Machine Learning for Positioning

Abstract

Various aspects of the present disclosure relate to methods, apparatuses, and systems that support machine learning for positioning. For example, implementations provide for direct artificial intelligence (AI)-based and AI-assisted positioning that can be utilized to improve user equipment (UE) location accuracy performance. In exemplary implementations, techniques such as fingerprinting can be utilized by AI / ML models for direct AI / ML positioning to obtain improved location accuracy via measurements, environmental data, and the like. Accordingly, the present disclosure provides techniques for configuring direct AI / ML positioning assistance data and defining measurements for performing AI / ML direct positioning. Additionally, the present disclosure provides techniques for configuring reporting criteria for nodes and / or other entities that perform AI / ML direct positioning.

Description

[Technical Field]

[0001] Related Applications This application claims priority to U.S. Provisional Application No. 63 / 484,102, entitled "MACHINE LEARNING FOR POSITIONING," filed February 9, 2023, and U.S. Provisional Application No. 63 / 444,469, entitled "MACHINE LEARNING FOR POSITIONING," filed February 9, 2023, the disclosures of which are incorporated herein by reference in their entireties.

[0002] FIELD OF THE DISCLOSURE The present disclosure relates to wireless communications, and more particularly to position determination in wireless communications. [Background technology]

[0003] A wireless communication system may include one or more network communication devices, such as base stations, which may otherwise be known as eNodeBs (eNBs), next-generation NodeBs (gNBs), or other appropriate terminology. Each network communication device, such as a base station, may support wireless communication for one or more user communication devices, which may otherwise be known as user equipment (UE) or other appropriate terminology. A wireless communication system may support wireless communication with one or more user communication devices by utilizing wireless communication system resources (e.g., time resources (e.g., symbols, slots, subframes, frames, etc.) or frequency resources (e.g., subcarriers, carriers)). In addition, a wireless communication system may support wireless communication over various radio access technologies, including third-generation (3G) radio access technology, fourth-generation (4G) radio access technology, fifth-generation (5G) radio access technology, or other suitable access technology beyond 5G (e.g., sixth-generation (6G)). Summary of the Invention [Problem to be solved by the invention]

[0004] Some wireless communication systems provide methods for determining the location of a device (e.g., a UE), such as the geographic location of the UE. However, current implementations for UE positioning may be inaccurate. [Means for solving the problem]

[0005] The present disclosure relates to methods, apparatus, and systems that support machine learning for positioning. For example, implementations provide for direct artificial intelligence / machine learning (AI / ML)-based positioning and AI / ML-assisted positioning, which can be utilized to improve UE location accuracy performance. In example implementations, techniques such as fingerprinting can be utilized by AI / ML models for direct AI / ML positioning to obtain improved location accuracy via measurements, environmental data, and the like. Accordingly, the present disclosure provides techniques for configuring direct AI / ML positioning assistance data and defining measurements for performing AI / ML direct positioning. Additionally, the present disclosure provides techniques for configuring reporting criteria for nodes and / or other entities that perform AI / ML direct positioning.

[0006] Thus, by utilizing the described techniques, more accurate positioning of the UE may be obtained and the use of system resources to determine the UE location may be reduced.

[0007] Some implementations of the methods and apparatus described herein may further include sending one or more machine learning positioning report requests including a machine learning reporting configuration and one or more common reporting standards, receiving one or more machine learning positioning reports, processing the one or more machine learning positioning reports through a machine learning model, and generating an estimated location of the user equipment (UE) based at least in part on output from the machine learning model.

[0008] Some implementations of the methods and apparatus described herein may further include: the machine learning reporting configuration includes one or more of a direct machine learning reporting configuration or an assisted machine learning reporting configuration; the method is performed by an apparatus including a configuration entity, wherein the configuration entity includes at least one of a location server, a Next Generation Radio Access Network (NG-RAN), a positioning reference unit (PRU), a UE, an anchor UE, or a target UE; sending one or more machine learning positioning report requests from the first apparatus to one or more second apparatuses; and receiving one or more machine learning positioning reports from the one or more second apparatuses; the one or more second apparatuses including at least one of a location server, a Next Generation Radio Access Network (NG-RAN), a positioning reference unit (PRU), a UE, an anchor UE, or a target UE.

[0009] Some implementations of the methods and apparatus described herein may further include: the one or more common reporting criteria include one or more of a fingerprint type, a ground truth reference location type, a time domain report type, a measurement preprocessing, a measurement validity, a UE type, a mobility indication, an orientation indication, a fingerprinting environment indication, a fingerprint quality indication, or a label quality indication; configuring, for at least one machine learning positioning report request, one or more of the common reporting criteria to be one or more of augmented, deleted, updated, enabled, or disabled; broadcasting the one or more common reporting criteria via positioning system information broadcast signaling; and the machine learning reporting configuration may include instructions for reporting correlation of machine learning position measurements between different sets of measurements.

[0010] Some implementations of the methods and apparatus described herein may further include: correlation of machine learning position measurements includes one or more of spatial domain correlation or time domain correlation; one or more machine learning positioning reports include one or more of machine learning position measurements or machine learning positioning location information; the machine learning reporting configuration includes instructions for reporting path loss at different locations including ground truth reference locations; the machine learning reporting configuration includes instructions for averaging the machine learning position measurements over a configured number of measurements and reporting the average as part of one or more machine learning positioning reports; and the machine learning reporting configuration includes instructions for determining a similarity score at the configured locations to determine an optimal correspondence between the fingerprint measurements and the estimated location of the target UE.

[0011] Some implementations of the methods and apparatus described herein may further include receiving one or more machine learning positioning report requests including a machine learning reporting configuration and one or more common reporting criteria, generating one or more machine learning positioning reports based at least in part on the machine learning reporting configuration and the one or more common reporting criteria, and transmitting the one or more machine learning positioning reports.

[0012] Some implementations of the methods and apparatus described herein may further include that the method is performed by an apparatus including one or more of a user equipment (UE), an anchor UE, or a target UE; and that the method is performed by an apparatus including a configuration entity, wherein the configuration entity includes at least one of a location server, a next generation radio access network (NG-RAN), or a positioning reference unit (PRU).

[0013] Some implementations of the methods and apparatus described herein may further include sending one or more machine learning positioning report requests including a machine learning reporting configuration and one or more common reporting standards, receiving one or more machine learning positioning reports, generating a machine learning positioning training dataset based at least in part on the one or more machine learning positioning reports, and training a positioning machine learning model using the machine learning positioning training dataset to generate a trained positioning machine learning model.

[0014] Some implementations of the methods and apparatus described herein may further include receiving one or more additional machine learning positioning reports; inputting at least a portion of the one or more additional machine learning positioning reports into a trained positioning machine learning model; estimating a position of the target user equipment (UE) based at least in part on output from the trained positioning machine learning model; receiving a request for machine learning positioning training data for positioning and transmitting a machine learning positioning training dataset based at least in part on the request; and receiving a request for a trained positioning machine learning model and transmitting at least a portion of the trained positioning machine learning model based at least in part on the request. [Brief explanation of the drawings]

[0015] [Figure 1] FIG. 1 illustrates an example wireless communication system that supports machine learning for positioning according to aspects of the present disclosure. [Figure 2] FIG. 1 illustrates a system in which positioning reference signals may be utilized to obtain position measurements. [Figure 3] FIG. 1 illustrates a scenario for multi-cell RTT positioning. [Figure 4a] A figure showing a part of the LPP RequestLocationInformation message. [Figure 4b] A figure showing a part of the LPP RequestLocationInformation message. [Figure 5a] A figure showing a part of the LPP ProvideLocationInformation message. [Figure 5b] A figure showing a part of the LPP ProvideLocationInformation message. [Figure 6] FIG. 1 is a diagram of a system for machine learning based RAN intelligence. [Figure 7] FIG. 1 illustrates an example scenario for assisting machine learning for positioning according to aspects of the present disclosure. [Figure 8] FIG. 1 illustrates an example scenario for assisting machine learning for positioning according to aspects of the present disclosure. [Figure 9] FIG. 1 illustrates a message supporting machine learning for positioning according to an aspect of the present disclosure. [Figure 10a] 1 illustrates different portions of a message that supports machine learning for positioning according to an aspect of the present disclosure. [Figure 10b] 1 illustrates different portions of a message that supports machine learning for positioning according to an aspect of the present disclosure. [Figure 11] FIG. 1 illustrates a message supporting machine learning for positioning according to an aspect of the present disclosure. [Figure 12] FIG. 1 illustrates a message supporting machine learning for positioning according to an aspect of the present disclosure. [Figure 13] FIG. 1 illustrates a scenario for assisting machine learning for positioning according to aspects of the present disclosure. [Figure 14a] FIG. 1 illustrates a scenario for assisting machine learning for positioning according to aspects of the present disclosure. [Figure 14b] FIG. 1 illustrates a scenario for assisting machine learning for positioning according to aspects of the present disclosure. [Figure 15] FIG. 1 illustrates a scenario for assisting machine learning for positioning according to aspects of the present disclosure. [Figure 16] FIG. 1 illustrates a scenario for assisting machine learning for positioning according to aspects of the present disclosure. [Figure 17]FIG. 1 illustrates a scenario for assisting machine learning for positioning according to aspects of the present disclosure. [Figure 18] FIG. 1 is an example block diagram of a device that supports machine learning for positioning according to aspects of the present disclosure. [Figure 19] FIG. 1 is an example block diagram of a device that supports machine learning for positioning according to aspects of the present disclosure. [Figure 20] 1 is a flowchart of a method for assisting machine learning for positioning according to an aspect of the present disclosure. [Figure 21] 1 is a flowchart of a method for assisting machine learning for positioning according to an aspect of the present disclosure. [Figure 22] 1 is a flowchart of a method for assisting machine learning for positioning according to an aspect of the present disclosure. [Figure 23] 1 is a flowchart of a method for assisting machine learning for positioning according to an aspect of the present disclosure. [Figure 24] 1 is a flowchart of a method for assisting machine learning for positioning according to an aspect of the present disclosure. [Figure 25] 1 is a flowchart of a method for assisting machine learning for positioning according to an aspect of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0016] In wireless communication systems, techniques are utilized to estimate the position (e.g., location) of a UE, such as the UE's geographic position and / or the UE's relative network location. For example, some systems utilize beam-based attempts to estimate the UE's location, such as in commercial and regulatory (e.g., emergency) scenarios. However, current position determination techniques can be inaccurate and can result in an incorrect indication of the UE's location.

[0017] Accordingly, this disclosure provides techniques for supporting machine learning for positioning. For example, implementations provide direct AI-based and AI-assisted positioning that can be utilized to improve UE location accuracy performance, such as within the positioning framework defined by 3GPP. For example, for direct AI / ML positioning, techniques such as fingerprinting can be utilized by AI / ML models to obtain improved location accuracy via measurements, environmental data, and the like. Accordingly, this disclosure provides techniques for configuring direct AI / ML positioning assistance data and defining measurements for performing AI / ML direct positioning. Additionally, this disclosure provides techniques for configuring reporting criteria for nodes and / or other entities performing AI / ML direct positioning.

[0018] Thus, by utilizing the described techniques, more accurate positioning of the UE can be obtained by utilizing large amounts of radio data and other related data, and the use of system resources to determine the location of the UE can be reduced.

[0019] Aspects of the present disclosure are described in the context of a wireless communication system. Aspects of the present disclosure are further illustrated and described with reference to device diagrams and flow charts.

[0020] FIG. 1 illustrates an example wireless communication system 100 that supports machine learning for positioning according to aspects of the present disclosure. The wireless communication system 100 may include one or more network entities 102, one or more UEs 104, a core network 106, and a packet data network 108. The wireless communication system 100 may support various radio access technologies. In some implementations, the wireless communication system 100 may be a 4G network, such as an LTE network or an LTE-Advanced (LTE-A) network. In some other implementations, the wireless communication system 100 may be a 5G network, such as an NR network. In other implementations, the wireless communication system 100 may be a combination of a 4G network and a 5G network, or other suitable radio access technologies, including Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, or other suitable radio access technologies. The wireless communication system 100 may support 5G or later radio access technologies. Additionally, the wireless communication system 100 may support techniques such as time division multiple access (TDMA), frequency division multiple access (FDMA), or code division multiple access (CDMA).

[0021] One or more network entities 102 may be dispersed across a geographic region to form a wireless communication system 100. One or more of the network entities 102 described herein may be, include, or be referred to as a network node, base station, network element, Radio Access Network (RAN), base transceiver station, access point, NodeB, eNodeB (eNB), next generation NodeB (gNB), or other suitable terminology. The network entities 102 and the UEs 104 may communicate via a communication link 110, which may be a wireless connection or a wired connection. For example, the network entities 102 and the UEs 104 may conduct wireless communication (e.g., receive signaling, transmit signaling) over a Uu interface.

[0022] A network entity 102 may provide a geographic coverage area 112 for which the network entity 102 may support services (e.g., voice, video, packet data, messaging, broadcast, etc.) for one or more UEs 104 located therein. For example, the network entity 102 and the UEs 104 may support wireless communication of signals related to services (e.g., voice, video, packet data, messaging, broadcast, etc.) according to one or more radio access technologies. In some implementations, the network entity 102 may be mobile, e.g., a satellite associated with a non-terrestrial network. In some implementations, geographic coverage areas 112 associated with the same or different radio access technologies may overlap, while different geographic coverage areas 112 may be associated with different network entities 102. The information and signals described herein may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips that may be referenced throughout this description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

[0023] One or more UEs 104 may be dispersed throughout the geographic region of the wireless communication system 100. The UEs 104 may include or be referred to as mobile devices, wireless devices, remote devices, remote units, handheld devices, subscriber devices, or some other suitable terminology. In some implementations, the UEs 104 may be referred to as units, stations, terminals, or clients, among other examples. Additionally or alternatively, the UEs 104 may be referred to as Internet-of-Things (IoT) devices, Internet-of-Everything (IoE) devices, or machine-type communication (MTC) devices, among other examples. In some implementations, the UEs 104 may be fixed within the wireless communication system 100. In some other implementations, the UEs 104 may be mobile within the wireless communication system 100.

[0024] One or more UEs may be devices of different forms or with different capabilities. Some examples of UEs 104 are shown in FIG. 1. As shown in FIG. 1, the UE 104 may be capable of communicating with various types of devices, such as network entities 102, other UEs 104, or network equipment (e.g., the core network 106, the packet data network 108, a relay device, an integrated access and backhaul (IAB) node, or another network equipment). Additionally or alternatively, the UE 104 may act as a relay in the wireless communication system 100, facilitating communication with other network entities 102 or UEs 104.

[0025] The UE 104 may also be capable of facilitating direct wireless communication with other UEs 104 via a communication link 114. For example, the UE 104 may facilitate direct wireless communication with another UE 104 via a device-to-device (D2D) communication link. In some implementations, such as a vehicle-to-vehicle (V2V) deployment, a V2X deployment, or a cellular V2X deployment, the communication link 114 may be referred to as a sidelink. For example, the UE 104 may facilitate direct wireless communication with another UE 104 via a PC5 interface.

[0026] A network entity 102 may facilitate communication with the core network 106, with another network entity 102, or both. For example, a network entity 102 may interface with the core network 106 through one or more backhaul links 116 (e.g., via an S1, N2, N2, or another network interface). The network entities 102 may communicate with each other through the backhaul links 116 (e.g., via an X2, Xn, or another network interface). In some implementations, the network entities 102 may communicate with each other directly (e.g., between the network entities 102). In some other implementations, the network entities 102 may communicate with each other or indirectly (e.g., via the core network 106). In some implementations, one or more network entities 102 may include subcomponents such as an access network entity, which may be an example of an access node controller (ANC). The ANC may communicate with one or more UEs 104 through one or more other access network transmitting entities, which may be referred to as a radio head, a smart radio head, or a transmit / receive point (TRP).

[0027] In some implementations, the network entity 102 may be configured in a distributed architecture that may be configured to utilize a protocol stack that is physically or logically distributed between two or more network entities 102, such as an integrated access backhaul (IAB) network, an open RAN (O-RAN) (e.g., a network configuration sponsored by the O-RAN Alliance), or a virtualized RAN (vRAN) (e.g., Cloud RAN (C-RAN)). For example, the network entity 102 may include one or more of a central unit (CU), a distributed unit (DU), a radio unit (RU), a RAN Intelligent Controller (RIC) (e.g., a Near-Real Time RIC (Near-real time (RT) RIC), a Non-Real Time RIC (Non-RT RIC)), a Service Management and Orchestration (SMO) system, or any combination thereof.

[0028] An RU may also be referred to as a radio head, smart radio head, remote radio head (RRH), remote radio unit (RRU), or transmit / receive point (TRP). One or more components of the network entity 102 in a distributed RAN architecture may be co-located, or one or more components of the network entity 102 may be located in distributed locations (e.g., separate physical locations). In some implementations, one or more network entities 102 in a distributed RAN architecture may be implemented as virtual units (e.g., virtual CU (VCU), virtual DU (VDU), virtual RU (VRU)).

[0029] The division of functionality between the CU, DU, and RU may be flexible and may support different functions depending on which functions (e.g., network layer functions, protocol layer functions, baseband functions, radio frequency functions, and any combination thereof) are implemented in the CU, DU, or RU. For example, a functional division of the protocol stack between the CU and DU may be utilized such that the CU may support one or more layers of the protocol stack and the DU may support one or more different layers of the protocol stack. In some implementations, the CU may host higher protocol layer (e.g., Layer 3 (L3), Layer 2 (L2)) functions and signaling (e.g., Radio Resource Control (RRC), Service Data Adaptation Protocol (SDAP), Packet Data Convergence Protocol (PDCP)). A CU may be connected to one or more DUs or RUs, which may host lower protocol layers such as Layer 1 (L1) (e.g., physical (PHY) layer) or L2 (e.g., radio link control (RLC) layer, medium access control (MAC) layer) functions and signaling, each of which may be at least partially controlled by the CU.

[0030] Additionally or alternatively, a functional division of the protocol stack may be utilized between the DU and the RU, such that the DU may support one or more layers of the protocol stack, and the RU may support one or more different layers of the protocol stack. The DU may support one or more different cells (e.g., via one or more RUs). In some implementations, the functional division between the CU and the DU, or between the DU and the RU, may be within a protocol layer (e.g., some functions of the protocol layer may be performed by one of the CU, DU, or RU, while other functions of the protocol layer are performed by a different one of the CU, DU, or RU).

[0031] The CU may be further functionally divided into CU Control Plane (CU-CP) and CU User Plane (CU-UP) functions. The CU may be connected to one or more DUs via midhaul communication links (e.g., F1, F1-c, F1-u), and the DUs may be connected to one or more RUs via fronthaul communication links (e.g., open fronthaul (FH) interfaces). In some implementations, the midhaul or fronthaul communication links may be implemented according to interfaces (e.g., channels) between layers of protocol stacks supported by the respective network entities 102 communicating via such communication links.

[0032] The core network 106 may support user authentication, access authorization, tracking, connectivity, and other access, routing, or mobility functions. The core network 106 may be an evolved packet core (EPC) or 5G core (5GC), which may include control plane entities that manage access and mobility (e.g., a mobility management entity (MME), an access and mobility management function (AMF)) and user plane entities that route packets to or interconnect with external networks (e.g., a serving gateway (S-GW), a location management function (LMF) that is a control plane entity that manages location-related services, a packet data network (PDN) gateway (P-GW), or a user plane function (UPF)). In some implementations, the control plane entities may manage non-access stratum (NAS) functions, such as mobility, authentication, and bearer management (e.g., data bearers, signaling bearers, etc.) for one or more UEs 104 served by one or more network entities 102 associated with the core network 106.

[0033] The core network 106 may communicate with the packet data network 108 through one or more backhaul links 116 (e.g., via S1, N2, N3, or another network interface). The packet data network 108 may include an application server 118. In some implementations, one or more UEs 104 may communicate with the application server 118. The UE 104 may establish a session (e.g., a PDU session, etc.) with the core network 106 via the network entity 102. The core network 106 may route traffic (e.g., control information, data, etc.) between the UE 104 and the application server 118 using the established session (e.g., the established PDU session). The PDU session may be an example of a logical connection between the UE 104 and the core network 106 (e.g., one or more network functions of the core network 106).

[0034] In the wireless communication system 100, the network entity 102 and the UE 104 may use resources of the wireless communication system 100 (e.g., time resources (e.g., symbols, slots, subframes, frames, etc.) or frequency resources (e.g., subcarriers, carriers)) to perform various operations (e.g., wireless communications). In some implementations, the network entity 102 and the UE 104 may support different resource structures. For example, the network entity 102 and the UE 104 may support different frame structures. In some implementations, such as in 4G, the network entity 102 and the UE 104 may support a single frame structure. In some other implementations, such as in 5G and other suitable radio access technologies, the network entity 102 and the UE 104 may support various frame structures (e.g., multiple frame structures). The network entity 102 and the UE 104 may support various frame structures based on one or more numerologies.

[0035] One or more numerologies may be supported in the wireless communication system 100, and a numerology may include a subcarrier spacing and a cyclic prefix. A first numerology (e.g., μ=0) may be associated with a first subcarrier spacing (e.g., 15 kHz) and a normal cyclic prefix. A first numerology (e.g., μ=0) associated with a first subcarrier spacing (e.g., 15 kHz) may utilize one slot per subframe. A second numerology (e.g., μ=1) may be associated with a second subcarrier spacing (e.g., 30 kHz) and a normal cyclic prefix. A third numerology (e.g., μ=2) may be associated with a third subcarrier spacing (e.g., 60 kHz) and a normal cyclic prefix or an extended cyclic prefix. A fourth numerology (e.g., μ=3) may be associated with a fourth subcarrier spacing (e.g., 120 kHz) and a normal cyclic prefix. A fifth numerology (e.g., μ=4) may be associated with a fifth subcarrier spacing (e.g., 240 kHz) and a normal cyclic prefix.

[0036] Time intervals of resources (e.g., communication resources) may be organized according to frames (also called radio frames). Each frame may have a certain time length, for example, 10 milliseconds (ms). In some implementations, each frame may include multiple subframes. For example, each frame may include 10 subframes, and each subframe may have a certain time length, for example, 1 ms. In some implementations, each frame may have the same time length. In some implementations, each subframe of a frame may have the same time length.

[0037] Additionally or alternatively, resource time intervals (e.g., communication resources) may be organized according to slots. For example, a subframe may include a certain number (e.g., amount) of slots. Each slot may include a certain number (e.g., amount) of symbols (e.g., orthogonal frequency division multiplexing (OFDM) symbols). In some implementations, the number (e.g., amount) of slots for a subframe may depend on the numerology. With a normal cyclic prefix, a slot may include 14 symbols. With an extended cyclic prefix (e.g., applicable to a subcarrier spacing of 60 kHz), a slot may include 12 symbols. The relationship between the number of symbols per slot, the number of slots per subframe, and the number of slots per frame for a normal cyclic prefix and an extended cyclic prefix may depend on the numerology. It should be understood that references to a first numerology (e.g., μ=0) associated with a first subcarrier spacing (e.g., 15 kHz) may be used interchangeably between subframe and slot.

[0038] In the wireless communication system 100, the electromagnetic (EM) spectrum may be divided into various classes, frequency bands, frequency channels, etc. based on frequency or wavelength. By way of example, the wireless communication system 100 may support one or more operating frequency bands, such as frequency range designations FR1 (410 MHz-7.125 GHz), FR2 (24.25 GHz-52.6 GHz), FR3 (7.125 GHz-24.25 GHz), FR4 (52.6 GHz-114.25 GHz), FR4a or FR4-1 (52.6 GHz-71 GHz), and FR5 (114.25 GHz-300 GHz). In some implementations, the network entity 102 and the UE 104 may conduct wireless communications over one or more of the operating frequency bands. In some implementations, FR1 may be used by the network entity 102 and the UE 104, among other equipment or devices, for cellular communication traffic (e.g., control information, data). In some implementations, FR2 may be used by the network entity 102 and the UE 104, among other equipment or devices, for short-range, high-data-rate capabilities.

[0039] FR1 may be associated with one or more numerologies (e.g., at least three numerologies). For example, FR1 may be associated with a first numerology (e.g., μ=0) including a subcarrier spacing of 15 kHz, a second numerology (e.g., μ=1) including a subcarrier spacing of 30 kHz, and a third numerology (e.g., μ=2) including a subcarrier spacing of 60 kHz. FR2 may be associated with one or more numerologies (e.g., at least two numerologies). For example, FR2 may be associated with a third numerology (e.g., μ=2) including a subcarrier spacing of 60 kHz, and a fourth numerology (e.g., μ=3) including a subcarrier spacing of 120 kHz.

[0040] According to an implementation of machine learning for positioning, the network entity 102 transmits an ML positioning configuration to the UE 104. The ML positioning configuration 120 includes various information and / or parameters, for example, for the UE 104 to measure various positioning information, generate position measurements, and / or process the position measurements. Accordingly, based at least in part on the ML positioning configuration 120, the UE 104 performs ML position measurements 122, such as to measure and process various attributes of wireless signals detected at the UE 104. The UE 104 generates an ML positioning response 124 based at least in part on the ML position measurements 122 and / or the ML positioning configuration 120 and transmits the ML positioning response to the network entity 102. In an implementation, the ML positioning response 124 may include an estimated position (e.g., location) of the UE 104, and the network entity 102 may utilize ML techniques to process the ML positioning response to estimate the position of the UE 104.

[0041] In some wireless communication systems, NR positioning based on NR Uu signals and standalone (SA) architectures (e.g., beam-based transmission) are specified. Target use cases include commercial and regulatory (emergency services) scenarios. Performance parameters include the following [Technical Report (TR) 38.855]:

[0042] [Table 1]

[0043] Additionally, some systems specify positioning performance parameters for commercial and IIoT use cases [TR 38.857] as follows:

[0044] [Table 2]

[0045] At least some supported positioning techniques are listed in Table 1 below [TS38.305].

[0046] [Table 3]

[0047] Currently, different positioning techniques can be configured and implemented based on the LMF and UE capability requirements, as shown in Table 1. Positioning Reference Signal (PRS) transmission enables the UE to perform UE positioning-related measurements to enable the calculation of the UE location estimate, and is configured per Transmit / Receive Point (TRP), where a TRP may transmit one or multiple beams.

[0048] FIG. 2 illustrates a system 200 in which positioning reference signals may be utilized to obtain position measurements. For example, PRSs may be transmitted by different base stations (serving and neighboring base stations) using narrow beams over FR1 and FR2, which is relatively different compared to LTE in which PRSs are transmitted throughout the entire cell. The PRSs may be locally associated with the PRS resource identifier (ID) and resource set ID of the base station (TRP). Similarly, UE location measurements, such as reference signal time difference (RSTD) and PRS RSRP measurements, are performed between beams (e.g., between different pairs of downlink (DL) PRS resources or DL ​​PRS resource sets), rather than between different cells as in LTE. In addition, there are additional UL positioning methods for the network to utilize to calculate the location of a target UE.

[0049] Tables 2 and 3 show the reference signal and measurement mappings required for each RAT-dependent positioning technique supported in the UE and gNB, respectively. RAT-dependent positioning techniques involve 3GPP® RATs and core network entities to perform UE location estimation, which differs from RAT-independent positioning techniques, which rely on GNSS, inertial measurement unit (IMU) sensors, WLAN, and Bluetooth technologies to perform target device (UE) positioning.

[0050] [Table 4]

[0051] [Table 5]

[0052] The following RAT-dependent positioning techniques may be supported [TS38.305]:

[0053] The Downlink Time Difference of Arrival (DL-TDOA) positioning method utilizes the DL Reference Signal Time Difference (RSTD) (and optionally the DL PRS Reference Signal Received Power (RSRP)) at the UE of downlink signals received from multiple TPs. The UE measures the DL RSTD (and optionally the DL PRS RSRP) of the received signals using assistance data received from a positioning server, and the resulting measurements are used together with other configuration information to locate the UE relative to neighboring TPs.

[0054] The DL AoD positioning method utilizes measured DL PRS RSRPs of downlink signals received from multiple TPs at the UE: the UE measures the DL PRS RSRPs of the received signals using assistance data received from a positioning server, and the resulting measurements are used together with other configuration information to locate the UE relative to neighboring TPs.

[0055] 3 illustrates a scenario 300 for multi-cell round trip time (RTT) positioning. The multi-round trip time (RTT) positioning method utilizes UE Rx-Tx measurements and DL PRS RSRPs of downlink signals received from multiple TRPs, measured by the UE, as well as gNB Rx-Tx measurements and uplink (UL) sounding reference signal (SRS)-RSRPs measured in multiple TRPs of uplink signals transmitted from the UE. The UE measures the UE Rx-Tx measurements (and optionally the DL PRS RSRPs of the received signals) using assistance data received from the positioning server, and the TRPs measure the gNB Rx-Tx measurements (and optionally the UL SRS-RSRPs of the received signals) using assistance data received from the positioning server. The measurements are used to determine the RTT at the positioning server, which is used to estimate the UE's location.

[0056] In the Enhanced Cell Identifier (E-CID) positioning method, the UE's location is estimated using knowledge of its serving ng-eNB, gNB, and cells and is based on LTE signals. Information about the serving ng-eNB, gNB, and cells may be obtained by paging, registration, or other methods. NR E-CID positioning refers to a technique that uses additional UE measurements and / or NR radio resource and other measurements to improve the UE's location estimation using NR signals. NR E-CID positioning may utilize some of the same measurements as the measurement control system in the RRC protocol, but the UE is generally not expected to perform additional measurements solely for positioning. For example, the measurement procedure does not provide measurement configuration or measurement control messages, and the UE reports its available measurements rather than being required to perform additional measurement activities.

[0057] The UL TDOA positioning method utilizes UL TDOA (and optionally UL SRS-RSRP) at multiple reception points (RPs) of uplink signals transmitted from a UE. The RPs measure the UL TDOA (and optionally UL SRS-RSRP) of the received signals using assistance data received from a positioning server, and the resulting measurements are used together with other configuration information to estimate the location of the UE.

[0058] The UL AoA positioning method utilizes the measured azimuth and zenith angles of arrival at multiple RPs of an uplink signal transmitted from a UE. The RPs use assistance data received from a positioning server to measure the A-AoA and Z-AoA of the received signal, and the resulting measurements are used along with other configuration information to estimate the location of the UE.

[0059] RAT-independent positioning techniques may also be implemented, including [TS38.305].

[0060] Network-assisted Global Navigation Satellite System (GNSS) methods: These methods utilize UEs equipped with radio receivers capable of receiving GNSS signals. In 3GPP® standards, the term GNSS encompasses both global navigation satellite systems and regional / augmented navigation satellite systems. Examples of global navigation satellite systems include the Global Positioning System (GPS), Modernized GPS, Galileo, GLONASS, and the BeiDou Navigation Satellite System (BDS). Regional navigation satellite systems include the Quasi-Zenith Satellite System (QZSS), while some augmentation systems fall under the general term Navigation Satellite Augmentation System (SBAS) and provide regional augmentation services. In this concept, different GNSS (e.g., GPS, Galileo, etc.) can be used separately or in combination to determine the location of a UE.

[0061] Barometric Pressure Sensor Positioning: The barometric pressure sensor method utilizes a barometric pressure sensor to determine the vertical component of the UE's position. The UE measures the barometric pressure to calculate the vertical component of its location or to send measurements to a positioning server for position calculation, optionally aided by assistance data. This method can be combined with other positioning methods to determine the 3D position of the UE.

[0062] Wireless Local Area Network (WLAN) Positioning: WLAN positioning methods utilize WLAN measurements (access point (AP) identifiers and optionally other measurements) and databases to determine the location of a UE. The UE measures received signals from WLAN access points, optionally aided by assistance data, to send the measurements to a positioning server for position calculation. Using the measurement results and a reference database, the UE's location is calculated. Alternatively, the UE utilizes WLAN measurements and optionally WLAN AP assistance data provided by the positioning server to determine its location.

[0063] Bluetooth Positioning: The Bluetooth positioning method utilizes Bluetooth measurements (beacon identifiers and optionally other measurements) to determine the location of the UE. The UE measures the received signals from the Bluetooth beacons. Using the measurement results and a reference database, the location of the UE is calculated. The Bluetooth method can be combined with other positioning methods (e.g., WLAN) to improve the positioning accuracy of the UE.

[0064] TBS Positioning: TBS consists of a network of terrestrial transmitters that broadcast signals solely for positioning purposes. Current types of TBS positioning signals are MBS (Metropolitan Beacon System) signals and PRS (Technical Specification (TS) 36.211 [4]). A UE measures the received TBS signals to calculate its location or transmits measurements to a positioning server for position calculation, optionally aided by assistance data.

[0065] Motion Sensor Positioning: The motion sensor method utilizes various sensors, such as accelerometers, gyros, and magnetometers, to calculate the displacement of the UE. The UE estimates the relative displacement based on a reference position and / or a reference time. The UE transmits a report with the determined relative displacement, which can be used to determine the absolute position. This method can be used with other positioning methods for hybrid positioning.

[0066] Figures 4a and 4b show a portion of an LPP RequestLocationInformation message 400. The RequestLocationInformation message 400 body in an LPP message may be used by a location server to request a location measurement or estimate from a target device.

[0067] Figures 5a and 5b show a portion of an LPP ProvideLocationInformation message 500. The ProvideLocationInformation message 500 body in an LPP message may be used by a target device to provide position measurements or estimates to a location server.

[0068] For RAT-dependent positioning measurements, the various DL measurements including DL PRS-RSRP, DL RSTD, and UE Rx-Tx time difference used for the supported RAT-dependent positioning techniques are shown in Table 4 below. For example, the following measurement configurations are specified [TS38.215]: Four pairs of DL RSTD measurements may be performed per cell pair, each between a different pair of DL PRS resources / resource sets using a single reference timing. · 8 DL PRS RSRP measurements may be performed for different DL PRS resources from the same cell.

[0069] [Table 6A] [Table 6B]

[0070] Figure 6 shows a system 600 for machine learning-based RAN intelligence. In the system 600, Data Collection is a function that provides input data to the Model Training function and the Model Inference function. AI / ML algorithm-specific data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) may not be performed in the Data Collection function. Examples of input data may include measurements from UEs or different network entities, feedback from Actors, and outputs from AI / ML models. Training Data: Data required as input for AI / ML Model Training functions Inference Data: Data required as input for AI / ML Model Inference functions

[0071] Model Training is a function that performs training, validation, and testing of ML models, which may generate model performance measures as part of the model testing procedure. The Model Training function is also responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on the Training Data delivered by the Data Collection function.

[0072] Model Deployment / Update: Used to initially deploy a trained, validated, and tested AI / ML model to the Model Inference function, or to deliver an updated model to the Model Inference function.

[0073] Model Inference is a function that provides AI / ML model inference output (e.g., predictions or decisions). The Model Inference function is also responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation), if needed, based on the Inference Data delivered by the Data Collection function.

[0074] Output: The inference output of the AI / ML model produced by the Model Inference function.

[0075] Model Performance Feedback: Applied when some information derived from the Model Inference function is suitable for improving the AI / ML model trained in the Model Training function. Feedback from Actors or other network entities (via the Data Collection function) may be required in the Model Inference function to create the Model Performance Feedback.

[0076] An Actor is a function that receives the output from a Model inference function and triggers or performs a corresponding action. An Actor can trigger actions directed at other entities or itself.

[0077] Feedback: Information that can be used to derive training data or inference data or performance feedback.

[0078] Therefore, approaches to assist machine learning for positioning are provided in this disclosure. For example, direct AI-based and AI-assisted positioning methods may be utilized to improve the location accuracy performance of a UE. In scenarios for direct AI / ML positioning, techniques such as fingerprinting may be utilized by AI / ML models to obtain improved location accuracy using measurements and environmental data. This disclosure describes techniques for configuring direct AI / ML positioning assistance data and defining measurements for performing AI / ML direct positioning. Furthermore, this disclosure describes techniques for configuring reporting criteria for devices, nodes, and / or entities that perform AI / ML direct positioning.

[0079] With respect to aspects of the present disclosure, implementations are described for configuring a target UE, a positioning reference unit (PRU) UE, a sidelink (SL) UE, or an NG-RAN node to perform direct AI / ML position measurements based on positioning reference signal transmissions to generate a training data set; enabling a target UE, a PRU UE, a SL UE, or an NG-RAN node to perform required measurements for different scenarios, which may form part of a fingerprint based on environmental topology and AI / ML measurement parameters; enabling a target UE, a PRU UE, an NG-RAN node, a configuration entity, a SL UE, and / or a location server to indicate AI / ML positioning assistance data or measurement error sources; enabling a reporting configuration framework for a target UE, a PRU UE, a SL UE, and / or an NG-RAN node to receive desired direct AI / ML position measurements, e.g., fingerprinting information; enabling multiple common reporting standards for AI / ML position measurements; and enabling configuration and reporting of assistance information for accurately reporting AI / ML position measurements.

[0080] Some notes regarding the implementations described in this disclosure: different implementations can be combined with each other in various ways; measurement-related reference signals may be referred to as reference signals used for positioning procedures and / or for the purpose of estimating the location of a target UE, e.g., signals based on existing reference signals such as PRS, Channel State Information (CSI) Reference Signals (RS) (CSI-RS) or SRS; target UE may be referred to as a device and / or entity to be located and / or positioned; the term "PRS" may refer to any signal, such as a reference signal, that may or may not be used primarily for positioning; target UE may be referred to as a UE of interest whose position (e.g., absolute and / or relative) is to be obtained by the network and / or the UE itself; the terms AI and ML may be used interchangeably to refer to intelligent software components or systems, where AI may represent a subset and / or implementation of ML; references made to device position and / or location information may refer to 2D / 3D absolute position, relative position with respect to another node and / or entity, distance-related ranging, direction-related ranging, and combinations thereof.

[0081] Implementations disclosed herein support direct AI / ML position measurement and processing configurations. For example, fingerprinting is described, such as where inference AI / ML models may be deployed in different entities. Examples of such implementations include UE-based positioning using UE-side ML modes, UE-assisted and / or LMF-based positioning using LMF-side ML models, NG-RAN node-assisted positioning using LMF-side ML models, etc.

[0082] In implementations involving UE-based positioning, the target UE may request a training data set based on DL and SL reference signals (e.g., DL-PRS, SL-PRS, etc.) from various data sources, including measurements performed and collected within the target UE, other UEs, location servers, NG-RAN nodes, PRUs, network operations, administration, and maintenance (OAM), trace collection entities (TCEs), and / or combinations thereof. The training data set may include reference points and / or reference locations, and fingerprint information and / or other location measurements may be sampled, measured, and / or associated with them. Various network entities and / or nodes may be enabled in the following manner to enable the configuration. · The target UE, anchor UE, and / or PRU UE may send a request and receive a response including downlink (DL) direct AI / ML positioning assistance (e.g., configuration) data, e.g., configuration for fingerprinting on the location server. The target UE may send a request and receive training data (e.g., instead of a configuration to perform measurements) or instructions to obtain training data from a second node, such as a location server, an NG-RAN node, a positioning reference unit, a network OAM, a TCE, or a combination thereof. Another node (e.g., a location server, an NG-RAN node, and / or another node) may send a request to the target UE to receive training data that the target UE has collected and / or measured. A location server may receive DL direct AI / ML positioning assistance (e.g., configuration) data for radio frequency (RF) fingerprinting requests from multiple UEs, including a target UE and a PRU UE, and the location server may provide a configuration response. · One or more UEs, including anchor UEs and / or PRU UEs, may receive a request for SL direct AI / ML positioning assistance data (e.g., configuration and / or RF fingerprinting) and may provide an appropriate configuration response.

[0083] In implementations involving UE-assisted positioning, the location server may request multiple training data sets based on DL and SL reference signals (e.g., DL-PRS, SL-PRS) from various data sources, including measurements collected within the location server, multiple UEs, other nearby location servers, NG-RAN nodes, positioning reference units, and combinations thereof. These data sets may include reference points and / or reference locations, and fingerprint information may be sampled, measured, and / or correlated. Various network entities and / or nodes may be enabled with the following capabilities to enable such implementations: Location server may transmit downlink (DL) or sidelink (SL) direct AI / ML positioning assistance (configuration), e.g. fingerprinting data. At least one or more UEs, including target UE or PRU UE, may receive a response / configuration for DL ​​and / or SL AI / ML direct positioning configuration, e.g., fingerprinting with respect to a location server.

[0084] 7 illustrates an example scenario 700 supporting machine learning for positioning according to aspects of the present disclosure. Scenario 700 includes a representation of a DL and SL direct AI / ML configuration mechanism, such as that discussed above, within a rectangular environment 702 of length L and width W (e.g., an indoor factory building environment) that includes, for example, 18 gNBs / TRPs and reference points separated by an inter-gNB / TRP distance D.

[0085] In scenario 700, DL LTE Positioning Protocol (LPP) signaling 704 from a location server 706 to a target UE 708 and / or an anchor / PRU UE 710 may be utilized to convey multiple direct AI / ML positioning configurations, e.g., using an LPP ProvideAssistanceData message or a new LPP ProvideMLAssistanceData message, while a Sidelink Positioning Protocol (SLPP) or a new positioning protocol for exchanging SL positioning messages may be used for signaling 712 to provide multiple direct AI / ML positioning configurations from the anchor / PRU UE 710, e.g., using an SLPP ProvideAssistanceData message. Alternatively or additionally, the SL positioning server UE may provide the direct AI / ML positioning configurations via SLPP or the like. Furthermore, the target UE 708 may configure surrounding UEs, PRU UEs, and / or SL positioning server UEs to perform direct AI / ML positioning, e.g., fingerprinting based on reference locations / points. For illustrative purposes, direct signaling from the location server 706 is shown. However, such signaling may be transparently routed to the UE via the serving gNB.

[0086] In an implementation, an anchor / PRU UE 710 may configure other anchor / PRU UEs 710 to perform AI / ML position measurements. Additionally, the LMF may configure a first set of anchor / PRU UEs 710 to transmit SL PRS to a second set of anchor / PRU UEs 710.

[0087] In an implementation such as that shown in scenario 700, the target UE 708, the anchor / PRU UE 710, and / or the location server 706 may request multiple DL or SL direct AI / ML positioning assistance data, for example, using an LPP RequestAssistanceData message. Alternatively or additionally, the target UE 708 may request multiple SL direct AI / ML positioning assistance data from the anchor / PRU UE 710 and / or the SL positioning server UE, for example, using an SLPP and / or SL positioning protocol message RequestAssistanceData.

[0088] In implementations involving NG-RAN-assisted positioning, the location server may request multiple training data sets based on UL reference signals (e.g., SRS for positioning) from various data sources, including neighboring gNBs, TRPs, NG-RAN nodes, PRU TRPs, CUs, DUs, and / or combinations thereof. The training data sets may include reference points and / or reference locations corresponding to NG-RAN nodes, CU locations, and / or DU locations, and fingerprint information may be sampled, measured, and / or associated. In implementations, various network entities and / or nodes may involve the following procedures. NG-RAN nodes, including gNBs and / or TRPs, may send UL AI / ML direct positioning configurations (e.g., fingerprinting) to one or more UEs upon request from a location server. · UEs, including target UEs, may receive responses and / or configurations for UL AI / ML direct positioning configuration (e.g., fingerprinting) with respect to the location server. The location server may send a UL AI / ML direct positioning assistance, e.g., fingerprinting data request, to one or more NG-RAN nodes, including a gNB, a TRP, a CU, a DU, a PRU, and / or a combination thereof, and then receive a configuration response.

[0089] 8 illustrates an example scenario 800 for supporting machine learning for positioning according to aspects of the present disclosure. In scenario 800, in step 802, a location server 804 triggers a configuration request to an NG-RAN node 806, e.g., a serving gNB and / or a neighboring gNB. Step 806 requires, for example, a UL direct AI / ML positioning configuration, e.g., an NRPPa with fingerprinting of N reference locations.

[0090] In step 808, the NG-RAN node 806 forwards the UL-RS configuration (e.g., SRS for positioning configuration) to the target UE 810 and / or PRU / anchor UE 812, such as to enable UL transmission in the gNT / TRP and subsequent UL direct AI / ML measurements to be performed. Step 808 may require, for example, an RRC with UL direct AI / ML positioning configuration, e.g., fingerprinting of N reference locations.

[0091] In an implementation, the location server 804 may directly transfer the UL-RS configuration at the NG-RAN node 806, e.g., a gNB / TRP, via DL LPP signaling for performing UL transmission and subsequent UL direct AI / ML measurements. In an alternative implementation, the NG-RAN node 806 may be implemented as a CU and a DU, and the location server 804 may signal that the CU and DU may perform UL-RS measurements at different distributed reference locations and / or reference points, e.g., in an indoor factory scenario such as that described above. For example, in step 814, the location server 804 may transmit the UL direct AI / ML positioning configuration, e.g., fingerprinting of N reference locations.

[0092] In an implementation, the location of the PRU / anchor UE 812 may be utilized along with the gNB / TRP ground truth reference location to construct a fingerprint that includes the ground truth reference location. In such an implementation, the PRU / anchor UE 812 may signal a 2D and / or 3D location at which the SRS is being transmitted towards a configuration entity, e.g., the NG-RAN node 806 and / or the location server 804. In scenarios that involve signaling location information towards the location server 804, LPP signaling (e.g., a ProvideLocationInformation message) may be used, and in scenarios that require signaling location information to the NG-RAN node 806, RRC signaling, e.g., LocationMeasurementIndication, may be used.

[0093] Alternatively or additionally, the configuration entity may request the PRU / anchor UE 812 to transmit the UL SRS or SL PRS at certain predefined locations, which may be included in the AI / ML configuration directly along with the positioning reference signal configuration.

[0094] In implementations, certain types of NG-RAN nodes (e.g., PRU gNB / TRP) may also transmit SRS to other NG-RAN nodes, UEs, and / or devices. NG-RAN nodes that receive the SRS may perform direct AI / ML position measurements for purposes of direct AI / ML position estimation. Thus, NG-RAN nodes capable of transmitting and receiving SRS, such as PRU TRPs, can support this type of measurement. In implementations, new reference signals may also be supported between NG-RAN nodes for purposes of direct AI / ML position estimation, and may be transmitted over the Xn interface and / or another wireless transmission medium, etc. In implementations, the configuration methods discussed above may be combined, such as to enable the individual and combined utilization of DL, SL, and / or UL direct AI / ML position measurements.

[0095] In implementations, configurations such as those signaled as described above may be used to enable direct AI / ML location estimation, e.g., using fingerprinting methods. For example, configurations according to the implementations described above and as discussed below are considered.

[0096] In a UE-based positioning scenario using, e.g., a UE-side model, the target UE may create multiple fingerprint training data sets based on measurements performed, data, received measurements, and / or data from other network entities, e.g., a location server, other UEs, PRUs, etc. The target UE may initiate a request to the location server for configurations related to measurements of DL or SL direct AI / ML measurements (e.g., fingerprint measurements) and / or request transmission configurations of the UL-RS for direct AI / ML positioning. Exemplary configurations are discussed below.

[0097] 9 illustrates a message 900 for assisting machine learning for positioning according to an aspect of the present disclosure. Message 900 represents an NR-Direct-AI-ML-AssistanceData information element that may be used by a target device to request AI / ML positioning assistance data directly from a location server and / or configuration entity, e.g., an SL positioning server UE, an anchor UE, etc.

[0098] Table 5 provides an example field description of message 900.

[0099] [Table 7A] [Table 7B]

[0100] In implementations, message 900 may include direct AI / ML positioning assistance data, assisted AI / ML positioning, or a combination thereof. Assisted AI / ML position measurements may be defined as measurements that have been refined and / or optimized using AI / ML models, e.g., RSTD, relative time of arrival (RTOA), RSRP, RSRPP, Rx-Tx, AoA, AoD, time difference, etc.

[0101] In implementations, in connection with UE-based positioning such as that described above, the target UE may provide ground truth reference locations, e.g., an index or list of absolute and / or relative locations. Exemplary ground truth reference locations are defined below.

[0102] In implementations such as those requiring UE-based positioning (e.g., using a UE-side model) and / or UE-assisted positioning using an LMF-side model, the location server may transmit direct AI / ML positioning assistance data. Alternatively or additionally, the location server may transmit assisted AI / ML positioning assistance data to one or more target devices, such as PRU UEs, anchor UEs, SL positioning server UEs, etc., to perform direct AI / ML measurements and / or assisted AI / ML measurements to be used as training data input. For example, the target UE may receive from the location server multiple configurations for DL ​​or SL direct AI / ML measurements, e.g., fingerprint measurements, and / or UL-RS transmission configurations for direct AI / ML positioning.

[0103] 10a and 10b illustrate different portions of a message 1000 for assisting machine learning for positioning according to an aspect of the present disclosure. Message 1000 may represent, for example, the NR-Direct-AI-ML-ProvideAssistanceData message.

[0104] Table 6 provides an example field description of message 1000.

[0105] [Table 8A] [Table 8B]

[0106] In implementations, the DL-PRS configuration information described above may be used to enable devices (e.g., target UEs, PRU UEs, SL UEs, etc.) to perform AI / ML measurements directly at each of the configured ground truth reference locations, such as those signaled above. This process may be performed offline, and the measurements and their respective locations may be signaled to a location server or stored in a single UE or multiple UEs.

[0107] In implementations requiring NG-RAN-assisted positioning (e.g., using an LMF-side model), the location server may send one or more requests for direct AI / ML positioning assistance data for available SRS and / or other UL-PRS configurations to multiple gNBs and / or TRPs. One or more gNBs and / or TRPs may determine an SRS configuration for each target UE for performing SRS transmission-related AI / ML positioning, which may be configured per carrier. In implementations, the SRS configuration may be broadcast to multiple UEs for use in multiple cells within a predetermined positioning system information area, within an area with associated validity for time and / or area, and combinations thereof.

[0108] In implementations, the gNB and / or TRP may configure the UE to perform SRS for positioning transmissions via RRC signaling, e.g., using an RRCReconfiguration message. The gNB and / or TRP may configure the UE to perform SRS for positioning transmissions to perform direct AI / ML positioning or assisted AI / ML positioning.

[0109] In an implementation, the target UE may acknowledge receipt of the SRS for positioning configuration to perform direct AI / ML positioning measurements and / or assisted AI / ML positioning measurements along with other non-AI / ML timing or angle-based measurements. The location server (e.g., LMF) may request one or more gNBs and / or TRPs to enable the SRS for positioning configuration for transmission by the target UE. The gNB and / or TRP may enable transmission of the SRS to the UE by sending a DL MAC control element (CE) enable command to the target UE. The location server may further disable SRS transmission via the gNB, which can send the disable command, for example, using the DL MAC CE.

[0110] In an implementation, the location server may receive multiple available SRS or UL-PRS configurations for performing UL direct AI / ML positioning. In one example scenario, the gNB can derive SRS and / or UL-PRS fingerprints for location estimation of multiple UEs.

[0111] In implementations, lower layer signaling for LPP (e.g., RRC signaling, MAC CE, downlink control information (DCI) signaling, and combinations thereof) may be used to convey direct AI / ML configurations or assisted AI / ML configurations. In at least one implementation, LPP and / or RRC signaling may be used to add, modify, delete, update, enable, and / or disable one or more UE direct AI / ML positioning configurations.

[0112] Implementations enable direct AI / ML measurements and processing procedures. For example, methods for performing direct AI / ML measurements are presented based on the type of AI / ML technique. In at least one implementation, fingerprint measurements may rely on received signal strength (RSS) measurements, including RSRP, reference signal received quality (RSRQ), RSSI, or a combination thereof. In implementations, fingerprint measurements may include a combination of RSS, timing-based measurements, and angle-based measurements to learn a location estimate for the UE.

[0113] In implementations, a target UE, PRU UE, SL UE, etc. may be configured to make the following measurements to build an RF fingerprint applicable to: RAT dependency measurements: DL / SL RSTD (measurement based on DL or SL) DL / SL PRS Time of Arrival (TOA) (DL-based or SL-based measurement) DL / SL PRS RSRP (measurement based on DL or SL) DL / SL PRS RSRPP (measurement based on DL or SL) UE Rx-Tx time difference (measured either DL-based or SL-based) Synchronization Signal (SS)-RSRP (RSRP for RRM), SS-RSRQ (for RRM), CSI-RSRP (for RRM), CSI-RSRQ (for RRM), SS-RSRP (for RRM) (measurement based on DL) DL / SL carrier phase measurement (DL-based or SL-based measurement) DL / SL carrier phase difference measurement (DL-based or SL-based measurement) DL E-CID LTE E-CID SL Physical Sidelink Shared Channel (PSSCH) RSRP DL PRS RSSI (Received Signal Strength Indicator) LTE Observed Time Difference of Arrival (OTDOA) measurement RAT-independent measurement A-GNSS measurements, including common assistance data that may be applicable to any GNSS constellation, e.g., Galileo, GPS, GLONASS, etc., generic assistance data for a specific GNSS constellation, or periodic GNSS assistance data used to periodically provide GNSS control information to the UE / device. Bluetooth RSS measurements including RSSI WLAN (WiFi) measurements including RSSI and RTT information IMU sensor measurements including gyroscopes, accelerometers, etc. Barometric pressure sensor measurement

[0114] In an implementation, an NG-RAN node, gNB / TRP, CU-DU, etc. may be configured to perform the following measurements as applicable: RAT-dependent measurements UL-RTOA (measurement based on UL) UL SRS RSRP (measured according to UL) UL SRS RSRPP (measured according to UL) gNB Rx-Tx time difference measurement (measurement based on UL) UL-AoA (measurement according to UL) UL Carrier Phase Measurement (UL based measurement) UL carrier phase difference measurement (measurement based on UL) UL NR E-CID LTE E-CID

[0115] The above measurement instances may constitute multiple fingerprint measurements that include part of DL or UL direct AI / ML position measurements at one or more ground truth locations. The use of RAT-dependent and RAT-independent methods may help derive hybrid fingerprints to improve the accuracy of direct AI / ML positioning methods.

[0116] In an implementation, the location server (e.g., LMF) may prepare direct and / or assisted AI / ML configurations for the measurement based on the type of AI and / or machine learning model, etc. These models may include, but are not limited to, any one or more of the following combinations: Supervised learning methods: k-NN (nearest neighbor) clustering This model classifies fingerprints according to the geometric distance between neighboring training data points and determines the K nearest neighbors to the input fingerprint. Support Vector Machine (SVM) The model is based on margin calculations, where the input fingerprint data is plotted in n-dimensional space with n-1 hyperplanes drawn to divide the training data among n classes so that the distance between each class and the hyperplane is maximized. Decision Tree Classification or regression problems related to fingerprint matching can be solved using structures such as decision trees: rules are used to split the training data into labels, and a label is predicted for every new fingerprint data point through this decision tree. Random Forest The model is an ensemble of several decision trees, where the result of each tree provides a fingerprint classification, or in another implementation, the average prediction of all decision trees is in the output. This helps overcome the overfitting problem that standalone decision trees experience. Artificial Neural Networks (ANN) Based on the backpropagation learning algorithm, the input dataset of fingerprint data is transformed into the final location estimation output using a nonlinear transfer function in the hidden units / nodes. Such a model can be robust to noisy or interference-constrained fingerprint data. Unsupervised methods: K-means This model partitions the fingerprints into K unique, non-overlapping clusters or groups to characterize a particular location. Gaussian Mixture Model (GMM) A GMM is a probabilistic model that can be used to estimate the distribution of RF fingerprints at different locations, including ground truth reference locations as well as unknown locations. A GMM may be trained using collected RF fingerprints and then used to determine the most likely location for a given set of RF fingerprints. · Both supervised and unsupervised methods: Bayesian Networks (BN) The BN can be used to model the probabilistic relationship between RF fingerprints and environmental factors, such as wireless channel parameters, e.g., channel state information (CSI), path loss, and attenuation parameters, for a given location. The BN can be trained using a training set composed of the BN of RF fingerprints and environmental data to perform RF fingerprint localization. ·study Reinforcement learning Learning algorithms based on trial and error methods, where decisions are based on so-called "reward" or "punishment" methods, where correct decisions are rewarded while incorrect decisions are punished in order to improve model performance. Deep Learning · It is based on ANN, which utilizes an iterative weight adjustment technique between neuron / node pairs, which is trained using a large set of fingerprint data collected from the environment. Transfer learning Leveraging the model's ability to learn new features and material to its own system knowledge, allowing for minimal changes to already existing trained models. This could be utilizing direct AI / ML positioning, e.g., fingerprinting, to provide a scalable solution to eliminate the significant effort of collecting fingerprints on-site during an offline phase, e.g., during an initial fieldwork.

[0117] In an implementation, the location server may explicitly indicate the ML model to the target UE and / or the PRU UE using UE-specific LPP / SLPP signaling, e.g., SLPP / LPP ProvideAssistanceData messages. In an implementation, the model may be indicated to multiple UEs using positioning system information broadcast messages, e.g., new and / or existing posSIBs.

[0118] In an implementation, the location server and / or configuration entity may receive a request for direct AI / ML positioning or assisted AI / ML positioning assistance data from a target UE, a PRU UE, and / or an SL UE along with an indication of the above-described model whose measurements should be used as input data.

[0119] In an implementation, the ML model used to initiate a direct or assisted AI / ML positioning session may be indicated via applicable UE capability signaling (e.g., LPP ProvideCapabilities message), which may be based on an active request from the location server and / or configuration entity, e.g., an LPP RequestCapabilities message.

[0120] In an implementation, PRS RSSI measurements may be defined for AI / ML positioning purposes, including both direct and assisted techniques. In an implementation, PRS RSSI may be applicable to non-AI / ML positioning techniques. Furthermore, these measurements may be performed in the RRC_CONNECTED, RRC_INACTIVE, and RRC_IDLE states. The PRS RSSI for the downlink, sidelink, and uplink may be defined in Table 7 as follows:

[0121] [Table 9A] [Table 9B]

[0122] In an implementation, and according to the measurement definitions presented in Table 7, the DL, SL, and UL PRS RSSI may include a fingerprint feature or signature that can be used to enable direct AI / ML positioning. Additionally, PRS or SRS TOA measurements may be further defined to act as an additional feature or signature for purposes of AI / ML positioning, including both direct and assisted techniques. In an implementation, the PRS TOA may be applicable to non-AI / ML positioning techniques. Furthermore, these measurements may be performed in the RRC_CONNECTED, RRC_INACTIVE, and RRC_IDLE states. The PRS TOAs for the downlink, sidelink, and uplink (SRS) are defined in Table 8 as follows:

[0123] [Table 10A] [Table 10B] [Table 10C]

[0124] In an implementation, the target UE and / or PRU UE may be configured to measure DL PRS and / or SL PRS for AI / ML positioning, such as in one or more of the following scenarios: Configured with a Measurement Gap (MG) associated with a Gap Pattern ID, a Measurement Gap Length (MGL), and a Measurement Gap Repetition Period (MGRP) or a combination thereof. This MG can be pre-configured with an enable or disable command. · Configured without or outside a measurement gap when the DL PRS is within a valid DL Bandwidth Portion (BWP) in the same numerology as the valid DL BWP. Configured with a training measurement gap (T-MG) that is predefined by a gap pattern ID, a measurement gap length (MGL), a measurement gap repetition period (T-MGRP), a T-MG start time, a T-MG duration, a T-MG end time, and a flag indicating whether the measurement is based on offline training, online training, or a combination thereof. In other implementations, the time length given by the measurement interval or timer expiration can be used to indicate the start and end of the time length for performing measurements for online or offline training of an AI / ML positioning model.

[0125] In an implementation, for each received DL / SL PRS, the UE may be configured with a configuration of the priority of PRS resources used to perform AI / ML and non-AI / ML positioning measurements. These resources may form subsets of resources, which may form part of the same or different PRS resource sets. This priority signaled to the UE / device may indicate the priority of performing measurements, which may build a training data set in addition to or instead of performing measurements for non-AI / ML positioning.

[0126] Implementations also provide for providing assistance data and / or measurement error causes. For example, the UE may indicate to the network and / or configuration entity that one or more measurements related to the ground truth location and / or fingerprint have an associated error cause. The error cause may be, for example, not receiving a PRS configuration or a missing configuration parameter in the PRS configuration. For example, utilizing the implementations described above, LPP and / or SLPP signaling may be used to indicate the error cause to the network. Furthermore, the error cause may be UE-attributed, e.g., occurring at the UE side. In implementations, the error cause may be a location server-initiated instruction to the UE.

[0127] 11 illustrates a message 1100 for assisting machine learning for positioning according to an aspect of the present disclosure. Message 1100 represents an IE indicating error causes supported by a location server and / or configuration entity, such as may be conveyed via LPP. For example, message 1100 represents an NR-AI-ML-LocationServerErrorCauses IE that may be used by a location server to provide error reasons for AI / ML assistance data to a target device. Message 1100 may also be used for an SL configuration entity to provide such error causes to a target UE and / or device.

[0128] 12 illustrates a message 1200 for assisting machine learning for positioning according to an aspect of the present disclosure. Message 1200 presents error causes supported by a target UE, which may be conveyed, for example, via LPP. The message represents an NR-AI-ML-TargetDeviceErrorCauses IE, which may be used, for example, by a target UE to provide error reasons for NR direct AI / ML measurements or error reasons for assisted AI / ML measurements to a location server. Such an implementation may be applicable to SL target UEs and / or devices that provide the above error reasons to an SL configuration entity.

[0129] In an implementation, the NG-RAN node may signal the IE NR-AI-ML-NG-RANnodeErrorCauses, where one or more combinations of parameters are included in the NR-AI-ML-TargetDeviceErrorCauses IE described above. Error causes introduced in the NG-RAN node (e.g., gNB and / or TRP) can be signaled to the location server over the NRPPa interface, for example, using an Error Indication message. In addition, the following error causes can be signaled from the NG-RAN node side: · The target UE or PRU UE moves to another cell. ·Failure to provide required AI / ML location measurements on time. The AI / ML training model is no longer valid and needs to be retrained. The AI / ML inference model is no longer valid and needs to be reacquired.

[0130] In implementations, location measurements including the definitions contained in Tables 7 and 8 may have associated quality indicators that indicate: The quality of measurements taken based on timing and RSS parameters The quality of the measurements taken relative to similar measurements taken at surrounding ground truth reference locations

[0131] The implementations described herein also provide for reporting configuration procedures. For example, implementations that enable reporting configuration of direct AI / ML position measurement and reporting (e.g., fingerprinting) are described for scenarios such as the following, where inference AI / ML models may be deployed in the following entities to perform positioning: UE-based positioning using UE-side model UE-assisted / LMF-based positioning using LMF-side model Positioning assisted by NG-RAN nodes using LMF-side model

[0132] The above scenarios are presented as examples only, and the corresponding details can be extended beyond these illustrative scenarios.

[0133] In a UE-based positioning scenario, the target UE may request training data sets based on DL and SL reference signals (e.g., DL-PRS, SL-PRS, etc.) from various data sources, including measurements performed and collected within the target UE, at other UEs, at a location server, at an NG-RAN node, at a PRU, at an OAM, at a TCE, and / or combinations thereof. Additionally, training may be performed on the UE side, and the calculated location estimate may be calculated by the target UE device. In such implementations, reporting criteria and / or reporting configurations including assistance information and associated measurement reports may be initiated from the target UE.

[0134] Various network entities, UEs, and / or nodes may be enabled using the following procedures to enable reporting configuration, such as in scenarios where AI / ML model training is performed on the UE side.

[0135] 13 illustrates scenarios 1300 that support machine learning for positioning according to aspects of the present disclosure. Scenarios 1300 include, for example, scenario 1300a in which UE-side training may be performed using inference of the target UE with other UEs, and scenario 1300b in which UE-side training may be performed using inference of the target UE with network entities.

[0136] In scenario 1300, the target UE 104a may request multiple direct AI / ML position measurements based on defined reporting criteria at 1302. For example, in scenario 1300a, the SL Positioning Protocol (SLPP) and / or other defined positioning protocols may be utilized by the target UE 104a to request a direct AI / ML positioning report from the UE 104b, including measurement reporting criteria and / or assistance information, at 1304a, for transport of signaling to the UE. At 1300b, LPP signaling may be utilized to request a direct AI / ML positioning report from a network entity 102, such as a location server, at 1304b, including measurement reporting criteria and / or assistance information. In scenarios involving an NG-RAN node, RRC and / or associated UL signaling, such as UL MAC CE, may be utilized.

[0137] Further to scenario 1300, each network entity 102 and / or UE 104 may provide a response 1306 to the request 1304 to provide measurements that correlate to the reporting criteria and / or assistance information indicated in the request 1304. For example, UE 104b may respond via SLPP in 1306a, and the network entity may respond via LPP and / or RRC in 1306b. In a scenario in which the network entity 102 reports measurements, the location server may receive measurement reports from other UEs (e.g., PRU UEs and / or other UEs) based on active or inactive requests and report such measurements to the target UE 104a.

[0138] At 1308, the target UE 104a can build a training dataset based on the measurement reports from different sources and train the AI / ML model. In an implementation, the target UE 104a can utilize the trained ML model and perform inference based on new measurement data by repeating steps 1304a, 1304b, 1306a, and 1306b to obtain new measurement data for processing via the trained ML model. In an implementation, the training and inference datasets can be requested one-off, such as to avoid repeating 1304 and 1306 to train the ML model and subsequently perform inference.

[0139] In an implementation, ML model training may be performed on the network side (e.g., a location server or NG-RAN node (e.g., gNB)) and / or other UEs / devices, such as anchor UEs, PRU UEs, SL UEs, etc. In such an implementation, the network entities and / or UEs / devices may require multiple reporting criteria so that desired measurements and assistance information are reported in a timely and accurate manner. These data sets may include reference points or reference locations, where fingerprint information or other location measurements are sampled, measured, or associated.

[0140] 14a and 14b illustrate scenarios 1400 for supporting machine learning for positioning according to aspects of the present disclosure, including, for example, scenarios 1400a and 1400c in which UE-side training is performed using target UE inference, and scenario 1400b in which network-side training is performed using target UE inference.

[0141] In scenario 1400, each network entity 102 and / or UE 104 may request 1402 direct AI / ML location measurements from a target UE 104a based on certain defined reporting criteria. For transport of signaling to the UE 104, SLPP and / or a newly defined positioning protocol may be utilized, although in the case of a network entity 102 such as a location server, LPP signaling may be utilized, and in an NG-RAN node scenario, any relevant DL signaling such as RRC or DL ​​MAC CE may be utilized.

[0142] At 1404, the target UE 104a may respond to the received request and provide the requested measurements according to the reporting criteria and / or assistance information. For the network entity 102, the location server may, for example, receive measurement reports from other UEs (e.g., PRU UEs, other UEs, etc.) based on active or inactive requests and then report such measurements to the target UE 104a.

[0143] At 1406, each of the other UEs 104 and / or network entities 102 may generate a training data set based on the measurement reports from different sources and perform training of the AI / ML model.

[0144] At 1408, according to an implementation, each other UE 104b and / or network entity 102 can perform inference based on the new measurement data by repeating the procedures at 1402, 1404. In an implementation, training and inference data sets can alternatively be requested on a one-off basis, such as by repeating 1402, 1404.

[0145] In an implementation, various network entities or nodes may be enabled using the following procedures to allow reporting configuration in scenarios where AI / ML model training is not performed on the UE side. The target UE performing the training may send direct AI / ML positioning reporting configurations towards network entities and / or other UEs / services and receive corresponding reports of downlink (DL) or sidelink (SL) direct AI / ML position measurements, e.g., fingerprint measurements. In other implementations, UL measurements may also be provided, such as when the UE may train a model based on UL position measurements, e.g., fingerprints. The network entity performing the training (e.g., location server and / or NG-RAN node) may send direct AI / ML positioning reporting configurations towards the target UE and receive corresponding reports of downlink (DL) or sidelink (SL) direct AI / ML position measurements, e.g., fingerprint measurements. · The UE / node performing the training (e.g., anchor UE, PRU UE, SL UE, etc.) may send direct AI / ML positioning reporting configurations towards the target UE and receive corresponding reports of downlink (DL) or sidelink (SL) direct AI / ML position measurements, e.g., fingerprint measurements.

[0146] In a scenario for UE-assisted positioning, the location server may request a measurement training data set based on DL and SL reference signals (e.g., DL-PRS, SL-PRS, etc.) from various data sources, including measurements collected within the location server, multiple UEs, other nearby location servers, NG-RAN nodes, positioning reference units, and combinations thereof.

[0147] 15 illustrates a scenario 1500 for supporting machine learning for positioning according to aspects of the present disclosure. Scenario 1500 represents an implementation for the exchange of reports and network-side inference, for example, when network-side training is performed. In scenario 1500, training and inference are performed at a network entity 102 (e.g., a location server), which may utilize the illustrated signaling mechanisms to directly signal AI / ML positioning reporting configurations as well as receive measurements from UEs 104, e.g., target UEs, PRU UEs, etc.

[0148] At 1502, each network entity 102 may request multiple direct AI / ML position measurements based on certain defined reporting criteria from the UE 104. With regard to transporting signaling to the UE 104 for the request 1502, LPP signaling may be utilized, although in an NG-RAN node scenario, associated DL signaling such as RRC and / or DL ​​MAC CE may be utilized.

[0149] At 1504 , the UE 104 may similarly respond to the request 1502 received from the network entity 102 and provide measurements as part of the report 1504 according to reporting criteria and / or assistance information specified by the request 1502 .

[0150] At 1506, the network entity 102 builds a training dataset based on the measurement reports from different UEs 104 and trains the AI / ML model. At 1508, the network entity 102 performs inference based on the new measurement data by repeating steps 1502, 1504. Alternatively or additionally, the training and inference datasets may be requested one-off.

[0151] 16 illustrates a scenario 1600 for supporting machine learning for positioning according to aspects of the present disclosure. Scenario 1600 represents an implementation of a stored AI / ML training data set request and response procedure, for example, based on reported AI / ML measurements. In scenario 1600 where training is performed at a UE 104 (e.g., a PRU UE), the UE may receive the AI / ML training data set and perform training at the UE 104 utilizing example signaling as shown in scenario 1600 and described below.

[0152] At 1602, the network entity 102 may request multiple direct AI / ML position measurements based on defined reporting criteria from the UE 104. For transport of signaling from the network entity 102 to the UE 104, LPP signaling may be utilized, and in an NG-RAN node scenario, associated DL signaling such as RRC and / or DL ​​MAC CE may be utilized.

[0153] At 1604, the UE 104 may respond to the request 1602 from the network entity and provide measurements according to the reporting criteria and / or assistance information specified in the request 1602. At 1606, the network entity 102 constructs a training dataset based on the measurement reports from different source UEs / nodes and stores the AI / ML training dataset. The storage of the training dataset may be associated with further additional validity criteria, such as time criteria (e.g., time frame, validity length, timer expiration), and / or spatial criteria, e.g., geographic region ID, area ID, cell ID, tracking area ID, system information area ID, zone ID, AI-ML-Dataset-ValidityArea, or a combination thereof.

[0154] At 1608, in a scenario where training is performed at the UE 104 side, the UE 104 may request an AI / ML training data set, which is based in part on the provided measurements from 1604. At 1610, the network entity 102 may respond to the request 1608 with the AI / ML training data set, which may be based on several criteria including the applicability of the training data set to the UE 104's location, radio link quality, radio channel parameters, mobility pattern, orientation, etc.

[0155] At 1612, the UE 104 performs training based on the received training data set from the network entity 102, and at 1614, the network entity 102 and / or the UE 104 may perform inference to derive an estimated location of the target UE 104 based on the trained AI / ML model.

[0156] In an implementation, scenario 1600 may be applicable to scenarios where training is performed at an NG-RAN node, where the NG-RAN node may request and receive a constructed training dataset that is stored at a location server (e.g., an LMF) based in part on measurements of the NG-RAN node provided to the location server, as described below with reference to FIG. 17.

[0157] In an implementation, model training may be performed on the UE side, and the signaling mechanism in scenario 1300b may be utilized to signal the direct AI / ML positioning reporting configuration as well as receive measurements from a network entity. One or more UEs 104 (e.g., target UEs) may provide multiple direct AI / ML measurements for inference on the network side.

[0158] In an implementation, various network entities and / or nodes may be enabled using the following procedures to enable reporting configuration in scenarios where AI / ML model training and inference is performed on the network side: For example, a network entity (e.g., a location server) may send a direct AI / ML positioning reporting configuration towards a UE and receive corresponding reports of DL and / or SL direct AI / ML position measurements, e.g., fingerprint measurements.

[0159] In an NG-RAN assisted positioning scenario, the location server may request multiple UL direct AI / ML position measurements based on UL reference signals for positioning (e.g., SRS) from various data sources, including neighboring gNB / TRP or NG-RAN nodes, PRU TRP, CU, DU, or a combination thereof.

[0160] 17 illustrates a scenario 1700 for supporting machine learning for positioning according to an aspect of the present disclosure. Scenario 1700 represents a report exchange when, for example, LMF-side training is performed with LMF-side inference. In scenario 1700, if training and inference are performed at location server 1702, location server 1702 may utilize the illustrated signaling mechanism to signal UL direct AI / ML positioning reports.

[0161] At 1704, the location server 1702 may request multiple UL direct AI / ML position measurements based on defined reporting criteria from an NG-RAN node 1706, e.g., a serving gNB / TRP, neighboring gNBs / TRPs, PRU gNBs, TRPs, etc. For transport of signaling to the NG-RAN node 1706, NRPPa signaling, e.g., Positioning Measurement Request and Positioning Measurement Response messages, may be utilized.

[0162] At 1708, the NG-RAN node 1706 may respond to the request 1704 from the location server 1702 and provide measurements according to reporting criteria and / or assistance information, such as those specified in the request 1704.

[0163] At 1710, the location server 1702 builds a training dataset based on the measurement reports from different source NG-RAN nodes 1706 and performs training of the AI / ML model.

[0164] At 1712, the location server 1702 performs inference based on the new measurement data by repeating steps 1704, 1708. In implementations, training and inference data sets may be requested one-off.

[0165] In implementations in which training is performed at the NG-RAN node 1706, the NG-RAN node 1706 may request and receive UL direct AI / ML position measurement reports from the location server 1702, e.g., via NRPPa and / or other NG-RAN nodes, e.g., via an Xn interface.

[0166] In an implementation, various network entities and / or nodes may be enabled using the following procedures: A location server 1702 may send direct AI / ML positioning reporting configurations towards multiple NG-RAN nodes 1706 and receive corresponding reports of UL direct AI / ML position measurements, e.g., fingerprint measurements.

[0167] In additional or alternative implementations, the construction of the training dataset and the training of the dataset do not necessarily have to be performed by the same entity, but may be performed by other separate network entities or nodes. For example, according to scenario 1400, the PRU UE, the anchor UE, and / or other UEs may perform the construction of the dataset or the training of the dataset. Furthermore, similar to scenario 1600, either the serving gNB / TRP, a neighboring gNB / TRP, or the PRU gNB / TRP may perform the construction of the training dataset or the training of the dataset. Furthermore, the construction of the training dataset and the inference of the AI / ML model may also follow the same behavior, and they are not necessarily performed by the same entity. Alternatively or additionally, the reporting configuration methods discussed above may be combined in various ways, such as to utilize multiple DL, SL, and UL direct AI / ML position measurements in any one or more combinations.

[0168] The implementations described herein also define various ML-related reporting criteria, for example, configurations for reporting criteria are detailed to support direct AI / ML location estimation, for example, using fingerprinting methods.

[0169] In a UE-based positioning scenario (e.g., with a UE-side model), the target UE may request multiple DL or SL direct AI / ML position measurements or other data needed for training or inference. A set of common reporting standards may be defined for network entities or UEs / devices that provide measurement reports for dataset construction.

[0170] [Table 11A] [Table 11B] [Table 11C] [Table 11D]

[0171] In a UE-assisted positioning scenario, one or more of the common reporting criteria detailed in Table 9 may be signaled by a network entity, e.g., a location server, for reporting data types, e.g., measurement data.

[0172] In an NG-RAN assisted positioning scenario, one or more of the common reporting standards detailed in Table 9 may be signaled by a network entity, e.g., a location server, to an NG-RAN node, e.g., a gNB, to report a data type, e.g., measurement data.

[0173] In an implementation, lower layer signaling for the LPP (e.g., RRC signaling, MAC CE, DCI signaling, or a combination thereof) may be used to convey the direct AI / ML reporting criteria configuration. In an implementation, LPP or RRC signaling may be used to add, modify, delete, update, enable, and / or disable the direct AI / ML positioning reporting configuration of one or more UEs.

[0174] In an implementation, the reporting criteria and associated implementation details shown in Table 9 may be extended to AI / ML-assisted location measurements for Cases A, B, and C, where the location measurements are refined using one or more AI / ML models.

[0175] In an implementation, the common reporting criteria may be broadcast to multiple UEs within a given geographical area, for example, based on the same cell ID, system information area, zone ID, or a combination thereof, via a system information block (SIB) message or a positioning system information block (posSIB) message.

[0176] Implementations also provide for reporting various assistance information regarding direct AI / ML position measurements to aid in deriving a location estimate for the target UE. For example, this may extend to scenarios where AI / ML-assisted position measurements are reported, where possible.

[0177] In an implementation, a measurement entity (e.g., a UE or NG-RAN node performing AI / ML positioning measurements) may be configured to report the correlation of position measurements between different sets of measurements performed at the same measurement entity. This correlation measure may be affected, for example, by the UE's capabilities. In at least one implementation, the measurement entity may report the RSS-Correlation associated with each DL or SL PRS resource, e.g., a set of AI / ML positioning RSRP / RSSI measurements with a DL resource ID, via a higher layer parameter (e.g., LPP signaling). In an NG-RAN node measurement scenario, the RSS-Correlation may be associated with a different set of UL resources, e.g., UL RSS measurements with an SRS resource ID. In an enhanced implementation, the correlation measure may be applicable to timing-based (e.g., RSTD, ToA, etc.) or angle-based (e.g., AoA, AoD, etc.) measurements. A correlation measure may be obtained for each ground truth reference location to accurately and unbiasedly calculate the measurement correlation of multiple measurements obtained at the same ground truth reference location.

[0178] In implementations, location measurement correlations may be obtained from different UEs / devices at the same ground truth reference location. Because measurements may be based at least in part on vendor-specific differences in UEs / NG-RAN nodes, there may be differences in the same location measurements at the same ground truth reference location. In such implementations, the network entity or UE / device collecting the location measurements may correlate different measurements received from different network nodes / UEs / devices. This correlation may also be performed in the time domain (e.g., using a (sliding) time window) in addition to the spatial domain, e.g., based on location. In implementations, measurement correlations between adjacent reference points may also be configured, determined, and reported.

[0179] According to an implementation, a measurement entity (e.g., a UE and / or an NG-RAN node) performing an AI / ML location measurement may be configured to report channel measurements directly related to the AI / ML location measurement, including whether the measurement is line-of-sight (LOS) or non-line-of-sight (NLOS), based on binary (e.g., hard-decision) or soft indicators, link path loss, channel coefficients, or a combination thereof. Reporting additional channel characteristics related to the measurement can increase the stability and reliability of the reported AI / ML location measurements, e.g., RSS measurements such as RSRP.

[0180] In an implementation, the path loss difference between the direct AI / ML (e.g., fingerprint measurements) at the ground truth reference point and the target UE's measurements may be used to derive PRS / SRS RSS measurements as a function of Tx and Rx antenna gain, path loss reference, path loss exponent, standard deviation of attenuation parameters, e.g., shadow fading at the ground truth reference point and the unknown target UE's location. One or more of the above parameters may be configured for reporting and reported to a requesting entity, e.g., the UE / device or an NG-RAN node or location server. In an implementation, the measurement entity and / or the target UE may calculate the path losses and report them to the requesting entity along with the direct AI / ML location measurements.

[0181] In an implementation, a measurement entity (e.g., a UE or an NG-RAN node) that performs AI / ML location measurements may have a total of (NxM i ) j may be configured to report the average measurement at each ground truth reference location over NxM sample points, where N is the configured samples for each measurement instance, and M is the total number of measurements from each ith gNB / TRP for DL ​​location measurements at each jth ground truth reference location, while for UL measurements, M is the total number of measurements collected from each ith UE. In implementations, additional statistical measures including variance, standard deviation, probability distribution function, cumulative distribution function, etc. at each reference location / point may be reported over an NxM i can be acquired over NxM measurement points. i may also be configurable using higher layer signaling, such as LPP, RRC, SLPP, or a combination thereof.

[0182] In implementations where the configured direct AI / ML positioning model includes k-NN for the supervised case or K-Means for the unsupervised case, a network entity utilizing inference to determine the location of the target UE based on the configured fingerprint data may use the following generalized distance formula according to the Minkowski distance to calculate the newly received measurements:

[0183]

number

[0184] The location of the target UE may be derived by processing using, where n is the total number of measurements received for the pair (x, y) parameters, and a may be configurable depending on which distance algorithm is utilized, e.g., if a=1, then the Manhattan distance method is used, and if a=2, then the geometric distance method is used. In other implementations, Hamming distance or cosine distance and cosine similarity may be utilized to determine the similarity between multidimensional direct AI / ML positioning data.

[0185] In implementations where online measurements are to be matched against fingerprint measurements at each ground truth reference location / point, the similarity score may be based on the cumulative Manhattan distance in equation (1), where a=1, to determine the location of the target UE, so that the measuring entities are collectively i,j The system is configured to report the minimum and maximum PRS / SRS RSS measurements among the measurements, where i refers to the measurement originating from the respective ith gNB / TRP or UE at each jth ground truth reference location. The system is configured to report the similarity score (β Ref-Location ) may be given by the following mathematical relationship:

[0186]

number

[0187] where

[0188]

number

[0189] is the minimum PRS or SRS RSS / fingerprint location measurement from the i-th gNB / TRP or UE, while

[0190]

number

[0191] is the smallest sample position measurement from the set of measurements provided by the target UE,

[0192]

number

[0193] is the maximum PRS or SRS RSS / fingerprint location measurement from the i-th gNB / TRP or UE, while

[0194]

number

[0195] is the maximum sample position measurement from the set of measurements provided by the target UE. Ref-Location The smallest value of (j) corresponds to the most likely location where the target UE may be located.

[0196] In the implementation, β Ref-Location (j) may be derived according to a predefined time window, relating to a start time, a time window length, an end time, and a period, to capture the variation of the location measurements and therefore the similarity score over time.

[0197] In an implementation, for the RSS measurements above, the first arrival path is considered to be used as part of the fingerprinting training data set. In an implementation, the first arrival path and up to T configurable additional paths may be associated with the fingerprint RSS measurements and reported to a requesting network entity / node / UE.

[0198] In an implementation, a measurement entity (e.g., a UE, a PRU UE, or an SL UE) may be configured to indicate whether RSS / fingerprint measurements (e.g., DL PRS RSRP) from a set of configured PRS resources in the same resource set were measured using the same DL receive beam or the same spatial filter for reception.

[0199] In an implementation, the measurement, training, and / or inference entity may be configured to self-calibrate direct or assisted AI / ML location measurements based on the provision of several parameters for inclusion in a training or inference dataset to a reference device, e.g., a PRU UE. In at least one example, linear calibration may be utilized to map the measurements of a target UE with the measurements of a reference device, such as a PRU UE, which may be expressed as:

[0200]

number

[0201] where:

[0202]

number

[0203] denotes the average target UE PRS / SRS location measurements from the i-th gNB / TRP or UE at each j-th ground truth reference location,

[0204]

number

[0205] denotes the average PRU UE PRS / SRS location measurement from the i-th gNB / TRP or UE at each j-th ground truth reference location, while δ TP and μ TP is a linear calibration parameter for correlating RSS measurements from a target UE with a PRU UE. This is especially useful when measurements are performed by different network entities or UEs / devices from different vendors. The linear parameter δ TP and μ TP may be configured to the measurement entity via higher layer signaling, e.g., LPP, NRPPa, SLPP, etc., to calibrate measurements before reporting. The measurement, training, and / or inference entity may further receive requests to perform self-calibration of direct or assisted AI / ML positioning measurements. In another implementation, nonlinear functions may also be utilized to self-calibrate direct or assisted AI / ML positioning measurements, using similar procedures as outlined for linear self-calibration with respect to preparation and reporting of nonlinear self-calibration parameters.

[0206] The RSS measurements referred to in the implementations described herein may include values ​​of RSRP, RSRPP, RSSI, RSRQ, which are associated with DL PRS, SL PRS, or UL SRS.

[0207] 18 illustrates an example block diagram 1800 of a device 1802 (e.g., apparatus) that supports machine learning for positioning according to aspects of the present disclosure. The device 1802 may be an example of a UE 104 described herein. The device 1802 may support wireless communication with one or more network entities 102, UEs 104, or any combination thereof. The device 1802 may include components for bidirectional communication, including components for transmitting and receiving communications, such as a processor 1804, a memory 1806, a transceiver 1808, and an I / O controller 1810. These components may be in electrical communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces (e.g., buses).

[0208] The processor 1804, the memory 1806, the transceiver 1808, or various combinations thereof, or various components thereof, may be examples of means for implementing various aspects of the disclosure as described herein. For example, the processor 1804, the memory 1806, the transceiver 1808, or various combinations or components thereof may facilitate a method for performing one or more of the operations described herein.

[0209] In some implementations, the processor 1804, the memory 1806, the transceiver 1808, or various combinations or components thereof may be implemented in hardware (e.g., in communications management circuitry). The hardware may include a processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof configured as or otherwise supporting a means for performing the functions described in this disclosure. In some implementations, the processor 1804 and the memory 1806 coupled thereto may be configured to perform one or more of the functions described herein (e.g., execute instructions stored in the memory 1806 by the processor 1804). In the context of a UE 104, for example, the transceiver 1808 and the processor 1804 coupled thereto may be configured to cause the UE 104 to perform various described operations and / or combinations thereof.

[0210] For example, the processor 1804 and / or the transceiver 1808 may facilitate wireless communication in the device 1802 according to examples as disclosed herein. For example, the processor 1804 and / or the transceiver 1808 may be configured as and / or otherwise facilitate a means for receiving a machine learning positioning configuration request and transmitting, based at least in part on the machine learning positioning configuration request, a machine learning positioning configuration response including a positioning reference signal configuration to be measured at each reference location along with one or more associated validity criteria.

[0211] Further, in some implementations, the processor is configured to cause the device to receive a machine learning positioning configuration request from one or more network nodes or user equipment (UE) and to send a machine learning positioning configuration response to the one or more network nodes or UE, wherein the reference locations include one or more ground truth reference locations and the machine learning positioning configuration response includes an artificial intelligence configuration for positioning reference signal configuration, and the processor is configured to cause the device to send the one or more machine learning positioning configuration responses independent of the machine learning positioning configuration request, wherein the machine learning positioning configuration response includes one or more of a direct machine learning configuration or an assisted machine learning configuration, and wherein the direct machine learning configuration includes a configuration for performing radio frequency fingerprinting.

[0212] Further, in some implementations, the machine learning positioning configuration request includes a request for one or more of a training type, a ground truth location request, a machine learning method, a machine learning on-demand positioning reference signal request, or pre-configured machine learning assistance data; the positioning reference signal configuration includes one or more of a positioning reference signal resource, a resource set, a transmission / reception point, or a positioning frequency layer to be measured at each reference location; the one or more associated valid criteria include one or more of a time reference or a spatial reference, the time reference including a measurement time defined by one or more time origins, the one or more time origins including at least one of a system frame number, Coordinated Universal Time (UTC), or Global Navigation Satellite System (GNSS) time; and the one or more associated valid criteria include a spatial reference referring to an indication of a geographical region, the spatial reference including one or more of an area identifier, a cell identifier, or a zone identifier.

[0213] Further, in some implementations, the positioning reference signal configuration includes one or more instructions of one or more of uplink radio access technology-dependent measurements, downlink radio access technology-dependent measurements, or sidelink radio access technology-dependent measurements to be performed; the positioning reference signal configuration includes one or more instructions of one or more of downlink radio access technology-independent measurements or sidelink radio access technology-independent measurements to be performed; the machine learning positioning configuration response further includes one or more configurations for at least one of a k-nearest neighbor (k-NN) algorithm, a support vector machine, a decision tree, a random forest, a Gaussian mixture model, a Bayesian network, an artificial neural network, K-means, reinforcement learning, deep learning, or transfer learning; and the device includes at least one of a location server, a next generation radio access network (NG-RAN), a positioning reference unit (PRU), a user equipment (UE), an anchor UE, or a target UE.

[0214] Further, in some implementations, the positioning reference signal configuration includes a received signal strength indicator measurement for one or more of the downlink, uplink, or sidelink, where the received signal strength indicator measurement for one or more of the downlink, uplink, or sidelink is defined as including a linear average of the total received power observed in resource elements of a slot carrying the positioning reference signal configured for measurement; the positioning reference signal configuration includes a positioning reference signal time of arrival measurement for one or more of the downlink, uplink, or sidelink, where the positioning reference signal time of arrival measurement for one or more of the downlink, uplink, or sidelink is defined as including a reception time of the positioning reference signal at a receiver reference point; the positioning reference signal configuration includes an indication that the location server is permitted to transmit error sources related to misconfiguration of the positioning reference signal configuration; and the positioning reference signal configuration includes an indication that the target user equipment (UE) is permitted to transmit error sources related to one or more of errors in receiving a machine learning positioning configuration response or measurement errors related to the machine learning position measurements.

[0215] In a further example, the processor 1804 and / or the transceiver 1808 may facilitate wireless communication in the device 1802 in accordance with examples described herein. The processor 1804 and / or the transceiver 1808 may be configured as or otherwise facilitate a means for, for example, sending a machine learning positioning configuration request, receiving a machine learning positioning configuration response including a positioning reference signal configuration to be measured at one or more respective reference locations along with one or more associated validity criteria, and performing one or more machine learning position measurements based at least in part on the positioning reference signal configuration.

[0216] Further, in some implementations, the processor and transceiver are configured to cause the device to perform one or more of: receiving a machine learning positioning configuration response in response to a machine learning positioning configuration request; or receiving a machine learning positioning configuration response independent of a machine learning positioning configuration request; the processor is configured to cause the device to input one or more machine learning position measurements to a machine learning model and receive output from the machine learning model; and the processor is configured to cause the device to generate an estimated location of the device based at least in part on the output from the machine learning model, and the device includes one or more of a target user equipment (UE), a positioning reference unit (PRU), or an anchor UE.

[0217] In a further example, the processor 1804 and / or the transceiver 1808 may facilitate wireless communication in the device 1802 in accordance with examples disclosed herein. The processor 1804 and / or the transceiver 1808 may be configured with or otherwise facilitate a means for, for example, transmitting a configuration request to configure a reference signal for machine learning position measurement, receiving a configuration response including the reference signal configuration, and transmitting a reference signal transmission enable command based at least in part on the reference signal configuration.

[0218] Further, in some implementations, the reference signal includes one or more of a sounding reference signal or a positioning reference signal, the processor is configured to cause the device to transmit a reference signal transmission disable command, the device includes a location server, and the processor is configured to cause the device to transmit a reference signal transmission enable command to one or more other devices configured to transmit the reference signal.

[0219] In a further example, the processor 1804 and / or the transceiver 1808 may facilitate wireless communication in the device 1802 in accordance with examples as disclosed herein. The processor 1804 and / or the transceiver 1808 may be configured with or otherwise assist in, for example, transmitting one or more machine learning positioning report requests including a machine learning reporting configuration and one or more common reporting criteria, receiving one or more machine learning positioning reports, processing the one or more machine learning positioning reports through a machine learning model, and generating an estimated location of the user equipment (UE) based at least in part on output from the machine learning model.

[0220] Further, in some implementations, the machine learning reporting configuration includes one or more of a direct machine learning reporting configuration or an assisted machine learning reporting configuration, the device includes a configuration entity, the configuration entity including at least one of a location server, a Next Generation Radio Access Network (NG-RAN), a positioning reference unit (PRU), a UE, an anchor UE, or a target UE, and the processor is configured to cause the device to send one or more machine learning positioning report requests to one or more second devices and receive one or more machine learning positioning reports from the one or more second devices, the one or more second devices including at least one of a location server, a Next Generation Radio Access Network (NG-RAN), a positioning reference unit (PRU), a UE, an anchor UE, or a target UE.

[0221] Further, in some implementations, the one or more common reporting criteria include one or more of a fingerprint type, a ground truth reference location type, a time domain report type, a measurement preprocessing, a measurement validity, a UE type, a mobility indication, an orientation indication, a fingerprinting environment indication, a fingerprint quality indication, or a label quality indication, and for at least one machine learning positioning report request, the one or more of the common reporting criteria are configured to be one or more of augmented, deleted, updated, enabled, or disabled, and the processor is configured to cause the device to broadcast the one or more common reporting criteria via positioning system information broadcast signaling, and the machine learning reporting configuration includes instructions for reporting correlation of the machine learning position measurements between different sets of measurements.

[0222] Further, in some implementations, the correlation of the machine learning position measurements includes one or more of a spatial domain correlation or a time domain correlation, the one or more machine learning positioning reports include one or more of the machine learning position measurements or the machine learning positioning location information, the machine learning reporting configuration includes instructions for reporting path loss at different locations including ground truth reference locations, the machine learning reporting configuration includes instructions for averaging the machine learning position measurements over a configured number of measurements and reporting the average as part of one or more machine learning positioning reports, and the machine learning reporting configuration includes instructions for determining a similarity score at the configured locations to determine an optimal correspondence between the fingerprint measurements and the estimated location of the target UE.

[0223] In a further example, the processor 1804 and / or the transceiver 1808 may facilitate wireless communication in the device 1802, according to examples as disclosed herein. The processor 1804 and / or the transceiver 1808 may be configured with or otherwise facilitate a means for, for example, receiving one or more machine learning positioning report requests including a machine learning reporting configuration and one or more common reporting criteria, generating one or more machine learning positioning reports based at least in part on the machine learning reporting configuration and the one or more common reporting criteria, and transmitting the one or more machine learning positioning reports.

[0224] Further, in some implementations, the device includes one or more of a user equipment (UE), an anchor UE, or a target UE, and the device includes a configuration entity, which includes at least one of a location server, a next generation radio access network (NG-RAN), or a positioning reference unit (PRU).

[0225] In a further example, the processor 1804 and / or the transceiver 1808 may facilitate wireless communication in the device 1802, according to examples as disclosed herein. The processor 1804 and / or the transceiver 1808 may be configured with or otherwise assist in a means for, for example, sending one or more machine learning positioning report requests including a machine learning reporting configuration and one or more common reporting criteria, receiving one or more machine learning positioning reports, generating a machine learning positioning training dataset based at least in part on the one or more machine learning positioning reports, and training a positioning machine learning model using the machine learning positioning training data to generate a trained positioning machine learning model.

[0226] Further, in some implementations, the processor and transceiver are configured to cause the device to receive one or more further machine learning positioning reports, input at least a portion of the one or more further machine learning positioning reports into a trained positioning machine learning model, and estimate a position of a target user equipment (UE) based at least in part on output from the trained positioning machine learning model; the processor is configured to cause the device to receive a request for machine learning positioning training data for positioning and transmit a machine learning positioning training dataset based at least in part on the request; and the processor is configured to cause the device to receive a request for a trained positioning machine learning model and transmit at least a portion of the trained positioning machine learning model based at least in part on the request.

[0227] In a further example, the processor 1804 and / or the transceiver 1808 may facilitate wireless communication in the device 1802, according to examples as disclosed herein. The processor 1804 and / or the transceiver 1808 may be configured with or otherwise facilitate a means for, for example, receiving a machine learning positioning configuration request and transmitting, based at least in part on the machine learning positioning configuration request, a machine learning positioning configuration response including a positioning reference signal configuration to be measured at each reference location along with one or more associated validity criteria.

[0228] Further, in some implementations, the processor 1804 and / or the transceiver 1808 may be configured as or otherwise assist in receiving, for example, a machine learning positioning configuration request from one or more network nodes or user equipment (UE), and transmitting a machine learning positioning configuration response to one or more of the network nodes or UEs, wherein the reference locations include one or more ground truth reference locations, and the machine learning positioning configuration response includes an artificial intelligence configuration for positioning reference signal configuration, and transmitting the one or more machine learning positioning configuration responses independent of the machine learning positioning configuration request, wherein the machine learning positioning configuration response includes one or more of a direct machine learning configuration or an assisted machine learning configuration, and wherein the direct machine learning configuration includes a configuration for performing radio frequency fingerprinting.

[0229] Further, in some implementations, the machine learning positioning configuration request includes a request for one or more of a training type, a ground truth location request, a machine learning method, a machine learning on-demand positioning reference signal request, or pre-configured machine learning assistance data; the positioning reference signal configuration includes one or more of a positioning reference signal resource, a resource set, a transmission / reception point, or a positioning frequency layer to be measured at each reference location; the one or more associated valid criteria include one or more of a time reference or a spatial reference, the time reference including a measurement time defined by one or more time origins, the one or more time origins including at least one of a system frame number, Coordinated Universal Time (UTC), or Global Navigation Satellite System (GNSS) time; and the one or more associated valid criteria include a spatial reference referring to an indication of a geographical region, the spatial reference including one or more of an area identifier, a cell identifier, or a zone identifier.

[0230] Further, in some implementations, the positioning reference signal configuration includes one or more instructions for one or more of uplink radio access technology-dependent measurements, downlink radio access technology-dependent measurements, or sidelink radio access technology-dependent measurements to be performed; the positioning reference signal configuration includes one or more instructions for one or more of downlink radio access technology-independent measurements or sidelink radio access technology-independent measurements to be performed; the machine learning positioning configuration response further includes one or more configurations for at least one of a k-nearest neighbor (k-NN) algorithm, a support vector machine, a decision tree, a random forest, a Gaussian mixture model, a Bayesian network, an artificial neural network, K-means, reinforcement learning, deep learning, or transfer learning; and the method is performed by an apparatus including at least one of a location server, a next generation radio access network (NG-RAN), a positioning reference unit (PRU), a user equipment (UE), an anchor UE, or a target UE.

[0231] Further, in some implementations, the positioning reference signal configuration includes a received signal strength indicator measurement for one or more of the downlink, uplink, or sidelink, where the received signal strength indicator measurement for one or more of the downlink, uplink, or sidelink is defined as including a linear average of the total received power observed in resource elements of a slot carrying the positioning reference signal configured for measurement; the positioning reference signal configuration includes a positioning reference signal time of arrival measurement for one or more of the downlink, uplink, or sidelink, where the positioning reference signal time of arrival measurement for one or more of the downlink, uplink, or sidelink is defined as including a reception time of the positioning reference signal at a receiver reference point; the positioning reference signal configuration includes an indication that the location server is permitted to transmit error sources related to misconfiguration of the positioning reference signal configuration; and the positioning reference signal configuration includes an indication that the target user equipment (UE) is permitted to transmit error sources related to one or more of errors in receiving a machine learning positioning configuration response or measurement errors related to machine learning position measurements.

[0232] In a further example, the processor 1804 and / or the transceiver 1808 may facilitate wireless communication in the device 1802, according to examples as disclosed herein. The processor 1804 and / or the transceiver 1808 may be configured as or otherwise facilitate a means for, for example, sending a machine learning positioning configuration request, receiving a machine learning positioning configuration response including a positioning reference signal configuration to be measured at one or more respective reference locations along with one or more associated validity criteria, and performing one or more machine learning position measurements based at least in part on the positioning reference signal configuration.

[0233] In some implementations, the processor 1804 and / or the transceiver 1808 may be configured with or otherwise assist in, for example, receiving a machine learning positioning configuration response in response to a machine learning positioning configuration request or receiving a machine learning positioning configuration response independent of a machine learning positioning configuration request, inputting one or more machine learning position measurements into a machine learning model and receiving an output from the machine learning model, generating an estimated location of the device based at least in part on the output from the machine learning model. The method is performed by an apparatus including one or more of a target user equipment (UE), a positioning reference unit (PRU), or an anchor UE.

[0234] In a further example, the processor 1804 and / or the transceiver 1808 may facilitate wireless communication in the device 1802, in accordance with examples as disclosed herein. The processor 1804 and / or the transceiver 1808 may be configured with or otherwise facilitate a means for, for example, transmitting a configuration request to configure a reference signal for machine learning position measurement, receiving a configuration response including the reference signal configuration, and transmitting a reference signal transmission enable command based at least in part on the reference signal configuration.

[0235] Further, in some implementations, the reference signal includes one or more of a sounding reference signal or a positioning reference signal, and transmitting the reference signal transmission disable command, the method is performed by an apparatus including a location server, and the method further includes transmitting the reference signal transmission enable command to one or more other apparatuses configured to transmit the reference signal.

[0236] In a further example, the processor 1804 and / or the transceiver 1808 may facilitate wireless communication in the device 1802 in accordance with examples as disclosed herein. The processor 1804 and / or the transceiver 1808 may be configured with or otherwise assist in, for example, transmitting one or more machine learning positioning report requests including a machine learning reporting configuration and one or more common reporting criteria, receiving one or more machine learning positioning reports, processing the one or more machine learning positioning reports through a machine learning model, and generating an estimated location of the user equipment (UE) based at least in part on output from the machine learning model.

[0237] Further, in some implementations, the machine learning reporting configuration includes one or more of a direct machine learning reporting configuration or an assisted machine learning reporting configuration, and the method is performed by an apparatus including a configuration entity, wherein the configuration entity includes at least one of a location server, a Next Generation Radio Access Network (NG-RAN), a positioning reference unit (PRU), a UE, an anchor UE, or a target UE, and further includes sending one or more machine learning positioning report requests from the first apparatus to one or more second apparatuses and receiving one or more machine learning positioning reports from the one or more second apparatuses, wherein the one or more second apparatuses include at least one of a location server, a Next Generation Radio Access Network (NG-RAN), a positioning reference unit (PRU), a UE, an anchor UE, or a target UE.

[0238] Further, in some implementations, the one or more common reporting criteria include one or more of a fingerprint type, a ground truth reference location type, a time domain report type, a measurement preprocessing, a measurement validity, a UE type, a mobility indication, an orientation indication, a fingerprinting environment indication, a fingerprint quality indication, or a label quality indication, and for at least one machine learning positioning report request, the one or more common reporting criteria are configured as one or more of augmented, deleted, updated, enabled, or disabled, and further including broadcasting the one or more common reporting criteria via positioning system information broadcast signaling, and the machine learning reporting configuration includes instructions for reporting correlation of the machine learning position measurements between different sets of measurements.

[0239] Further, in some implementations, the correlation of the machine learning position measurements includes one or more of a spatial domain correlation or a time domain correlation, the one or more machine learning positioning reports include one or more of the machine learning position measurements or the machine learning positioning location information, the machine learning reporting configuration includes instructions for reporting path loss at different locations including ground truth reference locations, the machine learning reporting configuration includes instructions for averaging the machine learning position measurements over a configured number of measurements and reporting the average as part of one or more machine learning positioning reports, and the machine learning reporting configuration includes instructions for determining a similarity score at the configured locations to determine an optimal correspondence between the fingerprint measurements and the estimated location of the target UE.

[0240] In a further example, the processor 1804 and / or the transceiver 1808 may facilitate wireless communication in the device 1802, in accordance with examples as disclosed herein. The processor 1804 and / or the transceiver 1808 may be configured with or otherwise facilitate a means for, for example, receiving one or more machine learning positioning report requests including a machine learning reporting configuration and one or more common reporting criteria, generating one or more machine learning positioning reports based at least in part on the machine learning reporting configuration and the one or more common reporting criteria, and transmitting the one or more machine learning positioning reports.

[0241] Further, in some implementations, the method is performed by an apparatus including one or more of a user equipment (UE), an anchor UE, or a target UE, and the method is performed by an apparatus including a configuration entity, the configuration entity including at least one of a location server, a next generation radio access network (NG-RAN), or a positioning reference unit (PRU).

[0242] In a further example, the processor 1804 and / or the transceiver 1808 may facilitate wireless communication in the device 1802 in accordance with examples as disclosed herein. The processor 1804 and / or the transceiver 1808 may be configured as or otherwise assist in a means for, for example, sending one or more machine learning positioning report requests including a machine learning reporting configuration and one or more common reporting criteria, receiving one or more machine learning positioning reports, generating a machine learning positioning training dataset based at least in part on the one or more machine learning positioning reports, and training a positioning machine learning model using the machine learning positioning training dataset to generate a trained positioning machine learning model.

[0243] Further, in some implementations, the processor 1804 and / or the transceiver 1808 may be configured as or otherwise assist in a means for, for example, receiving one or more further machine learning positioning reports, inputting at least a portion of the one or more further machine learning positioning reports into a trained positioning machine learning model, and estimating a position of the target user equipment (UE) based at least in part on output from the trained positioning machine learning model, further including receiving a request for machine learning positioning training data for positioning and transmitting a machine learning positioning training dataset based at least in part on the request; receiving a request for a trained positioning machine learning model and transmitting at least a portion of the trained positioning machine learning model based at least in part on the request.

[0244] The processor 1804 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, a CPU, a microcontroller, an ASIC, an FPGA, a programmable logic device, a discrete gate or transistor logic component, a discrete hardware component, or any combination thereof). In some implementations, the processor 1804 may be configured to operate a memory array using a memory controller. In some other implementations, the memory controller may be integrated into the processor 1804. The processor 1804 may be configured to execute computer-readable instructions stored in a memory (e.g., memory 1806) to cause the device 1802 to perform various functions of the present disclosure.

[0245] The memory 1806 may include random access memory (RAM) and read-only memory (ROM). The memory 1806 may store computer-readable, computer-executable code including instructions that, when executed by the processor 1804, cause the device 1802 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium, such as system memory or another type of memory. In some implementations, the code may not be directly executable by the processor 1804, but may cause a computer (e.g., when compiled and executed) to perform the functions described herein. In some implementations, the memory 1806 may include, among other things, a basic I / O system (BIOS), which may control basic hardware or software operations such as interaction with peripheral components or devices.

[0246] The I / O controller 1810 may manage input and output signals for the device 1802. The I / O controller 1810 may also manage peripherals not integrated into the device 1802. In some implementations, the I / O controller 1810 may represent a physical connection or port to an external peripheral. In some implementations, the I / O controller 1810 may utilize an operating system such as iOS®, ANDROID®, MS-DOS®, MS-WINDOWS®, OS / 2®, UNIX®, LINUX®, or another known operating system. In some implementations, the I / O controller 1810 may be implemented as part of a processor, such as the processor 1804. In some implementations, a user may interact with the device 1802 through the I / O controller 1810 or through hardware components controlled by the I / O controller 1810.

[0247] In some implementations, the device 1802 may include a single antenna 1812. However, in some other implementations, the device 1802 may have more than one antenna 1812 (e.g., multiple antennas) including multiple antenna panels or antenna arrays that may be capable of simultaneously transmitting or receiving multiple wireless transmissions. The transceiver 1808 may communicate bidirectionally via one or more antennas 1812, a wired link, or a wireless link, as described herein. For example, the transceiver 1808 may represent a wireless transceiver and may communicate bidirectionally with another wireless transceiver. The transceiver 1808 may also include a modem to modulate packets, provide the modulated packets to one or more antennas 1812 for transmission, and demodulate packets received from the one or more antennas 1812.

[0248] FIG. 19 shows an example block diagram 1900 of a device 1902 (e.g., apparatus) that supports machine learning for positioning according to aspects of the present disclosure. The device 1902 may be an example of a network entity 102 as described herein. The device 1902 may support wireless communication with one or more network entities 102, UEs 104, or any combination thereof. The device 1902 may include components for bidirectional communication, including components for transmitting and receiving communications, such as a processor 1904, a memory 1906, a transceiver 1908, and an I / O controller 1910. These components may be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces (e.g., buses).

[0249] The processor 1904, the memory 1906, the transceiver 1908, or various combinations or components thereof may be examples of means for implementing various aspects of the disclosure as described herein. For example, the processor 1904, the memory 1906, the transceiver 1908, or various combinations or components thereof may facilitate a method for performing one or more of the operations described herein.

[0250] In some implementations, the processor 1904, the memory 1906, the transceiver 1908, or various combinations or components thereof may be implemented in hardware (e.g., in communications management circuitry). The hardware may include a processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof configured as or otherwise assisting in performing the functions described in this disclosure. In some implementations, the processor 1904 and the memory 1906 coupled to the processor 1904 may be configured to perform one or more of the functions described herein (e.g., by the processor 1904 executing instructions stored in the memory 1906). In the context of the network entity 102, for example, the transceiver 1908 and the processor 1904 coupled to the transceiver 1908 are configured to cause the network entity 102 to perform various described operations and / or combinations thereof.

[0251] For example, the processor 1904 and / or the transceiver 1908 may facilitate wireless communication in the device 1902 according to examples as disclosed herein. For example, the processor 1904 and / or the transceiver 1908 may be configured as and / or otherwise facilitate a means for receiving a machine learning positioning configuration request and transmitting, based at least in part on the machine learning positioning configuration request, a machine learning positioning configuration response including a positioning reference signal configuration to be measured at each reference location along with one or more associated validity criteria.

[0252] Further, in some implementations, the processor is configured to cause the device to receive a machine learning positioning configuration request from one or more network nodes or user equipments (UEs) and to send a machine learning positioning configuration response to the one or more network nodes or UEs, wherein the reference locations include one or more ground truth reference locations and the machine learning positioning configuration response includes an artificial intelligence configuration for positioning reference signal configuration, and the processor is configured to cause the device to send the one or more machine learning positioning configuration responses independent of the machine learning positioning configuration request, wherein the machine learning positioning configuration response includes one or more of a direct machine learning configuration or an assisted machine learning configuration, and wherein the direct machine learning configuration includes a configuration for performing radio frequency fingerprinting.

[0253] Further, in some implementations, the machine learning positioning configuration request includes a request for one or more of a training type, a ground truth location request, a machine learning method, a machine learning on-demand positioning reference signal request, or pre-configured machine learning assistance data; the positioning reference signal configuration includes one or more of a positioning reference signal resource, a resource set, a transmission / reception point, or a positioning frequency layer to be measured at each reference location; the one or more associated valid criteria include one or more of a time reference or a spatial reference, the time reference including a measurement time defined by one or more time origins, the one or more time origins including at least one of a system frame number, Coordinated Universal Time (UTC), or Global Navigation Satellite System (GNSS) time; and the one or more associated valid criteria include a spatial reference referring to an indication of a geographical region, the spatial reference including one or more of an area identifier, a cell identifier, or a zone identifier.

[0254] Further, in some implementations, the positioning reference signal configuration includes one or more instructions for one or more of uplink radio access technology-dependent measurements, downlink radio access technology-dependent measurements, or sidelink radio access technology-dependent measurements to be performed; the positioning reference signal configuration includes one or more instructions for one or more of downlink radio access technology-independent measurements or sidelink radio access technology-independent measurements to be performed; the machine learning positioning configuration response further includes one or more configurations for at least one of a k-nearest neighbor (k-NN) algorithm, a support vector machine, a decision tree, a random forest, a Gaussian mixture model, a Bayesian network, an artificial neural network, K-means, reinforcement learning, deep learning, or transfer learning; and the device includes at least one of a location server, a next generation radio access network (NG-RAN), a positioning reference unit (PRU), a user equipment (UE), an anchor UE, or a target UE.

[0255] Further, in some implementations, the positioning reference signal configuration includes a received signal strength indicator measurement for one or more of the downlink, uplink, or sidelink, where the received signal strength indicator measurement for one or more of the downlink, uplink, or sidelink is defined as including a linear average of the total received power observed in resource elements of a slot carrying the positioning reference signal configured for measurement; the positioning reference signal configuration includes a positioning reference signal time of arrival measurement for one or more of the downlink, uplink, or sidelink, where the positioning reference signal time of arrival measurement for one or more of the downlink, uplink, or sidelink is defined as including a reception time of the positioning reference signal at a receiver reference point; the positioning reference signal configuration includes an indication that the location server is permitted to transmit error sources related to misconfiguration of the positioning reference signal configuration; and the positioning reference signal configuration includes an indication that the target user equipment (UE) is permitted to transmit error sources related to one or more of an error in receiving a machine learning positioning configuration response or a measurement error related to the machine learning position measurement.

[0256] In a further example, the processor 1904 and / or the transceiver 1908 may facilitate wireless communication in the device 1902, according to examples as disclosed herein. The processor 1904 and / or the transceiver 1908 may be configured as or otherwise facilitate a means for, for example, sending a machine learning positioning configuration request, receiving a machine learning positioning configuration response including a positioning reference signal configuration to be measured at one or more respective reference locations along with one or more associated validity criteria, and performing one or more machine learning position measurements based at least in part on the positioning reference signal configuration.

[0257] Further, in some implementations, the processor and / or transceiver is configured to cause the device to receive a machine learning positioning configuration response in response to a machine learning positioning configuration request or to receive a machine learning positioning configuration response independent of a machine learning positioning configuration request, the processor is configured to cause the device to input one or more machine learning position measurements to a machine learning model and receive output from the machine learning model, and the processor is configured to cause the device to generate an estimated location of the device based at least in part on the output from the machine learning model, and the device includes one or more of a target user equipment (UE), a positioning reference unit (PRU), or an anchor UE.

[0258] In a further example, the processor 1904 and / or the transceiver 1908 may facilitate wireless communication in the device 1902, according to examples as disclosed herein. The processor 1904 and / or the transceiver 1908 may be configured with or otherwise facilitate a means for, for example, transmitting a configuration request to configure a reference signal for machine learning position measurement, receiving a configuration response including the reference signal configuration, and transmitting a reference signal transmission enable command based at least in part on the reference signal configuration.

[0259] Further, in some implementations, the reference signal includes one or more of a sounding reference signal or a positioning reference signal, the processor causes the device to send a reference signal transmission disable command, the device includes a location server, and the processor is configured to cause the device to send a reference signal transmission enable command to one or more other devices configured to transmit the reference signal.

[0260] In a further example, the processor 1904 and / or the transceiver 1908 may facilitate wireless communication in the device 1902 in accordance with examples as disclosed herein. The processor 1904 and / or the transceiver 1908 may be configured with or otherwise assist in, for example, transmitting one or more machine learning positioning report requests including a machine learning reporting configuration and one or more common reporting criteria, receiving one or more machine learning positioning reports, processing the one or more machine learning positioning reports through a machine learning model, and generating an estimated location of the user equipment (UE) based at least in part on output from the machine learning model.

[0261] Further, in some implementations, the machine learning reporting configuration includes one or more of a direct machine learning reporting configuration or an assisted machine learning reporting configuration, the device includes a configuration entity, the configuration entity including at least one of a location server, a Next Generation Radio Access Network (NG-RAN), a positioning reference unit (PRU), a UE, an anchor UE, or a target UE, and the processor is configured to cause the device to send one or more machine learning positioning report requests to one or more second devices and receive one or more machine learning positioning reports from the one or more second devices, the one or more second devices including at least one of a location server, a Next Generation Radio Access Network (NG-RAN), a positioning reference unit (PRU), a UE, an anchor UE, or a target UE.

[0262] Further, in some implementations, the one or more common reporting criteria include one or more of a fingerprint type, a ground truth reference location type, a time domain report type, a measurement preprocessing, a measurement validity, a UE type, a mobility indication, an orientation indication, a fingerprinting environment indication, a fingerprint quality indication, or a label quality indication, and for at least one machine learning positioning report request, one or more of the common reporting criteria are configured as one or more of augmented, deleted, updated, enabled, or disabled, and the processor is configured to cause the device to broadcast the one or more common reporting criteria via positioning system information broadcast signaling, and the machine learning reporting configuration includes instructions for reporting correlation of the machine learning position measurements between different sets of measurements.

[0263] Further, in some implementations, the correlation of the machine learning position measurements includes one or more of a spatial domain correlation or a time domain correlation, the one or more machine learning positioning reports include one or more of the machine learning position measurements or the machine learning positioning location information, the machine learning reporting configuration includes instructions for reporting path loss at different locations including ground truth reference locations, the machine learning reporting configuration includes instructions for averaging the machine learning position measurements over a configured number of measurements and reporting the average as part of one or more machine learning positioning reports, and the machine learning reporting configuration includes instructions for determining a similarity score at the configured locations to determine an optimal correspondence between the fingerprint measurements and the estimated location of the target UE.

[0264] In a further example, the processor 1904 and / or the transceiver 1908 may facilitate wireless communication in the device 1902, in accordance with examples as disclosed herein. The processor 1904 and / or the transceiver 1908 may be configured with or otherwise facilitate a means for, for example, receiving one or more machine learning positioning report requests including a machine learning reporting configuration and one or more common reporting criteria, generating one or more machine learning positioning reports based at least in part on the machine learning reporting configuration and the one or more common reporting criteria, and transmitting the one or more machine learning positioning reports.

[0265] Further, in some implementations, the device includes one or more of a user equipment (UE), an anchor UE, or a target UE, and the device includes a configuration entity, which includes at least one of a location server, a next generation radio access network (NG-RAN), or a positioning reference unit (PRU).

[0266] In a further example, the processor 1904 and / or the transceiver 1908 may facilitate wireless communication in the device 1902, according to examples as disclosed herein. The processor 1904 and / or the transceiver 1908 may be configured with or otherwise assist in a means for, for example, sending one or more machine learning positioning report requests including a machine learning reporting configuration and one or more common reporting criteria, receiving one or more machine learning positioning reports, generating a machine learning positioning training dataset based at least in part on the one or more machine learning positioning reports, and training a positioning machine learning model using the machine learning positioning training dataset to generate a trained positioning machine learning model.

[0267] Further, in some implementations, the processor and transceiver are configured to cause the device to receive one or more further machine learning positioning reports, input at least a portion of the one or more further machine learning positioning reports into a trained positioning machine learning model, and estimate a position of a target user equipment (UE) based at least in part on output from the trained positioning machine learning model; the processor is configured to cause the device to receive a request for machine learning positioning training data for positioning and transmit a machine learning positioning training dataset based at least in part on the request; and the processor is configured to cause the device to receive a request for a trained positioning machine learning model and transmit at least a portion of the trained positioning machine learning model based at least in part on the request.

[0268] In a further example, the processor 1904 and / or the transceiver 1908 may facilitate wireless communication in the device 1902, according to examples as disclosed herein. For example, the processor 1904 and / or the transceiver 1908 may be configured with or otherwise facilitate a means for receiving a machine learning positioning configuration request and transmitting, based at least in part on the machine learning positioning configuration request, a machine learning positioning configuration response including a positioning reference signal configuration to be measured at each reference location along with one or more associated validity standards.

[0269] Further, in some implementations, the processor 1904 and / or the transceiver 1908 may be configured as or otherwise assist in receiving, for example, a machine learning positioning configuration request from one or more network nodes or user equipment (UE), and transmitting a machine learning positioning configuration response to one or more of the network nodes or UEs, wherein the reference locations include one or more ground truth reference locations, and the machine learning positioning configuration response includes an artificial intelligence configuration for positioning reference signal configuration, and transmitting the one or more machine learning positioning configuration responses independent of the machine learning positioning configuration request, wherein the machine learning positioning configuration response includes one or more of a direct machine learning configuration or an assisted machine learning configuration, and wherein the direct machine learning configuration includes a configuration for performing radio frequency fingerprinting.

[0270] Further, in some implementations, the machine learning positioning configuration request includes a request for one or more of a training type, a ground truth location request, a machine learning method, a machine learning on-demand positioning reference signal request, or pre-configured machine learning assistance data; the positioning reference signal configuration includes one or more of a positioning reference signal resource, a resource set, a transmission / reception point, or a positioning frequency layer to be measured at each reference location; the one or more associated valid criteria include one or more of a time reference or a spatial reference, the time reference including a measurement time defined by one or more time origins, the one or more time origins including at least one of a system frame number, Coordinated Universal Time (UTC), or Global Navigation Satellite System (GNSS) time; and the one or more associated valid criteria include a spatial reference referring to an indication of a geographical region, the spatial reference including one or more of an area identifier, a cell identifier, or a zone identifier.

[0271] Further, in some implementations, the positioning reference signal configuration includes one or more instructions for one or more of uplink radio access technology-dependent measurements, downlink radio access technology-dependent measurements, or sidelink radio access technology-dependent measurements to be performed; the positioning reference signal configuration includes one or more instructions for one or more of downlink radio access technology-independent measurements or sidelink radio access technology-independent measurements to be performed; the machine learning positioning configuration response further includes one or more configurations for at least one of a k-nearest neighbor (k-NN) algorithm, a support vector machine, a decision tree, a random forest, a Gaussian mixture model, a Bayesian network, an artificial neural network, K-means, reinforcement learning, deep learning, or transfer learning; and the method is performed by an apparatus including at least one of a location server, a next generation radio access network (NG-RAN), a positioning reference unit (PRU), a user equipment (UE), an anchor UE, or a target UE.

[0272] Further, in some implementations, the positioning reference signal configuration includes a received signal strength indicator measurement for one or more of the downlink, uplink, or sidelink, where the received signal strength indicator measurement for one or more of the downlink, uplink, or sidelink is defined as including a linear average of the total received power observed in resource elements of a slot carrying the positioning reference signal configured for measurement; the positioning reference signal configuration includes a positioning reference signal time of arrival measurement for one or more of the downlink, uplink, or sidelink, where the positioning reference signal time of arrival measurement for one or more of the downlink, uplink, or sidelink is defined as including a reception time of the positioning reference signal at a receiver reference point; the positioning reference signal configuration includes an indication that the location server is permitted to transmit error sources related to misconfiguration of the positioning reference signal configuration; and the positioning reference signal configuration includes an indication that the target user equipment (UE) is permitted to transmit error sources related to one or more of an error in receiving a machine learning positioning configuration response or a measurement error related to the machine learning position measurement.

[0273] In a further example, the processor 1904 and / or the transceiver 1908 may facilitate wireless communication in the device 1902, according to examples as disclosed herein. The processor 1904 and / or the transceiver 1908 may be configured as or otherwise facilitate a means for, for example, sending a machine learning positioning configuration request, receiving a machine learning positioning configuration response including a positioning reference signal configuration to be measured at one or more respective reference locations along with one or more associated validity criteria, and performing one or more machine learning position measurements based at least in part on the positioning reference signal configuration.

[0274] Further, in some implementations, the processor 1904 and / or the transceiver 1908 may be configured as or otherwise assist in one or more of, for example, receiving a machine learning positioning configuration response in response to a machine learning positioning configuration request or receiving a machine learning positioning configuration response independent of a machine learning positioning configuration request, inputting one or more machine learning position measurements into a machine learning model and receiving an output from the machine learning model, generating an estimated location of the device based at least in part on the output from the machine learning model, and the method is performed by an apparatus including one or more of a target user equipment (UE), a positioning reference unit (PRU), or an anchor UE.

[0275] In a further example, the processor 1904 and / or the transceiver 1908 may facilitate wireless communication in the device 1902, according to examples as disclosed herein. The processor 1904 and / or the transceiver 1908 may be configured with or otherwise facilitate a means for, for example, transmitting a configuration request to configure a reference signal for machine learning positioning, receiving a configuration response including the reference signal configuration, and transmitting a reference signal transmission enable command based at least in part on the reference signal configuration.

[0276] Further, in some implementations, the reference signal includes one or more of a sounding reference signal or a positioning reference signal, and transmitting the reference signal transmission disable command, the method is performed by an apparatus including a location server, and the method further includes transmitting the reference signal transmission enable command to one or more other apparatuses configured to transmit the reference signal.

[0277] In a further example, the processor 1904 and / or the transceiver 1908 may facilitate wireless communication in the device 1902 in accordance with examples as disclosed herein. The processor 1904 and / or the transceiver 1908 may be configured with or otherwise assist in, for example, transmitting one or more machine learning positioning report requests including a machine learning reporting configuration and one or more common reporting criteria, receiving one or more machine learning positioning reports, processing the one or more machine learning positioning reports through a machine learning model, and generating an estimated location of the user equipment (UE) based at least in part on output from the machine learning model.

[0278] Further, in some implementations, the machine learning reporting configuration includes one or more of a direct machine learning reporting configuration or an assisted machine learning reporting configuration, and the method is performed by an apparatus including a configuration entity, wherein the configuration entity includes at least one of a location server, a Next Generation Radio Access Network (NG-RAN), a positioning reference unit (PRU), a UE, an anchor UE, or a target UE, and further includes sending one or more machine learning positioning report requests from the first apparatus to one or more second apparatuses; and receiving one or more machine learning positioning reports from the one or more second apparatuses, wherein the one or more second apparatuses include at least one of a location server, a Next Generation Radio Access Network (NG-RAN), a positioning reference unit (PRU), a UE, an anchor UE, or a target UE.

[0279] Further, in some implementations, the one or more common reporting criteria include one or more of a fingerprint type, a ground truth reference location type, a time domain report type, a measurement preprocessing, a measurement validity, a UE type, a mobility indication, an orientation indication, a fingerprinting environment indication, a fingerprint quality indication, or a label quality indication, and for at least one machine learning positioning report request, the one or more common reporting criteria are configured as one or more of augmented, deleted, updated, enabled, or disabled, and further including broadcasting the one or more common reporting criteria via positioning system information broadcast signaling, and the machine learning reporting configuration includes instructions for reporting correlation of the machine learning position measurements between different sets of measurements.

[0280] Further, in some implementations, the correlation of the machine learning position measurements includes one or more of a spatial domain correlation or a time domain correlation, the one or more machine learning positioning reports include one or more of the machine learning position measurements or the machine learning positioning location information, the machine learning reporting configuration includes instructions for reporting path loss at different locations including ground truth reference locations, the machine learning reporting configuration includes instructions for averaging the machine learning position measurements over a configured number of measurements and reporting the average as part of one or more machine learning positioning reports, and the machine learning reporting configuration includes instructions for determining a similarity score at the configured locations to determine an optimal correspondence between the fingerprint measurements and the estimated location of the target UE.

[0281] In a further example, the processor 1904 and / or the transceiver 1908 may facilitate wireless communication in the device 1902, in accordance with examples as disclosed herein. The processor 1904 and / or the transceiver 1908 may be configured with or otherwise facilitate a means for, for example, receiving one or more machine learning positioning report requests including a machine learning reporting configuration and one or more common reporting criteria, generating one or more machine learning positioning reports based at least in part on the machine learning reporting configuration and the one or more common reporting criteria, and transmitting the one or more machine learning positioning reports.

[0282] Further, in some implementations, the method is performed by an apparatus including one or more of a user equipment (UE), an anchor UE, or a target UE, and the method is performed by an apparatus including a configuration entity, the configuration entity including at least one of a location server, a next generation radio access network (NG-RAN), or a positioning reference unit (PRU).

[0283] In a further example, the processor 1904 and / or the transceiver 1908 may facilitate wireless communication in the device 1902, according to examples as disclosed herein. The processor 1904 and / or the transceiver 1908 may be configured with or otherwise assist in a means for, for example, sending one or more machine learning positioning report requests including a machine learning reporting configuration and one or more common reporting criteria, receiving one or more machine learning positioning reports, generating a machine learning positioning training dataset based at least in part on the one or more machine learning positioning reports, and training a positioning machine learning model using the machine learning positioning training dataset to generate a trained positioning machine learning model.

[0284] Further, in some implementations, the processor 1904 and the transceiver 1908 may be configured as or otherwise assist in a means for, for example, receiving one or more further machine learning positioning reports, inputting at least a portion of the one or more further machine learning positioning reports into a trained positioning machine learning model, and estimating a position of a target user equipment (UE) based at least in part on output from the trained positioning machine learning model, further including receiving a request for machine learning positioning training data for positioning and transmitting a machine learning positioning training dataset based at least in part on the request, and further including receiving a request for a trained positioning machine learning model and transmitting at least a portion of the trained positioning machine learning model based at least in part on the request.

[0285] The processor 1904 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, a CPU, a microcontroller, an ASIC, an FPGA, a programmable logic device, a discrete gate or transistor logic component, a discrete hardware component, or any combination thereof). In some implementations, the processor 1904 may be configured to operate a memory array using a memory controller. In some other implementations, the memory controller may be integrated into the processor 1904. The processor 1904 may be configured to execute computer-readable instructions stored in a memory (e.g., memory 1906) to cause the device 1902 to perform various functions of the present disclosure.

[0286] The memory 1906 may include random access memory (RAM) and read-only memory (ROM). The memory 1906 may store computer-readable, computer-executable code including instructions that, when executed by the processor 1904, cause the device 1902 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium, such as system memory or another type of memory. In some implementations, the code may not be directly executable by the processor 1904, but may cause a computer (e.g., when compiled and executed) to perform the functions described herein. In some implementations, the memory 1906 may include, among other things, a basic I / O system (BIOS), which may control basic hardware or software operations such as interaction with peripheral components or devices.

[0287] The I / O controller 1910 may manage input and output signals for the device 1902. The I / O controller 1910 may also manage peripheral devices not integrated into the device 1902. In some implementations, the I / O controller 1910 may represent a physical connection or port to an external peripheral device. In some implementations, the I / O controller 1910 may utilize an operating system such as iOS®, ANDROID®, MS-DOS®, MS-WINDOWS®, OS / 2®, UNIX®, LINUX®, or another known operating system. In some implementations, the I / O controller 1910 may be implemented as part of a processor, such as the processor 1904. In some implementations, a user may interact with the device 1902 through the I / O controller 1910 or through hardware components controlled by the I / O controller 1910.

[0288] In some implementations, the device 1902 may include a single antenna 1912. However, in some other implementations, the device 1902 may have more than one antenna 1912 (e.g., multiple antennas) including multiple antenna panels or antenna arrays that may be capable of simultaneously transmitting or receiving multiple wireless transmissions. The transceiver 1908 may communicate bidirectionally via one or more antennas 1912, a wired link, or a wireless link, as described herein. For example, the transceiver 1908 may represent a wireless transceiver and may communicate bidirectionally with another wireless transceiver. The transceiver 1908 may also include a modem to modulate packets, provide the modulated packets to one or more antennas 1912 for transmission, and demodulate packets received from the one or more antennas 1912.

[0289] 20 illustrates a flowchart of a method 2000 for assisting machine learning for positioning according to an aspect of the present disclosure. The operations of method 2000 may be performed by a device or components thereof as described herein. For example, the operations of method 2000 may be performed by a network entity 102 and / or a UE 104 as described with respect to FIGS. 1 through 19. In some implementations, the device may execute a set of instructions to control functional elements of the device to perform the described functions. Additionally or alternatively, the device may perform aspects of the described functions using dedicated hardware.

[0290] At 2002, the method may include receiving a machine learning positioning configuration request. The operations of 2002 may be performed according to examples such as those described herein. In some implementations, aspects of the operations of 2002 may be performed by a device such as that described with respect to FIG.

[0291] At 2004, the method may include transmitting, based at least in part on the machine learning positioning configuration request, a machine learning positioning configuration response comprising a positioning reference signal configuration to be measured at each reference location along with one or more associated validity criteria. The operations of 2004 may be performed according to examples such as those described herein. In some implementations, aspects of the operations of 2004 may be performed by a device such as that described with respect to FIG.

[0292] 21 shows a flowchart of a method 2100 for assisting machine learning for positioning according to an aspect of the present disclosure. The operations of method 2100 may be performed by a device or components thereof as described herein. For example, the operations of method 2100 may be performed by a network entity 102 and / or a UE 104 as described with respect to FIGS. 1 through 19. In some implementations, the device may execute a set of instructions to control functional elements of the device to perform the described functions. Additionally or alternatively, the device may perform aspects of the described functions using dedicated hardware.

[0293] At 2102, the method may include transmitting a machine learning positioning configuration request. The operation of 2102 may be performed according to examples as described herein. In some implementations, aspects of the operation of 2102 may be performed by a device as described with respect to FIG.

[0294] At 2104, the method may include receiving a machine learning positioning configuration response comprising a positioning reference signal configuration to be measured along with one or more associated validity standards at one or more respective reference locations. The operations of 2104 may be performed according to examples such as those described herein. In some implementations, aspects of the operations of 2104 may be performed by a device such as that described with respect to FIG.

[0295] At 2106, the method may include performing one or more machine learning position measurements based at least in part on the positioning reference signal configuration. The operations of 2106 may be performed according to examples as described herein. In some implementations, aspects of the operations of 2106 may be performed by a device such as described with respect to FIG.

[0296] 22 illustrates a flowchart of a method 2200 for assisting machine learning for positioning according to an aspect of the present disclosure. The operations of method 2200 may be performed by a device or components thereof as described herein. For example, the operations of method 2200 may be performed by a network entity 102 and / or a UE 104 as described with respect to FIGS. 1 through 19. In some implementations, the device may execute a set of instructions to control functional elements of the device to perform the described functions. Additionally or alternatively, the device may perform aspects of the described functions using dedicated hardware.

[0297] At 2202, the method may include transmitting a configuration request to configure a reference signal for machine learning position measurement. The operations of 2202 may be performed according to examples such as those described herein. In some implementations, aspects of the operations of 2202 may be performed by a device such as that described with respect to FIG.

[0298] At 2204, the method may include receiving a configuration response comprising the reference signal configuration. The operations of 2204 may be performed according to examples as described herein. In some implementations, aspects of the operations of 2204 may be performed by a device such as described with respect to FIG.

[0299] At 2206, the method may include transmitting a reference signal transmission enable command based at least in part on the reference signal configuration. The operations of 2206 may be performed according to examples as described herein. In some implementations, aspects of the operations of 2206 may be performed by a device such as described with respect to FIG.

[0300] 23 illustrates a flowchart of a method 2300 for assisting machine learning for positioning according to an aspect of the present disclosure. The operations of method 2300 may be performed by a device or components thereof as described herein. For example, the operations of method 2300 may be performed by a network entity 102 and / or a UE 104 as described with respect to FIGS. 1 through 19. In some implementations, the device may execute a set of instructions to control functional elements of the device to perform the described functions. Additionally or alternatively, the device may perform aspects of the described functions using dedicated hardware.

[0301] At 2302, the method may include transmitting one or more machine learning positioning report requests comprising the machine learning reporting configuration and one or more common reporting standards. The operations of 2302 may be performed according to examples as described herein. In some implementations, aspects of the operations of 2302 may be performed by a device as described with respect to FIG.

[0302] At 2304, the method may include receiving one or more machine learning positioning reports. The operations of 2304 may be performed according to examples as described herein. In some implementations, aspects of the operations of 2304 may be performed by a device such as described with respect to FIG.

[0303] At 2306, the method may include processing the one or more machine learning positioning reports through a machine learning model. The operations of 2306 may be performed according to examples such as those described herein. In some implementations, aspects of the operations of 2306 may be performed by a device such as those described with respect to FIG.

[0304] At 2308, the method may include generating an estimated location of the user equipment (UE) based at least in part on output from the machine learning model. The operations of 2308 may be performed according to examples such as those described herein. In some implementations, aspects of the operations of 2308 may be performed by a device such as those described with respect to FIG.

[0305] 24 illustrates a flowchart of a method 2400 for assisting machine learning for positioning according to an aspect of the present disclosure. The operations of method 2400 may be performed by a device or components thereof as described herein. For example, the operations of method 2400 may be performed by a network entity 102 and / or a UE 104 as described with respect to FIGS. 1 through 19. In some implementations, the device may execute a set of instructions to control functional elements of the device to perform the described functions. Additionally or alternatively, the device may perform aspects of the described functions using dedicated hardware.

[0306] At 2402, the method may include receiving one or more machine learning positioning report requests comprising a machine learning reporting configuration and one or more common reporting standards. The operations of 2402 may be performed according to examples as described herein. In some implementations, aspects of the operations of 2402 may be performed by a device as described with respect to FIG.

[0307] At 2404, the method may include generating one or more machine learning positioning reports based at least in part on the machine learning reporting configuration and the one or more common reporting standards. The operations of 2404 may be performed according to examples as described herein. In some implementations, aspects of the operations of 2404 may be performed by a device such as described with respect to FIG.

[0308] At 2406, the method may include transmitting one or more machine learning positioning reports. The operations of 2406 may be performed according to examples as described herein. In some implementations, aspects of the operations of 2406 may be performed by a device such as described with respect to FIG.

[0309] 25 illustrates a flowchart of a method 2500 for assisting machine learning for positioning according to an aspect of the present disclosure. The operations of method 2500 may be performed by a device or components thereof as described herein. For example, the operations of method 2500 may be performed by a network entity 102 and / or a UE 104 as described with respect to FIGS. 1 through 19. In some implementations, the device may execute a set of instructions to control functional elements of the device to perform the described functions. Additionally or alternatively, the device may perform aspects of the described functions using dedicated hardware.

[0310] At 2502, the method may include transmitting one or more machine learning positioning report requests comprising the machine learning reporting configuration and one or more common reporting standards. The operations of 2502 may be performed according to examples as described herein. In some implementations, aspects of the operations of 2502 may be performed by a device as described with respect to FIG.

[0311] At 2504, the method may include receiving one or more machine learning positioning reports. The operations of 2504 may be performed according to examples as described herein. In some implementations, aspects of the operations of 2504 may be performed by a device such as described with respect to FIG.

[0312] At 2506, the method may include generating a machine learning positioning training dataset based at least in part on the one or more machine learning positioning reports. The operations of 2506 may be performed according to examples as described herein. In some implementations, aspects of the operations of 2506 may be performed by a device as described with respect to FIG.

[0313] At 2508, the method may include training a positioning machine learning model using the machine learning positioning training dataset to generate a trained positioning machine learning model. The operations of 2508 may be performed according to examples such as those described herein. In some implementations, aspects of the operations of 2508 may be performed by a device such as that described with respect to FIG.

[0314] It should be noted that the methods described herein describe possible implementations, and that the operations and steps may be rearranged or otherwise modified, and that other implementations are possible. Furthermore, aspects from two or more of the methods may be combined.

[0315] The various illustrative blocks and components described in connection with this disclosure may be implemented or performed using a general-purpose processor, a DSP, an ASIC, a CPU, an FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but alternatively, the processor may be any processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices (e.g., a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration).

[0316] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Other examples and implementations are within the scope of this disclosure and the appended claims. For example, due to the nature of software, the functions described herein may be implemented using software executed by a processor, hardware, firmware, hardwiring, or any combination thereof. Features implementing the functions may also be physically located in various locations, including being distributed such that portions of the functions are implemented in different physical locations.

[0317] Computer-readable media include both non-transitory computer storage media and communication media, including any medium that facilitates transfer of a computer program from one place to another. Non-transitory storage media may be any available medium that can be accessed by a general-purpose or special-purpose computer. By way of example, and not limitation, non-transitory computer-readable media may include RAM, ROM, Electrically Erasable Programmable Read Only Memory (EEPROM), Flash memory, Compact Disc (CD) ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to carry or store desired program code means in the form of instructions or data structures and that can be accessed by a general-purpose or special-purpose computer or processor.

[0318] Any connection may be properly termed a computer-readable medium. For example, if software is transmitted from a website, a server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included within the definition of computer-readable media. As used herein, disk and disc include CDs, laser discs, optical discs, digital versatile discs (DVDs), floppy disks, and Blu-ray® discs, where disks typically reproduce data magnetically and discs reproduce data optically with lasers. Combinations of the above are also included within the scope of computer-readable media.

[0319] As used herein, including the claims, "or" in a list of items (e.g., a list of items followed by phrases such as "at least one of" or "one or more of" or "one or both of") indicates an inclusive list, such that, for example, a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (e.g., A and B and C). Also, as used herein, the phrase "based on" should not be construed as referring to a closed set of conditions. For example, an example step described as "based on condition A" could be based on both condition A and condition B without departing from the scope of the present disclosure. In other words, as used herein, the phrase "based on" should be construed in the same manner as the phrase "based at least in part on." Furthermore, as used herein, including the claims, a "set" may include one or more elements.

[0320] The terms "transmit," "receive," or "communicate," when referring to a network entity, may refer to any portion of a network entity (e.g., a base station, a CU, a DU, a RU) of a RAN that is in communication with another device (e.g., directly or through one or more other network entities).

[0321] The description set forth herein, along with the accompanying drawings, describes exemplary configurations and does not represent every example that may be implemented or that is within the scope of the claims. As used herein, the term "example" means "serving as an example, instance, or illustration" and does not mean "preferred" or "advantageous over other examples." The detailed description includes specific details for the purpose of providing an understanding of the described techniques. However, these techniques may be practiced without these specific details. In some instances, well-known structures and devices are shown in block diagrams in order to avoid obscuring the concepts of the described examples.

[0322] The description herein is provided to enable those skilled in the art to make and use the disclosure. Various modifications to the disclosure will be apparent to those skilled in the art, and the general principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not limited to the examples and designs described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein. [Explanation of symbols]

[0323] 100 Wireless Communication System 102 Network Entities 104UE 106 Core Network 108 Packet Network 110 Communication Links 112 Geographic Coverage Areas 114 Communication Links 116 backhaul links 118 Application Server 120 ML positioning configuration 122 ML position measurement 124 ML positioning response 200 systems 400 LPP RequestLocationInformation Message 500 LPP ProvideLocationInformation Message 600 System 702 Rectangular environment 704 LPP Signaling 706 Location Server 708 Target UE 710 Anchor / PRU UE 712 Signaling 804 Location Server 806 NG-RAN nodes 808 NG-RAN nodes 810 Target UE 812 PRU / Anchor UE 900 Messages 1000 messages 1100 Messages 1200 messages 1802 devices 1804 processor 1806 memory 1808 Transceiver 1810 I / O Controller 1812 Antenna 1902 devices 1904 processor 1906 memory 1908 Transceiver 1910 I / O Controller 1912 Antenna

Claims

1. a processor; and a memory coupled to the processor, the processor causing the apparatus to: transmitting one or more machine learning positioning report requests comprising a machine learning reporting configuration and one or more common reporting standards; receiving one or more machine learning positioning reports; processing the one or more machine learning positioning reports through a machine learning model; generating an estimated location of a user equipment (UE) based at least in part on output from the machine learning model; The apparatus is configured to:

2. The apparatus of claim 1 , wherein the machine learning reporting configuration comprises one or more of a direct machine learning reporting configuration or an assisted machine learning reporting configuration.

3. 10. The apparatus of claim 1, wherein the apparatus comprises a configuration entity, the configuration entity comprising at least one of a location server, a Next Generation Radio Access Network (NG-RAN), a positioning reference unit (PRU), a UE, an anchor UE, or a target UE.

4. 2. The apparatus of claim 1, wherein the processor is configured to cause the apparatus to send the one or more machine learning positioning report requests to one or more second devices and receive the one or more machine learning positioning reports from the one or more second devices, wherein the one or more second devices comprise at least one of a location server, a next generation radio access network (NG-RAN), a positioning reference unit (PRU), a UE, an anchor UE, or a target UE.

5. 10. The apparatus of claim 1, wherein the one or more common reporting criteria comprise one or more of a fingerprint type, a ground truth reference location type, a time domain reporting type, measurement preprocessing, measurement validity, a UE type, a mobility indication, an orientation indication, a fingerprinting environment indication, a fingerprint quality indication, or a label quality indication.

6. 10. The apparatus of claim 1, wherein for at least one machine learning positioning report request, one or more of the common reporting standards are one or more of augmented, deleted, updated, enabled, or disabled.

7. The apparatus of claim 1 , wherein the processor is configured to cause the apparatus to broadcast the one or more common reporting criteria via positioning system information broadcast signaling.

8. The apparatus of claim 1 , wherein the machine learning reporting configuration comprises instructions for reporting correlations of machine learning position measurements between different sets of measurements.

9. 10. The apparatus of claim 8, wherein the correlation of the machine-learned location measurements comprises one or more of a spatial domain correlation or a time domain correlation.

10. The apparatus of claim 1 , wherein the one or more machine learning positioning reports comprise one or more of machine learning position measurements or machine learning positioning location information.

11. The apparatus of claim 1 , wherein the machine learning reporting configuration comprises instructions for reporting path loss at different locations, including a ground truth reference location.

12. 10. The apparatus of claim 1, wherein the machine learning reporting configuration comprises instructions for averaging machine learning position measurements over a configured number of measurements and reporting the average as part of the one or more machine learning positioning reports.

13. 10. The apparatus of claim 1, wherein the machine learning reporting configuration comprises instructions for determining a similarity score at the configured location to determine an optimal correspondence between fingerprint measurements and an estimated location of the target UE.

14. a processor; and a memory coupled to the processor, the processor causing the apparatus to: receiving one or more machine learning positioning report requests comprising a machine learning reporting configuration and one or more common reporting standards; generating one or more machine learning positioning reports based at least in part on the machine learning reporting configuration and the one or more common reporting standards; transmitting said one or more machine learning positioning reports; The apparatus is configured to:

15. 15. The apparatus of claim 14, wherein the apparatus comprises one or more of a user equipment (UE), an anchor UE, or a target UE.

16. 15. The apparatus of claim 14, wherein the apparatus comprises a configuration entity, the configuration entity comprising at least one of a location server, a Next Generation Radio Access Network (NG-RAN), or a Positioning Reference Unit (PRU).

17. a processor; a memory coupled to the processor, the processor causing the device to: transmitting one or more machine learning positioning report requests comprising a machine learning reporting configuration and one or more common reporting standards; receiving one or more machine learning positioning reports; generating a machine learning positioning training dataset based at least in part on the one or more machine learning positioning reports; Training a positioning machine learning model using the machine learning positioning training dataset to generate a trained positioning machine learning model. The apparatus is configured to:

18. The processor causes the device to: receiving one or more further machine learning positioning reports; inputting at least a portion of the one or more further machine learning positioning reports into the trained machine learning positioning model; and estimating a location of a target user equipment (UE) based at least in part on output from the trained positioning machine learning model.

18. The apparatus of claim 17, configured to:

19. The processor causes the device to: receiving a request for machine learning positioning training data for positioning; 20. The apparatus of claim 17, configured to cause the machine learning positioning training data set to be transmitted based at least in part on the request.

20. The processor causes the device to: receiving a request for the trained positioning machine learning model; 20. The apparatus of claim 17, configured to cause transmission of at least a portion of the trained localization machine learning model based at least in part on the request.

Images