8, or 12 consecutive OFDM symbols. In other examples, the comb size for the UL-SRS may be configured to be 2, 4, or 8.

[0098] Figure 6 600 is a diagram illustrating an example of estimating the positioning of a UE based on multi-RTT measurements from multiple TRPs according to various aspects of the present disclosure. The UE 602 may be configured by a serving base station to decode DL-PRS resources 612 corresponding to and transmitted from a first TRP 604 (TRP-1), a second TRP 606 (TRP-2), a third TRP 608 (TRP-3), and a fourth TRP 610 (TRP-4). The UE 602 may also be configured to transmit a UL-SRS on a UL-SRS resource set, which may include a first SRS resource 614, a second SRS resource 616, a third SRS resource 618, and a fourth SRS resource 620, so that a serving cell (e.g., the first TRP 604, the second TRP 606, the third TRP 608, and the fourth TRP 610) and other neighboring cells may be able to measure the UL-SRS resource set transmitted from the UE 602. For multi-RTT measurements based on DL-PRS and UL-SRS, since there may be a correlation between the UE's measurement of DL-PRS and the TRP's measurement of UL-SRS, the smaller the gap between the UE's DL-PRS measurement and the UE's UL-SRS transmission, the better the accuracy of estimating the UE's positioning and / or the UE's distance relative to each TRP may be.

[0099] It should be noted that the terms "positioning reference signal" and "PRS" generally refer to specific reference signals used for positioning in NR and LTE systems. However, as used herein, the terms "positioning reference signal" and "PRS" may also refer to any type of reference signal that can be used for positioning, such as but not limited to: PRS, TRS, PTRS, CRS, CSI-RS, DMRS, PSS, SSS, SSB, SRS, UL-PRS, etc. as defined in LTE and NR. In addition, the terms "positioning reference signal" and "PRS" may refer to downlink or uplink positioning reference signals, unless otherwise indicated by the context. If further distinction is needed between the types of PRS, the downlink positioning reference signal may be referred to as "DL-PRS", while the uplink positioning reference signal (e.g., SRS, PTRS used for positioning) may be referred to as "UL-PRS". In addition, for signals that can be transmitted in both uplink and downlink (e.g., DMRS, PTRS), these signals may be prepended with "UL" or "DL" to distinguish the direction. For example, "UL-DMRS" may be distinguished from "DL-DMRS".

[0100] In addition to combining Figures 4 to 6 In addition to the network-based positioning method described, the location of the UE can also be determined based on radio frequency (RF) fingerprints. In some scenarios, the RF transmitted from a wireless device (e.g., UE, TRP, wireless access point (AP), etc.) or from a group of wireless devices may contain one or more features / patterns that are different from another wireless device or another group of wireless devices. In other words, the RF transmitted from a wireless device or from a group of wireless devices may be unique, and the unique feature / pattern associated with the RF may be referred to as an RF fingerprint. For the purposes of this disclosure, the technology associated with RF fingerprints may be referred to as "RF fingerprinting" and / or "RFFP", and the positioning method associated with RF fingerprinting may be referred to as "RF fingerprinting-based positioning", "RFFP-based positioning" and / or "RFFP positioning". RF fingerprinting aims to develop a unique RF fingerprint of a wireless device that can be used as an identity, which may be similar to the operation of a biometric fingerprint. For example, an RF fingerprint may include radio measurements from multiple APs, such as received signal strength (RSS), path loss, and / or channel impulse response measurements, etc., to provide a fingerprint of the radio conditions at a specific location. The location of the fingerprint can then be estimated using the known locations of similar fingerprints previously recorded. For example, RF fingerprints from different locations can be captured and recorded in a database. Therefore, if the RF fingerprint captured by the wireless device matches the RF fingerprint stored in the database, the location of the wireless device can be estimated.

[0101] In some examples, the RF fingerprint database can be created and / or maintained based on machine learning (ML), and RFFP positioning with ML can be referred to as ML RFFP positioning. For ML RFFP positioning, RF fingerprints and their associated locations can be used as features and labels, respectively, to train the ML module in a supervised manner. After the ML module is trained, the ML module can be used to estimate the location by passing the newly captured RF fingerprint. In other words, the ML module can be configured to collect RF fingerprints and their associated locations, and the process can be referred to as ML location training or simply ML training. After the ML module is trained (for example, the RF fingerprints stored in the database are associated with known locations with a certain level of certainty / accuracy), the ML module can be used to estimate the location of the detected / captured RF fingerprint, and the process can be referred to as ML location inference or simply ML inference. In some examples, ML location training / inference can be applied to the UE side and / or the network side. RFFP ML training and inference can also be based on millimeter waves (mmW or mmwave), sub-THz and / or THz frequencies.

[0102] Figure 7 700 is a diagram illustrating an example of ML position training and inference for RFFP according to various aspects of the present disclosure. During an offline phase 702 (which may also be referred to as a training phase), a database may be configured to collect RF fingerprints (such as channel frequency responses (CFRs)) and their associated locations (e.g., locations where CFRs are captured). Thus, each fingerprint in the database may be associated with a known location, such as corresponding to local coordinates (X, Y) or (X, Y, Z), global coordinates (latitude, longitude), ground truth locations, addresses, and / or tags, etc. The collection of RF fingerprints may be based on field surveys, crowdsourcing, or by other means. After collecting the RF fingerprints and their associated locations, the database may process them and create a mapping between the RF fingerprints and their associated locations. The mapping may be accessed by a neural network (NN) or an ML module associated with the NN.

[0103] In an online phase 704 (which may also be referred to as an operation phase or a training phase), the NN or ML module may receive RF fingerprints captured by a wireless device with an unknown location. The NN may compare the RF fingerprint with the unknown location with the map, select one or more RF fingerprints from the map that are similar to the RF fingerprint with the unknown location, and calculate an estimated location of the wireless device. Throughout the process, the NN or ML module may continue to update the map to improve the accuracy of the location estimate.

[0104] Various aspects presented herein can improve the accuracy of RFFP-based positioning by associating RF fingerprints with beam directions and / or beam features to improve the uniqueness of RF fingerprints. Various aspects presented herein can enable the ML module to map directional RF fingerprint and / or beam feature inputs to device locations as outputs, wherein the directional RF fingerprint may include RF captured between antenna pairs and / or beam pairs (e.g., at least one antenna / beam of a transmitter and at least one antenna / beam of a receiver). For the purposes of this disclosure, an RF fingerprint including features associated with a transmission beam / beam and / or a receiving antenna / beam (e.g., a beam pair and / or an antenna pair)) can be referred to as a directional RF fingerprint or an RF fingerprint with directional features. For example, a directional RF fingerprint can be a channel impulse response (CIR) captured at one or more antenna pairs and / or one or more beam pairs, a channel frequency response (CFR) captured at one or more antenna pairs and / or one or more beam pairs, and / or a normalized histogram of received signal strength measured over a certain time period and / or frequency range captured at one or more antenna pairs and / or one or more beam pairs, and / or the like.

[0105] Figure 8 800 is a diagram illustrating an example ML module according to various aspects of the present disclosure. In one aspect, an ML module 802 (e.g., NN, deep NN, random forest, etc.) can receive a directional RF fingerprint 804 and its associated location from a database, such as in combination with Figure 7 As described. In some examples, the ML module 802 and the database may be located within the same entity (e.g., UE, base station) or connected to each other. In other examples, the ML module 802 and the database may be remotely located (e.g., the ML module 802 may remotely access the database). The ML module 802 may be associated with the UE (e.g., located at the UE), associated with a network entity (e.g., a base station), or associated with both. In addition, the training of the ML module 802 may be at the UE and / or at the network entity. After creating a mapping between the directional RF fingerprint 804 and its known location (e.g., through a database or through the ML module 802), the ML module 802 may estimate the location of the RF fingerprint based on the mapping. In some examples, the directional RF fingerprint 804 may also be associated with one or more beam features 806, and the ML module 802 may also estimate the location of the RF fingerprint based on the one or more beam features 806.

[0106] Fig. 9900 is a diagram illustrating an example directional RF fingerprint according to various aspects of the present disclosure. The UE may receive RF signals from multiple TRPs, which may include a first TRP (TRP 1), a second TRP (TRP 2), and up to an Nth TRP (TRPN) (collectively referred to as "TRP"). Each TRP may include multiple antennas capable of transmitting signals in multiple beam directions. For example, the first TRP may have ten antennas capable of forming twenty transmit beams (e.g., pointing in multiple directions), the second TRP may have fifteen antennas capable of forming thirty transmit beams, and the Nth TRP may also have twenty antennas capable of forming twenty transmit beams, and so on. Similarly, the UE may be able to receive signals via multiple antennas and via multiple beam directions. For example, the UE may have four antennas capable of forming six receive beams, where the UE may receive signals via six beam directions. Thus, the TRP may use one or more of its transmit antennas and / or one or more of its transmit beams to transmit signals to the UE, and the UE may use one or more of its receive antennas and / or one or more of its receive beams to receive signals. For the purposes of the present disclosure, a transmission antenna used by a transmission device or transmitter (e.g., UE or TRP) to transmit signals and a reception antenna used by a receiving device or receiver (e.g., TRP or UE) to receive signals may be referred to as an "antenna pair", and a transmission beam used by a transmission device or transmitter to transmit signals and a reception beam used by a receiving device or receiver to receive signals may be referred to as a "beam pair".

[0107] In one aspect of the present disclosure, a directional RF fingerprint (e.g., directional RF fingerprint 804) may include RF features captured at multiple antenna pairs between a UE and one or more TRPs. For example, a first antenna pair of the multiple antenna pairs may correspond to a first transmit antenna of a first TRP and a kth receive antenna of the UE, a second antenna pair of the multiple antenna pairs may correspond to a second transmit antenna of a second TRP and a kth receive antenna of the UE, and an Nth antenna pair of the multiple antenna pairs may correspond to a first transmit antenna of an Nth TRP and a kth receive antenna of the UE, and so on. In other words, the RF fingerprint may include directionally captured RF features, such as signals transmitted from multiple TRPs (e.g., one antenna from each TRP) and received by the UE at one or more receive antennas. Therefore, if there are N TRPs, the directional RF features may be captured based on N antenna pairs when the UE uses one receive antenna, or based on N×M antenna pairs when the UE uses M receive antennas.

[0108] In another example, multiple antenna pairs for capturing directional RF signatures may include signals transmitted from each antenna of the TRP and received by each antenna of the UE. Fig.10As shown in Figure 1000, if the first TRP (TRP 1) has N transmit antennas and the UE has k receive antennas, the RF characteristics can be captured based on N×k antenna pairs. Therefore, if the first TRP has 10 transmit antennas (i.e., N=10) and the UE has 4 receive antennas (i.e., k=4), the RF characteristics can be based on 40 antenna pairs (10×4=40) between the first TRP and the UE.

[0109] In one example, if Fig.11A As shown in FIG. 1100A of FIG. 1100A , the RF signature may be based on CIR (or directional CIR) captured at multiple antenna pairs. In another example, as Fig. 11B As shown in FIG. 1100B of , the RF signature may be based on CFR (or directional CFR) captured at multiple antenna pairs (e.g., CIR may be an inverse Fourier transform of CFR). In another example, Fig. 11C As shown in FIG. 1100C , the RF features can be based on a normalized histogram of received signal strengths measured over a certain time period and / or frequency range captured at multiple antenna pairs. For example, the RF features can be based on signal strengths measured over a defined duration or over a certain frequency range at multiple antenna pairs.

[0110] As combined Fig.10 As described, if the multiple antenna pairs used to capture directional RF features include signals transmitted from each antenna of the TRP and received by each antenna of the UE, there may be a large number of antenna pairs to be processed by the database or ML module. Therefore, in another aspect of the present disclosure, a directional RF fingerprint (e.g., directional RF fingerprint 804) may include RF features based on complex sums captured at multiple antenna pairs between the UE and one or more TRPs. For example, the RF features may be based on the complex sum of CIRs captured at multiple antenna pairs, the complex sum of CFRs captured at multiple antenna pairs, and / or a normalized histogram of received signal strength measured over a certain time period and / or frequency range captured at multiple antenna pairs and beam pairs.

[0111] For example, returning a reference Fig.10 , the complex sum of CIRs captured at multiple antenna pairs can be calculated based on the following. The first TRP (TRP 1) can have M tr transmit antennas and N transmit beams, and the UE may have M tu receive antennas and k receive beams. Therefore, there may be M tr M tu antenna pairs and kN TX-RX beam pairs. If cir j,iindicates the CIR captured for the i-th beam pair and the j-th antenna pair, then the RF fingerprint at antenna pair j can be based on the antenna pair j = ∑ i cir j，i The complex sum of the CIRs at .

[0112] In another aspect of the present disclosure, in order to further reduce the size of the RF fingerprint, the RF features of the RF fingerprint may be further compressed. Fig.12 1200 is a diagram illustrating an example directional RF fingerprint with compression according to various aspects of the present disclosure. In one example, an encoder network (which can be associated with an ML module) can be used to compress RF features captured from multiple antenna pairs. The encoder network can include a series of layers starting with a high-dimensional input, and the encoder network can map the input to a lower-dimensional output. In other words, the encoder network can convert a large number of inputs into a potential representation with a smaller number of outputs. Therefore, a directional RF fingerprint (e.g., directional RF fingerprint 804) can be based on the compression of RF features using an encoder network. For example, the RF fingerprint can be based on a compressed CIR captured at multiple antenna pairs using an encoder network, a compressed CFR captured at multiple antenna pairs using an encoder network, and / or a compressed normalized histogram of received signal strength measured over a certain time period and / or frequency range captured at multiple antenna pairs and multiple beam pairs using an encoder network. For example, as shown in diagram 1200, different CIRs measured using different combinations of beam pairs and antenna pairs (e.g., CIR of beam pair 1 and antenna pair 1, CIR of beam pair 2 and antenna pair 1, beam pair 1 and antenna pair 2, beam pair 2 and antenna pair 2, etc.) can be compressed by the encoder network to produce a latent representation, where the latent representation can be a simplified model of the input data created by the neural network.

[0113] In another aspect of the present disclosure, to further reduce the size of the RF fingerprint, the RF fingerprint may be based on a plurality of strongest beam pairs. Fig.13 1300 is a diagram illustrating an example directional RF fingerprint based on the strongest beam pairs in accordance with various aspects of the present disclosure. In one example, the RF fingerprint can be based on the P strongest CIRs (e.g., the four strongest CIRs) captured at multiple antenna pairs, the P strongest directional CFRs captured at multiple antenna pairs, and / or the P strongest normalized histograms of received signal strength measured over a certain time period and / or frequency range captured at multiple antenna pairs. For example, as shown at 1302, the RF characteristics of the first antenna pair can be based on the four strongest beam pairs.

[0114] As combined Figure 8As described, in some examples, the directional RF fingerprint 804 may also be associated with one or more beam characteristics 806, so that the ML module 802 may also estimate the location of the RF fingerprint based on the one or more beam characteristics 806. In other words, in addition to the directional RF fingerprint 804, the one or more beam characteristics 806 may also be input into the ML module 802 (or an associated NN).

[0115] In one example, one or more beam characteristics 806 may include a beam shape, such as a beam shape for collecting or measuring RF fingerprints and / or a beam shape for transmitting RF signals (or RF fingerprints). For example, the beam shape may include a beam width (azimuth and / or elevation) and / or a normalized radiation pattern of a receive / transmit beam (e.g., a beam pattern in azimuth and / or elevation directions), etc. The beam shape may also be stored as a lookup table in the UE or network entity, where the UE and the network entity may exchange beam shapes during operation (e.g., once during an operation lifecycle).

[0116] In another example, one or more beam characteristics 806 may include a cumulative distribution function (CDF) and / or a probability density function (PDF) based on a beam-based spherical effective isotropic radiated power (EIRP) measurement. For example, a wireless device capturing an RF fingerprint or transmitting an RF signal / fingerprint may make a spherical EIRP measurement for each beam configuration. Then, Z j The CDF or PDF of can be used to characterize the beam used (e.g., receive beam, target beam, transmit beam, etc.), where (Z j =EIRP j -Pmax) and j can be an arbitrary beam index. In some examples, the CDF and / or PDF of the beam can be calculated offline and stored as a lookup table. In other examples, the CDF and / or PDF of the beam-based spherical EIRP measurement can also include at least one beam direction as an additional feature, such as peak azimuth and / or elevation, etc.

[0117] For example, Fig.14 As shown in FIG1400 , a spherical coverage test on a per-UE basis can be used to ensure that the composite beam pattern on all beams is as wide as possible. The density of the measurement can be based on a planar uniform configuration and / or a spherical uniform configuration. In one aspect of the present disclosure, the spherical coverage test is configured to be extended to a per-beam basis to characterize the input to the ML module as well as the RF fingerprint. For example, for each beam j in B, where B can be a set of beams (e.g., a codebook), the wireless device can be configured to form beam j (e.g., codebook, settings of delay lines, etc.). A spherical measurement test can then be performed in the far-field region and the EIRP can be recorded in possible spherical directions (e.g., Where E j is the set of EIRPs recorded for beam j). The granularity of measurements in azimuth and elevation (e.g., δφ, δθ) can be determined based on regulatory specifications. For example, δφ, δθ can be configured to be uniform or non-uniform based on regulatory requirements. In addition, each EIRP measurement can be expressed with its azimuth angle φ i and the elevation angle θ i Then, the output can be expressed as Where E j contains the EIRP captured at all possible azimuth / elevation angles of beam j, e.g., E j ={EIRP φ ,θ:φ∈Φ,θ∈Θ}.

[0118] In another example, the one or more beam characteristics 806 may include a beam configuration, such as a phase shift and / or delay of a beam (e.g., a receive beam, a beam used to capture an RF fingerprint, etc.). The beam configuration may be based on a standardized codebook (e.g., a beam codebook) and / or based on a customized codebook. The beam configuration may also be stored as a lookup table in the UE or the network entity, where the UE and the network entity may exchange beam configurations during operation (e.g., once during an operation lifecycle).

[0119] In another example, the one or more beam characteristics 806 may include one or more beam measurements, such as a reference signal received power (RSRP) and / or a signal to interference plus noise ratio (SINR) of a beam (e.g., a transmit beam, a receive beam, etc.).

[0120] In another example, the one or more beam features 806 may include a graph convolutional network (GCN) based beam embedding. Fig.15 1500 is a diagram illustrating an example of GCN-based extraction of beam features in accordance with various aspects of the present disclosure. In one example, spherical measurements can be performed at a wireless device, and an icosahedron graph can be used to represent beam gains measured at different azimuth and elevation angles, where the vertices can correspond to the locations where the beam gains were measured. The icosahedron can then be encoded using GCN into a compact latent representation that can be used as a beam feature. Similarly, the GCN-based beam embeddings (or beam features) can also be stored as a lookup table in a UE or a network entity, where the UE and the network entity can exchange beam embeddings / features during operation (e.g., once during an operation lifecycle).

[0121] Return to reference Figure 8, after the ML module 802 is trained or has access to a database including mappings between directional RF fingerprints 804 / beam signatures 806 and their corresponding locations, the ML module 802 can perform interference of the location based on the directional RF fingerprint / beam signature input. For example, based on the received directional RF fingerprint, the ML module 802 can estimate local coordinates (X, Y) or (X, Y, Z), global coordinates (latitude, longitude), ground truth location, address and / or label, etc. based on the mapping.

[0122] Fig.16 1600 is a diagram illustrating an example of single-shot beam-based ML module training and inference according to various aspects of the present disclosure. In one aspect of the present disclosure, inference of location can be processed by considering single-shot beamforming and constructing applicable RF fingerprints and beam characteristics used as input for ML positioning. For example, a TRP can communicate with a UE based on a beam pair (e.g., a first transmit beam of the TRP and a second receive beam of the UE). When an RFFP-based positioning session is initiated for the UE, the UE can use the same beam pair to perform RF measurements (e.g., for receiving and measuring PRS transmitted from the TRP) and capture RF fingerprints and / or beam characteristics. Then, if the ML module (e.g., ML module 802) is located on the UE side, the UE can perform inference, or if the ML module is located on the network side, the UE can send the captured RF fingerprint and / or beam characteristics back to the network (e.g., to a serving base station) to perform inference. Since the beam used for positioning may be more likely to be the closest beam used for communication, the single-shot beam inference configuration can provide short positioning latency. Thus, for a single-shot beam-based inference configuration, the ML module can be trained to map directional RF fingerprint features (e.g., input) captured from one TRP on one beam pair to a UE position (e.g., output), where the captured RF fingerprint and beam features from one TRP can be passed to the ML module for ML module training and inference. In some examples, the beam features can be included as additional inputs. In addition, the RF fingerprint features can also include RF fingerprints of different transmit-receive (Tx-Rx) antenna pairs (if available).

[0123] In one aspect, as shown at 1602, ML module training and inference can be based on a single-input single-output (SISO) model, where the ML module can receive one RF fingerprint (e.g., CIR, CFR, and / or normalized histogram of a beam pair, etc.) and one or more beam features (if available) for ML module training and inference, and the ML module can map the one RF fingerprint and the one or more beam features (if available) to a location for ML module training and inference. In another aspect, as shown at 1604, ML module training and inference can be based on a multiple-input multiple-output (MIMO) configuration, where the ML module can receive multiple RF fingerprints (e.g., CIR, CFR, and / or normalized histogram of multiple antenna pairs, etc.) and one or more beam features (if available) for ML module training and inference, and the ML module can map the multiple RF fingerprints and the one or more beam features (if available) to a location for ML module training and inference.

[0124] Fig.171700 is a diagram illustrating an example of beam scanning based ML module training and inference according to various aspects of the present disclosure. In another aspect of the present disclosure, inference of location may be based on beam scanning. For example, the UE and the network (e.g., TRP) may each scan different beams and collect applicable RF fingerprints and beam characteristics that may be used as input for ML positioning. For example, when an RFFP-based positioning session is initiated for a UE, if the TRP has eight (8) transmit beams and the UE has six (6) receive beams, the TRP may transmit at least one PRS to the UE via its eight transmit beams, and the UE may receive the PRS via its six receive beams based on beam scanning. The UE may then collect applicable RF fingerprints and / or beam characteristics captured during the beam scanning. Similarly, based on the captured RF fingerprints and / or beam characteristics, if the ML module (e.g., ML module 802) is located on the UE side, the UE may perform inference, or if the ML module is located on the network side, the UE may send the captured RF fingerprints and / or beam characteristics back to the network (e.g., to a serving base station) to perform inference. In some examples, if the UE and / or the network has the capability to activate multiple beams simultaneously, the beam scanning overhead can be reduced. For example, if the TRP has the capability to transmit PRS via multiple transmit beams at a time, and / or the UE has the capability to receive PRS via multiple receive beams at a time, the beam scanning overhead for ML positioning can be reduced to improve positioning latency. Thus, the ML module can be trained to map RF fingerprint features (e.g., input) captured from one TRP on multiple scanning beam pairs to UE positions (e.g., output), where the RF fingerprint captured based on beam scanning and beam features (if available) from one TRP can be passed to the ML module for ML module training and inference. Similarly, beam features of the scanning beams can be included as additional inputs.

[0125] In one example, as shown at 1702, the RF fingerprint feature may include RF fingerprints (e.g., CIR, CFR, and / or normalized histogram, etc.) of different transmit-receive antenna pairs (if available). In another example, as shown at 1704, the RF fingerprint feature may include the sum of RF fingerprints captured on the scanning beam (e.g., ∑i). In addition, the scanning beam may include a subset of the transmission beam and / or the reception beam.

[0126] Fig.181800 is a diagram illustrating an example of ML module training and inference based on a multi-TRP single-shot beam according to various aspects of the present disclosure. In another aspect of the present disclosure, the inference of position can be processed by considering single-shot beamforming between the UE and multiple TRPs and constructing applicable RF fingerprints and beam characteristics used as input for ML positioning. For example, multiple TRPs can communicate with the UE based on multiple beam pairs (e.g., one beam pair between each TRP and the UE). When an RFFP-based positioning session is initiated for the UE, the UE can use the same beam pair to perform RF measurements (e.g., for receiving and measuring PRSs transmitted from multiple TRPs) and capture RF fingerprints and / or beam characteristics from multiple TRPs. Then, if the ML module (e.g., ML module 802) is located on the UE side, the UE can perform inference, or if the ML module is located on the network side, the UE can send the captured RF fingerprints and / or beam characteristics back to the network (e.g., to a serving base station) to perform inference. Since the beam used for positioning may be more likely to be the closest beam used for communication, the single-shot beam inference configuration can provide short positioning latency. Thus, for an inference configuration based on a multi-TRP single-trigger beam, the ML module may be trained to map directional RF fingerprint features (e.g., input) captured from multiple TRPs on a beam of one UE to a UE location (e.g., output), where the captured RF fingerprints and beam features from different TRPs may be passed to the ML module for ML module training and inference. In some examples, beam features may be included as additional inputs. In addition, the RF fingerprint features may also include RF fingerprints of different transmit-receive (Tx-Rx) antenna pairs (if available). For example, as shown at 1802, the ML module may receive multiple RF fingerprints (e.g., CIR, CFR, and / or normalized histograms of multiple antenna pairs, etc.) and one or more beam features (if available) from each TRP for ML module training and inference, and the ML module may map multiple RF fingerprints and one or more beam features (if available) from multiple TRPs to locations for ML module training and inference.

[0127] Fig.19Figure 1900 is an example of ML module training and inference based on multi-TRP beam scanning according to various aspects of the present disclosure. In another aspect of the present disclosure, the inference of location can be based on beam scanning between the UE and multiple TRPs. For example, the UE can perform beam scanning with each of the multiple TRPs and collect applicable RF fingerprints (e.g., CIR, CFR, and / or normalized histogram, etc.) and beam characteristics (if available) that can be used as input for ML positioning. Then, based on the RF fingerprints and / or beam characteristics captured from the multiple TRPs, if the ML module (e.g., ML module 802) is located on the UE side, the UE can perform inference, or if the ML module is located on the network side, the UE can send the captured RF fingerprints and / or beam characteristics back to the network (e.g., to a serving base station) to perform inference. In some examples, if the UE and / or TRP has the ability to activate multiple beams simultaneously, the beam scanning overhead can be reduced. For example, if a TRP has the capability to transmit PRS via multiple transmit beams at a time, and / or a UE has the capability to receive PRS via multiple receive beams at a time, the beam scanning overhead for ML positioning can be reduced to improve positioning latency. Thus, the ML module can be trained to map RF fingerprint features (e.g., input) captured from multiple TRPs on multiple scanning beam pairs to UE locations (e.g., output), where the RF fingerprints captured based on multiple scanning beams and beam features (if available) from multiple TRPs can be passed to the ML module for ML module training and inference. Similarly, beam features of the scanning beams can be included as additional inputs.

[0128] In one example, if Fig. 20A As shown in FIG. 2000A of FIG. 2000A , the RF fingerprint feature based on multi-TRP beam scanning may include RF fingerprints (e.g., CIR, CFR, and / or normalized histogram, etc.) of different transmit-receive antenna pairs (if available) from each TRP in a plurality of TRPs (e.g., from the first TRP to the Nth TRP). In another example, as Fig. 20B As shown in FIG. 2000B , the RF fingerprint feature based on multi-TRP beam scanning may include the sum (e.g., ∑ i ). Similarly, a scanning beam may include a subset of a transmit beam and / or a receive beam.

[0129] Fig.21 is a communication flow 2100 illustrating an example of directional RF fingerprint based ML module training and inference according to various aspects of the present disclosure. The numbers associated with the communication flow 2100 do not specify a particular chronological order and are only used as a reference for the communication flow 2100.

[0130] In one aspect, as shown at 2110, a network entity associated with the ML module 2102 may receive a plurality of RF fingerprints from one or more wireless devices 2104, wherein each of the plurality of RF fingerprints may be associated with at least one directional characteristic, a location, and / or at least one beam characteristic, such as in combination with Figure 8 20 . The network entity 2108 may be a UE, a location server, a LMF, a base station, etc. The ML module 2102 may be associated with a neural network, a deep neural network, or a random forest algorithm, etc. The one or more wireless devices 2104 may be UEs, TRPs, and / or other RF fingerprint capture devices that are collecting RF fingerprints and their associated locations for the ML module 2102.

[0131] In one example, if combined with Fig.11A , Fig. 11B and Fig. 11C As described, the at least one directional characteristic may correspond to a CIR or CFR captured from a reference signal (eg, a PRS or SRS) associated with UE positioning.

[0132] For example, if combined Fig. 9 and Fig.10 As described, at least one directional feature may correspond to a CIR or CFR captured at a plurality of antenna pairs, wherein each of the plurality of antenna pairs may include a transmission antenna of a transmitting device and a reception antenna of a receiving device. In some examples, at least one directional feature may correspond to at least one of a normalized histogram of received signal strength measured over a period of time or a frequency range captured at a plurality of antenna pairs, wherein each of the plurality of antenna pairs may include a transmission antenna of a transmitting device and a reception antenna of a receiving device.

[0133] In another example, in combination with Fig.10 As described, at least one directional feature may correspond to a complex sum of CIRs or CFRs captured at a plurality of antenna pairs or a plurality of beam pairs, each of the plurality of antenna pairs may include a transmission antenna of a transmission device and a reception antenna of a reception device, and each of the plurality of beam pairs may include a transmission beam of the transmission device and a reception beam of the reception device. In some examples, at least one directional feature may correspond to a normalized histogram of received signal strength measured over a period of time or at least one of frequency ranges captured at a plurality of antenna pairs and a plurality of beam pairs, each of the plurality of antenna pairs may include a transmission antenna of a transmission device and a reception antenna of a reception device, and each of the plurality of beam pairs may include a transmission beam of the transmission device and a reception beam of the reception device.

[0134] In another example, in combination with Fig.10As described, at least one directional feature may correspond to a compressed CIR or compressed CFR captured at a plurality of antenna pairs or a plurality of beam pairs, wherein each of the plurality of antenna pairs may include a transmission antenna of a transmitting device and a reception antenna of a receiving device, and each of the plurality of beam pairs may include a transmission beam of the transmitting device and a reception beam of the receiving device. In some examples, at least one directional feature may correspond to at least one of a compressed normalized histogram of received signal strength measured over a period of time or a frequency range captured at a plurality of antenna pairs and a plurality of beam pairs, wherein each of the plurality of antenna pairs may include a transmission antenna of a transmitting device and a reception antenna of a receiving device, and each of the plurality of beam pairs may include a transmission beam of the transmitting device and a reception beam of the receiving device.

[0135] In another example, in combination with Fig.13 As described, at least one directional feature may correspond to one or more strongest CIRs or one or more strongest CFRs captured at a plurality of antenna pairs or a plurality of beam pairs, wherein each of the plurality of antenna pairs may include a transmission antenna of a transmission device and a reception antenna of a reception device, and each of the plurality of beam pairs may include a transmission beam of a transmission device and a reception beam of a reception device. In some examples, at least one directional feature may correspond to at least one of one or more strongest normalized histograms of received signal strength measured over a period of time or over a frequency range captured at the plurality of antenna pairs, wherein each of the plurality of antenna pairs may include a transmission antenna of a transmission device and a reception antenna of a reception device.

[0136] In some examples, the RF fingerprint may also be associated with at least one beam feature, such as in combination with Figure 8 The position of the UE may be further estimated based at least in part on the at least one beam characteristic. In one example, the at least one beam characteristic may include one or more of the following: beam shape, CDF or PDF of a spherical EIRP measurement based on the beam, beam configuration, beam measurement, or GCN-based beam embedding (e.g., as combined with Fig.15 Additionally, at least one beam characteristic may be associated with at least one of a transmit beam at a transmitting device or a receive beam at a receiving device.

[0137] At 2112, the network entity 2108 or the ML module 2102 may be trained based on the plurality of RF fingerprints in the database and their directional characteristics, associated locations, and / or associated beam characteristics to create a mapping between each RF fingerprint in the plurality of RF fingerprints and at least one directional characteristic, location, and / or at least one beam characteristic. The mapping may also be stored in the database.

[0138] At 2114, the network entity 2108 or the ML module 2102 may receive a request from the UE positioning request entity 2106, which requests the ML module 2102 to determine the location of the UE based on the RF fingerprint associated with the UE or captured by the UE. In one example, the UE positioning request entity 2106 may be the UE itself, the UE's serving base station, the LMF and / or the location server, etc.

[0139] At 2116, the network entity 2108 or the ML module 2102 may estimate the location of the UE based on a mapping between the RF fingerprint and the associated directional characteristics, location, and / or beam characteristics obtained at 2112. For example, the ML module may estimate the location of the UE based at least in part on matching the RF fingerprint captured by the UE with at least one RF fingerprint of a plurality of RF fingerprints in a database. The process of estimating the location of the UE may be referred to as ML module inference or simply ML inference.

[0140] In one example, ML inference and / or training can be based on a beam pair between a beam of the UE and a beam of the TRP, such as for a combined Fig.16 Single-shot beam based training and inference described. For example, the ML module 2102 can map a directional feature captured from an antenna pair to a location, where the antenna pair can be associated with a TRP and a UE.

[0141] In another example, ML inference and / or training can be based on beam scanning between one or more beams of the UE and one or more beams of the TRP, such as for a combined Fig.17 For example, the ML module 2102 may map multiple directional features captured from multiple scanning beam pairs to a location, where the multiple scanning beam pairs may be associated with a TRP and a UE.

[0142] In some examples, such as combining Fig.18 As described in Figure 20, ML inference and training can be captured from or based on multiple beam pairs to a location, where the multiple beam pairs can be associated with a UE and multiple TRPs. For example, the ML inference and training module can map multiple directional features captured from multiple scanning beam pairs to a location, where the multiple scanning beam pairs can be associated with a UE and multiple TRPs.

[0143] At 2118 , the network entity 2108 or the ML module may report the estimated position of the UE to the UE positioning requesting entity 2106 .

[0144] Fig. 222200 is a flow chart of a method of wireless communication. The method may be performed by a network entity or a component of a network entity (e.g., a base station 102, 180, 310; a UE 104, 350, 404, 602; a TRP 402, 604, 606, 608, 610; an ML module 2102; 803; a device 2402). The method may enable the network entity to associate an RF fingerprint with a directional feature and / or a beam feature to improve UE positioning based on the RF fingerprint.

[0145] At 2202, a network entity may receive a plurality of first RF fingerprints from one or more wireless devices, each of the plurality of first RF fingerprints may be associated with at least one directional feature and a location, such as in combination with Fig.21 For example, at 2110, a network entity 2108 associated with the ML module 2102 may receive a plurality of first RF fingerprints from one or more wireless devices 2104, each of the plurality of first RF fingerprints may be associated with at least one directional feature and a location. The receiving of the plurality of first RF fingerprints may be performed by, for example Fig.24 The RF fingerprint processing component 2440 and / or the receiving component 2430 of the device 2402 are performed.

[0146] In one example, at least one directional feature may correspond to a CIR or CFR captured from a PRS or SRS.

[0147] In another example, the at least one directional feature may correspond to a CIR or CFR captured at a plurality of antenna pairs, each of which may include a transmit antenna of a transmitting device and a receive antenna of a receiving device.

[0148] In another example, at least one directional feature may correspond to a normalized histogram of received signal strength measured over a period of time or at least one of a frequency range captured at a plurality of antenna pairs, each of which may include a transmit antenna of a transmitting device and a receive antenna of a receiving device.

[0149] In another example, at least one directional feature may correspond to a complex sum of CIRs or CFRs captured at multiple antenna pairs or multiple beam pairs, each of the multiple antenna pairs may include a transmit antenna of a transmitting device and a receive antenna of a receiving device, and each of the multiple beam pairs may include a transmit beam of a transmitting device and a receive beam of a receiving device.

[0150] In another example, at least one directional feature may correspond to a normalized histogram of received signal strength measured over a period of time or at least one of a frequency range captured at multiple antenna pairs and multiple beam pairs, each of the multiple antenna pairs may include a transmit antenna of a transmitting device and a receive antenna of a receiving device, and each of the multiple beam pairs may include a transmit beam of a transmitting device and a receive beam of a receiving device.

[0151] In another example, at least one directional feature may correspond to a compressed CIR or a compressed CFR captured at multiple antenna pairs or multiple beam pairs, each of the multiple antenna pairs may include a transmit antenna of a transmitting device and a receive antenna of a receiving device, and each of the multiple beam pairs may include a transmit beam of the transmitting device and a receive beam of the receiving device.

[0152] In another example, at least one directional feature may correspond to at least one of a compressed normalized histogram of received signal strength measured over a period of time or a frequency range captured at multiple antenna pairs and multiple beam pairs, each of the multiple antenna pairs may include a transmit antenna of a transmitting device and a receive antenna of a receiving device, and each of the multiple beam pairs may include a transmit beam of a transmitting device and a receive beam of a receiving device.

[0153] In another example, at least one directional feature may correspond to one or more strongest CIRs or one or more strongest CFRs captured at multiple antenna pairs or multiple beam pairs, each of the multiple antenna pairs may include a transmit antenna of a transmitting device and a receive antenna of a receiving device, and each of the multiple beam pairs may include a transmit beam of a transmitting device and a receive beam of a receiving device.

[0154] In another example, at least one directional feature may correspond to at least one of one or more strongest normalized histograms of received signal strength measured over a period of time or a frequency range captured at multiple antenna pairs, each of which may include a transmit antenna of a transmitting device and a receive antenna of a receiving device.

[0155] In another example, each of the plurality of first RF fingerprints may also be associated with at least one beam characteristic, and the position of the UE may also be estimated based at least in part on the at least one beam characteristic. In such an example, the at least one beam characteristic may include one or more of: a beam shape, a CDF or PDF of a beam-based spherical EIRP measurement, a beam configuration, a beam measurement, or a GCN-based beam embedding. In such an example, the at least one beam characteristic may be associated with at least one of a transmit beam at a transmitting device or a receive beam at a receiving device.

[0156] In another example, the network entity may be a location server, UE, or base station associated with the ML module. In such an example, the ML module may be associated with a NN, a deep NN, or a random forest algorithm.

[0157] At 2204, the network entity may train the ML module based on each first RF fingerprint in the plurality of first RF fingerprints and the associated at least one directional feature and the associated location to create a mapping between each first RF fingerprint in the plurality of first RF fingerprints and the associated at least one directional feature and the associated location, wherein the location of the UE is estimated based on the mapping between the at least one second RF fingerprint and the associated at least one directional feature and the associated location, such as in combination with Fig.21 For example, at 2112, the network entity 2108 may train the ML module 2102 based on the plurality of RF fingerprints and the associated directional features and the associated locations to create a mapping between each RF fingerprint in the plurality of RF fingerprints and the associated directional features and the associated locations. The training of the ML module may be performed by, for example Fig.24 The ML module training component 2446 of the device 2402 is executed.

[0158] At 2206, the network entity may receive a request to determine the location of the UE based on at least one second RF fingerprint associated with or captured by the UE, such as in conjunction with Fig.21 For example, the network entity 2108 or the ML module 2102 may receive a request from the UE positioning request entity to determine the location of the UE based on at least one RF fingerprint captured by the UE. The reception of the request to determine the location of the UE may be performed by, for example, the location request processing component 2442 and / or the receiving component 2430.

[0159] At 2208, the network entity may estimate the location of the UE based at least in part on matching the at least one second RF fingerprint with at least one RF fingerprint of the plurality of first RF fingerprints, such as in combination with Fig.10 For example, at 2116, the network entity 2108 may estimate the location of the UE based at least in part on matching the at least one RF fingerprint with one of the RF fingerprints in the database. The estimate of the location of the UE may be determined by, for example Fig.24 The position inference component 2444 of the device 2402 is used to perform.

[0160] In one example, at least one second RF fingerprint associated with the UE can be based on a beam pair between a beam of the UE and a beam of the TRP.

[0161] In another example, at least one second RF fingerprint associated with the UE can be based on beam scanning between one or more beams of the UE and one or more beams of the TRP.

[0162] In another example, a network entity may be associated with an ML module, and the network entity may train the ML module to map a directional feature captured from an antenna pair associated with a TRP and a UE to a location.

[0163] In another example, a network entity is associated with an ML module, and the network entity may train the ML module to map multiple directional features captured from multiple scanning beam pairs associated with one TRP and one UE to one location.

[0164] In another example, a network entity is associated with an ML module, and the network entity may train the ML module to map multiple directional features captured from multiple beam pairs associated with a UE and multiple TRPs to a location.

[0165] In another example, a network entity is associated with an ML module, and the network entity may train the ML module to map multiple directional features captured from multiple scanning beam pairs associated with a UE and multiple TRPs to a location.

[0166] Fig.23 2300 is a flow chart of a method of wireless communication. The method may be performed by a network entity or a component of a network entity (e.g., a base station 102, 180, 310; a UE 104, 350, 404, 602; a TRP 402, 604, 606, 608, 610; an ML module 2102; 803; a device 2402). The method may enable the network entity to associate an RF fingerprint with a directional feature and / or a beam feature to improve UE positioning based on the RF fingerprint.

[0167] At 2302, a network entity may receive a plurality of first RF fingerprints from one or more wireless devices, each of the plurality of first RF fingerprints may be associated with at least one directional feature and a location, such as in combination with Fig.21 For example, at 2110, a network entity 2108 associated with the ML module 2102 may receive a plurality of first RF fingerprints from one or more wireless devices 2104, each of the plurality of first RF fingerprints may be associated with at least one directional feature and a location. The receiving of the plurality of first RF fingerprints may be performed by, for example Fig.24 The RF fingerprint processing component 2440 and / or the receiving component 2430 of the device 2402 are performed.

[0168] In one example, at least one directional feature may correspond to a CIR or CFR captured from a PRS or SRS.

[0169] In another example, the at least one directional feature may correspond to a CIR or CFR captured at a plurality of antenna pairs, each of which may include a transmit antenna of a transmitting device and a receive antenna of a receiving device.

[0170] In another example, at least one directional feature may correspond to a normalized histogram of received signal strength measured over a period of time or at least one of a frequency range captured at a plurality of antenna pairs, each of which may include a transmit antenna of a transmitting device and a receive antenna of a receiving device.

[0171] In another example, at least one directional feature may correspond to a complex sum of CIRs or CFRs captured at multiple antenna pairs or multiple beam pairs, each of the multiple antenna pairs may include a transmit antenna of a transmitting device and a receive antenna of a receiving device, and each of the multiple beam pairs may include a transmit beam of a transmitting device and a receive beam of a receiving device.

[0172] In another example, at least one directional feature may correspond to a normalized histogram of received signal strength measured over a period of time or at least one of a frequency range captured at multiple antenna pairs and multiple beam pairs, each of the multiple antenna pairs may include a transmit antenna of a transmitting device and a receive antenna of a receiving device, and each of the multiple beam pairs may include a transmit beam of a transmitting device and a receive beam of a receiving device.

[0173] In another example, at least one directional feature may correspond to a compressed CIR or a compressed CFR captured at multiple antenna pairs or multiple beam pairs, each of the multiple antenna pairs may include a transmit antenna of a transmitting device and a receive antenna of a receiving device, and each of the multiple beam pairs may include a transmit beam of the transmitting device and a receive beam of the receiving device.

[0174] In another example, at least one directional feature may correspond to at least one of a compressed normalized histogram of received signal strength measured over a period of time or a frequency range captured at multiple antenna pairs and multiple beam pairs, each of the multiple antenna pairs may include a transmit antenna of a transmitting device and a receive antenna of a receiving device, and each of the multiple beam pairs may include a transmit beam of a transmitting device and a receive beam of a receiving device.

[0175] In another example, at least one directional feature may correspond to one or more strongest CIRs or one or more strongest CFRs captured at multiple antenna pairs or multiple beam pairs, each of the multiple antenna pairs may include a transmit antenna of a transmitting device and a receive antenna of a receiving device, and each of the multiple beam pairs may include a transmit beam of a transmitting device and a receive beam of a receiving device.

[0176] In another example, at least one directional feature may correspond to at least one of one or more strongest normalized histograms of received signal strength measured over a period of time or a frequency range captured at multiple antenna pairs, each of which may include a transmit antenna of a transmitting device and a receive antenna of a receiving device.

[0177] In another example, each of the plurality of first RF fingerprints may also be associated with at least one beam characteristic, and the position of the UE may also be estimated based at least in part on the at least one beam characteristic. In such an example, the at least one beam characteristic may include one or more of: a beam shape, a CDF or PDF of a beam-based spherical EIRP measurement, a beam configuration, a beam measurement, or a GCN-based beam embedding. In such an example, the at least one beam characteristic may be associated with at least one of a transmit beam at a transmitting device or a receive beam at a receiving device.

[0178] In another example, the network entity may be a location server, a UE, or a base station associated with the ML module. In such an example, the ML module may be associated with a NN, a deep NN, or a random forest algorithm. In such an example, the network entity may train the ML module to create a mapping between each of the plurality of first RF fingerprints and the associated at least one directional feature and the associated location based on each first RF fingerprint in the plurality of first RF fingerprints and the associated at least one directional feature and the associated location, wherein the location of the UE is estimated based on the mapping between the at least one second RF fingerprint and the associated at least one directional feature and the associated location, such as in combination with Fig.21 For example, at 2112, the network entity 2108 may train the ML module 2102 based on the plurality of RF fingerprints and the associated directional features and the associated locations to create a mapping between each RF fingerprint in the plurality of RF fingerprints and the associated directional features and the associated locations. The training of the ML module may be performed by, for example Fig.24 The ML module training component 2446 of the device 2402 is executed.

[0179] At 2306, the network entity may receive a request to determine a location of the UE based on at least one second RF fingerprint associated with or captured by the UE, such as in conjunction with Fig.21 For example, the network entity 2108 or the ML module 2102 may receive a request from the UE positioning request entity to determine the location of the UE based on at least one RF fingerprint captured by the UE. The reception of the request to determine the location of the UE may be performed by, for example, the location request processing component 2442 and / or the receiving component 2430.

[0180] At 2308, the network entity may estimate the location of the UE based at least in part on matching the at least one second RF fingerprint with at least one RF fingerprint of the plurality of first RF fingerprints, such as in combination with Fig.10 For example, at 2116, the network entity 2108 may estimate the location of the UE based at least in part on matching the at least one RF fingerprint with one of the RF fingerprints in the database. The estimate of the location of the UE may be determined by, for example Fig.24 The position inference component 2444 of the device 2402 is used to perform.

[0181] In one example, at least one second RF fingerprint associated with the UE can be based on a beam pair between a beam of the UE and a beam of the TRP.

[0182] In another example, at least one second RF fingerprint associated with the UE can be based on beam scanning between one or more beams of the UE and one or more beams of the TRP.

[0183] In another example, a network entity may be associated with an ML module, and the network entity may train the ML module to map a directional feature captured from an antenna pair associated with a TRP and a UE to a location.

[0184] In another example, a network entity is associated with an ML module, and the network entity may train the ML module to map multiple directional features captured from multiple scanning beam pairs associated with one TRP and one UE to one location.

[0185] In another example, a network entity is associated with an ML module, and the network entity may train the ML module to map multiple directional features captured from multiple beam pairs associated with a UE and multiple TRPs to a location.

[0186] In another example, a network entity is associated with an ML module, and the network entity may train the ML module to map multiple directional features captured from multiple scanning beam pairs associated with a UE and multiple TRPs to a location.

[0187] Fig.242400 is an example of a hardware implementation for a device 2402. The device 2402 may be a network entity, a component of a network entity, or may implement network entity functions. In some aspects, the device 2402 may include a baseband unit 2404. The baseband unit 2404 may communicate with the UE 104, the base station 102 / 180, the LMF, and / or the location server via at least one transceiver 2422 (e.g., one or more RF transceivers and / or antennas). The at least one transceiver 2422 may be associated with or include a receiving component 2430 and / or a transmitting component 2434. The baseband unit 2404 may include a computer-readable medium / memory (e.g., a memory 2426). The baseband unit 2404 and / or at least one processor 2428 may be responsible for general processing, including executing software stored on the computer-readable medium / memory. The software, when executed by the baseband unit 2404 and / or at least one processor 2428, causes the baseband unit 2404 and / or at least one processor 2428 to perform the various functions described above. The computer-readable medium / memory may also be used to store data manipulated by the baseband unit 2404 when executing the software. The baseband unit 2404 also includes a receiving component 2430, a communication manager 2432, and a transmission component 2434. In a non-limiting example, the receiving component 2430 and the transmission component 2434 may include at least one transceiver and / or at least one antenna subsystem. The communication manager 2432 includes one or more of the illustrated components. The components within the communication manager 2432 may be stored in a computer-readable medium / memory and / or configured as hardware within the baseband unit 2404. The baseband unit 2404 may be a component of a network entity and may include a memory 376 and / or at least one of the TX processor 316, the RX processor 370, and the controller / processor 375.

[0188] The communication manager 2432 includes an RF fingerprint processing component 2440 that receives a plurality of first RF fingerprints from one or more wireless devices, each of the plurality of first RF fingerprints being associated with at least one directional feature and a location, such as in combination with Fig. 22 2202 and / or Fig.23 The communication manager 2432 also includes an ML module training component 2446, which trains the ML module to create a mapping between each of the plurality of first RF fingerprints and the associated at least one directional feature and the associated location based on each of the plurality of first RF fingerprints and the associated at least one directional feature and the associated location, wherein the location of the UE is estimated based on the mapping between the at least one second RF fingerprint and the associated at least one directional feature and the associated location, for example, as combined with Fig. 22The communication manager 2432 also includes a location request processing component 2442 that receives a request to determine the location of the UE based on at least one second RF fingerprint associated with the UE or captured by the UE, for example, as described in conjunction with Fig. 22 2206 and / or Fig.23 The communication manager 2432 also includes a location inference component 2444 that estimates the location of the UE based at least in part on matching at least one second RF fingerprint with at least one RF fingerprint in the plurality of first RF fingerprints, for example, as described in conjunction with Fig. 22 2208 and / or Fig.23 As described in 2308.

[0189] The device may include executing Fig. 22 and Fig.23 Each box in the flowchart of the algorithm has additional components. Therefore, Fig. 22 and Fig.23 Each block in the flowchart of can be performed by a component, and the device may include one or more of those components. These components can be one or more hardware components, which are specifically configured to perform the process / algorithm, implemented by a processor configured to perform the process / algorithm, stored in a computer-readable medium so as to be implemented by a processor, or some combination thereof.

[0190] As shown, the device 2402 may include a variety of components configured for various functions. In one configuration, the device 2402 (and specifically, the baseband unit 2404) includes a device (e.g., an RF fingerprint processing component 2440 and / or a receiving component 2430) for receiving a plurality of first RF fingerprints from one or more wireless devices, each of the plurality of first RF fingerprints being associated with at least one directional feature and a location. The device 2402 includes a device (e.g., a location request processing component 2442 and / or a receiving component 2430) for receiving a request to determine the location of the UE based on at least one second RF fingerprint associated with the UE or captured by the UE. The device 2402 includes a device (e.g., a location request processing component 2442 and / or a receiving component 2430) for estimating the location of the UE based at least in part on matching the at least one second RF fingerprint with at least one RF fingerprint of the plurality of first RF fingerprints. The device 2402 includes means (e.g., ML module training component 2446) for training an ML module to create a mapping between each of the plurality of first RF fingerprints and the associated at least one directional feature and the associated location based on each first RF fingerprint of the plurality of first RF fingerprints and the associated at least one directional feature and the associated location, wherein the location of the UE is estimated based on the mapping between at least one second RF fingerprint and the associated at least one directional feature and the associated location.

[0191] In one configuration, at least one directional feature may correspond to a CIR or CFR captured from a PRS or SRS.

[0192] In another configuration, the at least one directional characteristic may correspond to a CIR or CFR captured at a plurality of antenna pairs, each of which may include a transmit antenna of a transmitting device and a receive antenna of a receiving device.

[0193] In another configuration, at least one directional feature may correspond to at least one of a normalized histogram of received signal strength measured over a period of time or a frequency range captured at a plurality of antenna pairs, each of which may include a transmit antenna of a transmitting device and a receive antenna of a receiving device.

[0194] In another configuration, at least one directional feature may correspond to a complex sum of CIRs or CFRs captured at multiple antenna pairs or multiple beam pairs, each of the multiple antenna pairs may include a transmit antenna of a transmitting device and a receive antenna of a receiving device, and each of the multiple beam pairs may include a transmit beam of a transmitting device and a receive beam of a receiving device.

[0195] In another configuration, at least one directional feature may correspond to a normalized histogram of received signal strength measured over a period of time or at least one of a frequency range captured at a plurality of antenna pairs and a plurality of beam pairs, each of the plurality of antenna pairs may include a transmit antenna of a transmitting device and a receive antenna of a receiving device, and each of the plurality of beam pairs may include a transmit beam of a transmitting device and a receive beam of a receiving device.

[0196] In another configuration, at least one directional feature may correspond to a compressed CIR or a compressed CFR captured at multiple antenna pairs or multiple beam pairs, each of the multiple antenna pairs may include a transmit antenna of a transmitting device and a receive antenna of a receiving device, and each of the multiple beam pairs may include a transmit beam of a transmitting device and a receive beam of a receiving device.

[0197] In another configuration, at least one directional feature may correspond to at least one of a compressed normalized histogram of received signal strength measured over a period of time or a frequency range captured at multiple antenna pairs and multiple beam pairs, each of the multiple antenna pairs may include a transmit antenna of a transmitting device and a receive antenna of a receiving device, and each of the multiple beam pairs may include a transmit beam of a transmitting device and a receive beam of a receiving device.

[0198] In another configuration, at least one directional feature may correspond to one or more strongest CIRs or one or more strongest CFRs captured at multiple antenna pairs or multiple beam pairs, each of the multiple antenna pairs may include a transmit antenna of a transmitting device and a receive antenna of a receiving device, and each of the multiple beam pairs may include a transmit beam of a transmitting device and a receive beam of a receiving device.

[0199] In another configuration, at least one directional feature may correspond to at least one of one or more strongest normalized histograms of received signal strength measured over a period of time or a frequency range captured at multiple antenna pairs, each of which may include a transmit antenna of a transmitting device and a receive antenna of a receiving device.

[0200] In another configuration, each of the plurality of first RF fingerprints may also be associated with at least one beam characteristic, and the position of the UE may also be estimated based at least in part on the at least one beam characteristic. In such a configuration, the at least one beam characteristic may include one or more of: a beam shape, a CDF or PDF of a beam-based spherical EIRP measurement, a beam configuration, a beam measurement, or a GCN-based beam embedding. In such a configuration, the at least one beam characteristic may be associated with at least one of a transmit beam at a transmitting device or a receive beam at a receiving device.

[0201] In another configuration, the network entity may be a location server, UE, or base station associated with the ML module. In such a configuration, the ML module may be associated with a NN, a deep NN, or a random forest algorithm.

[0202] In another configuration, at least one second RF fingerprint associated with the UE may be based on a beam pair between a beam of the UE and a beam of the TRP.

[0203] In another configuration, at least one second RF fingerprint associated with the UE may be based on beam scanning between one or more beams of the UE and one or more beams of the TRP.

[0204] In another configuration, the network entity may be associated with the ML module, and the network entity may train the ML module to map a directional feature captured from an antenna pair associated with a TRP and a UE to a location.

[0205] In another configuration, the network entity is associated with the ML module, and the network entity may train the ML module to map multiple directional features captured from multiple scanning beam pairs associated with one TRP and one UE to one location.

[0206] In another configuration, the network entity is associated with the ML module, and the network entity may train the ML module to map multiple directional features captured from multiple beam pairs associated with one UE and multiple TRPs to one location.

[0207] In another configuration, the network entity is associated with the ML module, and the network entity may train the ML module to map multiple directional features captured from multiple scanning beam pairs associated with a UE and multiple TRPs to a location.

[0208] The means may be one or more of the components of the device 2402 configured to perform the functions recited by the means. As described above, the device 2402 may include the TX processor 316, the RX processor 370, and the controller / processor 375. Thus, in one configuration, the means may be the TX processor 316, the RX processor 370, and the controller / processor 375 configured to perform the functions recited by the means.

[0209] It should be understood that the specific order or hierarchy of the blocks in the disclosed process / flowchart is only an illustration of the exemplary method. It should be understood that the specific order or hierarchy of the blocks in the process / flowchart can be rearranged based on design preferences. Further, some blocks can be combined or omitted. The attached method claims present the elements of each block in a sample order, but are not meant to be limited to the specific order or hierarchy presented.

[0210] The foregoing description is provided to enable any person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects. Therefore, the claims are not intended to be limited to the aspects shown herein, but to conform to the full scope consistent with the language claims, wherein the elements mentioned in the singular are not intended to represent "one and only one", unless specifically so stated, but "one or more". Terms such as "if", "when ......" and "while ......" should be interpreted as "under the conditions of ......", rather than meaning an instantaneous time relationship or reaction. That is, these phrases, such as "when ......", do not mean instantaneous actions in response to the occurrence of an action or during the occurrence of an action, but simply imply that if the conditions are met, then the action will occur, but no specific or instantaneous time limit for the occurrence of the action is required. The word "exemplary" is used herein to mean "used as an example, instance, or illustration". Any aspect described as "exemplary" herein is not necessarily interpreted as being preferred or having advantages over other aspects. Unless otherwise specifically stated, the term "some" refers to one or more. Combinations such as “at least one of A, B, or C,” “one or more of A, B, or C,” “at least one of A, B and C,” “one or more of A, B, and C,” and “A, B, C, or any combination thereof” include any combination of A, B, and / or C, and may include multiple A, multiple B, or multiple C. Specifically, combinations such as “at least one of A, B, or C,” “one or more of A, B, or C,” “at least one of A, B, and C,” “one or more of A, B, and C,” and “A, B, C, or any combination thereof” may be only A, only B, only C, A and B, A and C, B and C, or A and B and C, where any such combination may include one or more members of A, B, or C. All structural and functional equivalents to the elements of the various aspects described throughout the disclosure that are known or later become known to those of ordinary skill in the art are expressly incorporated herein by reference and are intended to be encompassed by the claims. Furthermore, nothing disclosed herein is intended to be dedicated to the public, regardless of whether such disclosure is explicitly recited in the claims. Words such as "module," "mechanism," "element," "device," etc. cannot replace the word "means." Therefore, no claim element will be understood as a functional device unless the element is explicitly recited using the phrase "means for..."

[0211] The following aspects are merely illustrative and may be combined with other aspects or teachings described herein without limitation.

[0212] Aspect 1 is an apparatus for wireless communication, comprising: a memory; at least one transceiver; and at least one processor, the at least one processor being communicatively connected to the memory and the at least one transceiver, the at least one processor being configured to: receive a plurality of first RF fingerprints from one or more wireless devices, each of the plurality of first RF fingerprints being associated with at least one directional feature and a location; receive a request to determine a location of the UE based on at least one second RF fingerprint associated with the UE or captured by the UE; and estimate the location of the UE based at least in part on matching the at least one second RF fingerprint with at least one RF fingerprint of the plurality of first RF fingerprints.

[0213] Aspect 2 is the apparatus according to aspect 1, wherein the network entity is a location server associated with the ML module, the UE, or a base station.

[0214] Aspect 3 is an apparatus according to any one of aspects 1 and 2, wherein the ML module is associated with a NN, a deep NN or a random forest algorithm.

[0215] Aspect 4 is an apparatus according to any one of Aspects 1 to 3, wherein the at least one processor is further configured to: train the ML module to create a mapping between each of the multiple first RF fingerprints and the associated at least one directional feature and the associated location based on each first RF fingerprint of the multiple first RF fingerprints and the associated at least one directional feature and the associated location, wherein the location of the UE is estimated based on the mapping between the at least one second RF fingerprint and the associated at least one directional feature and the associated location.

[0216] Aspect 5 is an apparatus according to any one of aspects 1 to 4, wherein the request is received from the UE, a location server or a base station.

[0217] Aspect 6 is an apparatus according to any one of aspects 1 to 5, wherein the at least one directional feature corresponds to a CIR or CFR captured from a PRS or SRS.

[0218] Aspect 7 is an apparatus according to any one of Aspects 1 to 6, wherein the at least one directional feature corresponds to a CIR or CFR captured at a plurality of antenna pairs, each of the plurality of antenna pairs comprising a transmission antenna of a transmission device and a reception antenna of a reception device.

[0219] Aspect 8 is an apparatus according to any one of Aspects 1 to 7, wherein the at least one directional feature corresponds to a normalized histogram of received signal strength measured over a period of time or at least one of a frequency range captured at a plurality of antenna pairs, each of the plurality of antenna pairs comprising a transmitting antenna of a transmitting device and a receiving antenna of a receiving device.

[0220] Aspect 9 is an apparatus according to any one of Aspects 1 to 8, wherein the at least one directional feature corresponds to the complex sum of CIRs or CFRs captured at multiple antenna pairs or multiple beam pairs, each of the multiple antenna pairs includes a transmission antenna of a transmission device and a reception antenna of a receiving device, and each of the multiple beam pairs includes a transmission beam of the transmission device and a reception beam of the receiving device.

[0221] Aspect 10 is an apparatus according to any one of Aspects 1 to 9, wherein the at least one directional feature corresponds to a normalized histogram of received signal strength measured over a period of time or at least one of a frequency range captured at multiple antenna pairs and multiple beam pairs, each of the multiple antenna pairs comprising a transmission antenna of a transmission device and a reception antenna of a receiving device, and each of the multiple beam pairs comprising a transmission beam of the transmission device and a reception beam of the receiving device.

[0222] Aspect 11 is an apparatus according to any one of Aspects 1 to 10, wherein the at least one directional feature corresponds to a compressed CIR or a compressed CFR captured at a plurality of antenna pairs or a plurality of beam pairs, each of the plurality of antenna pairs includes a transmission antenna of a transmission device and a reception antenna of a reception device, and each of the plurality of beam pairs includes a transmission beam of the transmission device and a reception beam of the reception device.

[0223] Aspect 12 is an apparatus according to any one of Aspects 1 to 11, wherein the at least one directional feature corresponds to at least one of the compressed normalized histograms of received signal strength measured over a period of time or a frequency range captured at multiple antenna pairs and multiple beam pairs, each of the multiple antenna pairs comprising a transmitting antenna of a transmitting device and a receiving antenna of a receiving device, and each of the multiple beam pairs comprising a transmitting beam of the transmitting device and a receiving beam of the receiving device.

[0224] Aspect 13 is an apparatus according to any one of Aspects 1 to 12, wherein the at least one directional feature corresponds to one or more strongest CIRs or one or more strongest CFRs captured at multiple antenna pairs or multiple beam pairs, each of the multiple antenna pairs includes a transmission antenna of a transmission device and a reception antenna of a receiving device, and each of the multiple beam pairs includes a transmission beam of the transmission device and a reception beam of the receiving device.

[0225] Aspect 14 is an apparatus according to any one of Aspects 1 to 13, wherein the at least one directional feature corresponds to at least one of one or more strongest normalized histograms of received signal strength measured over a period of time or a frequency range captured at multiple antenna pairs, each of the multiple antenna pairs comprising a transmitting antenna of a transmitting device and a receiving antenna of a receiving device.

[0226] Aspect 15 is an apparatus according to any one of Aspects 1 to 14, wherein each of the plurality of first RF fingerprints is also associated with at least one beam characteristic, and wherein the position of the UE is estimated also based at least in part on the at least one beam characteristic.

[0227] Aspect 16 is an apparatus according to any one of Aspects 1 to 15, wherein the at least one beam characteristic includes one or more of the following: beam shape, CDF or PDF of beam-based spherical EIRP measurement, beam configuration, beam measurement, or GCN-based beam embedding.

[0228] Aspect 17 is an apparatus according to any one of aspects 1 to 16, wherein the at least one beam characteristic is associated with at least one of a transmission beam at a transmission device or a reception beam at a reception device.

[0229] Aspect 18 is an apparatus according to any one of Aspects 1 to 17, wherein the at least one second RF fingerprint associated with the UE is based on a beam pair between a beam of the UE and a beam of the TRP.

[0230] Aspect 19 is an apparatus according to any one of Aspects 1 to 18, wherein the at least one second RF fingerprint associated with the UE is based on beam scanning between one or more beams of the UE and one or more beams of the TRP.

[0231] Aspect 20 is an apparatus according to any one of Aspects 1 to 19, wherein the network entity is associated with an ML module, and the at least one processor is further configured to: train the ML module to map a directional feature captured from an antenna pair to a location, the antenna pair being associated with a TRP and a UE.

[0232] Aspect 21 is an apparatus according to any one of Aspects 1 to 20, wherein the network entity is associated with an ML module, and the at least one processor is further configured to: train the ML module to map multiple directional features captured from multiple scanning beam pairs to a location, the multiple scanning beam pairs being associated with a TRP and a UE.

[0233] Aspect 22 is an apparatus according to any one of Aspects 1 to 21, wherein the network entity is associated with an ML module, and the at least one processor is further configured to: train the ML module to map multiple directional features captured from multiple beam pairs to one location, the multiple beam pairs being associated with a UE and multiple TRPs.

[0234] Aspect 23 is an apparatus according to any one of Aspects 1 to 22, wherein the network entity is associated with an ML module, and the at least one processor is further configured to: train the ML module to map multiple directional features captured from multiple scanning beam pairs to a location, the multiple scanning beam pairs being associated with a UE and multiple TRPs.

[0235] Aspect 24 is a method for implementing wireless communication of any one of aspects 1 to 23.

[0236] Aspect 25 is an apparatus for wireless communication, comprising means for implementing any one of aspects 1 to 23.

[0237] Aspect 26 is a computer-readable medium storing computer-executable code, wherein the code, when executed by a processor, causes the processor to implement any one of aspects 1 to 23.

Claims

1. An apparatus for wireless communication at a network entity, the apparatus comprising: Memory; at least one transceiver; and at least one processor, the at least one processor being communicatively connected to the memory and the at least one transceiver, the at least one processor being configured to: Receiving a plurality of first radio frequency (RF) fingerprints from one or more wireless devices, each of the plurality of first RF fingerprints being associated with at least one directional feature and a location; receiving a request to determine a location of a user equipment (UE) based on at least one second RF fingerprint associated with the UE or captured by the UE; as well as estimating the location of the UE based at least in part on matching the at least one second RF fingerprint with at least one RF fingerprint of the plurality of first RF fingerprints; wherein the network entity is a location server, the UE, or a base station associated with a machine learning (ML) module; wherein the at least one processor is further configured to: The ML module is trained based on each first RF fingerprint of the plurality of first RF fingerprints and the associated at least one directional feature and the associated location to create a mapping between each first RF fingerprint of the plurality of first RF fingerprints and the associated at least one directional feature and the associated location, wherein the location of the UE is estimated based on the mapping between the at least one second RF fingerprint and the associated at least one directional feature and the associated location.

2. The apparatus according to claim 1, wherein the ML module is associated with a neural network (NN), a deep NN, or a random forest algorithm.

3. The apparatus of claim 1, wherein the request is received from the UE, a location server, or a base station. 4 . The apparatus according to claim 1 , wherein the at least one directional feature corresponds to a channel impulse response (CIR) or a channel frequency response (CFR) captured from a positioning reference signal (PRS) or a sounding reference signal (SRS).

5. The apparatus according to claim 1, wherein the at least one directional feature corresponds to a channel impulse response (CIR) or a channel frequency response (CFR) captured at a plurality of antenna pairs, each of the plurality of antenna pairs comprising a transmission antenna of a transmission device and a reception antenna of a reception device.

6. An apparatus according to claim 1, wherein the at least one directional feature corresponds to a normalized histogram of received signal strength measured over a period of time or at least one of a frequency range captured at multiple antenna pairs, each of the multiple antenna pairs comprising a transmitting antenna of a transmitting device and a receiving antenna of a receiving device.

7. An apparatus according to claim 1, wherein the at least one directional feature corresponds to a complex sum of a channel impulse response CIR or a channel frequency response CFR captured at multiple antenna pairs or multiple beam pairs, each of the multiple antenna pairs includes a transmission antenna of a transmission device and a reception antenna of a receiving device, and each of the multiple beam pairs includes a transmission beam of the transmission device and a reception beam of the receiving device.

8. An apparatus according to claim 1, wherein the at least one directional feature corresponds to a normalized histogram of received signal strength measured over a period of time or at least one of a frequency range captured at multiple antenna pairs and multiple beam pairs, each of the multiple antenna pairs comprising a transmit antenna of a transmitting device and a receive antenna of a receiving device, and each of the multiple beam pairs comprising a transmit beam of the transmitting device and a receive beam of the receiving device.

9. An apparatus according to claim 1, wherein the at least one directional feature corresponds to a compressed channel impulse response CIR or a compressed channel frequency response CFR captured at multiple antenna pairs or multiple beam pairs, each of the multiple antenna pairs includes a transmission antenna of a transmission device and a reception antenna of a receiving device, and each of the multiple beam pairs includes a transmission beam of the transmission device and a reception beam of the receiving device.

10. The apparatus of claim 1, wherein the at least one directional feature corresponds to a compressed normalized histogram of received signal strength measured over a period of time or at least one of a frequency range captured at a plurality of antenna pairs and a plurality of beam pairs, each of the plurality of antenna pairs comprising a transmit antenna of a transmitting device and a receive antenna of a receiving device, and each of the plurality of beam pairs comprising a transmit beam of the transmitting device and a receive beam of the receiving device.

11. An apparatus according to claim 1, wherein the at least one directional feature corresponds to one or more strongest channel impulse responses CIR or one or more strongest channel frequency responses CFR captured at multiple antenna pairs or multiple beam pairs, each of the multiple antenna pairs includes a transmission antenna of a transmission device and a reception antenna of a receiving device, and each of the multiple beam pairs includes a transmission beam of the transmission device and a reception beam of the receiving device.

12. An apparatus according to claim 1, wherein the at least one directional feature corresponds to one or more strongest normalized histograms of received signal strength measured over a period of time or at least one of frequency ranges captured at multiple antenna pairs, each of the multiple antenna pairs comprising a transmitting antenna of a transmitting device and a receiving antenna of a receiving device.

13. The apparatus of claim 1, wherein each of the plurality of first RF fingerprints is further associated with at least one beam characteristic, and wherein the location of the UE is estimated further based at least in part on the at least one beam characteristic.

14. An apparatus according to claim 13, wherein the at least one beam feature comprises one or more of the following: beam shape, a cumulative distribution function (CDF) or a probability density function (PDF) based on a beam-based spherical effective isotropic radiated power (EIRP) measurement, a beam configuration, a beam measurement, or a beam embedding based on a graph convolutional network (GCN).

15. The apparatus of claim 13, wherein the at least one beam characteristic is associated with at least one of a transmit beam at a transmitting device or a receive beam at a receiving device.

16. The apparatus of claim 1, wherein the at least one second RF fingerprint associated with the UE is based on a beam pair between a beam of the UE and a beam of a transmission reception point (TRP).

17. The apparatus of claim 1, wherein the at least one second RF fingerprint associated with the UE is based on a beam scan between one or more beams of the UE and one or more beams of a transmission reception point (TRP).

18. The apparatus of claim 1, wherein the network entity is associated with a machine learning (ML) module, and the at least one processor is further configured to: The ML module is trained to map a directional feature captured from an antenna pair to a location, wherein the antenna pair is associated with a transmission reception point TRP and a UE.

19. The apparatus of claim 1, wherein the network entity is associated with a machine learning (ML) module, and the at least one processor is further configured to: The ML module is trained to map a plurality of directional features captured from a plurality of scanning beam pairs to a location, wherein the plurality of scanning beam pairs are associated with a transmission reception point TRP and a UE.

20. The apparatus of claim 1, wherein the network entity is associated with a machine learning (ML) module, and the at least one processor is further configured to: The ML module is trained to map a plurality of directional features captured from a plurality of beam pairs associated with a UE and a plurality of transmission reception points (TRPs) to a location.

21. The apparatus of claim 1, wherein the network entity is associated with a machine learning (ML) module, and the at least one processor is further configured to: The ML module is trained to map a plurality of directional features captured from a plurality of scanning beam pairs associated with a UE and a plurality of transmission reception points (TRPs) to a location.

22. A method for wireless communication at a network entity, the method comprising: Receiving a plurality of first radio frequency (RF) fingerprints from one or more wireless devices, each of the plurality of first RF fingerprints being associated with at least one directional feature and a location; receiving a request to determine a location of a user equipment (UE) based on at least one second RF fingerprint associated with the UE or captured by the UE; as well as estimating the location of the UE based at least in part on matching the at least one second RF fingerprint with at least one RF fingerprint of the plurality of first RF fingerprints; wherein the network entity is a location server, the UE or a base station associated with a machine learning ML module, and The method further comprises: The ML module is trained based on each first RF fingerprint of the plurality of first RF fingerprints and the associated at least one directional feature and the associated location to create a mapping between each first RF fingerprint of the plurality of first RF fingerprints and the associated at least one directional feature and the associated location, wherein the location of the UE is estimated based on the mapping between the at least one second RF fingerprint and the associated at least one directional feature and the associated location.

23. The method of claim 22, wherein the ML module is associated with a neural network (NN), a deep NN, or a random forest algorithm.

24. The method of claim 22, wherein each of the plurality of first RF fingerprints is also associated with at least one beam characteristic, and wherein the position of the UE is estimated based at least in part on the at least one beam characteristic, and wherein the at least one beam characteristic comprises one or more of: beam shape, a cumulative distribution function CDF or a probability density function PDF of a beam-based spherical effective isotropic radiated power EIRP measurement, a beam configuration, a beam measurement, or a beam embedding based on a graph convolutional network (GCN).

25. The method of claim 22, wherein the at least one second RF fingerprint associated with the UE is based on a beam pair between a beam of the UE and a beam of a transmission receiving point TRP, or based on a beam scan between one or more beams of the UE and one or more beams of the TRP.

26. An apparatus for wireless communication at a network entity, the apparatus comprising: means for receiving a plurality of first radio frequency (RF) fingerprints from one or more wireless devices, each first RF fingerprint of the plurality of first RF fingerprints being associated with at least one directional characteristic and a location; means for receiving a request to determine a location of a user equipment (UE) based on at least one second RF fingerprint associated with the UE or captured by the UE; and means for estimating the location of the UE based at least in part on matching the at least one second RF fingerprint with at least one RF fingerprint of the plurality of first RF fingerprints; wherein the network entity is a location server, the UE or a base station associated with a machine learning ML module, and The device also includes: Means for training the ML module to create a mapping between each of the plurality of first RF fingerprints and the associated at least one directional feature and the associated location based on each first RF fingerprint of the plurality of first RF fingerprints and the associated at least one directional feature and the associated location, wherein the location of the UE is estimated based on the mapping between the at least one second RF fingerprint and the associated at least one directional feature and the associated location.

27. A non-transitory computer readable medium storing computer executable code at a network entity, the code, when executed by a processor, causing the processor to: Receiving a plurality of first radio frequency (RF) fingerprints from one or more wireless devices, each of the plurality of first RF fingerprints being associated with at least one directional feature and a location; receiving a request to determine a location of a user equipment (UE) based on at least one second RF fingerprint associated with the UE or captured by the UE; and estimating the location of the UE based at least in part on matching the at least one second RF fingerprint with at least one RF fingerprint of the plurality of first RF fingerprints; wherein the network entity is a location server, the UE, or a base station associated with a machine learning (ML) module, and The code, when executed by the processor, further causes the processor to: The ML module is trained based on each first RF fingerprint of the plurality of first RF fingerprints and the associated at least one directional feature and the associated location to create a mapping between each first RF fingerprint of the plurality of first RF fingerprints and the associated at least one directional feature and the associated location, wherein the location of the UE is estimated based on the mapping between the at least one second RF fingerprint and the associated at least one directional feature and the associated location.

Images