Method and apparatus for artificial intelligence and machine learning (ai / ML) positioning

Abstract

A wireless transmit / receive unit (WTRU) sends, to a base station associated with a first cell and based on the WTRU moving to the first cell from a second cell, capability information indicating the WTRU supports AI / ML positioning. The WTRU sends, to the base station, a request for assistance information for a positioning reference unit (PRU) inference. The WTRU receives configuration information indicating a fallback positioning method and resources associated with a set of positioning reference signals (PRSs). The WTRU measures the set of PRSs. The WTRU receives assistance information indicating a location of a PRU and / or a set of measurement information associated with a PRU inference of the location. The WTRU, based on a request from the base station, sends reporting information.

Description

METHOD AND APPARATUS FOR ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING (AI / ML) POSITIONINGCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of U.S. Provisional Patent Application No. 63 / 553,307 filed 14-Feb-2025, which is incorporated herein by reference.BACKGROUND

[0002] The present application is related to the fields of communications, software and encoding, including, for example, to methods, architectures, apparatuses, systems directed to procedures using artificial intelligence / machine learning (AI / ML) models for wireless transmit / receive unit (WTRU) positioning. More particularly, the present disclosure is directed to the selection and switching of AI / ML models.

[0003] In current 3 GPP specifications, radio access technology (RAT) dependent positioning methods are specified. These methods require a WTRU to be in a line-of-sight (LOS) environment with respect to a transmission / reception point (TRP). In non-line of sight (NLOS) environments, the performance of RAT dependent positioning methods deteriorate. It would be beneficial to move beyond this limitation for applicable use cases of WTRU-based positioning.BRIEF SUMMARY

[0004] Briefly stated, in one embodiment, a WTRU may send, to a base station associated with a first cell and based on the WTRU moving to the first cell from a second cell, capability information indicating the WTRU supports AI / ML positioning. The WTRU may send, to the base station, a request for assistance information for a positioning reference unit (PRU) inference. The WTRU may receive configuration information indicating a fallback positioning method and resources associated with a set of positioning reference signals (PRSs). The WTRU may measure the set of PRSs. The WTRU may receive assistance information indicating a location of a PRU and / or a set of measurement information associated with a PRU inference of the location. The WTRU, based on a request from the base station, may send, to the base station, reporting information indicating any of (i) a first AI / ML model used at the WTRU for positioning in the second cell is to be used in the first cell, (ii) fine tuning of the first AI / ML model used at the WTRU for positioning in the second cell, (iii) a second AI / ML model to be used at the WTRU for positioning in the second cell, (iv) the fallback positioning method is to be used at the WTRU for positioning in the second cell, and / or (v) an inference generated based on the indicated set ofmeasurement information and other measurement information associated with the measured set of PRSs.

[0005] In one embodiment, a WTRU may determine a location of the WTRU. The WTRU may select (i) an AI / ML model from a set of AI / ML models or (ii) a fallback positioning method based on the determined location. Each AI / ML model of the set of AI / ML models may be associated with a respective area. The WTRU may send, to a base station, information indicating the selected AI / ML model or the selected fallback positioning method.

[0006] In one embodiment, a WTRU may receive information indicating a first PRS configuration. The first PRS configuration may be associated with an AI / ML model. The WTRU may receive, upon the WTRU moving from a first cell to a second cell, information indicating a second PRS configuration associated with the second cell. The WTRU may select (i) the AI / ML model or (ii) a fallback positioning method based on whether or not the second PRS configuration is included in the first PRS configuration. The WTRU may send information associated with the selected AI / ML model or the selected fallback positioning method.

[0007] In one embodiment, a WTRU may receive information indicating a set of AI / ML models. Each AI / ML model may be associated with a respective range of timing advance (TA) values. The WTRU may receive information indicating a timing advance (TA) value associated with a base station. The WTRU may select an AI / ML model from the set of AI / ML models based on the indicated TA value falling within the range of TA values associated with the AI / ML model. The WTRU may send information associated with the selected AI / ML model.

[0008] In one embodiment, a WTRU may receive information indicating a first set of measurements associated with a PRU. The WTRU may obtain an inference of a location from an AI / ML model using the first set of measurements. The WTRU may send, to a network, information associated with the obtained inference.BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The following detailed description will be better understood when read in conjunction with the appended drawings, in which there are shown examples of one or more of the multiple embodiments of the present disclosure. It should be understood, however, that the embodiments described herein are not limited to the precise arrangements and instrumentalities shown in the drawings. In the drawings:

[0010] FIG. 1 A is a system diagram illustrating an example communications system, according to one or more embodiments of the present disclosure;

[0011] FIG. IB is a system diagram illustrating an example wireless transmit / receive unit (WTRU) that may be used within the communications system illustrated in FIG. 1 A, according to one or more embodiments of the present disclosure;

[0012] FIG. 1C is a system diagram illustrating an example radio access network (RAN) and an example core network (CN) that may be used within the communications system illustrated in FIG. 1 A, according to one or more embodiments of the present disclosure;

[0013] FIG. ID is a system diagram illustrating a further example RAN and a further example CN that may be used within the communications system illustrated in FIG. 1 A, according to one or more embodiments of the present disclosure;

[0014] FIG. 2 is a block diagram illustrating an example of a neural network, according to one or more embodiments of the present disclosure;

[0015] FIG. 3 is a block diagram illustrating an example of using an AI / ML model to estimate a WTRU location, according to one or more embodiments of the present disclosure;

[0016] FIG. 4 is a block diagram illustrating an example hierarchical structure of positioning reference signal (PRS) configurations, according to one or more embodiments of the present disclosure;

[0017] FIG. 5 is a block diagram illustrating an example association between an artificial intelligence / machine learning (AI / ML) model and PRS configuration information, according to one or more embodiments of the present disclosure;

[0018] FIG. 6 is a signaling diagram illustrating an example of communications for WTRU- based AI / ML positioning, according to one or more embodiments of the present disclosure;

[0019] FIG. 7 is a signaling diagram illustrating an example of communications for updating an association between an AI / ML model and a PRS configuration, according to one or more embodiments of the present disclosure;

[0020] FIG. 8 is a signaling diagram illustrating an example of communications for initiating AI / ML-based positioning, according to one or more embodiments of the present disclosure;

[0021] FIG. 9 is a signaling diagram illustrating another example of communications for initiating AI / ML-based positioning, according to one or more embodiments of the present disclosure;

[0022] FIG. 10 is a block diagram illustrating an example AI / ML model which predicts WTRU position and a best AI / ML model for the WTRU location, according to one or more embodiments of the present disclosure;

[0023] FIG. 11 is an operating area diagram illustrating examples of operating areas for different AI / ML models, according to one or more embodiments of the present disclosure;

[0024] FIG. 12 is a procedural diagram illustrating an example of a model switching process according to a WTRU trajectory, according to one or more embodiments of the present disclosure;

[0025] FIG. 13 is a block diagram illustrating an example AI / ML model which predicts WTRU position, a best AI / ML model for the WTRU location, and a future AI / ML model, according to one or more embodiments of the present disclosure;

[0026] FIG. 14 is a signaling diagram illustrating an example of communications for initiating AI / ML-based positioning when an AI / ML model is not available, according to one or more embodiments of the present disclosure;

[0027] FIG. 15 is a system diagram illustrating an example of measurement forwarding between a PRU and a WTRU, according to one or more embodiments of the present disclosure;

[0028] FIG. 16 is a signaling diagram illustrating an example of model verification after a mobility event, according to one or more embodiments of the present disclosure;

[0029] FIG. 17 is a signaling diagram illustrating another example of model verification after a mobility event, according to one or more embodiments of the present disclosure;

[0030] FIG. 18 is a system diagram illustrating an example of verification using measurements made by a PRU, according to one or more embodiments of the present disclosure;

[0031] FIG. 19 is a system diagram illustrating an example of verification using measurements of PRS, according to one or more embodiments of the present disclosure;

[0032] FIG. 20 is a signaling diagram illustrating an example of model verification using CIR;

[0033] FIG. 21 is a signaling diagram illustrating an example of ground truth acquisition, according to one or more embodiments of the present disclosure;

[0034] FIG. 22 is a signaling diagram illustrating an example of provisioning ground truth information with repetitions, according to one or more embodiments of the present disclosure;

[0035] FIG. 23 is a signaling diagram illustrating an example of verification of an AI / ML model using PRU measurements, according to one or more embodiments of the present disclosure;

[0036] FIG. 24 is a system diagram illustrating an example of a WTRU moving from one PRS set to another PRS set, according to one or more embodiments of the present disclosure;

[0037] FIG. 25 is a block diagram illustrating an example configuration of associations between AI / ML models, SSBs, and references, according to one or more embodiments of the present disclosure;

[0038] FIG. 26 is a block diagram illustrating another example configuration of associations between AI / ML models, SSBs, and references, according to one or more embodiments of the present disclosure;

[0039] FIG. 27 is a signaling diagram illustrating an example of PRS-area based AI / ML model determination, according to one or more embodiments of the present disclosure;

[0040] FIG. 28 is a system diagram illustrating an example of TRPs and timing advances (TAs) associated with AI / ML model, according to one or more embodiments of the present disclosure s;

[0041] FIG. 29 is a system diagram illustrating an example of a determination of an AI / ML model due to mobility, according to one or more embodiments of the present disclosure;

[0042] FIG. 30 is a system diagram illustrating another example of a determination of an AI / ML model due to mobility, according to one or more embodiments of the present disclosure;

[0043] FIG. 31 is a system diagram illustrating another example of a determination of an AI / ML model due to mobility, according to one or more embodiments of the present disclosure;

[0044] FIG. 32 is a procedural diagram illustrating an example of AI / ML model verification, according to one or more embodiments of the present disclosure;

[0045] FIG. 33 is a procedural diagram illustrating an example of switching AI / ML models, according to one or more embodiments of the present disclosure;

[0046] FIG. 34 is a procedural diagram illustrating another example of switching AI / ML models, according to one or more embodiments of the present disclosure;

[0047] FIG. 35 is a procedural diagram illustrating another example of switching AI / ML models, according to one or more embodiments of the present disclosure;

[0048] FIG. 36 is a procedural diagram illustrating another example of switching AI / ML models, according to one or more embodiments of the present disclosure;

[0049] FIG. 37 is a procedural diagram illustrating an example procedure, according to one or more embodiments of the present disclosure;

[0050] FIG. 38 is a procedural diagram illustrating an example procedure, according to one or more embodiments of the present disclosure;

[0051] FIG. 39 is a procedural diagram illustrating an example procedure, according to one or more embodiments of the present disclosure;

[0052] FIG. 40 is a procedural diagram illustrating an example procedure, according to one or more embodiments of the present disclosure; and

[0053] FIG. 41 is a procedural diagram illustrating an example procedure, according to one or more embodiments of the present disclosure.DETAILED DESCRIPTION

[0054] In describing the various embodiments of the present disclosure, certain terminology is used herein for convenience only and should not be considered as limiting such embodiments. In the drawings, the same reference numerals are employed for designating the same elements throughout the several figures and the present description.

[0055] In the following detailed description, numerous specific details are set forth to provide a thorough understanding of embodiments and / or examples disclosed herein. However, it will be understood that such embodiments and examples may be practiced without some or all of the specific details set forth herein. In other instances, well-known methods, procedures, components and circuits have not been described in detail, so as not to obscure the following description. Further, embodiments and examples not specifically described herein may be practiced in lieu of, or in combination with, the embodiments and other examples described, disclosed or otherwise provided explicitly, implicitly and / or inherently (collectively "provided") herein. Although various embodiments are described and / or claimed herein in which an apparatus, system, device, etc. and / or any element thereof carries out an operation, process, algorithm, function, etc. and / or any portion thereof, it is to be understood that any embodiments described and / or claimed herein assume that any apparatus, system, device, etc. and / or any element thereof is configured to carry out any operation, process, algorithm, function, etc. and / or any portion thereof.

[0056] Example Communications System

[0057] The methods, apparatuses and systems provided herein are well-suited for communications involving both wired and wireless networks. An overview of various types of wireless devices and infrastructure is provided with respect to FIGs. 1A-1D, where various elements of the network may utilize, perform, be arranged in accordance with and / or be adapted and / or configured for the methods, apparatuses and systems provided herein.

[0058] FIG. 1A is a system diagram illustrating an example communications system 100 in which one or more disclosed embodiments may be implemented. The communications system 100 may be a multiple access system that provides content, such as voice, data, video, messaging, broadcast, etc., to multiple wireless users. The communications system 100 may enable multiple wireless users to access such content through the sharing of system resources, including wireless bandwidth. For example, the communications systems 100 may employ one or more channel access methods, such as code division multiple access (CDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), singlecarrier FDMA (SC-FDMA), zero-tail (ZT) unique-word (UW) discreet Fourier transform (DFT) spread OFDM (ZT UW DTS-s OFDM), unique word OFDM (UW-OFDM), resource block- filtered OFDM, filter bank multicarrier (FBMC), and the like.

[0059] As shown in FIG. 1A, the communications system 100 may include wireless transmit / receive units (WTRUs) 102a, 102b, 102c, 102d, a radio access network (RAN) 104 / 113, a core network (CN) 106 / 115, a public switched telephone network (PSTN) 108, the Internet 110, and other networks 112, though it will be appreciated that the disclosed embodiments contemplate any number of WTRUs, base stations, networks, and / or network elements. Each of the WTRUs102a, 102b, 102c, 102d may be any type of device configured to operate and / or communicate in a wireless environment. By way of example, the WTRUs 102a, 102b, 102c, 102d, any of which may be referred to as a "station" and / or a "STA", may be configured to transmit and / or receive wireless signals and may include (or be) a user equipment (UE), a mobile station, a fixed or mobile subscriber unit, a subscription-based unit, a pager, a cellular telephone, a personal digital assistant (PDA), a smartphone, a laptop, a netbook, a personal computer, a wireless sensor, a hotspot or Mi- Fi device, an Internet of Things (loT) device, a watch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and applications (e.g., remote surgery), an industrial device and applications (e.g., a robot and / or other wireless devices operating in an industrial and / or an automated processing chain contexts), a consumer electronics device, a device operating on commercial and / or industrial wireless networks, and the like. Any of the WTRUs 102a, 102b, 102c and 102d may be interchangeably referred to as a UE.

[0060] The communications systems 100 may also include a base station 114a and / or a base station 114b. Each of the base stations 114a, 114b may be any type of device configured to wirelessly interface with at least one of the WTRUs 102a, 102b, 102c, 102d, e.g., to facilitate access to one or more communication networks, such as the CN 106 / 115, the Internet 110, and / or the networks 112. By way of example, the base stations 114a, 114b may be any of a base transceiver station (BTS), a Node-B (NB), an eNode-B (eNB), a Home Node-B (HNB), a Home eNode-B (HeNB), a gNode-B (gNB), a NR Node-B (NR NB), a site controller, an access point (AP), a wireless router, and the like. While the base stations 114a, 114b are each depicted as a single element, it will be appreciated that the base stations 114a, 114b may include any number of interconnected base stations and / or network elements.

[0061] The base station 114a may be part of the RAN 104 / 113, which may also include other base stations and / or network elements (not shown), such as a base station controller (BSC), a radio network controller (RNC), relay nodes, etc. The base station 114a and / or the base station 114b may be configured to transmit and / or receive wireless signals on one or more carrier frequencies, which may be referred to as a cell (not shown). These frequencies may be in licensed spectrum, unlicensed spectrum, or a combination of licensed and unlicensed spectrum. A cell may provide coverage for a wireless service to a specific geographical area that may be relatively fixed or that may change over time. The cell may further be divided into cell sectors. For example, the cell associated with the base station 114a may be divided into three sectors. Thus, in an embodiment, the base station 114a may include three transceivers, i.e., one for each sector of the cell. In an embodiment, the base station 114a may employ multiple-input multiple output (MIMO) technology and may utilize multiple transceivers for each or any sector of the cell. For example, beamforming may be used to transmit and / or receive signals in desired spatial directions.

[0062] The base stations 114a, 114b may communicate with one or more of the WTRUs 102a, 102b, 102c, 102d over an air interface 116, which may be any suitable wireless communication link (e.g., radio frequency (RF), microwave, centimeter wave, micrometer wave, infrared (IR), ultraviolet (UV), visible light, etc.). The air interface 116 may be established using any suitable radio access technology (RAT).

[0063] More specifically, as noted above, the communications system 100 may be a multiple access system and may employ one or more channel access schemes, such as CDMA, TDMA, FDMA, OFDMA, SC-FDMA, and the like. For example, the base station 114a in the RAN 104 / 113 and the WTRUs 102a, 102b, 102c may implement a radio technology such as Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access (UTRA), which may establish the air interface 116 using wideband CDMA (WCDMA). WCDMA may include communication protocols such as High-Speed Packet Access (HSPA) and / or Evolved HSPA (HSPA+). HSPA may include High-Speed Downlink Packet Access (HSDPA) and / or High-Speed Uplink Packet Access (HSUPA).

[0064] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as Evolved UMTS Terrestrial Radio Access (E-UTRA), which may establish the air interface 116 using Long Term Evolution (LTE) and / or LTE- Advanced (LTE-A) and / or LTE-Advanced Pro (LTE-A Pro).

[0065] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as NR Radio Access, which may establish the air interface 116 using New Radio (NR).

[0066] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement multiple radio access technologies. For example, the base station 114a and the WTRUs 102a, 102b, 102c may implement LTE radio access and NR radio access together, for instance using dual connectivity (DC) principles. Thus, the air interface utilized by WTRUs 102a, 102b, 102c may be characterized by multiple types of radio access technologies and / or transmissions sent to / from multiple types of base stations (e.g., an eNB and a gNB).

[0067] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement radio technologies such as IEEE 802.11 (i.e., Wireless Fidelity (Wi-Fi), IEEE 802.16 (i.e., Worldwide Interoperability for Microwave Access (WiMAX)), CDMA2000, CDMA2000 IX, CDMA2000 EV-DO, Interim Standard 2000 (IS-2000), Interim Standard 95 (IS-95), Interim Standard 856 (IS-856), Global System for Mobile communications (GSM), Enhanced Data rates for GSM Evolution (EDGE), GSM EDGE (GERAN), and the like.

[0068] The base station 114b in FIG. 1 A may be a wireless router, Home Node-B, Home eNode- B, or access point, for example, and may utilize any suitable RAT for facilitating wirelessconnectivity in a localized area, such as a place of business, a home, a vehicle, a campus, an industrial facility, an air corridor (e.g., for use by drones), a roadway, and the like. In an embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.11 to establish a wireless local area network (WLAN). In an embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.15 to establish a wireless personal area network (WPAN). In an embodiment, the base station 114b and the WTRUs 102c, 102d may utilize a cellular-based RAT (e.g., WCDMA, CDMA2000, GSM, LTE, LTE-A, LTE-A Pro, NR, etc.) to establish any of a small cell, picocell or femtocell. As shown in FIG. 1 A, the base station 114b may have a direct connection to the Internet 110. Thus, the base station 114b may not be required to access the Internet 110 via the CN 106 / 115.

[0069] The RAN 104 / 113 may be in communication with the CN 106 / 115, which may be any type of network configured to provide voice, data, applications, and / or voice over internet protocol (VoIP) services to one or more of the WTRUs 102a, 102b, 102c, 102d. The data may have varying quality of service (QoS) requirements, such as differing throughput requirements, latency requirements, error tolerance requirements, reliability requirements, data throughput requirements, mobility requirements, and the like. The CN 106 / 115 may provide call control, billing services, mobile location-based services, pre-paid calling, Internet connectivity, video distribution, etc., and / or perform high-level security functions, such as user authentication. Although not shown in FIG. 1 A, it will be appreciated that the RAN 104 / 113 and / or the CN 106 / 115 may be in direct or indirect communication with other RANs that employ the same RAT as the RAN 104 / 113 or a different RAT. For example, in addition to being connected to the RAN 104 / 113, which may be utilizing an NR radio technology, the CN 106 / 115 may also be in communication with another RAN (not shown) employing any of a GSM, UMTS, CDMA 2000, WiMAX, E-UTRA, or Wi-Fi radio technology.

[0070] The CN 106 / 115 may also serve as a gateway for the WTRUs 102a, 102b, 102c, 102d to access the PSTN 108, the Internet 110, and / or other networks 112. The PSTN 108 may include circuit-switched telephone networks that provide plain old telephone service (POTS). The Internet 110 may include a global system of interconnected computer networks and devices that use common communication protocols, such as the transmission control protocol (TCP), user datagram protocol (UDP) and / or the internet protocol (IP) in the TCP / IP internet protocol suite. The networks 112 may include wired and / or wireless communications networks owned and / or operated by other service providers. For example, the networks 112 may include another CN connected to one or more RANs, which may employ the same RAT as the RAN 104 / 114 or a different RAT.

[0071] Some or all of the WTRUs 102a, 102b, 102c, 102d in the communications system 100 may include multi-mode capabilities (e.g., the WTRUs 102a, 102b, 102c, 102d may include multiple transceivers for communicating with different wireless networks over different wireless links). For example, the WTRU 102c shown in FIG. 1A may be configured to communicate with the base station 114a, which may employ a cellular-based radio technology, and with the base station 114b, which may employ an IEEE 802 radio technology.

[0072] FIG. IB is a system diagram illustrating an example WTRU 102. As shown in FIG. IB, the WTRU 102 may include a processor 118, a transceiver 120, a transmit / receive element 122, a speaker / microphone 124, a keypad 126, a display / touchpad 128, non-removable memory 130, removable memory 132, a power source 134, a global positioning system (GPS) chipset 136, and / or other elements / peripherals 138, among others. It will be appreciated that the WTRU 102 may include any sub-combination of the foregoing elements while remaining consistent with an embodiment.

[0073] The processor 118 may be a general purpose processor, a special purpose processor, a conventional processor, a digital signal processor (DSP), a plurality of microprocessors, one or more microprocessors in association with a DSP core, a controller, a microcontroller, Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) circuits, any other type of integrated circuit (IC), a state machine, and the like. The processor 118 may perform signal coding, data processing, power control, input / output processing, and / or any other functionality that enables the WTRU 102 to operate in a wireless environment. The processor 118 may be coupled to the transceiver 120, which may be coupled to the transmit / receive element 122. While FIG. IB depicts the processor 118 and the transceiver 120 as separate components, it will be appreciated that the processor 118 and the transceiver 120 may be integrated together, e.g., in an electronic package or chip.

[0074] The transmit / receive element 122 may be configured to transmit signals to, or receive signals from, a base station (e.g., the base station 114a) over the air interface 116. For example, in an embodiment, the transmit / receive element 122 may be an antenna configured to transmit and / or receive RF signals. In an embodiment, the transmit / receive element 122 may be an emitter / detector configured to transmit and / or receive IR, UV, or visible light signals, for example. In an embodiment, the transmit / receive element 122 may be configured to transmit and / or receive both RF and light signals. It will be appreciated that the transmit / receive element 122 may be configured to transmit and / or receive any combination of wireless signals.

[0075] Although the transmit / receive element 122 is depicted in FIG. IB as a single element, the WTRU 102 may include any number of transmit / receive elements 122. For example, the WTRU 102 may employ MIMO technology. Thus, in an embodiment, the WTRU 102 may include twoor more transmit / receive elements 122 (e.g., multiple antennas) for transmitting and receiving wireless signals over the air interface 116.

[0076] The transceiver 120 may be configured to modulate the signals that are to be transmitted by the transmit / receive element 122 and to demodulate the signals that are received by the transmit / receive element 122. As noted above, the WTRU 102 may have multi-mode capabilities. Thus, the transceiver 120 may include multiple transceivers for enabling the WTRU 102 to communicate via multiple RATs, such as NR and IEEE 802.11, for example.

[0077] The processor 118 of the WTRU 102 may be coupled to, and may receive user input data from, the speaker / microphone 124, the keypad 126, and / or the display / touchpad 128 (e.g., a liquid crystal display (LCD) display unit or organic light-emitting diode (OLED) display unit). The processor 118 may also output user data to the speaker / microphone 124, the keypad 126, and / or the display / touchpad 128. In addition, the processor 118 may access information from, and store data in, any type of suitable memory, such as the non-removable memory 130 and / or the removable memory 132. The non-removable memory 130 may include random-access memory (RAM), readonly memory (ROM), a hard disk, or any other type of memory storage device. The removable memory 132 may include a subscriber identity module (SIM) card, a memory stick, a secure digital (SD) memory card, and the like. In other embodiments, the processor 118 may access information from, and store data in, memory that is not physically located on the WTRU 102, such as on a server or a home computer (not shown).

[0078] The processor 118 may receive power from the power source 134, and may be configured to distribute and / or control the power to the other components in the WTRU 102. The power source 134 may be any suitable device for powering the WTRU 102. For example, the power source 134 may include one or more dry cell batteries (e.g., nickel-cadmium (NiCd), nickel-zinc (NiZn), nickel metal hydride (NiMH), lithium-ion (Li-ion), etc.), solar cells, fuel cells, and the like.

[0079] The processor 118 may also be coupled to the GPS chipset 136, which may be configured to provide location information (e.g., longitude and latitude) regarding the current location of the WTRU 102. In addition to, or in lieu of, the information from the GPS chipset 136, the WTRU 102 may receive location information over the air interface 116 from a base station (e.g., base stations 114a, 114b) and / or determine its location based on the timing of the signals being received from two or more nearby base stations. It will be appreciated that the WTRU 102 may acquire location information by way of any suitable location-determination method while remaining consistent with an embodiment.

[0080] The processor 118 may further be coupled to other elements / peripherals 138, which may include one or more software and / or hardware modules / units that provide additional features, functionality and / or wired or wireless connectivity. For example, the elements / peripherals 138may include an accelerometer, an e-compass, a satellite transceiver, a digital camera (e.g., for photographs and / or video), a universal serial bus (USB) port, a vibration device, a television transceiver, a hands free headset, a Bluetooth® module, a frequency modulated (FM) radio unit, a digital music player, a media player, a video game player module, an Internet browser, a virtual reality and / or augmented reality (VR / AR) device, an activity tracker, and the like. The elements / peripherals 138 may include one or more sensors, the sensors may be one or more of a gyroscope, an accelerometer, a hall effect sensor, a magnetometer, an orientation sensor, a proximity sensor, a temperature sensor, a time sensor; a geolocation sensor; an altimeter, a light sensor, a touch sensor, a magnetometer, a barometer, a gesture sensor, a biometric sensor, and / or a humidity sensor.

[0081] The WTRU 102 may include a full duplex radio for which transmission and reception of some or all of the signals (e.g., associated with particular subframes for both the uplink (e.g., for transmission) and downlink (e.g., for reception) may be concurrent and / or simultaneous. The full duplex radio may include an interference management unit to reduce and or substantially eliminate self-interference via either hardware (e.g., a choke) or signal processing via a processor (e.g., a separate processor (not shown) or via processor 118). In an embodiment, the WTRU 102 may include a half-duplex radio for which transmission and reception of some or all of the signals (e.g., associated with particular subframes for either the uplink (e.g., for transmission) or the downlink (e.g., for reception)).

[0082] FIG. 1C is a system diagram illustrating the RAN 104 and the CN 106 according to an embodiment. As noted above, the RAN 104 may employ an E-UTRA radio technology to communicate with the WTRUs 102a, 102b, and 102c over the air interface 116. The RAN 104 may also be in communication with the CN 106.

[0083] The RAN 104 may include eNode-Bs 160a, 160b, 160c, though it will be appreciated that the RAN 104 may include any number of eNode-Bs while remaining consistent with an embodiment. The eNode-Bs 160a, 160b, 160c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In an embodiment, the eNode-Bs 160a, 160b, 160c may implement MIMO technology. Thus, the eNode-B 160a, for example, may use multiple antennas to transmit wireless signals to, and receive wireless signals from, the WTRU 102a.

[0084] Each of the eNode-Bs 160a, 160b, and 160c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, scheduling of users in the uplink (UL) and / or downlink (DL), and the like. As shown in FIG. 1C, the eNode-Bs 160a, 160b, 160c may communicate with one another over an X2 interface.

[0085] The CN 106 shown in FIG. 1C may include a mobility management entity (MME) 162, a serving gateway (SGW) 164, and a packet data network (PDN) gateway (PGW) 166. While each of the foregoing elements are depicted as part of the CN 106, it will be appreciated that any one of these elements may be owned and / or operated by an entity other than the CN operator.

[0086] The MME 162 may be connected to each of the eNode-Bs 160a, 160b, and 160c in the RAN 104 via an SI interface and may serve as a control node. For example, the MME 162 may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, bearer activation / deactivation, selecting a particular serving gateway during an initial attach of the WTRUs 102a, 102b, 102c, and the like. The MME 162 may provide a control plane function for switching between the RAN 104 and other RANs (not shown) that employ other radio technologies, such as GSM and / or WCDMA.

[0087] The SGW 164 may be connected to each of the eNode-Bs 160a, 160b, 160c in the RAN 104 via the SI interface. The SGW 164 may generally route and forward user data packets to / from the WTRUs 102a, 102b, 102c. The SGW 164 may perform other functions, such as anchoring user planes during inter-eNode-B handovers, triggering paging when DL data is available for the WTRUs 102a, 102b, 102c, managing and storing contexts of the WTRUs 102a, 102b, 102c, and the like.

[0088] The SGW 164 may be connected to the PGW 166, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices.

[0089] The CN 106 may facilitate communications with other networks. For example, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to circuit-switched networks, such as the PSTN 108, to facilitate communications between the WTRUs 102a, 102b, 102c and traditional land-line communications devices. For example, the CN 106 may include, or may communicate with, an IP gateway (e.g., an IP multimedia subsystem (IMS) server) that serves as an interface between the CN 106 and the PSTN 108. In addition, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to the other networks 112, which may include other wired and / or wireless networks that are owned and / or operated by other service providers.

[0090] Although the WTRU is described in FIGs. 1A-1D as a wireless terminal, it is contemplated that in certain representative embodiments that such a terminal may use (e.g., temporarily or permanently) wired communication interfaces with the communication network.

[0091] In representative embodiments, the other network 112 may be a WLAN.

[0092] A WLAN in infrastructure basic service set (BSS) mode may have an access point (AP) for the BSS and one or more stations (STAs) associated with the AP. The AP may have an access or an interface to a distribution system (DS) or another type of wired / wireless network that carriestraffic into and / or out of the BSS. Traffic to STAs that originates from outside the BSS may arrive through the AP and may be delivered to the STAs. Traffic originating from STAs to destinations outside the BSS may be sent to the AP to be delivered to respective destinations. Traffic between STAs within the BSS may be sent through the AP, for example, where the source STA may send traffic to the AP and the AP may deliver the traffic to the destination STA. The traffic between STAs within a BSS may be considered and / or referred to as peer-to-peer traffic. The peer-to-peer traffic may be sent between (e.g., directly between) the source and destination STAs with a direct link setup (DLS). In certain representative embodiments, the DLS may use an 802. l ie DLS or an 802.1 Iz tunneled DLS (TDLS). A WLAN using an Independent BSS (IBSS) mode may not have an AP, and the STAs (e.g., all of the STAs) within or using the IBSS may communicate directly with each other. The IBSS mode of communication may sometimes be referred to herein as an "ad-hoc" mode of communication.

[0093] When using the 802.1 lac infrastructure mode of operation or a similar mode of operations, the AP may transmit a beacon on a fixed channel, such as a primary channel. The primary channel may be a fixed width (e.g., 20 MHz wide bandwidth) or a dynamically set width via signaling. The primary channel may be the operating channel of the BSS and may be used by the STAs to establish a connection with the AP. In certain representative embodiments, Carrier sense multiple access with collision avoidance (CSMA / CA) may be implemented, for example in in 802.11 systems. For CSMA / CA, the STAs (e.g., every STA), including the AP, may sense the primary channel. If the primary channel is sensed / detected and / or determined to be busy by a particular STA, the particular STA may back off. One STA (e.g., only one station) may transmit at any given time in a given BSS.

[0094] High throughput (HT) STAs may use a 40 MHz wide channel for communication, for example, via a combination of the primary 20 MHz channel with an adjacent or nonadj acent 20 MHz channel to form a 40 MHz wide channel.

[0095] Very high throughput (VHT) STAs may support 20 MHz, 40 MHz, 80 MHz, and / or 160 MHz wide channels. The 40 MHz, and / or 80 MHz, channels may be formed by combining contiguous 20 MHz channels. A 160 MHz channel may be formed by combining 8 contiguous 20 MHz channels, or by combining two non-contiguous 80 MHz channels, which may be referred to as an 80+80 configuration. For the 80+80 configuration, the data, after channel encoding, may be passed through a segment parser that may divide the data into two streams. Inverse fast fourier transform (IFFT) processing, and time domain processing, may be done on each stream separately. The streams may be mapped on to the two 80 MHz channels, and the data may be transmitted by a transmitting STA. At the receiver of the receiving STA, the above-described operation for the80+80 configuration may be reversed, and the combined data may be sent to a medium access control (MAC) layer, entity, etc.

[0096] Sub 1 GHz modes of operation are supported by 802.1 laf and 802.11 ah. The channel operating bandwidths, and carriers, are reduced in 802.1 laf and 802.1 lah relative to those used in 802.1 In, and 802.1 lac. 802.1 laf supports 5 MHz, 10 MHz and 20 MHz bandwidths in the TV white space (TVWS) spectrum, and 802.1 lah supports 1 MHz, 2 MHz, 4 MHz, 8 MHz, and 16 MHz bandwidths using non-TVWS spectrum. According to a representative embodiment, 802.1 lah may support meter type control / machine-type communications (MTC), such as MTC devices in a macro coverage area. MTC devices may have certain capabilities, for example, limited capabilities including support for (e.g., only support for) certain and / or limited bandwidths. The MTC devices may include a battery with a battery life above a threshold (e.g., to maintain a very long battery life).

[0097] WLAN systems, which may support multiple channels, and channel bandwidths, such as 802.1 In, 802.1 lac, 802.1 laf, and 802.1 lah, include a channel which may be designated as the primary channel. The primary channel may have a bandwidth equal to the largest common operating bandwidth supported by all STAs in the BSS. The bandwidth of the primary channel may be set and / or limited by a STA, from among all STAs in operating in a BSS, which supports the smallest bandwidth operating mode. In the example of 802.1 lah, the primary channel may be 1 MHz wide for STAs (e.g., MTC type devices) that support (e.g., only support) a 1 MHz mode, even if the AP, and other STAs in the BSS support 2 MHz, 4 MHz, 8 MHz, 16 MHz, and / or other channel bandwidth operating modes. Carrier sensing and / or network allocation vector (NAV) settings may depend on the status of the primary channel. If the primary channel is busy, for example, due to a STA (which supports only a 1 MHz operating mode), transmitting to the AP, the entire available frequency bands may be considered busy even though a majority of the frequency bands remains idle and may be available.

[0098] In the United States, the available frequency bands, which may be used by 802.1 lah, are from 902 MHz to 928 MHz. In Korea, the available frequency bands are from 917.5 MHz to 923.5 MHz. In Japan, the available frequency bands are from 916.5 MHz to 927.5 MHz. The total bandwidth available for 802.1 lah is 6 MHz to 26 MHz depending on the country code.

[0099] FIG. ID is a system diagram illustrating the RAN 113 and the CN 115 according to an embodiment. As noted above, the RAN 113 may employ an NR radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 113 may also be in communication with the CN 115.

[0100] The RAN 113 may include gNBs 180a, 180b, 180c, though it will be appreciated that the RAN 113 may include any number of gNBs while remaining consistent with an embodiment. ThegNBs 180a, 180b, 180c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In an embodiment, the gNBs 180a, 180b, 180c may implement MIMO technology. For example, gNBs 180a, 180b may utilize beamforming to transmit signals to and / or receive signals from the WTRUs 102a, 102b, 102c. Thus, the gNB 180a, for example, may use multiple antennas to transmit wireless signals to, and / or receive wireless signals from, the WTRU 102a. In an embodiment, the gNBs 180a, 180b, 180c may implement carrier aggregation technology. For example, the gNB 180a may transmit multiple component carriers to the WTRU 102a (not shown). A subset of these component carriers may be on unlicensed spectrum while the remaining component carriers may be on licensed spectrum. In an embodiment, the gNBs 180a, 180b, 180c may implement Coordinated Multi-Point (CoMP) technology. For example, WTRU 102a may receive coordinated transmissions from gNB 180a and gNB 180b (and / or gNB 180c).

[0101] The WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using transmissions associated with a scalable numerology. For example, OFDM symbol spacing and / or OFDM subcarrier spacing may vary for different transmissions, different cells, and / or different portions of the wireless transmission spectrum. The WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using subframe or transmission time intervals (TTIs) of various or scalable lengths (e.g., including a varying number of OFDM symbols and / or lasting varying lengths of absolute time).

[0102] The gNBs 180a, 180b, 180c may be configured to communicate with the WTRUs 102a, 102b, 102c in a standalone configuration and / or a non- standalone configuration. In the standalone configuration, WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c without also accessing other RANs (e.g., such as eNode-Bs 160a, 160b, 160c). In the standalone configuration, WTRUs 102a, 102b, 102c may utilize one or more of gNBs 180a, 180b, 180c as a mobility anchor point. In the standalone configuration, WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using signals in an unlicensed band. In a non- standalone configuration WTRUs 102a, 102b, 102c may communicate with / connect to gNBs 180a, 180b, 180c while also communicating with / connecting to another RAN such as eNode-Bs 160a, 160b, 160c. For example, WTRUs 102a, 102b, 102c may implement DC principles to communicate with one or more gNBs 180a, 180b, 180c and one or more eNode-Bs 160a, 160b, 160c substantially simultaneously. In the non- standalone configuration, eNode-Bs 160a, 160b, 160c may serve as a mobility anchor for WTRUs 102a, 102b, 102c and gNBs 180a, 180b, 180c may provide additional coverage and / or throughput for servicing WTRUs 102a, 102b, 102c.

[0103] Each of the gNBs 180a, 180b, 180c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions,scheduling of users in the UL and / or DL, support of network slicing, dual connectivity, interworking between NR and E-UTRA, routing of user plane data towards user plane functions (UPFs) 184a, 184b, routing of control plane information towards access and mobility management functions (AMFs) 182a, 182b, and the like. As shown in FIG. ID, the gNBs 180a, 180b, 180c may communicate with one another over an Xn interface.

[0104] The CN 115 shown in FIG. ID may include at least one AMF 182a, 182b, at least one UPF 184a, 184b, at least one session management function (SMF) 183a, 183b, and at least one Data Network (DN) 185a, 185b. While each of the foregoing elements are depicted as part of the CN 115, it will be appreciated that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0105] The AMF 182a, 182b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via an N2 interface and may serve as a control node. For example, the AMF 182a, 182b may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, support for network slicing (e.g., handling of different protocol data unit (PDU) sessions with different requirements), selecting a particular SMF 183a, 183b, management of the registration area, termination of NAS signaling, mobility management, and the like. Network slicing may be used by the AMF 182a, 182b, e.g., to customize CN support for WTRUs 102a, 102b, 102c based on the types of services being utilized WTRUs 102a, 102b, 102c. For example, different network slices may be established for different use cases such as services relying on ultra-reliable low latency (URLLC) access, services relying on enhanced massive mobile broadband (eMBB) access, services for MTC access, and / or the like. The AMF 162 may provide a control plane function for switching between the RAN 113 and other RANs (not shown) that employ other radio technologies, such as LTE, LTE-A, LTE-A Pro, and / or non-3GPP access technologies such as WiFi.

[0106] The SMF 183a, 183b may be connected to an AMF 182a, 182b in the CN 115 via an N11 interface. The SMF 183a, 183b may also be connected to a UPF 184a, 184b in the CN 115 via an N4 interface. The SMF 183a, 183b may select and control the UPF 184a, 184b and configure the routing of traffic through the UPF 184a, 184b. The SMF 183a, 183b may perform other functions, such as managing and allocating UE IP address, managing PDU sessions, controlling policy enforcement and QoS, providing downlink data notifications, and the like. A PDU session type may be IP -based, non-IP based, Ethernet-based, and the like.

[0107] The UPF 184a, 184b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via an N3 interface, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, e.g., to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices. The UPF 184, 184b may perform otherfunctions, such as routing and forwarding packets, enforcing user plane policies, supporting multihomed PDU sessions, handling user plane QoS, buffering downlink packets, providing mobility anchoring, and the like.

[0108] The CN 115 may facilitate communications with other networks. For example, the CN 115 may include, or may communicate with, an IP gateway (e.g., an IP multimedia subsystem (IMS) server) that serves as an interface between the CN 115 and the PSTN 108. In addition, the CN 115 may provide the WTRUs 102a, 102b, 102c with access to the other networks 112, which may include other wired and / or wireless networks that are owned and / or operated by other service providers. In an embodiment, the WTRUs 102a, 102b, 102c may be connected to a local Data Network (DN) 185a, 185b through the UPF 184a, 184b via the N3 interface to the UPF 184a, 184b and an N6 interface between the UPF 184a, 184b and the DN 185a, 185b.

[0109] In view of FIGs. 1 A-1D, and the corresponding description of FIGs. 1 A-1D, one or more, or all, of the functions described herein with regard to any of: WTRUs 102a-d, base stations 114a- b, eNode-Bs 160a-c, MME 162, SGW 164, PGW 166, gNBs 180a-c, AMFs 182a-b, UPFs 184a- b, SMFs 183a-b, DNs 185a-b, and / or any other element(s) / device(s) described herein, may be performed by one or more emulation elements / devices (not shown). The emulation devices may be one or more devices configured to emulate one or more, or all, of the functions described herein. For example, the emulation devices may be used to test other devices and / or to simulate network and / or WTRU functions.

[0110] The emulation devices may be designed to implement one or more tests of other devices in a lab environment and / or in an operator network environment. For example, the one or more emulation devices may perform the one or more, or all, functions while being fully or partially implemented and / or deployed as part of a wired and / or wireless communication network in order to test other devices within the communication network. The one or more emulation devices may perform the one or more, or all, functions while being temporarily implemented / deployed as part of a wired and / or wireless communication network. The emulation device may be directly coupled to another device for purposes of testing and / or may performing testing using over-the-air wireless communications.

[0111] The one or more emulation devices may perform the one or more, including all, functions while not being implemented / deployed as part of a wired and / or wireless communication network. For example, the emulation devices may be utilized in a testing scenario in a testing laboratory and / or a non-deployed (e.g., testing) wired and / or wireless communication network in order to implement testing of one or more components. The one or more emulation devices may be test equipment. Direct RF coupling and / or wireless communications via RF circuitry (e.g., which mayinclude one or more antennas) may be used by the emulation devices to transmit and / or receive data.

[0112] Introduction

[0113] The following abbreviations and acronyms may be used herein:ACK AcknowledgementAo A Angle of ArrivalAoD Angle of DepartureARFCN Absolute Radio-Frequency Channel NumberBLER Block Error RateBW BandwidthBWP Bandwidth PartCAP Channel Access PriorityCAPC Channel access priority classCCA Clear Channel AssessmentCCE Control Channel ElementCDF Cumul ati ve Di stributi on F uncti onCE Control ElementCG Configured Grant or Cell GroupCIR Channel Impulse ResponseCORESET Control Resource SetCP Cyclic PrefixCP-OFDM Conventional OFDM (relying on cyclic prefix)CQI Channel Quality IndicatorCRC Cyclic Redundancy CheckCSI Channel State InformationCW Contention WindowCWS Contention Window SizeCO Channel OccupancyDAI Downlink Assignment IndexDCI Downlink Control InformationDFI Downlink feedback informationDG Dynamic grantDL DownlinkDM-RS Demodulation Reference SignalDP Delay ProfileDRB Data Radio BearerDRX Discontinuous ReceptionECID Enhanced Cell ID eLAA enhanced Licensed Assisted Access eMBB enhanced Mobile BroadbandFeLAA Further enhanced Licensed Assisted AccessHARQ Hybrid Automatic Repeat RequestIM Interference MeasurementKPI Key Performance IndicatorLAA License Assisted AccessLBT Listen Before TalkLCH Logical ChannelLCM Life Cycle ManagementLCP Logical Channel PriorityLBT Listen-Before-TalkLOS Line of SightNLOS Non Line of SightLMF Location Management FunctionLPP LTE Positioning ProtocolLTE Long Term Evolution e.g. from 3 GPP LTE R8 and upMAC CE MAC Control ElementMAC Medium Access ControlMCS Modulation and Coding SchemeMIMO Multiple Input Multiple OutputMSE Mean Squared ErrorNACK Negative ACKNAS Non-access stratumNR New RadioOFDM Orthogonal Frequency-Division MultiplexingOTDOA Observed Time Difference of ArrivalPDCCH Physical Downlink Control ChannelPDSCH Physical Downlink Shared ChannelPDP Power Delay ProfilePDU Packet Data UnitPFL Positioning Frequency LayerPHY Physical LayerPID Process IDPO Paging OccasionPRACH Physical Random Access ChannelPRS Positioning Reference SignalPRU Positioning Reference UnitPSS Primary Synchronization SignalPTRS Phase Tracking Reference SignalPUCCH Physical Uplink Control Channel PUSCH Physical Uplink Shared ChannelRA Random Access (or procedure)RACH Random Access ChannelRAR Random Access ResponseRAT Radio Access TechnologyRCU Radio access network Central UnitRE Resource ElementRF Radio Front endRLF Radio Link FailureRLM Radio Link MonitoringRMSE Root Mean Squared ErrorRNTI Radio Network IdentifierRNA RAN Notification AreaRO RACH occasionRRC Radio Resource ControlRRM Radio Resource ManagementRTT Round Trip TimeRP Reception PointRS Reference SignalRSRP Reference Signal Received PowerRSTD Reference Signal Time DifferenceRTT Round Trip TimeRS SI Received Signal Strength IndicatorRTOA Relative Time of ArrivalSDAP Service data adaptation protocolSDU Service Data UnitSRB Signaling Radio BearerSRS Sounding Reference SignalSRSp SRS for positioningSS Synchronization SignalSSB Synchronization Signal BlockSSS Secondary Synchronization SignalSWG Switching Gap (in a self-contained subframe)SPS Semi-persistent schedulingSUL Supplemental UplinkTA Timing AdvanceTB Transport BlockTBS Transport Block SizeTDoA Time Difference of ArrivalTEG Timing Error GroupTRP Transmission-Reception PointTSC Time-sensitive communicationsTSN Time-sensitive networkingTTI Transmission Time IntervalUCI Uplink Control InformationUL UplinkURLLC Ultra-Reliable and Low Latency CommunicationsWBWP Wide Bandwidth PartWLAN Wireless Local Area Networks and related technologies (IEEE 802. xx domain)

[0114] Positioning Methods

[0115] In 3GPP Release 16, DL, UL, and DL and UL positioning methods are used (e.g., as in TS 38.305).

[0116] In certain representative embodiments, a WTRU 102 and / or a network may use one or more positioning methods.

[0117] For example, a “DL positioning method” may refer to any positioning method that uses downlink reference signals, such as PRS. A WTRU 102 may receive multiple reference signals from one or more transmission points (TPs) and measure a DL RSTD and / or RSRP. Examples of DL positioning methods are DL-AoD and DL-TDOA positioning.

[0118] For example, a “UL positioning method” may refer to any positioning method that uses uplink reference signals, such as SRS for positioning. A WTRU 102 may transmit SRS to multiple reception points (RPs) and the RPs may measure an UL RTOA and / or RSRP. Examples of UL positioning methods are UL-TDOA and UL-AoA positioning.

[0119] For example, a “DL & UL positioning method” may refer to any positioning method that uses both uplink and downlink reference signals for positioning. In one example, a WTRU 102 may transmit one or more SRSs to multiple TRPs and a gNB may measure a Rx-Tx time difference which is calculated based on the time of arrival of DL RS (e.g., PRS). The gNB may measure aRSRP for the received SRS. The WTRU 102 may measure a Rx-Tx time difference for the PRS transmitted from multiple TRPs. The WTRU 102 may measure a RSRP for the received PRS. The Rx-TX difference and / or the RSRP measured at WTRU 102 and gNB may be used to compute a round trip time (RTT). As used herein, the phrase “UE Rx - Tx time difference” may refer to the difference between the arrival time of a reference signal transmitted by the TRP and the transmission time of a reference signal transmitted from the WTRU 102. An example of DL & UL positioning method is multi-RTT positioning.

[0120] Machine Learning (ML)

[0121] For example, machine learning may refer to types of algorithms that solve a problem based on learning through experience (e.g., data), without explicitly being programmed (e.g., configuring a set of rules). Machine learning can be considered as a subset of Al. Different machine learning paradigms may be envisioned based on the nature of data and / or feedback available to the learning algorithm. For example, a supervised learning approach may involve learning a function that maps an input to an output based on labeled training examples, wherein each training example may be a pair consisting of an input and a corresponding output. For example, an unsupervised learning approach may involve detecting patterns in the data with no pre-existing labels. For example, a reinforcement learning approach may involve performing a sequence of actions in an environment to maximize the cumulative reward. In some embodiments, machine learning algorithms may be applied using a combination or interpolation of the above-mentioned approaches. For example, a semi-supervised learning approach may use a combination of a small amount of labeled data with a large amount of unlabeled data during training. In this regard, semisupervised learning falls between unsupervised learning (e.g., with no labeled training data) and supervised learning (e.g., with only labeled training data).

[0122] Artificial Intelligence (Al) for Positioning

[0123] Artificial intelligence may be broadly defined as the behavior exhibited by machines that mimic cognitive functions including to sense, reason, adapt, act, and / or provide the ability to discern patterns.

[0124] Neural Networks

[0125] FIG. 2 is a block diagram illustrating an example of a neural network 200. The objective of training is to apply inputs and adjust weights, indicated as 202 and 204 in FIG. 2, which may be referred to as neuron weights or link weights, such that the output from the neural network 200 approaches desired target values which are associated with the input values. In the example of FIG. 2, the neural network 200 consists of 3 layers. During the training, for a given input, the difference between the output values and the desired values are computed and a difference is used to update the weights 202, 204 in the neural network 200. If a large difference between outputvalues and desired values is observed, large changes in the weights 202, 204 may be expected while small differences may lead to small changes in the weights 202, 204.

[0126] For example, for positioning, an input may be reference signal parameters and an output may be an estimated position. The desired value may be location information, such as may be acquired by GNSS with high accuracy. Once the neural network 200 completes its training (e.g., the difference between the output and desired values is below a threshold), it can be applied for positioning by feeding inputs and using the outputs as the expected outcome for the associated input. For example, the output may be the estimated position or location of the WTRU 102.

[0127] Thus, for training a neural network, it may be considered important to identify the following: (i) input for the neural network; (ii) expected output associated with the input; and (iii) actual output from the neural network against which the target values are compared.

[0128] As an example, a neural network model may be characterized by the following parameters: (i) number of weights; (ii) number of layers of the neural network; and (iii) number of neurons per layer.

[0129] As an example, a neural network may be characterized by the following parameters: (i) number and types of layers, and (ii) values of parameters (e.g., weights) associated with each layer.

[0130] Deep Learning

[0131] Deep learning refers to a class of ML algorithms that employ artificial neural networks (e.g., deep neural networks) which were loosely inspired from biological systems and include at least one hidden layer. Deep Neural Networks (DNNs) are a special class of machine learning models inspired by the human brain wherein an input is linearly transformed and passes through a non-linear activation function multiple times. DNNs typically consist of multiple layers where each layer consists of a linear transformation and a given non-linear activation function. The DNNs can be trained using training data via a back-propagation algorithm. Recently, DNNs have shown state-of-the-art performance in a variety of domains (e.g., speech, vision, natural language) and for various machine learning settings (e.g., supervised, un-supervised, and semi-supervised).

[0132] As used herein, “events” and “occasions” may be used interchangeably.

[0133] AI / ML positioning methods are effective in both line-of-sight and non-line-of sight environment due to the use of fingerprinting as it relates to positioning (e.g., association of RSRP and / or timing measurements to a WTRU location). However, a WTRU 102 needs to determine which AI / ML model to use. As the RS configuration or environment (e.g., cell, TRPs nearby) of the WTRU 102 changes due to WTRU mobility, the performance of the AI / ML model the WTRU 102 uses for positioning may deteriorate due to a mismatch between the trained AI / ML model and the changing environment. It would be beneficial to provide procedures which allow a WTRU 102 to determine whether to switch AI / ML models, fine-tune an AI / ML model, and / or use a fallbackpositioning method to maintain the positioning performance. It would also be beneficial to provide procedures for the WTRU to notify the network as to any changes in AI / ML model.

[0134] Overview

[0135] In current 3 GPP specifications, RAT dependent positioning methods are specified. These methods require the WTRU 102 to be in a line-of-sight environment with respect to a TRP, limiting the applicable use cases. In non-line of sight environments, the performance of RAT dependent positioning methods deteriorate.

[0136] In certain representative embodiments, AI / ML positioning methods may be effective in both line-of-sight and non-line-of sight environments due to the use of fingerprinting-based positioning (e.g., association of RSRP and / or timing measurements to a WTRU location). However, the WTRU 102 needs to determine which AI / ML model to use. As the RS configuration or environment (e.g., cell, TRPs nearby) of the WTRU 102 changes (e.g., due to WTRU mobility), the performance of the AI / ML model the WTRU 102 uses for positioning may deteriorate due to a mismatch between the trained AI / ML model and the changing environment. It would be beneficial to provide techniques for the WTRU 102 the determine whether to switch and / or finetune a positioning method and / or use a fallback positioning method to maintain positioning performance. Further, it would be beneficial to provide techniques to allow the WTRU 102 to notify the network as to any changes in the AI / ML model being used.

[0137] In certain representative embodiments, a WTRU may perform positioning reference unit (PRU) assisted AI / ML model switching.

[0138] For example, an AI / ML model may be associated with a cell. When a WTRU 102 moves to a different cell, the WTRU 102 may ask (e.g., request) for PRU measurements and its location. The network may provide requested information to the WTRU 102, and the WTRU 102 may determine whether the current AI / ML model (e.g., the model used in the previous cell) can still be used or not. After assistance information is provided, the WTRU 102 may report (e.g., indicate) whether the WTRU 102 is still using the same model or not.

[0139] For example, a WTRU may move to a new cell (e.g., due to mobility). The WTRU 102 may indicate WTRU capability information (e.g., support for WTRU-based AI / ML-based positioning) to the network.

[0140] For example, the WTRU 102 may send a request for assistance information (e.g., PRU location, PRU’s inference, time stamp, associated measurements) indicating (e.g., required)an uncertainty level (e.g., standard deviation) for PRU inference, desired association information (e.g., desired SSBs) and / or a cell ID of a previous cell.

[0141] For example, the WTRU 102 may be configured with a fallback positioning method (e.g., DL-TDOA).

[0142] For example, the WTRU 102 may perform measurement on a configured set of PRSs within a configured time window (e.g., periodic, duration).

[0143] For example, the WTRU 102 may receive assistance information (e.g., PRU measurements, corresponding PRU inference, PRU location) periodically from the network. In some embodiments, the assistance information may contain a duration of provisioning of the assistance information, such as where the duration is the same as the duration of the time window.

[0144] For example, at the end of the provisioning of the assistance information or if the WTRU 102 receives a request from the network, the WTRU 102 may report (e.g., send) information indicating any of the following: (i) Fine tuning is performed with the current AI / ML model; (ii) Association information (e.g., cell ID) of a new model; (iii) The model used in the previous cell is used again; and / or (iv) Use of the fallback positioning method.

[0145] General WTRU Behavior

[0146] In certain representative embodiments, a WTRU 102 may send a request to the network for configuration information (e.g., PRS configurations and / or SRSp configurations), such as via PUSCH, PUCCH, UCI, MAC-CE, RRC or LPP message. The request from the WTRU 102 may include configurations of a measurement gap, PRS processing window and / or window for transmission of SRS for positioning (SRSp).

[0147] In certain representative embodiments, a WTRU 102 may send an acknowledgement message (e.g., in PUSCH or PUCCH) for a grant received from the network.

[0148] In certain representative embodiments, more than one condition and / or criterion may be used in a combination. For example, a WTRU 102 may be configured with multiple conditions and associated WTRU behaviors. The WTRU 102 may determine which behavior the WTRU 102 may or shall use based on the applicable conditions.

[0149] In certain representative embodiments, a WTRU 102 may measure a DL-PRS inside or outside of a (e.g., active) BWP. The WTRU 102 may transmit SRSp inside or outside of a (e.g., active) BWP.

[0150] In certain representative embodiments, a WTRU 102 may be preconfigured with parameters (e.g., measurement gaps, PRS processing windows, PRS configurations, SRSp configurations) via a semi-static message (e.g., LPP, RRC).

[0151] In certain representative embodiments, any actions the WTRU 102 determines to take may be configured by the network. For example, the WTRU 102 may be configured with a rule and according to the rule, the WTRU 102 may determine to take an associated action.

[0152] In certain representative embodiments, a WTRU 102 may (e.g., in addition to the measurements made on PRS) make (e.g., perform and / or report) any of the following cell-related measurements: (i) SSB RSRP from a serving cell with corresponding cell ID; (ii) SSB RSRP fromany neighboring cell(s) with corresponding cell ID(s); (iii) RSRP of CSI-RS with CSI-RS resource ID; and / or (iv) RSRS of DM-RS.

[0153] Terminology

[0154] As used herein, the phrase “network” may be used interchangeably with any of AMF, LMF, gNB, and / or NG-RAN.

[0155] As used herein, the phrases “pre-configuration” and “configuration” may be used interchangeably.

[0156] As used herein, the phrases “non-serving gNB” and “neighboring gNB” may be used interchangeably.

[0157] As used herein, the phrases “gNB” and “TRP” may be used interchangeably in this disclosure.

[0158] As used herein, the phrases “PRS”, “SRS”, “SRS for positioning” and / or “SRS for positioning purpose” may be used interchangeably.

[0159] As used herein, the phrases “PRS” and “PRS resource” may be used interchangeably.

[0160] As used herein, the phrases “PRS(s)” and “PRS resource(s)” may be used interchangeably. The PRS(s) and / or PRS resource(s) may belong to different PRS resource sets.

[0161] As used herein, the phrases “PRS”, “DL-PRS” and / or “DL PRS” may be used interchangeably.

[0162] As used herein, the phrases “Measurement gap” and “Measurement gap pattern” may be used interchangeably. A measurement gap pattern may include parameters such as measurement gap duration, measurement gap repetition period, and / or measurement gap periodicity.

[0163] As used herein, the phrases “position” and “location” may be used interchangeably.

[0164] In certain embodiments, a PRU may be a WTRU 102 or TRP whose location (e.g., altitude, latitude, geographic coordinate, or local coordinate) is known by the network (e.g., gNB, LMF). Capabilities of a PRU may be same as a WTRU 102 or TRP (e.g., capable of receiving PRS or transmitting SRS or SRSp, return measurements, and / or transmitting PRS). Any WTRUs 102 acting as PRUs may be used by the network for calibration purposes (e.g., to correct unknown timing offset, to correct unknown angle offset).

[0165] As an example, a LMF is a non-limiting example of a node or entity (e.g., network node or entity) that may be used for or to support positioning. Any other node or entity may be substituted for the LMF and still be consistent with the examples and embodiments described herein.

[0166] In certain embodiments, a WTRU 102 may receive a preconfigured threshold(s) from the network (e.g., LMF, gNB).

[0167] In certain embodiments, a LOS indicator may be a hard (e.g., 1 or 0) or soft indicator (e.g., 0, 0.1, 0.2. . .,1) and it indicates the likelihood of the presence of a LOS path between a TRP and a WTRU 102 or along a PRS. A LOS indicator may be associated with a TRP or PRS resource ID (e.g., index). The WTRU 102 may receive the LOS indicator from the network (e.g., per TRP and / or resource ID). In some embodiments, the WTRU 102 may determine the LOS indicator (e.g., per TRP and / or resource ID) based on measurements.

[0168] As used herein, the phrases, “ID” and “index” may be used interchangeably.

[0169] In certain embodiments, a WTRU location may be expressed in terms of any of altitude, latitude, geographic coordinates, and / or local coordinates. Altitude, latitude, geographic coordinates, and / or local coordinates may be used interchangeably.

[0170] As used herein, “preconfiguration”, “configuration”, “preconfigured” and “configured” may be used interchangeably.

[0171] Configurations for RS for Positioning

[0172] In certain representative embodiments, a WTRU 102 may receive PRS and / or SRS configurations for positioning purposes from the network (e.g., LMF). The LMF may forward the PRS configuration and SRS configurations to the gNB so that the gNB can schedule PRS transmission and / or SRS reception at the TRP, TP and / or RP.

[0173] Configurations for PRS

[0174] In certain representative embodiments, a PRS configuration may contain information indicating at least one of the following parameters: number of symbols, transmission power, number of PRS resources included in PRS resource set, muting pattern for PRS (for example, the muting pattern may be expressed via a bitmap), periodicity, type of PRS (e.g., periodic, semi- persistent, or aperiodic), slot offset for periodic transmission for PRS, vertical shift of PRS pattern in the frequency domain, time gap during repetition, repetition factor, RE (resource element) offset, comb pattern, comb size, spatial relation, QCL information (e.g., QCL target, QCL source) for PRS, number of PRUs, number of TRPs, Absolute Radio-Frequency Channel Number (ARFCN), subcarrier spacing, expected RSTD, uncertainty in expected RSTD, start Physical Resource Block (PRB), bandwidth, BWP ID, number of frequency layers, start / end time for PRS transmission, on / off indicator for PRS, TRP ID, PRS ID, cell ID, global cell ID, PRU ID, and / or applicable time window. A WTRU 102 may apply a PRS configuration under a condition that the current time is within the applicable time window.

[0175] Configurations for SRS for Positioning

[0176] In certain representative embodiments, a SRS for positioning (SRSp) and / or a SRS configuration may include information indicating at least one of: resource ID; comb offset values, cyclic shift values; start position in the frequency domain; number of SRSp symbols; shift in thefrequency domain for SRSp; frequency hopping pattern; type of SRSp (e.g., aperiodic, semi- persistent or periodic); sequence ID used to generate SRSp, or other IDs used to generate SRSp sequence; spatial relation information, indicating which reference signal (e.g., DL RS, UL RS, CSI-RS, SRS, DM-RS) or SSB (e.g., SSB ID, cell ID of the SSB) the SRSp is related to spatially where the SRSp and DL RS may be aligned spatially; QCL information (e.g., a QCL relationship between SRSp and other reference signals or SSB); QCL type (e.g., QCL type A, QCL type B, QCL type C, QCL type D); resource set ID; list of SRSp resources in the resource set; transmission power related information; pathloss reference information which may contain index for SSB, CSI- RS or PRS; periodicity of SRSp transmission; and / or spatial information, such as spatial direction information of SRSp transmission (e.g., beam information, angles of transmission) and / or spatial direction information of DL RS reception (e.g., beam ID used to receive DL RS, angle of arrival).

[0177] Measurements

[0178] In certain representative embodiments, a WTRU and / or gNB may perform timing-based measurements.

[0179] For example, a RSTD may be defined by the difference in time of arrival between PRSs transmitted from a reference TRP and a target TRP. The WTRU 102 may be configured with the reference TRP index and target TRP index. The WTRU 102 may be configured with the PRS resource indices to make measurements. The WTRU 102 may determine the time of arrival from the (e.g., target) TRP based on one or more PRS resources associated with the (e.g., target) TRP. In another example, the RSTD may be defined as the difference in time of arrival between the reference PRS transmitted from a TRP and a target PRS transmitted from a TRP.

[0180] For example, a “UE Rx - Tx time difference” may refer to the difference between an arrival time of a reference signal transmitted by a TRP and a transmission time of the reference signal transmitted from a WTRU 102. The WTRU Rx-Tx time difference may be associated with a PRS resource ID and / or a SRSp resource ID.

[0181] In certain representative embodiments, a WTRU and / or gNB may perform phase-based measurements.

[0182] For example, a RSCP (RS Carrier Phase) may be defined as the carrier phase measurement on a PRS. A RSCP Difference (RSCPD) may be defined as the difference in carrier phase measurements between two PRS resources.

[0183] In certain representative embodiments, a WTRU and / or gNB may perform power-based measurements. For example, a RSRP per path may be defined as the RSRP per path if the WTRU 102 observes a multipath channel in the measurement. The WTRU 102 may determine a RSRP for a DL RS resource. RSRP or RSRPP may be reported using units dBm and / or a relative power difference compared to a reference (e.g., RSRP of the first path, such as in dB).

[0184] In certain representative embodiments, a WTRU and / or gNB may perform impulse response-based measurements. Channel impulse response (CIR) may be associated with a RS configuration.

[0185] For example, a channel impulse response (e.g., for N paths) may be defined by the following equation h(t) = / ik(t)<5(t — Tfc) where / ik(t) and Tkare time-varying complex valued coefficients (e.g., expressed by a + bj where j =for the channel impulse response and delay, measured in seconds, for the kthpath, respectively). The delta function is defined as <5(t) = 1 for t = 0 and <5(t) = 0 for t0. For the sake of simplicity, we assume the coefficients are constant over time (e.g., hk(t) = hk). The WTRU 102 may report hkand Tkfor each path k to the network. The WTRU 102 may report the number of paths, N, to the network. Alternatively, the WTRU 102 may receive hkand Tkfor each path k from the network and / or the number of paths.

[0186] For example, the WTRU 102 may obtain CIR from the network. The network may indicate PRS configuration(s) such as PRS resource IDs associated with the CIR. For example, the CIR may be associated with a resource ID. In this case, the WTRU 102 may determine that the CIR is derived based on the measurements made on the PRS resource associated with the ID. Alternatively, the WTRU 102 may determine that the channel along the direction of transmission of the PRS or reception of the PRS corresponds to the CIR.

[0187] For example, CIR may be associated with a TRP ID. In this case, the WTRU 102 may determine that the CIR represents the channel between the TRP and WTRU 102.

[0188] For example, CIR may be associated with more than one TRP or PRS resource ID. In this case, the WTRU 102 may determine that the channel between the TRPs and the WTRU 102 corresponds to the CIR. Alternatively, the WTRU 102 may determine that the channel along the transmission directions of PRSs associated with IDs or reception directions of the PRS correspond to the CIR.

[0189] For example, more than one CIR may be associated with one parameter from the PRS configurations (e.g., TRP ID, PRS resource ID, frequency layer ID). For example, the WTRU 102 may receive information related to 2 CIRs associated with a TRP from the network (e.g., / ix(t) =— T1(k)and h2(t)=Sfc=i h2ik(.t)8(t — T2, / C) from the network). Alternatively, the WTRU 102 may report information related to more than one CIR associated with the PRS configuration (e.g., TRP ID, PRS resource ID) based on the measurements to the network. There can be more than one CIR associated with a PRS configuration since the WTRU 102 or network may observe different channel characteristics based on AoA of DL RS or UL RS, for example.

[0190] In some embodiments, a CIR may be represented by a delay profile or power delay profile. A power delay profile may be defined as a set of delays and power profiles, such asand [Po’ Pi’ "’ ’ PN-IL where pkmay corresponds to relative power at the kthpath compared to the first path. A delay profile may be defined as a set of delays [T0, T1(• •• , TW-X] which indicates path delay for each path above Pthreshoid- The WTRU 102 may receive Pthreshoid from the network to derive a delay profile from a power delay profile.

[0191] For example, the WTRU 102 may receive an indication from the network on how to generate CIR, PDP and / or DP based on timing, phase and / or power measurements. In one example, the WTRU 102 may send a request to the network to receive an indication on which methodologies to use to generate CIR, Power Delay Profile (PDP) and / or Delay Profile (DP) based on the measurements the WTRU 102 made. For example, the WTRU 102 may receive a message from the network (e.g., via LPP, RRC, MAC-CE, DCI) indicating the PRS resource indices and associated measurement type(s) (e.g., RSTD, AOA) to use to generate CIR, PDP and / or DP. In one example, the WTRU 102 may receive an indication from the network indicating to generate CIR, PDP and / or DP.

[0192] In certain representative embodiments, a WTRU 102 may send measurements in a report to the network (e.g., LMF, gNB) via a semi-static (e.g., LPP, RRC) or dynamic message (e.g., UCI, UL MAC-CE).

[0193] As used herein, the phrases “PRS”, DL-RS (e.g.., CSLRS, DM-RS, TRS) and SSB may be used interchangeably.

[0194] In certain representative embodiments, a WTRU may acquire a CIR from the network.

[0195] For example, a WTRU 102 may receive CIR, PDP and / or DP from the network, based on the reported measurements. For example, the WTRU 102 may receive a request from the network for measurements. The request may indicate a positioning method (e.g., DL TDOA) with which the WTRU 102 determines required measurements (e.g., RSTD for DL-TDOA). The WTRU 102 may report the measurements to the network. The WTRU 102 may receive CIR from the network based on the measurements reported by the WTRU 102.

[0196] For example, the WTRU 102 may include information related to PRS configuration in the measurement report (e.g., PRS resource IDs). The WTRU 102 may receive, from the network, at least of the reported PRS resource IDs associated with the CIR obtained from the network.

[0197] For example, the WTRU 102 may receive a request to report the measurements periodically at the configured periodicity. In another example, the WTRU 102 may report measurement aperiodically. In another example, the WTRU 102 may be configured to report in a semi-persistent manner, such as periodic reporting during a configured duration or time window. The WTRU 102 may be configured with a starting time and end time (e.g., absolute time, symbolindex, slot index, frame index, SFN). The WTRU 102 may be configured with a duration in terms of the number of symbols, slots, frames, subframes, milliseconds or other transmission time intervals (TTIs).

[0198] For example, a WTRU 102 may determine to activate or deactivate semi-persistent reporting or semi-persistent measurement (e.g., making measurements during a time window) based on signaling from the network (e.g., MAC-CE). In another example, a WTRU 102 may determine that semi-persistent PRS transmission or SRSp transmission is activated or deactivated by the network based on signaling (e.g., MAC-CE).

[0199] For example, a WTRU 102 may send a request to the network for periodic assistance information (e.g., containing CIR) or aperiodic assistance information. In the WTRU’s request, the WTRU 102 may include information indicating any of the following: (i) PRS configuration (e.g., TRP ID, PRS resource ID) to request CIR, DP or PDP associated with the indicated PRS configuration; (ii) a maximum and / or minimum number of taps for CIR, DP and / or PDP; (iii) requested / needed CIR, DP and / or PDP; and / or (iv) requested periodicity or duration of provisioning of CIR, DP and / or PDP from the network.

[0200] For example, the WTRU 102 may be requested by the network to report CIR, DP and / or PDP. The WTRU 102 may determine CIR, DP and / or PDP based on the measurements made on configured PRSs. In the request, the WTRU 102 may receive from the network information indicating any of the following: (i) a PRS configuration (e.g., TRP ID, PRS resource ID) where the network requests for CIR, DP or PDP associated with the indicated PRS configuration; (ii) the maximum and / or minimum number of taps for CIR, DP, and / or PDP; (iii) requested / needed CIR, DP and / or PDP; and / or (iv) periodicity and / or duration of reporting of CIR, DP and / or PDP from the WTRU 102.

[0201] In certain representative embodiments, a WTRU 102 may determine to send a request for CIR, DP and / or PDP, and / or determine CIR, DP and / or PDP based on the channel conditions. For example, if the hard or soft LOS indicator associated with a PRS resource or TRP is NLOS, or below a configured threshold, the WTRU 102 may determine to send a request for CIR, DP and / or PDP from the network. In another example, if a condition (e.g., the hard or soft LOS indicator associated with a PRS resource or TRP is NLOS, or below a configured threshold) is satisfied, the WTRU 102 may determine CIR, DP and / or PDP based on the measurements made by the WTRU 102.

[0202] Contents of Measurement and Location Reporting

[0203] In certain representative embodiments, a WTRU 102 may receive a request (e.g., from the network) to report its location and / or measurements (e.g., made on a PRS). The WTRU 102 may report (e.g., a measurement report to the network) information indicating any of the following:(i) PRS ID; (ii) TRP ID; (iii) Cell ID; (iv) ARFCN; (v) PRS Resource ID(s); (vi) PRS Resource Set ID(s); (vii) Frequency layer ID(s); (viii) Timestamp indicating when the measurements are made or when the report is made; (ix) RSTD associated with PRS resource ID(s) for each path in a multipath; (x) RSRP associated with PRS resource ID(s) for each path in a multipath; (xi) Phase measurement (e.g., RSCP, RSCPD) for each path in a multipath; (xii) Uncertainty information (e.g., expressed in terms of a range such as ±2 us) for measurements; (xiii) Quality information (e.g., indicating whether the indicated measurement is in the unit of 0.1 us or O.Olus) for measurements; (xiv) TEG (timing error group) associated with measurements, PRS resource ID, and / or PRS resource set ID; (xiv) LOS indicator associated with PRS resource ID and / or TRP ID; (xv) WTRU location (e.g., absolute location with geographical coordinates expressed by x and y coordinates, relative location with respect to a reference point, such as TRP, cell center), such as upon network request; (xvi) Uncertainty information for the determined WTRU location (e.g., expressed in terms of a range such as ±2 meter) and / or quality information (e.g., indicating whether the indicated WTRU location is in the unit of 0.1 meter or 0.01 meter); (xvii) the method is used to determine the WTRU location; (xviii) Channel impulse response and associated DL-RS configurations used to determine CIRs; and / or (xix) Information related to AI / ML model(s) (e.g., association information) used to determine WTRU location.

[0204] Artificial Intelligence (Al) for Positioning

[0205] In certain representative embodiments, an Al model may be used by a WTRU to determine its position.

[0206] In certain representative embodiments, a ML model may be used by a WTRU to determine its position.

[0207] As described herein, the phrase “AI / ML model” may be used interchangeably with “Al model” and “ML model”.

[0208] Al for positioning : Inputs, Outputs, Association

[0209] In certain representative embodiments, an AI / ML model may be used to obtain a WTRU location. FIG. 3 is a block diagram illustrating an example of using an AI / ML model 300 to estimate a WTRU location. As shown in FIG. 3, a WTRU may provide the AI / ML model 300 with inputs, such as measurements (e.g., timing, phase, power measurements such as RSTD, time of flight, ToA, ToD, carrier phase measurement, carrier phase difference measurement, RSRP, RSRP per path), and the WTRU 102 may obtain the WTRU location from an output of the AI / ML model 300. The output of the AI / ML model 300 may be referred to as an “inference.”

[0210] For example, as an input to the AI / ML model 300, if the AI / ML model 300 is associated with or trained with measurements from multiple TRPs, the WTRU 102 may use measurements made from more than one TRP, or associated TRPs as the input to the AI / ML model 300. If theAI / ML model 300 is trained with measurements from more than one TRP, the WTRU 102 may receive an indication or configuration from the network about identification information about the TRPs (e.g., TRP IDs, PRS IDs) the AI / ML model 300 is trained with.

[0211] For example, a WTRU 102 may receive an indication from the network that an AI / ML model 300 is trained with measurements from one TRP and the WTRU 102 may receive an indication from the network about identification information of the associated TRP.

[0212] In certain representative embodiments, inputs for an AI / ML model 300 (e.g., for positioning) may include information indicting any of the following: (i) RSRP of PRS resource(s); (ii) Statistical measure of RSRP (e.g., mean, variance etc.) per PRS resource(s); (iii) Maximum or minimum value of RSRP per PRS resource(s); (iv) RSRP of PRS resource(s) per path; (v) RSRP of PRS resource(s) per antenna port; (vi) RSCP of PRS resource(s) per path; (vii) RSCP of PRS resource(s) per antenna port; (viii) RSTD and / or RSCPD of PRS resource(s); (ix) Statistical measure of RSTD per PRS resource(s); (x) Maximum or minimum value of RSTD per PRS resource(s); (xi) RSTD and / or RSCPD of PRS resource(s) per path; (xii) RSTD and / or RSCPD of PRS resource(s) per antenna port; (xiii) Time of arrival per PRS resource(s); (xiv) Time of arrival per PRS resource(s) per path; (xv) Time of arrival per PRS resource(s) per port; (xvi) Statistical measure of Time of arrival per PRS resource(s); (xvii) Maximum or minimum value of time of arrival per PRS resource(s); (xviii) CIR estimated based on DL-RS(s) (e.g., PRS, CSI-RS, DM- RS) where CIR may be associated with a TRP or TRPs; (xix) PDP estimated based on DL-RS(s) (e.g., PRS, CSLRS, DM-RS) ) where CIR may be associated with a TRP or TRPs; and / or (xx) DP estimated based on DL-RS(s) (e.g., PRS, CSLRS, DM-RS) ) where CIR may be associated with a TRP or TRPs.

[0213] In certain representative embodiments, masking of inputs may be performed.

[0214] For example, an inference can be performed by inputting a subset of measurements to one or more AI / ML models 300 while masking (e.g., inputting 0 or NULL values) any remaining measurement(s). The WTRU 102 may receive a minimum number of CIR measurements to be inputted to the AI / ML model 300 for inference.

[0215] For example, an AI / ML model 300 may allow a WTRU 102 to mask a subset of CIR measurements (e.g., reporting only a first N path for a CIR measurement and masking the remaining paths of the same measurement). Due to a one-to-one mapping between an acceptable CIR measurement and model input dimension (e.g., number of acceptable CIR measurements to the AI / ML model 300 is the same as the number of CIR measurements simultaneously inputted to the AI / ML model), the WTRU 102 may not provide the PRS resource set number as an input to the AI / ML model. The WTRU 102 may receive additional validity conditions along with the trained AI / ML model 300. Examples of these validity conditions include: (i) Present minimum N(e.g., N=3 CIR measurements) CIR measurements; (ii) Present minimum X (e.g., X= 128 paths) paths for each CIR measurements; and / or (iii) Present CIR measurements associated with a PRS set whose PRS-RSRP is above a threshold.

[0216] For example, the input dimension of an AI / ML model 300 may be smaller than an acceptable set of CIR measurements. In such situations, a WTRU 102 may input a PRS resource ID along with the CIR measurements when performing an inference operation. The WTRU 102 may present or mask measurements based on validity conditions received along with the trained AI / ML model 300.

[0217] For example, the WTRU 102 may receive a masking pattern from the network, indicating which measurements to use as inputs for the AI / ML model 300 for generating an inference. The masking pattern may be part of a PRS configuration or an AI / ML related configuration. For example, the AI / ML model 300 may require CIR estimates from N TRPs where each CIR may be associated with one TRP. The WTRU 102 may receive a masking pattern from the network, indicating which CIRs to use. For example, if N=3, the WTRU 102 may have 3 CIRs, each corresponding to a respective TRP. The WTRU 102 may receive a masking pattern or bitmap indicating to use certain CIRs (e.g.,

[0110] corresponding to TRP1 and TRP2). The WTRU 102 may replace the CIR as indicated (e.g., for TRP3) with 0 or null as an input to the AI / ML model 300.

[0218] FIG. 4 is a block diagram illustrating an example hierarchical structure of PRS configurations. As shown in FIG. 4, PRS parameters may be organized in a hierarchical manner 400. Parameters associated with a higher layer may be used by parameters at lower layer(s). For example, if a frequency layer has a parameter value of “comb factor = 2”, PRS resource sets, TRPs and PRS resources under the frequency layer may also use the parameter value of “comb factor =2.” The parameters may be organized in a hierarchical manner 400 to reduce signaling overhead from the network.

[0219] In certain representative embodiments, an AI / ML model may be associated with a higher- layer parameter or first parameter. A WTRU 102 may determine that the AI / ML model may be applicable to any parameters at lower level compared to the first parameter. The WTRU 102 may receive configurations about an AI / ML model from the network. For example, the AI / ML model may be associated with frequency layer #1. The WTRU 102 may determine that the parameters associated with the frequency layer #1 may also be associated with the AI / ML model. Thus, the WTRU 102 may determine to use measurements obtained from the TRPs which transmit PRSs with or using frequency layer #1 as an input to the AI / ML model to obtain the WTRU location.

[0220] In certain representative embodiments, a WTRU 102 may determine association between a configuration parameter (e.g., TRP ID) and an AI / ML model explicitly (e.g., via model ID) orimplicitly. For example, if the WTRU 102 receives an indication from the network to use AI / ML- based positioning based on a TRP configuration, the WTRU 102 may (e.g., implicitly) determine an AI / ML model to use based on the TRP configuration (e.g., TRP ID indicates which model the WTRU 102 should use).

[0221] In certain representative embodiments, a WTRU 102 may be configured with an association between an AI / ML model and one or more RS configurations. For example, the configurations may include one or more parameters of PRS and / or SRS. The WTRU 102 may determine the AI / ML model for inference and / or performance monitoring and / or verification based on the active RS configuration.

[0222] In certain representative embodiments, an association between a configuration and a model indicates inputs the WTRU 102 should use for the AI / ML model. For example, if an AI / ML model is associate with TRP ID #1, TRP ID #2 and TPR ID#3, the WTRU 102 may determine to use the measurements made on PRSs transmitted from the TRP ID #1, TRP ID #2 and TPR ID#3 as an input to the AI / ML model to obtain an inference.

[0223] In certain representative embodiments, a WTRU 102 may be configured with an AI / ML model where the model is trained with measurements from one TRP and the model is associated with a cell. This indicates that the model may be used anywhere in the cell and the WTRU 102 needs to input measurements from one TRP from the cell to obtain the WTRU location.

[0224] In certain representative embodiments, an AI / ML model may be associated with at least one or combination of the following: (i) Parameter(s) in PRS configuration (e.g., PRS ID, cell ID, TRP ID, frequency information such as frequency layer ID, ARFCN); (ii) Param eter(s) in SRS or SRSp configuration (e.g., SRS sequence ID); (iii) Cell ID; (iv) Area which may be defined by more than one cell IDs and area may be associated with an ID, such as area ID; (v) multiple TRPs or cell IDs indicating that the AI / ML model can be used with the measurements made on the associated TRPs or cell IDs; (vii) ID related to RS or signals (e.g., CSLRS ID, DM-RS ID, SSB ID); (viii) Input information and / or type thereof; (ix) Output information and / or type thereof; (x) Model version information; (xi) Model format information and / or type thereof; (xii) AI / ML capability (e.g., AI / ML positioning, AI / ML beam management) which may be defined at finer granularities (e.g., AI / ML direct positioning, AI / ML assisted positioning, AI / ML spatial domain beam prediction, AI / ML temporal domain beam prediction, etc.); (xiii) Vendor information (e.g., vendor ID); (xiv) Applicable scenario and / or configuration (e.g., frequency range, antenna configuration, site information, cell ID, etc. in which AI / ML model is applicable for inference, based for example on matching with the training scenario); (xv) Computational complexity (e.g., FLOPs, level of pre- / post- processing that may be needed before deploying the model and / or before using the model for inference); (xvi) Complexity (e.g., number of real-value modelparameter, number of real-value operations for the model, number and / or ID representing model complexity in terms of any of the aforementioned parameters); (xvii) Size (e.g., fixed sizes associated to some models, <5 MB, < 50 MB, < 100 MB, etc.); (xviii) Performance metric (e.g., accuracy, bias, variance and / or number / ID associated to any thereof); (xix) Functionality and / or sub-functionality and / or use case and / or sub use case (e.g., what (sub) functionality and / or (sub) use cases are applicable for a specific model, such as CSI / BM / positioning); (xx) What types are applicable to a specific model (e.g., UE-sided model, UE-part of a two-sided model, such as encoder at UE, decoder at gNB for a CSI compression use case); and / or (xxi) Model monitoring method.

[0225] In certain representative embodiments, any of the parameters may be included as part of the model ID and / or transmitted to the WTRU 102 and / or network as part of model metadata. In certain other embodiments, such information may be inherently known to the other termination point (e.g., due to the association between specific models and specific parameters).

[0226] In certain representative embodiments, model switching may be completely visible to the network, such as where the WTRU 102 may inform the network of the model ID of the model it switched to.

[0227] In certain representative embodiments, model switching may be partially visible to the network, such as where the WTRU 102 may send an indication to the network that there has been a switch without necessarily including the model ID of the target model. This may be applicable for functionality-based LCM. If the network is doing performance monitoring of UE-side models, the network may send an indication to the WTRU 102 of poor performance (e.g., based on low throughput measured at the network, inaccurate location estimate). This indication may trigger the WTRU 102 to switch to a different model to improve performance. Following the switch, the WTRU 102 may indicate a simple switch indication to the network without model ID. For example, the WTRU 102 may only provide to the network the information at the functionality level. For example, the WTRU 102 may transmit to the network a functionality ID and / or indicate a specific functionality to the network as part of an initial capability exchange (e.g., the WTRU 102 may indicate in RRC that it has AI / ML capability for positioning and / or the WTRU 102 may transmit a functionality ID associated to AI / ML positioning capability). The WTRU 102 may have multiple models associated to the AI / ML positioning capability but any switch within those models may not be indicated to the network (e.g., model switching within the functionality is transparent to the NW). If none of the models at the WTRU 102 has a good enough performance and the WTRU 102 has to fallback to legacy procedures, the WTRU 102 may then send an indication to the network that it has fallen back to the legacy (e.g., non- AI / ML such as GNSS, RAT dependent positioning method, WiFi or sensor based positioning method) procedure for that functionality.Such model switching transparent to the network may also be applicable if the performance monitoring is at the UE. For example, the WTRU 102 may determine that the performance of a specific model is below a preconfigured threshold and switch to another model within a functionality. For functionality -based LCM, the WTRU 102 may not report any model switch within a functionality or the WTRU 102 may simply send a switch indication to the network without including the model ID of the target model.

[0228] In certain representative embodiments, a WTRU 102 may receive configuration information for an AI / ML model (e.g., a configuration associating a model with PRS configuration). For example, the WTRU 102 may receive an association between a PRS configuration (e.g., TRP ID) with an AI / ML model. The WTRU 102 may receive, from the network, CIR, DP and / or PDP associated with the TRP, for example.

[0229] Availability of Models at WTRU

[0230] In certain representative embodiments, a WTRU 102 may be preconfigured or configured with multiple AI / ML models. The WTRU 102 may have more than one model associated with different combinations of PRS configurations, or general configurations. The WTRU 102 may be configured with AI / ML models where each AI / ML model may be associated with a different PRS configuration.

[0231] FIG. 5 is a block diagram illustrating an example association between an AI / ML model and PRS configuration information. As shown in FIG. 5, a first (e.g., high-level) AI / ML model may be associated with a frequency layer (e.g., an AI / ML model is associated with a frequency layer ID#1) and / or a second (e.g., low-level) AI / ML model may be associate with a TRP (e.g., an AI / ML model is associated with a TRP ID#1). The WTRU 102 may be configured with N AI / ML models under frequency layer #1 where each model is associated with a TRP (e.g., AI / ML model #1 with TRP #1, AI / ML model #2 with TRP #2, etc.). The WTRU 102 may be configured to make measurements on PRSs transmitted from N TRPs.

[0232] For example, the WTRU 102 may be configured with criteria (e.g., highest RSRP) to determine which AI / ML model to use based on the measurements. For example, the WTRU 102 may determine to use one or more AI / ML models associated with the configured PRS parameters. The WTRU 102 may determine to report information regarding the AI / ML model (e.g., model ID) and / or PRS configuration associated with the model (e.g., TRP ID).

[0233] For example, the WTRU 102 may indicate to the network whether more than one AI / ML model is used or not. For example, the WTRU 102 may report, along with the determined WTRU location, (e.g., to the network) information indicating multiple AI / ML model (e.g., more than one AI / ML model IDs) and / or multiple PRS configuration parameters where each parameter is associated with an AI / ML model. In another example, the WTRU 102 may indicate to the network,along with its determined WTRU location, whether a single or multiple AI / ML models is / are used or not to determine the WTRU location.

[0234] For example, a WTRU capability may indicate the type(s) of AI / ML models or AI / ML model(s) or availability of AI / ML model(s) at the WTRU 102. In one example, the WTRU 102 may send an indication to the network, indicating association of AI / ML model(s) available at the WTRU 102 with PRS configurations. For example, the WTRU 102 may indicate to the network that the WTRU 102 has two AI / ML models where each model is associated with PFL#1 and PFL#2, respectively. In another example, a WTRU 102 may indicate to the network that the WTRU 102 has two AI / ML models where each model is associated with cell#I and cell#2, respectively. The WTRU 102 may indicate to the network that it is capable of training an AI / ML model that can be associated with a TRP and / or a cell. In another example, the WTRU 102 may indicate to the network that the AI / ML model is capable of using positioning measurements as its input to generate an inference (e.g., WTRU location).

[0235] In certain representative embodiments, a WTRU 102 may determine to send WTRU capability and / or assistance information to the network to indicate the AI / ML model(s) at the WTRU 102. For example, the WTRU 102 may send an indication to the network about level(s) of association of AI / ML model(s) the WTRU 102 can train. For example, the WTRU 102 may indicate to the network that the WTRU 102 can train an AI / ML model associated with a cell. In this case, the WTRU 102 may train AI / ML models using the measurements obtained from PRSs transmitted from TRPs within the serving cell and / or neighboring cell(s). The WTRU 102 may indicate that the AI / ML model is associated with at least one of the PRS configuration parameters (e.g., frequency layer). In this case, the WTRU 102 may train the AI / ML model using the measurements obtained from PRSs associated with the configured frequency layer(s).

[0236] In certain representative embodiments, a WTRU 102 may have AI / ML models where the AI / ML models are preconfigured and / or configured by the network. For example, the WTRU 102 may determine one or more AI / ML models from preconfigured weights. The WTRU 102 may send a request to the network to receive weights or parameters associated with the AI / ML model(s). The WTRU 102 may indicate a type of an AI / ML model (e.g., AI / ML model that can be associated with a cell, TRP, etc.).

[0237] For example, the WTRU 102 may indicate to the network (e.g., via WTRU capability and / or assistance information) the location(s) at which the AI / ML models at the WTRU 102 are trained. Location information associated with the AI / ML models may include any of the following: (i) absolute or relative locations of the WTRU 102 at which AI / ML models are trained, (ii) locations of TRPs whose PRSs are used for training, (iii) TRP IDs, (iv) cell IDs, (v) area ID, and / or (vi) zone ID. For example, zone IDs or area IDs may be configured and / or preconfigured by thenetwork. In another example, the WTRU 102 may indicate area information in which PRSs are received for training.

[0238] For example, the WTRU 102 may indicate a completion level of the training and / or number of training data that the AI / ML model is trained with to the network.

[0239] In certain representative embodiments, a WTRU 102 may be hardcoded, preconfigured or programmed with AI / ML models. For example, the WTRU 102 may have weights in its memory and the WTRU 102 may be able to adjust the weights so that after training using ground truths and measurements, the AI / ML model can yield desired outputs. In another example, the weights may be hardcoded. In another example, the WTRU 102 may receive configurations (e.g., weights) from the network. The receipt of the configurations may only happen at a configured event (e.g., when the WTRU 102 connects to the network for the first time, and / or when the WTRU 102 transitions from IDLE to CONNECTED).

[0240] In certain representative embodiments, a single AI / ML model may not be generalized for all possible scenarios, conditions, and / or configurations that the WTRU 102 may be expected to operate. In such cases, the WTRU 102 may have more than one AI / ML model for any AI / ML enabled feature and / or functionality, wherein each AI / ML model may be associated with an applicable condition. For example, a first set of models may be preconfigured and / or pre-loaded in the WTRU 102. For example, a second set of models may be downloaded by the WTRU 102 from the network and / or an external server. For example, the WTRU 102 may have a third set of models which may be a result of fine-tuning and / or updating of the first set and / or second set of models.

[0241]

[0242] General Procedure

[0243] FIG. 6 is a signaling diagram illustrating an example of communications for WTRU- based AI / ML positioning. In FIG. 6, a WTRU 102 may communicate with a gNB 180 and a LMF 600 (e.g., in CN 106 / 115).

[0244] As shown in FIG. 6, a WTRU 102 may determine to send at 602 WTRU capability information to the network, such as information indicating available AI / ML model(s) at the WTRU 102. The WTRU 102 may receive one or more PRS configurations from the network at 604. The WTRU 102 may receive a request from the network to perform positioning using AI / ML model(s) at the WTRU 102 at 606.

[0245] Based on availability of the AI / ML models at the WTRU 102, the WTRU 102 may send at 608 to the network an acceptance or rejection message (e.g., ACK / NACK), indicating the WTRU 102 can or cannot perform AI / ML-based positioning respectively. The models may be available at the WTRU 102 under any of the following conditions: (i) the WTRU 102 receives theparameters for the AI / ML models from the network; and / or (ii) the WTRU 102 is configured and / or preconfigured with the AI / ML models and the training for the AI / ML models are completed at a preconfigured level (e.g., 50%, 90%, yields configured level of accuracy).

[0246] For example, if the WTRU 102 is capable of determining its location using the AI / ML model(s) at the WTRU 102, the WTRU 102 may determine to make measurements (e.g., CIR) at 612 on the received PRS at 610. Based on the measurements, the WTRU 102 may report at 616 its location to the network, along with uncertainty information (e.g., range indicating the fluctuation in determined location).

[0247] In certain representative embodiments, in a first step, the WTRU 102 may use an AI / ML model to determine the WTRU location. The WTRU 102 may be preconfigured and / or configured with an AI / ML model. The WTRU 102 may train the AI / ML model at the WTRU 102 and use the model. The AI / ML model may be associated with configurations (e.g., cell, TA, PFL, and / or PRS configuration). The WTRU 102 may determine, based on measurements and / or assistance information from the network, the AI / ML model at the WTRU 102 may need to be turned off or deactivated. The WTRU 102 may determine to switch to a model which may be associated with a different configuration based on a condition (e.g., configuration such as PRS configuration, measurements). The WTRU 102 may send an indication to the network indicating information about the new model (e.g., model ID, association information). If the WTRU 102 falls back to a fallback positioning method, the WTRU 102 may indicate to the network that the fallback positioning method is used.

[0248] For example, a WTRU 102 may be using a first model “model-1.” One or more conditions may change (e.g., WTRU 102 moving to a new cell, PRS change, TA change, PFL change). The WTRU 102 may determine that model-1 is not satisfactory (e.g., based on model performance monitoring). The WTRU 102 may obtain information for selecting a different model. The WTRU 102 may select a model if some criteria are satisfied (e.g., model switching and / or selection conditions) or otherwise fallback. The WTRU 102 may send information indicating a change in the model or fallback (e.g., including indicating a model ID, functionality ID, and / or the association to an applicable condition).

[0249] Model ID and its Relationship to Configuration

[0250] In certain representative embodiments, a model ID may be associated with a PRS configuration.

[0251] For example, a model ID may be used to identify an AI / ML model. The WTRU 102 may be configured and / or indicated with a model ID by the network (e.g., gNB, LMF). A model ID may be associated with a logical AI / ML model or a physical AI / ML model. In a first example, the models may be identified based on offline collaboration between the WTRU 102 and the network.In a second example, the models may be identified based on over the air signalling between the WTRU 102 and the network. For example, the over the air signalling maybe initiated by the WTRU 102 or the network.

[0252] In certain representative embodiments, model ID-based LCM may be used. In certain representative embodiments, functionality-based LCM may be used. For example, one more AI / ML models may be abstracted with a functionality within an AI / ML-enabled feature. For example, a functionality ID and / or a configuration ID may be used in place of a model ID. In certain representative embodiments, any of a functionality ID, a configuration ID, and / or a model ID may be used (e.g., to identify an AI / ML model).

[0253] For example, a WTRU 102 may be preconfigured and / or configured with a set of PRS configuration parameters associated with a model ID.

[0254] For example, a WTRU 102 may determine from an association rule that a model ID #N is associated with a PRS frequency layer ID #1 (e.g., with a bandwidth of 100MHz). Thus, the WTRU 102 may determine to make measurements on the PRS associated with the PRS frequency layer ID #1 and use the measurements (e.g., timing, power, carrier phase) as an input for the AI / ML model with model ID #N to determine the WTRU location which is the output of the AI / ML model.

[0255] For example, the WTRU 102 may determine from an association rule that a model ID #N is associated with TRP IDs #1, #2 and #3 with a frequency layer ID #1. The WTRU 102 may determine to make measurements on any PRSs transmitted from the TRPs with IDs #1, #2 and #3 and use measurements thereof as an input for the AI / ML model with the model ID #N to determine the WTRU location which is the output of the AI / ML model.

[0256] For example, the WTRU 102 may determine from an association rule that a model ID #N is associated with a cell ID #1. The WTRU 102 may determine to make measurements on any PRSs transmitted in a cell with ID #land use measurements thereof as an input for the AI / ML model with the model ID #N to determine the WTRU location which is the output of the AI / ML model.

[0257] For example, the WTRU 102 may receive an indication from the WTRU 102 to change the model that is associated with a PRS configuration. For example, the WTRU 102 may be preconfigured with an AI / ML model with ID #1 with a PRS frequency layer ID #1. The WTRU 102 may receive a configuration message (e.g., RRC message, LPP message) from the network to associate the AI / ML model with an ID #2 with a frequency layer ID #1. The WTRU 102 may receive AI / ML model parameters (e.g., weights) for the AI / ML model with ID #2 from the network. Alternatively, the WTRU 102 may determine to associate the AI / ML model with ID #2, which is preconfigured at the WTRU 102, to frequency layer ID #1.

[0258] FIG. 7 is a signaling diagram illustrating an example of communications for updating an association between an AI / ML model and a PRS configuration.

[0259] As shown in FIG. 7, a WTRU 102 indicates the availability of AI / ML models at the WTRU 102 to the LMF in a first message at 704. The LMF indicates to the WTRU 102 an association between an AI / ML model and a PRS configuration in a second message at 704. In a third message, the LMF indicates to the WTRU 102 an update of the association between the AI / ML model and the PRS configuration at 706. As the response for the second message, the WTRU 102 may indicate to the network that the update of the association is complete at 708. The WTRU 102 may need to send the response since the WTRU 102 may need to determine whether the newly associated AI / ML model is trained and ready for use. After (e.g., the third message), the network may send the parameters (e.g., weights) for the newly associated AI / ML model to the WTRU 102.

[0260] In certain representative embodiments, multiple model IDs may be associated with a PRS configuration.

[0261] For example, multiple model IDs may be associated with a PRS configuration(s). The WTRU 102 may be preconfigured with such association information. In another example, the WTRU 102 may receive a configuration message associating the model IDs to the PRS configuration(s).

[0262] For example, one PRS configuration may be associated with multiple model IDs. For example, model IDs #N1, #N2 and #N3 may be associated with a cell ID #1.

[0263] For example, a set of PRS configurations may be associated with multiple model IDs. For example, TRP IDs #1, #2 and #3 with frequency layer ID #1 may be associated with model IDs #N1, #N2 and #N3.

[0264] After a WTRU 102 is configured with multiple AI / ML models, the WTRU 102 may determine which model to use based on at least one configured criterion.

[0265] In certain representative embodiments, a WTRU 102 may determine which AI / ML model to use implicitly and / or based on an explicit message.

[0266] For example, the WTRU 102 may determine which model to use based on configured PRS parameters. For example, the WTRU 102 may receive a request or configuration message to use an indicated AI / ML model for positioning.

[0267] For example, the WTRU 102 may indicate the availability of AI / ML models at the WTRU 102 to the network. Availability of an AI / ML model at the WTRU 102 may be indicated as “yes” or “no”. In another example, the WTRU 102 may indicate the PRS configuration(s) in the message to indicate the WTRU 102 has AI / ML models associated with the indicated PRS configurations.

[0268] For example, the WTRU 102 may receive a request from the network to perform AI / ML positioning. The request may indicate the PRS configuration to which the AI / ML model used for positioning should be associated with. For example, the WTRU 102 may receive a request from the network to use AI / ML positioning and the request may include a frequency layer ID #1. This may indicate that the WTRU 102 should use the AI / ML model associated with the frequency layer ID #1.

[0269] For example, the WTRU 102 may receive a request to perform AI / ML positioning using a model that the WTRU 102 does not have. For example, the WTRU 102 may receive a request to use AI / ML positioning associated with the serving cell with a cell ID#1, for example. The WTRU 102 may not have an AI / ML model that is associated with the serving cell. In this case, the WTRU 102 may determine to initiate training of an AI / ML model that can be used for the serving cell by performing measurements on PRSs.

[0270] FIG. 8 is a signaling diagram illustrating an example of communications for initiating AI / ML-based positioning. As shown in FIG. 8, in a first message, the WTRU 102 indicates the availability of AI / ML models at the WTRU 102 to the network at 802. In a second message, the network sends a request for AI / ML-based positioning to the WTRU 102 at 804. Based on the request and availability of AI / ML models at the WTRU 102, the WTRU 102 determines to perform AI / ML-based positioning and report the obtained WTRU location to the network at 806.

[0271] The WTRU 102 may determine to use AI / ML-based positioning if the model associated with a PRS configuration is available. If the model is available, the WTRU 102 may determine to use AI / ML-based positioning based on the associated PRS configuration.

[0272] FIG. 9 is a signaling diagram illustrating another example of communications for initiating AI / ML-based positioning. As shown in FIG. 9, in a first message, the WTRU 102 indicates the availability of AI / ML models at the WTRU 102 to the network at 902. In a second message, the network sends a request for AI / ML-based positioning to the WTRU 102 at 904. Based on the request and availability of AI / ML models at the WTRU 102, the WTRU 102 may determine to perform training of an AI / ML model at 906 and report the training outcome to the network at 908. The network may send grant information to the WTRU 102 at 910, and the WTRU 102 may determine to use AI / ML-based positioning (e.g., based on the associated PRS configuration) and send information indicating the WTRU location at 912 after receiving the grant.

[0273] Model Monitoring and Switching at the Network when the WTRU 102 has AI / ML Models

[0274] In certain representative embodiments, a WTRU 102 may be configured to report measurements and / or indicators to the network such that the network can monitor or switch anymodels at the WTRU 102. The WTRU 102 may receive an indicator from the network about which AI / ML model to use for positioning purposes.

[0275] For example, the measurements and / or indicators that the WTRU 102 may transmit to the network to assist the network in the monitoring of the model(s) at the WTRU 102 side and / or determining if a switch of model(s) at the WTRU 102 side may be needed may include any of the following: (i) a performance report; (ii) raw model output; (iii) processed output data; (iv) a request to switch AI / ML models; and / or (v) a measurement report.

[0276] For example, a report may include the performance results of a currently activated model. For example, the report may include the performance results of another model (e.g., a better performing model) that the WTRU 102 may have tested. The WTRU 102 may also include the model ID of the better performing model in the report.

[0277] For example, a report may include a raw model output from the currently activated AI / ML model at the WTRU 102.

[0278] For example, a report may include processed data from the output of the currently activated AI / ML model at the WTRU 102.

[0279] For example, a report may include a simple request to switch to another model. The WTRU 102 may be able to determine that it needs a switch to another model and the target model to switch to but may still require an ACK from the network before activating the new model for inference.

[0280] For example, a report may include measurements reported by the WTRU 102, such as measurements in WTRU 102 speed, rotational movement, location, positioning and / or changes thereof (e.g., the NW may assess the measurements reported from traditional non- AI / ML positioning methods against the raw and / or processed output of the ML model at the WTRU 102 and determine that the ML model is not performing well enough and a model switch at the WTRU 102 may be needed).

[0281] For example, a report may include measurements reported by the WTRU 102, such as channel measurements and / or changes thereof. Channel measurements may include any of the following: CSI parameters (e.g., CQI, PMI, RI), doppler, doppler spread, channel coherence time, channel coherence bandwidth, cell RSRP, Ll-RSRP (e.g., beam RSRP), and / or SINR. For example, if the WTRU 102 reports a sudden drop in RSRP, the NW may determine that the degradation in the channel measurements may be due to a change in location to an area of poor coverage. If the WTRU 102 is also reporting the output of an AI / ML positioning model to the NW, the NW may determine that the drop in channel quality does not match the currently reported WTRU 102 position and determine that the AI / ML positioning model at the WTRU 102 is not performing well and a model switch at the WTRU 102 may be needed.

[0282] In certain representative embodiments, a WTRU 102 may be requested to report measurements and a WTRU location for model monitoring purposes by the network.

[0283] For example, a WTRU 102 may be configured with a time window during which the WTRU 102 makes measurements on DL-RSs. The network may configure time windows so that multiple WTRUs can make measurements during a configured window duration. The WTRU 102 may be configured with a time window with an ID. The WTRU 102 may include the ID in the report to indicate the association between the measurements and the time window.

[0284] For example, the WTRU 102 may be configured with an event to report the measurements and location information. For example, the event may be periodic, trigger-based (e.g., aperiodic reporting), or semi-persistent reporting (e.g., periodic during a configurated time window). The event may be time-based event where the WTRU 102 receives an indication from the network when the WTRU 102 should send the report (e.g., a specific time, a relative time with respect to the reference). If the configured event occurs, the WTRU 102 may send the report.

[0285] Model Monitoring or Switching at the WTRU 102

[0286] In certain representative embodiments, a WTRU 102 may perform model monitoring and / or switching when the WTRU 102 in an area of coverage associated with multiple AI / ML models.

[0287] For example, when a WTRU 102 is in coverage of multiple AI / ML models, the WTRU 102 may perform an inference from a target or first AI / ML model in addition to a source or second AI / ML model.

[0288] In certain representative embodiments, a WTRU 102 may use a quality indicator offset for model switching. For example, upon entering an area corresponding to a target model (e.g., model 2), the WTRU 102 may (e.g., simultaneously) performs a prediction of its position and use a quality indicator (e.g., range of the ground truth expressed by lower and upper limits in terms of meters, such as ±X meters) for both (e.g., source and target) AI / ML models. When the quality indicator of the target model becomes better or smaller than the source model by the quality indicator offset, the WTRU 102 may switch to the target model for AI / ML positioning.

[0289] In certain representative embodiments, a WTRU 102 may use a monitoring measurement threshold for model switching: Upon entering the area of a target model (e.g., model 2), the WTRU 102 may (e.g., simultaneously) perform a prediction of its position using both (e.g., source and target) AI / ML models. The WTRU 102 may receive a monitoring measurement threshold (e.g., RSRP threshold) associated with an AI / ML model for positioning. If the RSRP of the target TRP (e.g., associated with the target model) becomes the threshold or better than the RSRP of the source TRP (e.g., associated with source model), the WTRU 102 may switch to the target model for AI / ML positioning.

[0290] In certain representative embodiments, a WTRU 102 may use a network controlled approach. For example, upon entering the area associated with a target model (e.g., model 2), the WTRU 102 may (e.g., simultaneously) perform a prediction of its position using both (e.g., source and target) AI / ML models. The WTRU 102 may report both positions and associated quality indicators to the network until the network decides to switch to the target model.

[0291] In certain representative embodiments, a WTRU 102 may switch an AI / ML model for positioning using a quality indicator offset. For example, the WTRU 102 may determine to use an AI / ML model to perform positioning. The WTRU 102 may receive AI / ML models for positioning (e.g., both source and target) which can predict a quality indicator of the model output and a coverage area of each model. The WTRU 102 may receive a quality indicator Offset (e.g., Qloffset) from the network. The WTRU 102 may receive a PRS configuration associated with source model from the network. The WTRU 102 may make measurements on any PRSs associated with the source model, input the measurements to the source model and estimate the WTRU 102 position and quality indicator associated with it (e.g., QIsource). The WTRU 102 may report the estimated position from the source model to the network. By comparing the estimated position from source model, the WTRU 102 may determine whether it entered the coverage area associated with the target model. The WTRU 102 may determine that it is in the coverage area of the target model, and the WTRU 102 may request the network to send PRSs associated with the target model. The WTRU 102 may make measurements on the PRSs associated with the target model, input the measurements to the target model and estimate the WTRU 102 position and a quality indicator associated with it (e.g., Qltarget). If the quality indicator of the target model is better than the source model by the quality indicator offset (e.g., Qltarget < (QIsource + Qloffset)), the WTRU 102 may switch to the target model for AI / ML positioning. The WTRU 102 may notify the network that it switched to the target AI / ML model for positioning.

[0292] In certain representative embodiments, a WTRU 102 may monitor and / or switch the configured AI / ML model based on KPI measurements and its monitoring. For example, the WTRU 102 may receive one or more combinations of the KPI(s) (e.g., LoS / NLoS ID(s), SNR, SINR, RSRP, measurement uncertainty, delay spread, and / or doppler spread) associated with the configured AI / ML models. In one example, the KPI(s) may be associated with the model ID(s) associated with the AI / ML models. The KPI(s) may be model specific (e.g., associated with a model ID) or common for more than one model (e.g., a same KPI(s) associated with more than one model ID).

[0293] For example, the WTRU 102 may be configured with the conditions and / or thresholds associated with each KPI. These conditions and thresholds may indicate the conditions where theWTRU 102 may determine to either monitor other configured models for switching or switch to another model.

[0294] For example, the WTRU 102 may be configured by the network with the KPI measurement configurations (for e.g., measurement time, periodicity, frequency, bandwidth etc.) to indicate the measurement parameters. In one example, a measurement configuration may (e.g., also) be associated with the KPI measurement conditions and / or thresholds. In one example, the WTRU 102 may measure the KPIs (e.g., based on the KPI measurement configuration) and based on it, determine to either keep using the current AI / ML model with the same or different KPI measurement, switch to another AI / ML model, or terminate the procedure. The WTRU 102 may make this determination based on the configured conditions based on the measured KPIs being above or below configured thresholds.

[0295] For example, a configured AI / ML model with a model ID #1 may be associated with the KPIs of LoS / NLoS ID(s) (e.g., associated with one or more TRPs) and RSRP. Model ID #1 may be further associated with a KPI measurement time t, with a first measurement periodicity pl, associated with first thresholds, such as thresholdl_LoS / NLOS and thresholdl RSRP, and a second measurement periodicity p2, associated with second measurement thresholds, such as threshold2_LoS / NLOS and threshold2_RSRP.

[0296] For example, the configured AI / ML model with ID #2 may be associated with the KPI delay spread with its conditions and thresholds (e.g., threshold2_del ay spread). Additionally, the measurement configuration may be associated with the second measurement configurations associated with model ID #1. In this example, the WTRU 102 may measure the KPIs LoS / NLoS ID(s) and RSRPP with the first measurement configuration (e.g., periodicity pl) and determine to keep using the model #1 but with a second measurement configuration (e.g., periodicity p2) based on any of the following conditions: (i) determined LoS / NLoS ID associated with one or more TRP(s) is below the (pre-)configured thresholdl_LoS / NLOS; and / or (ii) the measured RSRP associated with one or more received RS(s) is below a (pre-)configured thresholdl RSRP.

[0297] The WTRU 102 may then, based on the measurement configuration (e.g., periodicity p2) decide to switch the AI / ML model to model #2 based on any of the following conditions: (i) the determined LoS / NLoS ID associated with one or more TRP(s) is below the configured threshold2_LoS / NLOS; (ii) the measured RSRP associated with one or more received RS(s) is below a configured threshold2_RSRP; and / or (iii) the measured delay spread is below a configured threshold2_delayspread, etc.

[0298] The WTRU 102 may determine to terminate the AI / ML-based positioning procedure if it determines that all the (pre-)configured AI / ML models are not suitable for positioning based of the measured KPI(s).

[0299] For example, the WTRU 102 may also be configured with a priority of the (pre- )configured AI / ML models. The indicated priority, for example, may be categorical (e.g., high, medium, low) or numerical (e.g., 0, 0.1, ..., 1). The priority associated with the AI / ML models (e.g., with the model ID) may indicate the order with which the WTRU 102 may select the models. For example, an AI / ML model associated with time-based measurements as inputs may have one priority and an AI / ML model associated with power-based measurements as inputs may have another priority. Priority can be a way to indicate the preference for certain AI / ML models.

[0300] In some embodiments, the WTRU 102 may not be configured with a priority for the models, and the WTRU 102 may determine a priority. The WTRU 102 may determine the priority for the models based on any of the following: (i) model inputs; (ii) DL-RS configurations; (iii) WTRU 102 capabilities; (iv) WTRU 102 mobility status; and / or (v) KPI measurements.

[0301] For example, the WTRU 102 may allocate a priority to a model based on the model inputs. The model inputs can, for example, determine the performance of the AI / ML model. A model with RSRP inputs may have higher errors compared to a model with timing measurements (e.g. TDoA, etc.) as inputs.

[0302] For example, the WTRU 102 may allocate a certain priority to a model based on the DLRS (e.g., SSB, CSLRS, DL-PRS, etc.) configurations for positioning. For instance, a configuration with a certain bandwidth allocation may benefit certain models (for e.g., model with timing measurements as input) and the WTRU 102 may determine to prioritize (e.g., allocate priority above a threshold) those models over others.

[0303] For example, the WTRU 102 may allocate a certain priority to a model based on the WTRU capability information. For instance, a WTRU 102 with a large number of antenna elements may determine accurate angle measurements. The WTRU 102 may determine to prioritize the models with angle-based measurements (e.g., AoD) as inputs in such scenario.

[0304] For example, the WTRU 102 may allocate a certain priority based on if the WTRU 102 is mobile or not. The WTRU 102 may determine to prioritize the AI / ML models trained in dynamic conditions if the WTRU 102 is moving.

[0305] For example, the WTRU 102 may allocate certain priority to a model based on the KPIs. For example, if the WTRU 102 measures the DL-RSs with a number of multipath components above a threshold, the WTRU 102 may determine to prioritize a model that exploits multipath measurements. If the WTRU 102 measures that the measured channel SNR is above a configured threshold, the WTRU 102 may allocate a priority to a certain model. In one example, as one or more KPIs may be associated with an AI / ML model (e.g., with its model ID), the WTRU 102 may determine to prioritize the models with the measured KPIs above the configured threshold.

[0306] In certain representative embodiments, a WTRU 102 may be configured by the network either with different priority updates or to determine and update the priority of the AI / ML models during a positioning procedure. As the channel conditions may change throughout the positioning procedure (e.g., due to WTRU 102 mobility, changes in channel conditions), the WTRU 102 may either receive or determine the updated priority and perform the subsequent procedures based on it. The WTRU 102 may determine to update the priority based on any of the following conditions: (i) a measured KPI (e.g., associated with the AI / ML models) between multiple time instances (e.g., measurement occasions) is below a (pre)configured threshold; (ii) a difference in the WTRU location between multiple time instances is above a (pre)configured threshold; and / or (iii) a difference in inputs to the AI / ML models between multiple time instances is above a (pre)configured threshold.

[0307] In one example, when the WTRU 102 wants to switch the AI / ML model (e.g., based on KPIs), the order with which the WTRU 102 may consider the suitability of a model among a set of models may be based on the model priority. For example, the WTRU 102 may determine to check the KPIs associated with the AI / ML model to switch to from the set of available models with the highest priority.

[0308] For example, the WTRU 102 may report information indicating any of the following: (i) Measured KPI(s); (ii) Determined model priorities (e.g., associated with the AI / ML models and / or model IDs); (iii) Updated model priorities (e.g., associated with the AI / ML model and / or model IDs); and / or (iv) Timestamp (associated with e.g., measured KPIs, priority determination).

[0309] For example, the WTRU 102 may send the measurement report to the network (e.g., LMF, gNB) via a semi-static (e.g., LPP, RRC) and / or dynamic message (e.g., UCI, UL MAC-CE).

[0310] In certain representative embodiments, a WTRU 102 may receive a request for AI / ML- based positioning from the network. The WTRU 102 may be configured with multiple AI / ML models, such as where each model is associated with one or more KPI(s) and thresholds, model priority and KPI measurement configurations (e.g., time, periodicity, etc.). The WTRU 102 measures the KPI(s) associated with the configured AI / ML models (e.g., based on the KPI measurement configuration) and determines a subset of suitable AI / ML models for positioning based on the measured associated KPI(s) being above the (pre)configured threshold. The WTRU 102 may select an AI / ML model from the determined subset of the suitable models based on the configured model priority (e.g., model with the highest priority). The WTRU 102 may report the measured KPI and / or the selected AI / ML model and start a positioning procedure with the model.

[0311] In some embodiments the WTRU 102 may measure the KPI(s) (e.g., associated with the selected AI / ML model) based on the KPI measurement configuration and determines to switch the model if the measured KPI drops below the (pre)configured threshold. The WTRU 102 maymeasure the KPI(s) associated with the different configured AI / ML models based on the KPI measurement configurations and select a model based on the measurement and the model priority.

[0312] In some embodiments, if the WTRU 102 determines that the measured KPI(s) associated with all the configured AI / ML models are below (pre)configured thresholds, the WTRU 102 may terminate the positioning procedure.

[0313] Turning On and Off Assistance Information

[0314] In certain representative embodiments, a WTRU 102 may send a request for PRS configuration information. The WTRU 102 may send a request to verify the AI / ML models, for training, and / or retuning a model. The WTRU 102 may include a cause of the request, such as training, retuning, and / or verification. In one example, the WTRU 102 may indicate a duration of PRS transmissions for the cause indicated in the request. For example, the WTRU 102 may send the request via LPP and / or RRC messaging.

[0315] Predicting and determination of AI / ML model to use

[0316] In certain representative embodiments, a WTRU 102 may predict and / or determine which AI / ML model to use. For example, a WTRU 102 may use AI / ML models that, given the input measurements, are capable of predicting both the WTRU’s position and the best model at that position.

[0317] FIG. 10 is a block diagram illustrating an example AI / ML model 1000 which predicts a WTRU position and a best AI / ML model for the WTRU location. In FIG. 10, an AI / ML model 1000 may receive a set of measurements as inputs, and the AI / ML model 1000 may output a prediction (e.g., inference). The prediction may include the WTRU’s position (e.g., x, y and z coordinates) and information indicating a best AI / ML model (e.g., for the predicted WTRU position).

[0318] For example, the AI / ML model 1000 may be made up of 2 sub-models trained separately (e.g., one regression model for the position, and one classification model for the best model). It can also be the same model with 2 sets of outputs that is trained end-to-end for both positioning regression and best-model classification.

[0319] In certain representative embodiments, each model may be trained for a specific operating area. The operating area of a model may be associated with a cell or a set of TRPs. FIG. 11 is a operating area diagram 1100 illustrating examples of operating areas for different AI / ML models. As shown in FIG. 11, the operating area for each model may contain a smaller inner sub-area (e.g., darker shading in FIG. 11) in which the model works best in predicting the position. Each model may also have an outer sub-area (e.g., lighter shading in FIG. 11) where the model is still capable of predicting the positioning, but it may not be the best model (e.g., provide the most accurate prediction). For example, model switching may occur in the outer sub-areas. In one example, asub-model may be associated with a PRS configuration. In another example, a sub-model may be associated with a model ID.

[0320] FIG. 12 is a procedural diagram illustrating an example of a model switching process according to a WTRU trajectory. As shown in FIG. 12, the process of model switching from model A to B may occur as a WTRU 102 moves along a specified trajectory. In FIG. 12, it is assumed that the WTRU is initially using model A at location 1. The output of the model gives the position at this location (e.g., Xi,Yi,Zi) and the best model is predicted to be “Model A”. Since this model is currently being used, no switching is necessary.

[0321] As the WTRU 102 moves to location 2, the model predicts the position (e.g., X2,Y2,Z2) and the best model is still model A. Although that model B also works at this location, model A is still the best choice.

[0322] Now the WTRU 102 moves to location 3, in this location model A still works but model B is the best model. Using its current model (Model A), the WTRU 102 predicts its current position (e.g., X3,Y3,ZS) and the best model predicted is now Model B. The WTRU 102 now initiates the model switching process as explained herein. Note that if model B were available to the WTRU 102 at this location, it could get a more accurate positioning prediction using this model.

[0323] By the time WTRU 102 reaches location 4, the model switching process has already been completed and the model predicts the position (e.g., X4,Y4,Z4) and the best model is determined to be Model B.

[0324] For example, a more advanced type of AI / ML may be used that can predict the possible future model together with current best model. FIG. 13 is a block diagram illustrating an example AI / ML model 1300 which predicts WTRU 102 position, a best AI / ML model for the WTRU location, and a future AI / ML model. In the example of the WTRU 102 trajectory in FIG. 12, the WTRU 102 can determine the best future model at location 2. At this location, while Model A is still the best model, there is a high probability that model B will be the best in the future. So, while still using model A, the WTRU 102 can get ready for switching to model B by requesting it from the gNB (e.g., in advance). This way the WTRU 102 can immediately switch the model when it detects that model A is not the best model anymore (e.g., at location 3). This may expedite the model switching and minimize the duration of time that the WTRU 102 is using a sub-optimal model. The WTRU 102 could also get a better prediction of position at location 3 using model B if it is already available.

[0325] Training Metrics

[0326] In certain representative embodiments, a WTRU 102 may communicate with the network when a (e.g., certain) AI / ML model is not available at the WTRU 102.

[0327] FIG. 14 is a signaling diagram illustrating an example of communications for initiating AI / ML-based positioning when an AI / ML model is not available. In FIG. 14, the WTRU 102 indicates the availability of AI / ML models at the WTRU 102 to the network at 1402. In a second message, the network sends a request for AI / ML-based positioning to the WTRU 102 at 1404. In the request, the network may indicate any parameters (e.g., cell ID) the AI / ML model should be associated with. The WTRU 102 may determine that the AI / ML model is not available at the WTRU 102. In this case, the WTRU 102 may start training an AI / ML model at 1406. After training is complete, the WTRU 102 may send an outcome of training (e.g., performance metrics) to the network at 1408. Examples of outcome of training include any of the following: (i) Mean Absolute Error (MAE); (ii) Mean Squared Error (MSE); (iii) Root Mean Squared Error (RMSE) (e.g., where the WTRU may evaluate RMSE based on a dataset for training and / or a dataset for validation); (iv) X percentile (%) Cumulative Distribution Function (CDF) Error, where X can be in the range of 0 to 100; and / or (v) a Number of samples (e.g., used for training). In some embodiments, the RMSE may be defined as the root mean squared error between the ground truth and inference generated by an AIML model.

[0328] For training, a MSE as the Loss function may be used. Other training metrics may include RMSE, 2D-distance, MAE, and CDF (90%) (e.g., 90% probability that 90% of instances MSE performance is below a value), or CDF (80%) error values.

[0329] Based on the reported performance metrics, the WTRU 102 may receive a grant (e.g., permission) to perform AI / ML-based positioning using the trained AI / ML model at 1412. The WTRU 102 may determine its location using the AI / ML model and report the determined WTRU location at 1412.

[0330] For example, the WTRU 102 may receive an indication from the network to use a specific model. In this case, the WTRU 102 may receive an explicit indication (e.g., via DCI, MAC-CE, RRC, LPP) of a model ID from the network.

[0331] Common Benefits

[0332] In certain representative embodiments, a WTRU 102 may maintain positioning accuracy by seamlessly switching AI / ML models, or switching back to a different positioning method (e.g., RAT dependent positioning method, RAT independent positioning method) using the model switching, validation and model monitoring techniques described herein.

[0333] Verification based on Measurements from Network

[0334] In certain representative embodiments, an AI / ML model may be associated with a cell. When a WTRU 102 moves to a different cell, the WTRU 102 may ask (e.g., request) for PRU measurements and its location. The network may provide the requested information to the WTRU 102 and the WTRU 102 may determines whether the current AI / ML model (e.g., the model usedin the previous cell) can still be used or not. After assistance information is provided, the WTRU 102 may report whether the WTRU 102 is still using the same model or not.

[0335] General Principles

[0336] In certain representative embodiments, a WTRU 102 may use an AI / ML model for positioning. In one example, the AI / ML model may be associated with a cell or an area (e.g., defined by one or more cells) The WTRU 102 may determine the cell or area that is serving the WTRU 102, and use the AI / ML model associated with the serving cell or the area. When the WTRU 102 moves out of the serving cell or the area and into another cell or area, the WTRU 102 may determine to use the same or different AI / ML model based on the outcome of verification. Verification described herein relies on measurements, ground truth and / or WTRU locations determined by other WTRUs or PRUs. The WTRU 102 may obtain measurements, ground truth and / or WTRU locations determined by other WTRUs or PRUs from the network based on the request made by the WTRU 102.

[0337] Content of Request and Conditions for Sending a Request

[0338] In certain representative embodiments, a WTRU 102 may send a request to the network for measurements and / or inferences made by other WTRUs (e.g., PRUs) in the same cell the WTRU 102 is located. If a PRU in the cell is configured with an AI / ML model, the WTRU 102 may want to compare the inference generated by the PRU and the inference generated by the AI / ML model at the WTRU 102 to determine whether to change AI / ML models, update the AI / ML model, or fallback to a default positioning method.

[0339] In certain representative embodiments, a WTRU 102 may request for measurements and / or inferences made by other WTRUs and / or PRUs in neighboring cells. The WTRU 102 may indicate cell IDs from which the WTRU 102 requests to obtain measurements. The WTRU 102 may receive the cell IDs in configuration from the network as part of a positioning method (e.g., to make measurements on PRSs transmitted from neighboring cells for DL-TDOA). Based on the request, the WTRU 102 may receive the measurements and / or inferences made by other WTRUs and / or PRUs from the network. The WTRU 102 may receive assistance information from the network, associating location and measurements, indicating measurements made at the location. The WTRU 102 may use the measurements sent by the network to determine whether to use the same AI / ML model(s) the WTRU 102 was using, or use a different AI / ML model, or use the fallback positioning method.

[0340] FIG. 15 is a system diagram illustrating an example of measurement forwarding between a PRU 1502 and a WTRU 102. In FIG. 15, the PRU 1502 may be another WTRU 102. For example, the WTRU 102 may send a request to the network for measurements made by anotherWTRU 102 (e.g., PRU) and / or location. Location information can be specific (e.g., expressed by geographical coordinates) or area-based (e.g., cell ID, area ID, zone ID).

[0341] In FIG. 15, the WTRU 102 may receive an acknowledgement of the request from the network and the WTRU 102 may receive an inference made by the PRU 1502. The inference made by the PRU 1502 may be based on an AI / ML model. The WTRU 102 may receive the inference made by the PRU 1502 from the network periodically. The WTRU 102 may receive the inference made with the PRSs from a TRP 1504 which are measured by the PRU 1502. For example, the PRU 1502 may make measurements on PRS1, PRS2 and PRS3 at times t=Tl, t=T2 and t=T3, respectively. As described herein, “inference” and “measurements” may be used interchangeably. As described herein, “PRU” and “WTRU” may be used interchangeably. As described herein, “WTRU” and “PRU” may be interchangeably used with “target WTRU” and “reference WTRU”, respectively, such as where a target WTRU 102 needs to check the performance of its AI / ML model using measurements and / or inference generated by a reference WTRU 102.

[0342] After the network receives a request from the WTRU 102, the WTRU 102 may receive requested information as assistance information (e.g., via LPP, RRC) from the network. In the request sent to the network, the WTRU 102 may include information indicating any of the following to indicate desired information from the network, PRU 1502 and / or WTRU 102.

[0343] For example, the request may indicate the contents of the assistance information where the WTRU 102 may indicate whether the WTRU 102 needs measurements, an inference and / or a ground truth of another WTRU 102 or PRU in the assistance information from the network. In one example, the WTRU 102 may indicate that the measurements provided in assistance information should be associated with the inference provided in assistance information. In another example, the WTRU 102 may indicate that measurements provided in assistance information should be associated with the ground truth provided in the assistance information. If the WTRU 102 requests for measurements, the WTRU 102 may additionally request for the measurements for specific PRS configurations associated with the measurements (e.g., PRS resources IDs, PFL IDs, TRP IDs).

[0344] For example, the request may indicate a type of measurements associated with the ground truth. The WTRU 102 may indicate PRS configurations associated with the measurements in the request. For example, the WTRU 102 may indicate the request for Channel Impulse Response (CIR) associated with the ground truth. The WTRU 102 may indicate the number of TRPs or TRP IDs in the request and request the network to provide a CIR for each TRP.

[0345] For example, the request may indicate desired location information. A requested PRU location may indicate the desire for the WTRU 102 to obtain inference and measurements made from a specific location and / or inference made by PRU(s) located at the specific location. A requested location information (e.g., specific location expressed by geographical coordinates orarea information such as cell ID(s), area ID(s), zone ID(s)) where the WTRU 102 requests for measurements and / or an inference associated with the indicated location information; and / or desired location(s) of PRUs or WTRUs which may be indicated by zone IDs, locations, area where the area may be collection of cells indicated by cell IDs. The WTRU 102 may include the information to request for inference made by PRUs or WTRUs in the specific area. For example, SSB ID, indicating PRU location(s) or the area that is covered by the SSB. Another example is the area ID where an area may be defined by a collection of cell IDs or geographical coordinates.

[0346] For example, the request may indicate the WTRU location (e.g., geographical coordinates expressed by x and y coordinates) to assist the network to select PRUs close to the WTRU 102. The WTRU 102 may indicate the method used to obtain the WTRU location (e.g., GNSS, RAT dependent positioning method). In another example, the WTRU 102 may indicate area information (e.g., area ID, zone ID) in which the WTRU 102 is located.

[0347] For example, the request may indicate the PRS configuration (e.g., PRS resource ID, frequency layer ID) of the AI / ML model at the PRU or WTRU 102 is associated therewith. The WTRU 102 may send a request to the network so that the inputs (e.g., measurements) for the AI / ML model (e.g., measurements) at the PRU and / or WTRU 102 are made by the requested PRS configuration.

[0348] For example, the request may indicate the desired time instance(s) and / or periodicity (e.g., every Monday at 9pm, every 20 seconds) of delivery of assistance information from the network. For example, the WTRU 102 may send a request to ask the network for periodic provisioning of assistance information at the desired periodicity. The WTRU 102 may indicate the duration of provisioning of assistance information (e.g., for 4 hours).

[0349] For example, the request may indicate information about the AI / ML model(s) the WTRU 102 is configured with (e.g., cell ID the AI / ML model is associated with, PRS configuration(s) the AI / ML model is associated with, model ID). The WTRU 102 may include such information so that the network can choose a PRU or a WTRU 102 that uses the similar or same AI / ML model to generate an inference. For example, the WTRU 102 may include a cell ID (e.g., serving cell ID, camped cell ID, ID of the cell the WTRU 102 was previously served by) to indicate the WTRU 102’s desire to obtain an inference made by the AI / ML model associated with the cell ID. The cell ID the WTRU 102 includes may be the ID of the cell associated with the AI / ML model the WTRU 102 uses. The network may search for PRUs or WTRUs that use the AI / ML model associated with the cell ID.

[0350] For example, the request may indicate a number of PRUs or WTRUs, number of location(s), data size (e.g., expressed in terms of the number of samples, bytes, measurementinstances, time instances, number of time stamps), number of samples (e.g., 100 occasions of provisions of assistance information).

[0351] For example, the request may indicate whether the WTRU 102 requests for the ground truth from the same location or different locations. If the WTRU 102 indicates that the WTRU 102 wants the ground truth from the same location or area, the WTRU 102 may receive the ground truth and associated measurements and ground truth label quality indicator from the same location or area (e.g., same WTRU 102, same PRU) in assistance information at every occasion of provisioning of assistance information. If the WTRU 102 requests for different ground truths, the WTRU 102 may receive different ground truths and associate the ground truths and measurements and ground truth label quality indicator from the same location (e.g., same WTRU 102, same PRU) in assistance information at every occasion of provisioning of assistance information. As described herein, the phrases “ground truth” and “ground truth label” may be used interchangeably. As described herein, the phrases “ground truth label quality indicator”, “quality indicator” and “ground truth quality indicator” may be used interchangeably.

[0352] For example, the request may indicate a repetition factor for provisioning of assistance information per ground truth. The WTRU 102 may want to request repeated provisioning of assistance information so that the WTRU 102 can determine the consistency in the ground truth and associated information (e.g., measurements) or determine to process or combine them. For example, the WTRU 102 may determine to generate one set of ground truths and associated information (e.g., measurement) based on N sets of ground truths and associated information by averaging N ground truths and N measurements (e.g., averaged CIR, averaged RSRP, averaged RSTD, averaged time of flight). For example, the WTRU 102 may indicate, in the request, the repetition factor N. If, for example, N=2, the WTRU 102 may receive the ground truth and association information (e.g., measurements, ground truth label quality indicator) at two occasions from the network where each occasion may have a different timestamp, indicating that the ground truth measurements are made at two different time instances (e.g., different days, different hours, different minutes). The repetition factor may be applied when the WTRU 102 receives different ground truths. For example, the WTRU 102 may receive the first ground truth for two occasions and the second ground truth for two occasions, followed by the receipt of the two occasions of the first ground truth.

[0353] For example, the request may indicate the quality of the ground truths where the WTRU 102 may indicate the quality of WTRU 102 or PRU location estimates. For example, uncertainty in the PRU location may be expressed by a range of uncertainty (e.g., ±0.5 meters). In another example, the WTRU 102 may request a type of WTRU 102 (e.g., WTRU 102, PRU). This is because PRU locations may be verified and known by the network and WTRU locations (e.g.,locations of non-PRUs) may not be verified by the network. Thus, in terms of quality of the ground truth, PRU locations may be more reliable than WTRU locations. Another example of quality of ground truths is a method used to determine the ground truth (e.g., GNSS, RAT dependent positioning method, RAT independent positioning method (e.g., sensor, WIFI) NW verified locations).

[0354] For example, the request may indicate a type of the ground truth label quality indicator associated with the ground truth (e.g., hard indicator, soft indicator).

[0355] For example, the request may indicate a threshold for the ground truth label quality indicator associated with the ground truth and the WTRU 102 expects the network to provide location information of a WTRU 102 or PRU with the associated ground truth label quality indicator above or equal to the threshold.

[0356] For example, the request may indicate an AI / ML model ID in the request such that the network can forward measurements, the inference and / or ground truth associated with the requested AI / ML model ID.

[0357] For example, the request may indicate a cause of the request. For example, potential causes are mobility events, a timer associated with an AI / ML model at the WTRU 102 expiring, accuracy of AI / ML model output falling below a configured threshold, variations (e.g., standard deviation, variance, range) of the AI / ML model output are above a configured threshold, and / or a validity condition associated with an AI / ML model is not satisfied.

[0358] For example, the WTRU 102 may include more than one parameter (e.g., PRS configuration, cell ID) in the request. The WTRU 102 may have multiple AI / ML models and each model may be associated with different parameters (e.g., different cell ID, different PRS configuration). The request from the WTRU 102 may be made in one message or in separate messages. For example, the WTRU 102 may indicate a preference for a ground truth label quality indicator in the first message. The WTRU 102 may send a request for the ground truth in a second message.

[0359] Content of Forwarded Measurements and Inferences from Network

[0360] In certain representative embodiments, a WTRU 102 may receive measurements and / or inferences made by a PRU (e.g., from the network). In certain representative embodiments, a WTRU 102 may receive information that is determined by the network. The information may include any of the following: (i) measurements (e.g., timing, power, phase, CIR) made by the PRU; (ii) DL-RS resource IDs and / or RS configurations (e.g., PRS resource set IDs, frequency layer IDs, TRP IDs) associated with the measurements; (iii) training-related information (e.g., ground truth(s) used by the PRU, quality of the ground truth label, amount of data used) of the AI / ML model(s) used by the PRU; (iv) an inference made by the PRU and information about the AI / MLmodel associated with the generated inference (e.g., model ID, measurements used as inputs to the AI / ML model, DL-RS configuration associated with the AI / ML model, parameters related to PRS configurations); (v) a location of the PRU (e.g., geographical coordinates of the PRU); (vi) a location where the location and associated measurements may imply what a WTRU 102 measures if the WTRU 102 is at the location; (vii) a PRU ID; (viii) timestamp(s) (e.g., absolute time, symbol index, slot index, subframe index, frame index, SFN) associated with measurements and / or inferences where the timestamps may indicate when an inference or measurements are made; (ix) a number of ground truths to be provided; and / or (x) a number of repetitions for provision of ground truth and associated information.

[0361] For example, the WTRU 102 may receive measurements, inference and / or associated information made by the PRU as assistance information from the network via LPP and / or RRC messaging. As an example, the WTRU 102 may receive, from the network, measurements and / or an inference made by multiple PRUs. The WTRU 102 may receive measurements and / or inferences from the network in one set of assistance information or multiple sets of assistance information, such as where each set may contain measurements and / or inferences made by one PRU. For example, the WTRU 102 may determine to use any of measurements, inferences and / or associated information for training the AIML model(s) at the WTRU 102.

[0362] For example, the WTRU 102 may receive measurements and / or inferences from multiple PRUs or WTRUs in a sequential manner from the network. For example, the WTRU 102 may be configured with a set of PRUs or WTRUs identified by indices. If periodic delivery of PRU and / or WTRU 102 inferences and / or measurements is configured, the WTRU 102 may receive an indication from the network indicating the order of delivery of assistance information of measurements and / or ground truths. The WTRU 102 may receive a set of indices, and each index may correspond to a WTRU 102 or PRU indicating the order of delivery. For example, if there are three PRUs with respective indices, 1, 2 and 3, the WTRU 102 may receive the set of indices

[0123] indicating the order of delivery of measurements and inference from the PRUs. In one example, the WTRU 102 may be configured to receive measurements and / or inference in increasing order of the indices.

[0363] Periodicity, Termination or Initiation of Measurements and Inference Forwarding

[0364] In certain representative embodiments, a WTRU 102 may receive measurements and / or inferences made by a PRU periodically from the network, such as assistance information from the network. The WTRU 102 may be configured with a periodicity of the assistance information by the network. For example, the WTRU 102 may send a request to the network (e.g., via RRC and / or LPP) to initiate the transmission of assistance information. For example, the WTRU 102 may send a request to the network to stop the transmission of assistance information.

[0365] For example, the WTRU 102 may indicate to the network information indicating any of the following: (i) when inference and / or measurement forwarding should start (e.g., indicated by absolute time, SFN, slot or frame number, relative timing in seconds); (ii) whether inference and / or measurements should be forwarded periodically or aperiodically; and / or (iii) a duration of inference and / or measurement forwarding, such as where the duration may be expressed in terms of number of symbols, slots, frames, time (e.g., seconds, minutes, hours), etc.

[0366] For example, the WTRU 102 may determine to send a request to terminate transmission of assistance information when the WTRU 102 determines to terminate a positioning session (e.g., a positioning session starts when the WTRU 102 receives PRS configurations to initiate positioning) or fall back to a fallback positioning method (e.g., DL-TDOA) which does not require measurements and / or inference made by PRUs or other WTRUs.

[0367] Verification of AI / ML Model

[0368] In certain representative embodiments, a WTRU 102 may verify an AI / ML model.

[0369] For example, once the WTRU 102 receives an inference and / or measurements made by the PRU, the WTRU 102 may determine to verify or validate the AI / ML model(s) at the WTRU 102 using the inference and / or measurements made by the PRU.

[0370] For example, the WTRU 102 may send a request for verification to the network. The WTRU 102 may determine to send a request based on an event. The request may be sent before the WTRU 102 asks for assistance information (e.g., measurements and / or inference made by the PRU) to the network. Examples of events include mobility based events (e.g., change in a cell, area), periodic event (e.g., periodic verification), measurement based events (e.g., RSRP of PRS or SSB is below threshold), and / or time based events (e.g., expiry of timer associated with the AI / ML model at the WTRU 102). For example, the WTRU 102 may be configured with occasions at which the WTRU 102 should perform verification. An occasion may be periodic and the WTRU 102 may be configured with periodicity of the occasion. The occasions may be semi-persistent, such as where the WTRU 102 may be configured with a time window during which the WTRU 102 should perform periodic verification.

[0371] For example, the WTRU 102 may send a request to the network for the measurements and / or inference made by a PRU. The WTRU 102 may be configured with an AI / ML model that is applicable in an area, such as where the area may consist of multiple cells. If the WTRU 102 moves to another cell (e.g., second cell) from a current cell (e.g., first cell) where the area contains both the first and second cells, the WTRU 102 may determine to send a request to the network for measurements and / or an inference made by the PRU. The WTRU 102 may want to check whether an AI / ML model can yield the desired performance compared to the measurements and / or inference made by the PRU. The WTRU 102 may request for the ground truth and associatedmeasurements to train the AI / ML model(s) at the WTRU 102. The WTRU 102 may include the reason for the request as a cause in the request.

[0372] For example, the WTRU 102 may determine to verify the AI / ML model(s) at the WTRU 102 after a mobility event is complete. One example of a mobility event may be a change of the serving cell, or when the WTRU 102 moves to a neighboring cell from the current serving cell. The WTRU 102 may determine the mobility event is complete when the WTRU 102 receives cell identity information (e.g., cell ID) of the new cell (e.g., neighboring cell of the current serving cell) from the network, for example.

[0373] FIG. 16 is a signaling diagram illustrating an example of model verification after a mobility event. In FIG. 16, a WTRU 102 moves to a new cell after a mobility event 1602 and obtains information about the new serving cell from the network (e.g., gNB 180) at 1604. The WTRU 102 may receive a request for positioning form the network at 1606. The request for positioning may include a positioning method (e.g., AI / ML-based positioning) the WTRU 102 should use to determine its location. The WTRU 102 may send a request for assistance information (e.g., measurements and / or inference made by PRU) to the network at 1608. Once the WTRU 102 receives the measurement and / or inference made by the PRU at 1610, the WTRU 102 may determine to validate or verify the AI / ML model(s) the WTRU 102 has at 1612. The WTRU 102 may report the verification result to the network at 1614. Examples of verification results may include the error between the AI / ML model output at the WTRU 102 and received ground truth label or inference(s) made by the PRU, or a hard indicator indicating 1 for successful verification or 0 for unsuccessful verification. After the verification is reported, the WTRU 102 may receive a configuration for a positioning method (e.g., AI / ML-based positioning method, which AIM model to use, configurations related to DL-TDOA) at 1616.

[0374] FIG. 17 is a signaling diagram illustrating another example of model verification after a mobility event. In FIG. 17, the WTRU 102 may perform AI / ML-based positioning without verifying AI / ML model(s) at the WTRU 102 after a mobility event. For example, after the mobility event at 1702 and obtaining information about the new serving cell from the network (e.g., gNB 180) at 1704, the WTRU 102 may determine to send WTRU capability information and / or the status of AI / ML model(s) at the WTRU 102 to the network at 1706. For example, the WTRU 102 may indicate association information of the AI / ML model(s) to the network (e.g., AI / ML models can be associated with a cell) as assistance information. In another example, the WTRU 102 may indicate capabilities of AI / ML models at the WTRU 102 (e.g., number or type of inputs the AI / ML model can accept). After sending the assistance information and / or WTRU capability information, the WTRU 102 may receive a request for positioning at 1708 and / or one or more configurationsrelated to a positioning method (e.g., which AI / ML model(s) to use, model ID, configuration message related to DL-TDOA) at 1710.

[0375] For example, the WTRU 102 may be configured with a timer for the AI / ML model at the WTRU 102. The WTRU 102 may determine to start a timer for the AI / ML model once the AI / ML model is activated. The WTRU 102 may determine to perform verification or send a request for verification or assistance information (e.g., PRU measurements) if the timer (e.g., time duration) associated with the AI / ML model expires.

[0376] For example, the WTRU 102 may receive a request to perform verification from the network. The request from the network or WTRU 102 may be received or sent in any of DCI, UCI, MAC-CE, RRC and / or LPP messaging.

[0377] In certain representative embodiments, a WTRU 102 may use measurements made by PRU and compares an inference (e.g., based on the PRU measurements).

[0378] FIG. 18 is a system diagram illustrating an example of verification using measurements made by a PRU. In FIG. 18, the WTRU 102 may determine to use the measurements made by the PRU 1502 to generate an inference (e.g., WTRU location) using an AI / ML model at the WTRU 102. The WTRU 102 may determine the difference (e.g., absolute error, square error, mean square error) between the generated inference and the inference generated by the PRU 1502. The WTRU 102 and PRU 1502 may or may not use the same AI / ML model. For example, the WTRU 102 may determine a difference between the generated inference and the ground truth associated with the PRU 1502 (e.g., PRU location). An example of the error may be e =where x and x are the generated inference at the WTRU 102 and the ground truth (e.g., PRU location).

[0379] In certain representative embodiments, a WTRU 102 may use measurements made by the WTRU 102 and compares an inference (e.g., based on the WTRU 102 measurements).

[0380] FIG. 19 is a system diagram illustrating an example of verification using measurements of PRSs. In FIG. 19, the WTRU 102 may determine to make measurements on a PRS and compare the inference generated by an AI / ML model at the WTRU 102 against the inference generated by an AI / ML model at the PRU 1502. For example, the WTRU 102 may be configured to make measurements on indicated PRS resource(s) during the configured time window(s) where the parameters associated with the window may be a start / end time or a duration (e.g., number of symbols, number of frames or subframes, number of slots). The WTRU 102 may determine the inference (e.g., WTRU location) based on the measurements of indicated PRSs the WTRU 102 made. The WTRU 102 may compare the generated inference against the inference generated by the PRU 1502. The WTRU 102 may determine to compare inferences which are generated based on the measurements made on the same PRS resource(s). For example, the WTRU 102 may determine the error between the inferences made by the WTRU 102 and the PRU 1502 which aregenerated based on the measurements made on PRS1. In FIG. 19, the WTRU 102 and PRU make measurements on PRS1, PRS2 and PRS3, and generate respective inferences using the AI / ML models #1 and #X at the WTRU 102 and PRU 1502, respectively.

[0381] In certain representative embodiments, a WTRU 102 may use processed measurements from the network. For example, the WTRU 102 may receive CIR from the network based on the measurements (e.g., power, timing, phase, phase measurements) reported by the WTRU 102.

[0382] FIG. 20 is a signaling diagram illustrating an example of model verification using CIR. For example, the WTRU 102 may send WTRU capability information to the network at 2002. The WTRU 102 may send a request to the network for assistance information (e.g.., measurements made by the PRU) at 2004. The WTRU 102 may receive a PRS configuration from the network at 2006. For example, the PRU 1502 may receive the PRS configuration from the network. The WTRU 102 may receive a PRS transmitted by the network at 2008 and make measurements on the received PRS at 2010. The PRU 1502 may receive the PRS transmitted by the network at 2008 and make measurements on the received PRS at 2010.

[0383] The PRU 1502 may send a measurement report to the network at 2012. The WTRU 102 may send a measurement report to the network at 2014. The network may contain a timestamp indicating when the reported measurements are made. The WTRU 102 may receive CIR associated with the measurements reported by the WTRU 102 at 2016. The network may associate information about measurements used to determine the CIR. The information may be at least one of the parameters from PRS configurations (e.g., PRS resource IDs, TRP IDs, PRS IDs, locations of TRPs). If the CIR is determined based on the PRUs or other WTRUs’ measurements, the WTRU 102 may receive location information about the PRUs or WTRUs.

[0384] The WTRU 102 may receive CIRs based on PRU measurements from the network. The PRU 1502 may send an inference (e.g., based on PRS measurement) to the network at 2018. At 2020, the WTRU 102 may also receive the inference made by the AI / ML model at the PRU 1502 based on the measurements made by the PRU 1502 . The WTRU 102 may use CIRs determined based on the PRU measurements as an input to the AI / ML model at the WTRU 102 and obtain a corresponding inference from the AI / ML model. For example, the WTRU 102 may determine an error metric based on the inference and the inference obtained from the AI / ML model at the PRU. For example, the WTRU 102 may determine the error metric based on the inference obtained from the AI / ML model at the WTRU 102 and a ground truth related to the PRU (e.g., PRU location). The WTRU 102 may verify the inference obtained from the AI / ML model at 2022. At 2024, the WTRU 102 may send to the network information indicating a status of the AI / ML model used at the WTRU 102. For example, the status may reflect a result of the verification.

[0385] In certain representative embodiments, an error metric used to verify an AI / ML model at the WTRU 102 may be defined as follows. The WTRU 102 may receive an indication from the network as to which definition to use. If the WTRU 102 determines the definition autonomously, the WTRU 102 may report to the network which metric the WTRU 102 used. For example, the WTRU 102 may report a difference between the inference generated by the AI / ML model at the WTRU 102 (e.g., inference 1 in FIG. 18) and the inference generated by the AI / ML model at the PRU (e.g., inference X in FIG. 18). For example, the WTRU 102 may report a difference between the inference generated by the AI / ML model at the WTRU 102 and a ground truth of the PRU (e.g., geographical coordinate of the PRU). For example, the WTRU 102 may report a difference between the inference generated by the AI / ML model at the WTRU 102 and a ground truth of the WTRU 102 (e.g., geographical coordinate of the WTRU 102).

[0386] For example, an error metric may be used with any combinations of inputs described herein, such as FIGs. 18 and 19. For example, the WTRU 102 may determine the inference using the AI / ML model at the WTRU 102 based on measurements made by the WTRU 102, and / or measurements made by the PRU.

[0387] In certain representative embodiments, a WTRU 102 may report error metrics during verification.

[0388] For example, the WTRU 102 may report the error metric during verification. The WTRU 102 may be configured, by the network, to report the error metric periodically. The WTRU 102 may report an aggregated error metric report (e.g., averaged error metrics during a verification period) to the network. The WTRU 102 may indicate that the error metric is averaged. The WTRU 102 may determine to stop reporting the error metric if the WTRU 102 receives a message to terminate reporting of the error metric.

[0389] In certain representative embodiments, a WTRU 102 may receive an indication from the network about information the WTRU 102 should use to verify the AI / ML model at the WTRU 102. For example, the WTRU 102 may receive an indication to use PRU measurements to generate an inference using an AI / ML model at the WTRU 102 for verification. For example, the WTRU 102 may receive an indication from then network to use measurements made by the WTRU 102 to generate the inference using the AI / ML model at the WTRU 102.

[0390] In certain representative embodiments, a WTRU 102 may determine to use an AI / ML model at the WTRU 102 if the error determined during verification is below or equal to a configured threshold. If the error is above the configured threshold, the WTRU 102 may perform any of the following actions: (i) determine to verify another AI / ML model, if available at the WTRU 102; (ii) determine to use the preconfigured fallback positioning method (e.g., RATdependent positioning method, GNSS); and / or (iii) determine to train or fine-tune the AI / ML model.

[0391] In certain representative embodiments, a threshold (e.g., for determining the error) may be configured by the network along with the configuration of the AI / ML model.

[0392] In certain representative embodiments, the threshold may be configured by the network when the WTRU 102 moves to a new cell.

[0393] In certain representative embodiments, a duration and / or an amount of data for verification may be configured. For example, a WTRU 102 may be configured with the duration and / or the amount of data to be used for verification. For example, the WTRU 102 may be configured with a start and / or an end time for verification. The start and / or end time may be specified as any of a absolute time, slot index, frame index, SFN, and / or other TTI. The start and / or end time may be specified as the relative timing with respect to an occasion (e.g., after the WTRU 102 receives assistance information from the network, or after the WTRU 102 receives an indication from the network to initiate verification).

[0394] For example, the WTRU 102 may be configured with the amount of data to be used for verification. For example, the WTRU 102 may be configured with the number of occasions, N, of reception of assistance information from the network. Once the WTRU 102 receives N occasions of assistance information from the network, the WTRU 102 may determine that the verification period is completed.

[0395] Fallback Mechanism

[0396] In certain representative embodiments, a WTRU 102 may determine that AI / ML model based positioning cannot be performed. The WTRU 102 may determine to send a message to the network indicating that the positioning process is terminated. For example, a fallback positioning method may be configured at the WTRU 102 and the WTRU 102 may determine to perform the fallback positioning method. The WTRU 102 may send a message to the indicating that the fallback positioning method is being used.

[0397] WTRU Behavior After Verification

[0398] In certain representative embodiments, a WTRU 102 may determine to report the AI / ML model(s) the WTRU 102 determines to use to the network.

[0399] In certain representative embodiments, a WTRU 102 may, after a verification period, determine to send (e.g., to the network) information indicating any of the AI / ML models the WTRU 102 determined to use (e.g., model IDs). For example, the WTRU 102 may determine to indicate any of the PRS configurations (e.g., TRP ID, PRS resource ID) and / or general configurations (e.g., cell ID) associated with the AI / ML models (e.g., the models the WTRU 102 determines to use). The WTRU 102 may indicate the positioning methods to the network, such aswhere the WTRU 102 determines to use RAT dependent and / or RAT independent positioning methods. For example, the WTRU 102 may report information related to the model (e.g., model ID, PRS resource ID, TRP ID) to the network, if there are any changes to the model the WTRU 102 uses.

[0400] For example, if the WTRU 102 determines to use the same AI / ML model before a verification event, the WTRU 102 may indicate to the network whether the same or a different model is used at the WTRU 102. For example, if the WTRU 102 was using an AI / ML model at cell #X and the WTRU 102 moves to cell #Y (e.g., a new cell) the WTRU 102 may indicate to the network after verification that the same AI / ML model used in the cell #X is used in the cell #Y.

[0401] For example, if the WTRU 102 determines to train or finetune a AI / ML model, the WTRU 102 may determine to indicate the progress of training (e.g., start of the training, end of the training) and the WTRU 102 may indicate completion of training or finetuning to the network, along with model information (e.g., model ID, PRS configuration associated with the model).

[0402] Examples of Verification and Validation Reports

[0403] In certain representative embodiments, a WTRU 102 may receive a request from the network to send a verification report to the network as the result of verification or validation. The WTRU 102 may include in the report information indicating any of the following: (i) an (e.g., hard) indicator indicating whether verification or validation of AI / ML model(s) at the WTRU 102 is successful or not; (ii) result(s) of verification or validation, including error metrics such as MSE between the output of AI / ML and ground truth(s) or inferences made by PRU; (iii) any PRS configurations and / or inferences used by the WTRU 102 or PRU for verification (e.g., to derive the error metric) or validation; (iv) timestamps associated with verification or validation; and / or (v) any measurements used for verification (e.g., RSTD, RSRP, ToF) and associated information (e.g., PRS resource IDs used to obtain the measurements) .

[0404] Acquisition of Ground Truths from Other Virtual and Actual WTRUs from Network

[0405] In certain representative embodiments, a ground truth label indicator may be used. For, example, a ground truth label quality indicator may be an (e.g., hard) indicator such as where the values of “1” and “0” may indicate that the associated ground truth is suitable or unsuitable for training an AI / ML model, respectively. For, example, a ground truth label quality indicator may be an (e.g., soft) indicator such as where a value of “0.8” indicates relatively high confidence in using the associated ground truth for training an AI / ML model. On the other hand, a value of “0.2” may indicate that a relatively low confidence in using the associated ground truth for training an AI / ML model.

[0406] In certain representative embodiments, for a soft or hard quality indicator, the value of “1” may correspond to a ground truth generated by a PRU. For a soft quality indicator with a value less than 1 and greater than 0, it may be used to indicate the quality of the ground truth generated by a WTRU or PRU, such as where the ground truth is generated using a RAT dependent positioning method (e.g., DL-TDOA) or RAT independent positioning method (e.g., GNSS). For a soft or hard quality indicator with a value equal to 0, it may indicate that the ground truth label quality indicator cannot be assigned to the ground truth.

[0407] For example, a ground truth label indicator may have a range (e.g., defined by minimum value and maximum value). The minimum and maximum values for a soft indicator may be 0 and 1, respectively. The WTRU 102 may be preconfigured or configured with the range of the indicator by the network. Granularity of the soft indicator may be predefined (e.g., 0.1, 0.01, etc.).

[0408] In another example, a ground truth label indicator may be a range of values indicating the uncertainty of the ground truth. For example, if the ground truth is expressed as a set of coordinates (e.g., x, y), the indicator may be a range of uncertainty for each of the values, such as x±0.2 meters.

[0409] For example, a ground truth label quality indicator may be associated with each coordinate of the ground truth. For example, there may be two indicators for a ground truth represented by the coordinates (x, y) where each of “x” and “y” may be associated with a ground truth label indicator.

[0410] A ground truth label quality indicator indicates a confidence level of an associated ground truth location. For example, a ground truth obtained by DL-TDOA in a NLOS heavy environment may be associated with a low ground truth label indicator. On the other hand, the ground truth obtained by DL-TDOA in a LOS heavy environment may be associated with a high ground truth label indicator.

[0411] In another example, the WTRU 102 may be configured with an association table which associates the ground truth label quality indicator with a range of uncertainty in the ground truth. For example, the ground truth indicator may be an index for a configured association table where the index indicates the uncertainty (e.g., ±2 meters) in the ground truth.

[0412] In certain representative embodiments, a ground truth label quality indicator requirement may be included in a request (e.g., from a WTRU 102).

[0413] For example, a WTRU 102 may include information indicating a threshold for a ground truth label quality indicator in a request sent to the network for ground truths. The WTRU 102 may send a request as a semi-static message (e.g., RRC message, LPP message), or dynamic message (e.g., MAC-CE, UCI), for example. The threshold indicated by the WTRU 102 may be used by the network to forward the ground truth and associated measurements from other WTRUs or PRUs with the ground truth label quality indicator above the threshold, for example.

[0414] For example, a WTRU 102 may indicate that the WTRU 102 requests to obtain a ground truth and associated measurements with a (e.g., soft or hard) ground truth label quality indicator greater than 0.7. In an example, the ground truth label quality indicator may be a soft value between 0 and 1. As a response to the request, the WTRU 102 may receive measurements, an associated ground truth, and an associated ground truth label quality indicator above 0.7 from the network. The WTRU 102 may receive the ground truth which is greater than or equal to the requested threshold. The WTRU 102 may indicate a threshold in the request, indicating that the WTRU 102 does not want any ground truth with an associated ground truth label quality indicator below the threshold.

[0415] For example, a WTRU 102 may indicate in the request that the WTRU 102 requests to obtain any ground truth with a ground truth label quality indicator with a value of 1. In such a request, the WTRU 102 provides an indication of a preference on the quality of the ground truth.

[0416] For example, a WTRU 102 may not include the threshold for the ground truth label quality indicator in the request. In such a case, the WTRU 102 may receive ground truths and associated measurements from the network without any restrictions on the ground truth label quality indicator (e.g., the network will forward any ground truths and associated measurements). In another example, a WTRU 102 may be configured by the network with a threshold where the WTRU 102 may use a ground truth with an associated ground truth quality indicator which is above the threshold for training or verification. If the WTRU 102 is not configured with the threshold, the WTRU 102 may determine to send, to the network, a request which includes a threshold for the ground truth quality indicator.

[0417] In certain representative embodiments, the threshold may be in units of meters. For example, if the ground truth indicator is indicative of uncertainty (e.g., uncertainty of ±0.2 meters), the threshold may be expressed in meters. For example, the WTRU 102 may indicate that the threshold is 0.1 meters, indicating that the WTRU 102 requests to receive any ground truths with a maximum uncertainty less than 0. 1 meters. In the example, an uncertainty of ±0.01 meters satisfies the WTRU 102’s request but an uncertainty of ±0.3 meters does not satisfy the WTRU 102’s request.

[0418] In an example, a (e.g., first) WTRU 102 may send a request for any ground truths and associated measurements from the network. The WTRU 102 may receive, from the network, ground truths, associated ground truth label quality indicators and associated measurements.

[0419] The measurements associated with the ground truth indicates that the measurements are made at a location indicated by the ground truth. Another WTRU 102 (e.g., a second WTRU 102) or PRU may be located at the ground truth and the measurements may be made by the other WTRU 102 or PRU. The measurements and ground truths or location estimates may be reported by theother WTRU 102 or PRU and the network may forward the ground truth and associated measurements to the WTRU 102 (e.g., the first WTRU 102 who made the request for the ground truth and associated measurements).

[0420] In certain representative embodiments, a ground truth label quality indicator associated with a ground truth may be determined by the WTRU 102, PRU, and / or network. For example, the network may determine the ground truth and associated measurements based on measurements reported by the WTRU 102 and / or PRU. In some embodiments, the network may perform interpolation and / or extrapolation using the ground truths and measurements reported by the WTRU 102(s) and / or PRU(s), and may derive a new pair of a virtual ground truth and associated measurements. For example, the virtual ground truths may be identified as or associated with virtual WTRUs or PRUs by the network or WTRU 102. The WTRU 102 may receive an indication form the network whether any of the measurements and / or ground truths indicated in assistance information are actual measurements and / or ground truths derived by the WTRU 102 or PRU or virtual measurements and / or ground truth derived by the network.

[0421] FIG. 21 is a signaling diagram illustrating an example of ground truth acquisition. In the example shown in FIG. 21, a second WTRU 102b (e.g., a PRU) may receive PRS configurations from the network (e.g., LMF) at 2102 and PRSs from the gNB 180 at 2104. The second WTRU 102b makes measurements on the received PRS and reports the measurements to the LMF 600 at 2108. A first WTRU 102a may make a request for ground truth at 2106 may receive the ground truth of the second WTRU 102b from the LMF 600 as assistance information which may contain measurements or an inference made by the second WTRU 102b, a ground truth of the second WTRU 102b and / or a ground truth determined by the second WTRU 102b.

[0422] When the ground truth for the second WTRU 102b is provided by the network, the first WTRU 102a may receive information indicating any of the following from the network: (i) a ground truth of the second WTRU 102b; (ii) a ground truth label quality indicator (e.g., hard or soft indicator) associated with the ground truth; (iii) measurements associated with the ground truth; (iv) one or more PRS configurations (e.g., PRS resource IDs) associated with the measurements which indicates PRS information used to obtain measurements at the second WTRU 102b; (v) an identity of the second WTRU 102b (e.g., PRU ID, UE ID, RNTI associated with the WTRU); (vi) a type of ground truth or measurements (e.g., actual ground truth or actual measurements, virtual ground truth, virtual measurements); (vii) timestamp(s) of the measurements indicating when they are reported by the second WTRU 102b; (viii) timestamp(s) of the measurements indicating when they are made by the second WTRU 102b; and / or (ix) any method(s) used to derive the ground truth (e.g., PRU, RAT dependent positioning method such as DL-TDOA).

[0423] In certain representative embodiments, a WTRU 102 may send a request for ground truth information. For example, the request may include information indicating any of the following: (i) a threshold for the ground truth label quality indicator (e.g., indicating the WTRU’s request to obtain a ground truth with an associated ground truth indicator above the threshold); (ii) a periodicity for provisioning of the ground truth; (iii) whether the WTRU 102 requests a same or different ground truths for each provisioning of the ground truths; and / or (iv) a number of repetitions per ground truth (e.g., N). The WTRU 102 may receive, from the network, configuration information which may include any of the following: (i) the number of ground truths (e.g., M); (ii) the number of repetitions; and / or (iii) the periodicity of the provisioning of ground truths. For each ground truth from the network, the WTRU 102 may receive the ground truth, associated ground truth indicator and measurements (e.g., RSTD, CIR, timing measurements, power measurements or phase measurements) associated with the ground truth for N occasions (e.g., the WTRU 102 receives assistance information containing the ground truth and associated information at N different occasions). For example, the WTRU 102 may receive timestamp(s) and information indicating any PRS configurations associated with the measurements. The WTRU 102 may receive assistance information for each of the M ground truths at the N repetition factor per ground truth at the configured periodicity. The WTRU 102 may send a message to the network, requesting to terminate the provisioning of the ground truths and / or associated information.

[0424] FIG. 22 is a signaling diagram illustrating an example of provisioning ground truth information with repetitions. In FIG. 22, M=2 (the number of ground truths) and N=3 (the number of repetitions) are assumed as examples. A first WTRU 102a may send a request to the network for ground truth information. The measurements reported by a second WTRU 102b and a PRU 1502 are used to derive the ground truths. Both the second WTRU 102b and the PRU 1502 may report measurements to the network periodically.

[0425] In the example of FIG. 22, the requested number of ground truths and / or requested number of repetitions may be different from configured number of ground truths and number of repetitions.

[0426] Example Embodiments

[0427] FIG. 23 is a signaling diagram illustrating an example of verification of an AI / ML model using PRU measurements. In FIG. 23, a WTRU 102 may send WTRU capability information (e.g., model ID the WTRU 102 carries, the cell ID of the previous cell) to the network (e.g., gNB 180) at 2302. The WTRU 102 may send a request for assistance information at 2304. The WTRU 102 may include a request for inference and / or measurements from PRUs in the cell. The WTRU 102 may additionally include desired locations of PRUs in the request.

[0428] The WTRU 102 may receive one or more PRS configurations from the network (e.g., PRS resource IDs to make measurements) at 2306. The WTRU 102 receives a PRS from the network at 2308. The WTRU 102 may perform PRS measurement on the received PRS at 2310. The PRU 1502 may perform PRS measurement on the PRS at 2310. The PRU 1502 may send a measurement report to the network at 2312. The WTRU 102 may receive measurements and / or an inference made by the PRU from the network at 2314. The measurement information may include PRS resource IDs that PRUs used to make measurements. The measurement and / or inference information may include information about the AI / ML model used by the PRU (e.g., model ID, associated PRS configuration(s)) to generate inference, measurements used as inputs for the AI / ML model and / or PRU location, for example.

[0429] Based on the received measurements and / or inference from the network, the WTRU 102 may determine to verify the AI / ML model at the WTRU 102 at 2316. Once the model is verified, the WTRU 102 may determine to perform any of the following at 2318: (i) send an indication that fine tuning is completed (e.g., fine tuning is performed with the current AI / ML model); (ii) send an indication of association information (e.g., cell ID) of a new model; (iii) send an indication the model used in the previous cell is used again; and / or (iv) send an indication that the WTRU 102 falls back to the fallback positioning method.

[0430] The WTRU 102 may determine its position and report the position to the network.

[0431] In an example embodiment, the WTRU 102 may move to a new cell (e.g., due to mobility), The WTRU 102 may indicate WTRU capability information (e.g., support for WTRU- based AI / ML-based positioning) to the network.

[0432] The WTRU 102 may send a request for assistance information (e.g., PRU location, PRU’ s inference, time stamp, associated measurements) indicating required uncertainty (e.g., standard deviation) for PRU inference, desired association information (e.g., desired SSBs) and / or a cell ID of the previous cell.

[0433] The WTRU 102 may be configured with a fallback positioning method (e.g., DL-TDOA).

[0434] The WTRU 102 may perform measurements on a configured set of PRSs within a configured time window (e.g., periodic, duration).

[0435] The WTRU 102 may receive assistance information (e.g., PRU measurements corresponding PRU inference, PRU location) from the network (e.g., periodically). For example, the assistance information may include information indicating a duration of the provisioning of assistance information, such as where the duration is the same as the duration of the time window.

[0436] At the end of the provisioning of the assistance information (or if the WTRU 102 receives a request from the network), the WTRU 102 may report information indicating any of the following: (i) fine tuning is completed (e.g., fine tuning is performed with the current AI / MLmodel); (ii) association information (e.g., cell ID) of a new model; (iii) the model used in the previous cell is used again; and / or (iv) the WTRU 102 falls back to the fallback positioning method.

[0437] Reference-based AI / ML Model Determination

[0438] In certain representative embodiments, a WTRU 102 may perform a reference-based AI / ML model determination.

[0439] In certain representative embodiments, an AI / ML model may be associated with an area defined by a set of PRSs. A WTRU 102 may be configured with N sets of PRSs (e.g., associated with N areas). Based on a measurement condition associated with a PRS set (e.g., average RSRP above / below a configured threshold), the WTRU 102 may determine whether to use a different model or not. The WTRU 102 may transmit AI / ML output, fallback positioning output (e.g., WTRU location estimate), and / or measurements used for AI / ML and / or fallback positioning method to the network for verification purposes (e.g., for a configured duration).

[0440] Association of AI / ML Model with Area

[0441] In certain representative embodiments, an AI / ML model may be associated with an area. The area may be defined as a collection of cells (e.g., indicated by cell ID), PRS resource IDs, PRS resource set IDs and / or TRP IDs. The WTRU 102 may be configured with a reference (e.g., cell ID, PRS resource ID(s), SSB ID(s), TRP ID(s)) associated with the area and / or AI / ML model.

[0442] FIG. 24 is a system diagram illustrating an example of a WTRU 102 moving from one PRS set to another PRS set. In FIG. 24, the WTRU 102 may, for example, be configured with two sets of PRS resources, namely a PRS set #1 and a PRS set #2.

[0443] The WTRU 102 may (e.g., initially) make measurements on the PRS set #1. Due to mobility, the WTRU 102 may move to another area, where the PRS set #2 may have a higher RSRP than the RSRP measured for the PRS set #1. The WTRU 102 may be configured with an AI / ML model associated with the PRS set #1, and the WTRU 102 may determine to use this AI / ML model if the RSRP associated with the PRS set #1 is above a preconfigured threshold.

[0444] Due to mobility, for example, the WTRU 102 moves into another area and observes that the RSRP corresponding to the PRS set #1 is lower than the threshold, the WTRU 102 may determine to verify the AI / ML model that it uses. The WTRU 102 may make measurements on the PRS set #2 and if the WTRU 102 determines that the RSRP of the PRS set #2 is higher than the preconfigured threshold, the WTRU 102 may determine to use the AI / ML model associated with the PRS set #2 (e.g., if available at the WTRU 102).

[0445] In FIG. 24, the WTRU 102 may be configured with an AI / ML model that is associated with an area encompassing the area that the PRS set #1 and the PRS set #2 are associated with. For example, TRP1, TRP2, TRP3 and TRP4 in FIG. 23 may be located within the area. In anexample, the WTRU 102 may determine to use the measurements made from any of the TRPs in the area as the input to the AI / ML model (e.g., as long as the WTRU 102 is located within the area).

[0446] Examples of References and Conditions

[0447] In certain representative embodiments, a WTRU 102 may be configured with a reference associated with a group (e.g., a set of cells, PRS resources, PRS resource sets, TRPs, or SSB IDs). The WTRU 102 may perform measurements (e.g., RSRP) on the reference and determine whether the measurements satisfy one or more conditions. If the one or more conditions are satisfied, the WTRU 102 may determine to use the AI / ML model associated with the reference (e.g., the group the reference is associated with).

[0448] In certain representative embodiments, a WTRU 102 may be configured with multiple (e.g., a set of) references associated with multiple (e.g., a set of) groups. The WTRU 102 may be configured with an AI / ML model associated with each group. The WTRU 102 may be configured with the reference so that the WTRU 102 can determine an AI / ML model to use based on the measurement on the reference. The reference may be one of the signals or resources from the set and the WTRU 102 may receive an indication from the network indicating which signal or resource to use as the reference.

[0449] For example, if the WTRU 102 is configured with a set of PRS resources, the reference may be one of the PRS resources. The WTRU 102 may be configured with a resource ID, by the network, indicating which PRS resource to use as the reference. Another example of a reference may be an SSB from one of the cells in a set of cells. In this case, the WTRU 102 may receive a cell ID and SSB ID, from the network, indicating which SSB to use as the reference.

[0450] FIG. 25 is a block diagram illustrating an example configuration of associations between AI / ML models, SSBs, and references. In FIG. 25, each AI / ML model may be associated with a set (e.g., group) of SSBs or other DL RSs. For example, the AI / ML model #1 is associated with a SSB ID#1 and a SSB ID#2 while the AI / ML model #2 is associated with a SSB ID#3 and a SSB ID#4. The WTRU 102 may receive information indicating to use the SSB ID#1 and the SSB ID#4 as the references for the AI / ML model #1 and AI / ML model #2, respectively.

[0451] In certain representative embodiments, a reference may be a collection or a group of signals and / or resources. For example, a WTRU 102 may receive a request from the network to use a group of PRS resources as the reference. In this case, the WTRU 102 may determine to process and / or aggregate measurements from the group of PRS resources (e.g., average RSRP from the group of PRS resources) and determine whether the processed and / or aggregated measurements satisfy the condition. For example, the WTRU 102 may be configured with N PRS resources as a reference. The WTRU 102 may determine to average the RSRP measured from theN PRS resources and compare the averaged RSRP against the condition to determine whether the AI / ML model associated with the N PRS resources or the AI / ML model associated with the group of PRS resources that the N PRS resources are associated with should be used or not.

[0452] Switching Models Associated with an Area based on Measurement Conditions

[0453] In certain representative embodiments, a WTRU 102 may be configured with multiple sets (e.g., groups) of TRPs and the TRPs may be located within a preconfigured area (e.g., consisting of multiple cells). The WTRU 102 may determine to use measurements from different sets of TRPs and use them as inputs to the AI / ML model, such as when a condition(s) is satisfied (e.g., above or below a preconfigured threshold). If the condition is not satisfied, the WTRU 102 may determine to use the measurements from another set of TRPs, which satisfies the condition(s), as inputs to the AI / ML model. The WTRU 102 may determine to use the measurements from a configured set of TRPs (e.g., a first set, as inputs to the AI / ML model if the measurement of RSRP of the reference associated with the set of TRPs, such as SSBs transmitted from one of the TRPs, satisfy a condition). If the measurements from the set of TRPs does not satisfy the condition, the WTRU 102 may determine to make measurements on a different set (e.g., a second set of TRPs). If the WTRU 102 makes measurements on PRSs from the second set of TRPs and they satisfy the condition, the WTRU 102 may determine to use the measurements from the second set of TRPs as an input to the AI / ML model.

[0454] FIG. 26 is a block diagram illustrating another example configuration of associations between AI / ML models, SSBs, and references. In FIG. 26, the AI / ML model #1 is associated with a SSB ID#1, a SSB ID#2, a SSB ID#3 and a SSB ID#4. The AI / ML model #2 is associated with a SSB ID#5, a SSB ID#6, a SSB ID#7 and a SSB ID#8. The WTRU 102 may receive, from the network, a configuration message indicating the SSB ID#1 and the SSB ID#2 should be used as the reference for the AI / ML model #1. The WTRU 102 may receive a configuration message indicating the SSB ID#6, the SSB ID#7 and the SSB ID#8 should be used as the reference for the AI / ML model #2. The WTRU 102 may be configured with the same or different number of signals or reference signals to be used as the reference per AI / ML model.

[0455] For example, a WTRU 102 may be configured or requested to monitor measurements (e.g., RSRP) of the reference. The WTRU 102 may be configured with a reference signal (e.g., PRS) or signal (e.g., SSB) associated with the area. The WTRU 102 may also be configured with a threshold by the network. The WTRU 102 may be configured with multiple AI / ML models where each model may be associated with an area. If, for example, the RSRP of the SSB associated with the area is below a threshold, the WTRU 102 may determine whether a different model which may be associated with a different area, available at the WTRU 102, should be used.

[0456] Example Embodiments

[0457] In certain representative embodiments, a WTRU 102 may receive a request from the network to perform AI / ML-based positioning. The WTRU 102 may report its location to the network. For example, the location may be determined based on a RAT independent positioning method (e.g., GNSS).

[0458] In certain representative embodiments, a WTRU 102 may receive more than one set of PRS resource IDs, a fallback positioning method (e.g., GNSS, RAT dependent positioning method) and verification duration (e.g., 10 seconds), and / or RSRP threshold from the network.

[0459] The WTRU 102 may determine to use an AI / ML model associated with a set of PRS resources yielding at least K PRS resources associated with the highest RSRP (e.g., first measurement, first PRS set).

[0460] The WTRU 102 may determine AI / ML input values (e.g., channel impulse response) for the AI / ML model based on the measurements from the associated set of PRSs. For example, the WTRU 102 may determine the channel impulse response based on the associated set of PRSs with the AI / ML model. The WTRU 102 may determine to report, to the network, the CIR and the PRS resource(s) measured to determine the CIR. The WTRU 102 may receive, from the network, an indication of the PRS resource(s) to use to determine the CIR.

[0461] If the (e.g., averaged) RSRP (e.g., second measurement) of the associated set of PRSs falls below the RSRP threshold (e.g., due to WTRU mobility), the WTRU 102 may determine to use the AI / ML model associated with one (e.g., a second PRS set) of the preconfigured sets of PRSs with the highest (e.g., average) RSRP.

[0462] The WTRU 102 may indicate to the network which set of resources it is using. The WTRU 102 may send a location estimate generated by the AI / ML model and a fallback positioning method (e.g., GNSS, RAT dependent positioning method), and corresponding measurements (e.g., CIR, raw measurements such as RSRP, RSTD, measurements used for the fallback RAT dependent positioning method, AI / ML positioning method) for the verification duration (or until the WTRU 102 receives a termination message from the network).

[0463] If the WTRU 102 does not have an AI / ML model that is associated with one of the preconfigured sets of PRSs with the highest (e.g., average) RSRP, the WTRU 102 may determine to use the fallback positioning method.

[0464] FIG. 27 is a signaling diagram illustrating an example of PRS-area based AI / ML model determination. In FIG. 27, the WTRU 102 may indicate WTRU capability information to the network at 2702. The WTRU 102 may receive N sets of PRS configurations from the network at 2704. The WTRU 102 may receive PRSs at 2706 and perform measurements on the received PRSs at 2708. The WTRU 102 may perform verification on the AI / ML models at the WTRU 102 at2710. After the verification, the WTRU 102 may indicate which AI / ML model the WTRU 102 will use to the network at 2712.

[0465] In certain representative embodiments, a WTRU 102 may indicates WTRU capability information (e.g., support for WTRU-based AI / ML-based positioning) to the network. The WTRU 102 may receive a request for AI / ML-based positioning from the network. The WTRU 102 may report its location (e.g., based on RAT dependent positioning, GNSS) to the network. The WTRU 102 may be configured with N sets of PRSs, a fallback positioning method (e.g., GNSS, RAT dependent positioning method) and verification duration (e.g., 10 seconds), and a RSRP threshold. The WTRU 102 may determine to use an AI / ML model associated with a PRS set yielding at least K PRSs associated with the highest RSRP (e.g., from first measurements of a first PRS set)

[0466] The WTRU 102 may determine AI / ML input values (e.g., CIR) for the AI / ML model based on the measurements from the associated set of PRSs

[0467] If the averaged RSRP of the associated set of PRSs falls (e.g., using second measurements) below the RSRP threshold (e.g., due to WTRU mobility), the WTRU 102 may determine to use the AI / ML model associated with one (e.g., a second PRS set) of the preconfigured sets of PRSs with the highest average RSRP.

[0468] The WTRU 102 may indicate to the network which set it is using. The WTRU 102 may send a location estimate generated by the AI / ML model and a fallback positioning method (e.g., GNSS, RAT dependent positioning method), and corresponding measurements (e.g., CIR, raw measurements like RSRP, RSTD, measurements used for the fallback RAT dependent positioning method and / or AI / ML positioning method) for the verification duration (or until the WTRU 102 receives a termination message from the network).

[0469] If the WTRU 102 does not have an AI / ML model that is associated with one of the preconfigured sets of PRSs with the highest average RSRP, the WTRU 102 may fall back to the fallback positioning method.

[0470] Timing Advance based AI / ML Model Determination

[0471] In certain representative embodiments, an AI / ML model may be associated with a timing advance (TA) value (e.g., for a TRP). A WTRU 102 may determine a TA and associated AI / ML model. If the TA value changes, the WTRU 102 may determine to use an AI / ML model associated with the range that the changed (e.g., new) TA value falls into. When the ranges from different TRPs overlap, the WTRU 102 may determine the AI / ML model based on prioritization rules.

[0472] Association of an AI / ML Model with TA Range

[0473] In certain representative embodiments, a WTRU 102 may be configured with AI / ML model(s) associated with TA values. An AI / ML model may be associated with one TRP or a specific TRP indicated by a TRP ID.

[0474] FIG. 28 is a system diagram illustrating an example of TRPs and timing advances (TAs) associated with AI / ML models. In FIG. 28, a WTRU 102 may be configured with multiple AI / ML models, such as an AI / ML model #1 and an AI / ML model #2. The WTRU 102 may be configured with range(s) of TA values based on which the WTRU 102 may use to determine which AI / ML model to use. The AI / ML model #1 is associated with TA values between the range of 0 and TAI (e.g., in units of seconds). The AI / ML model #2 is associated with TA values between TAI and TA2. For TA values between TA2 and TA3, the WTRU 102 may determine to use a configured RAT dependent positioning method. As another example, for any values over TA2, the WTRU 102 may determine to use a configured RAT dependent positioning method.

[0475] In certain representative embodiments, a WTRU 102 may be configured to allow the WTRU 102 to use an AI / ML model based a distance from a reference point. The WTRU 102 may have an AI / ML model that is optimized for area close to the reference point and another AI / ML model that is far away from the reference point. For example, the AI / ML model that is trained at any locations far away from the reference point may be trained with measurements (e.g., CIR) with multipath or many NLOS paths. On the other hand, AI / ML models that are trained closer to the reference point may be trained based on the measurements that are mostly based on LOS paths.

[0476] In FIG. 28, there are three threshold values, TAI, TA2 and TA3. For example, the WTRU 102 may receive the threshold values from the network. For example, the WTRU 102 may determine the threshold values based on WTRU capability. As can be seen in FIG. 28, the AI / ML models are associated with a distance from TRPs #1 and #2 (e.g., the gNBs or reference points in a cell) with respect to which TAs are defined.

[0477] Configuration of TA Range

[0478] In certain representative embodiments, a WTRU 102 may send assistance information to the network indicating capabilities of the AI / ML models at the WTRU 102. For example, the WTRU 102 may indicate to the network the ranges of TA values associated with the AI / ML models. In another example, the WTRU 102 may indicate location(s) at which AI / ML models are trained.

[0479] For example, the WTRU 102 may receive a request to send its location to the network. Based on the request, the WTRU 102 may determine to send its location which is determined based on RAT dependent positioning method(s) (e.g., DL-TDOA) or RAT independent positioning method (e.g., GNSS).

[0480] For example, based on the assistance information or WTRU capabilities, the WTRU 102 may receive ranges of TA values from the network based on which the WTRU 102 determines which AI / ML model(s) to use. If the WTRU 102 does not receive ranges of TA values from the network, the WTRU 102 may determine which AI / ML model to use based on the ranges of TAs associated with the AI / ML model(s) at the WTRU 102.

[0481] For example, if the WTRU 102 is configured with more than one TA range, where each range is associated with a TRP, the WTRU 102 may also receive an index or ID associated with each TA range.

[0482] Solving Ambiguity in Configurations

[0483] In certain representative embodiments, a range may be associated with a TRP or gNB. The WTRU 102 may need to determine which model to use based on the TA value(s) transmitted from the network. As shown in FIG. 28, each of TRP1 and TRP2 are associated with respective range(s). For example, the WTRU 102 may receive two TA values each associated with TRP1 and TRP2. Based on each TA value, the WTRU 102 may determine which TRP and associated AI / ML model to use for determination of its location.

[0484] For example, the WTRU 102 may be located in an area where the TA ranges associated with the TRPs overlap (e.g., TA2 and TA3) as shown in FIG. 28. In this case, the WTRU 102 may need to determine which TA range to associate the AI / ML model at the WTRU 102. In one example, the WTRU 102 may determine to choose a TA range based on a configured priority rule.

[0485] For example, if the WTRU 102 needs to determine between a conventional positioning method and an AI / ML-based positioning due to the overlapping TA ranges (e.g., between 2 TRPs), the WTRU 102 may prioritize AI / ML-based positioning and the WTRU 102 may indicate a TRP ID or TA range index of the associated AI / ML model.

[0486] In certain representative embodiments, an AI / ML model may be associated with any TRP.

[0487] For example, if the WTRU 102 needs to determine between two AI / ML models each associated with different values of TAs, the WTRU 102 may determine to use the AI / ML model associated with the smaller TA value. For example, in FIG. 28, the WTRU 102 may receive TA commands from 2 TRPs where the TA value associated with the TRP1 falls (e.g., in the range) between TAI and TA2 and the TA value associated with the TRP2 falls (e.g., in the range) between TA2 and TA3. In this example, since the TA value associated with TRP1 is smaller than the TA value associated with TRP2, the WTRU 102 may determine to use the AI / ML model associated with the range between TAI and TA2 (e.g., AI / ML model #2). The WTRU 102 may report to the network that the AI / ML model associated with the range between TAI and TA2 is used. The WTRU 102 may report that the measurements on PRSs transmitted from TRP1 are used as input to the AI / ML model #2.

[0488] In certain representative embodiments, an AI / ML model may be associated with a specific TRP.

[0489] For example, if the WTRU 102 is configured with an AI / ML model associated with a specific TRP, the WTRU 102 may determine which AI / ML model to use based on TA values associated with TRPs. For example, the WTRU 102 may be configured with a first set of AI / ML models associated with TRP1 where each AI / ML model may be associated with a different TA value or range of TA values.

[0490] Example Embodiments

[0491] In certain representative embodiments, a WTRU 102 may indicate to the network the WTRU capability information which may indicate support for TA-associated AI / ML models and / or availability of AI / ML models. The WTRU 102 may receive a request from the network to perform AI / ML-based positioning. The WTRU 102 may be configured with threshold(s) for TA values and TRP locations. The thresholds may be associated with TRP(s). The WTRU 102 may receive a configuration for the fallback positioning method. If the WTRU 102 receives a TA command from the network (e.g., via MAC message), the WTRU 102 may determine which AI / ML model to use based on a TA value indicated in the TA command.

[0492] If there is a change in TA and the TA is within one of the preconfigured ranges (e.g., defined by thresholds), the WTRU 102 may determine to use the AI / ML model associated with the range. If the WTRU 102 is not configured with an AI / ML model that corresponds to the TA (e.g., the TA is below or above the minimum or maximum range of TA values), the WTRU 102 may determine to fall back to the fallback positioning method.

[0493] For example, the WTRU 102 may (e.g., need to) determine between a conventional positioning method and an AI / ML-based positioning due to the overlapping ranges (e.g., between 2 TRPs). The WTRU 102 may prioritize AI / ML-based positioning and indicate a TRP ID of the associated AI / ML model.

[0494] For example, the WTRU 102 may (e.g., need to) determine between two AI / ML models that are each associated with different values of TAs, and the WTRU 102 may determine to use the AI / ML model associated with a smaller TA value.

[0495] In certain representative embodiments, a WTRU 102 may indicate WTRU capability information (e.g., support for TRP -based AI / ML model) to the network. The WTRU 102 may be configured with TRP locations, ranges of TA values and AI / ML model(s) that are associated with each range by the network. The AI / ML models may be configured in common for the configured TRPs. The WTRU 102 may be configured with a fallback positioning method (e.g., DL-TDOA). The WTRU 102 may receive a request for AI / ML-based positioning from the network. The WTRU 102 may receive a TA command from the network. The TA command may containmultiple TA values specific to each of the TRPs. Based on the TA value and the preconfigured range that the TA values falls into, the WTRU 102 may determine the AI / ML model. If there is a change in TA and the TA is within one of the preconfigured ranges, the WTRU 102 determines to use the AI / ML model associated with the one of the ranges that the TA is within.

[0496] If the WTRU 102 is not configured with an AI / ML model that corresponds to the TA (e.g., the TA is below or above the minimum or maximum range of the TA values), the WTRU 102 may determine to fall back to a fallback positioning method.

[0497] For example, if the WTRU 102 needs to determine between a conventional positioning method and AI / ML-based positioning due to the overlapping ranges (e.g., between 2 TRPs), the WTRU 102 may prioritize AI / ML-based positioning and indicate a TRP ID of the associated AI / ML model.

[0498] For example, if the WTRU 102 needs to determine between two AI / ML models, each associated with different values of TA, the WTRU 102 may determine to use the AI / ML model associated with a smaller TA value.

[0499] PFL based AI / ML Model Determination

[0500] In certain representative embodiments, an AI / ML model may be associated with an initial set of PFLs. The WTRU 102 may determine whether to use the same AI / ML model (e.g., as a previous cell) or use a fallback positioning method in a new cell based on whether a PFL configuration in the new cell contains or is a subset of the initial set of PFLs.

[0501] Association of an AI / ML Model with Frequency Layers

[0502] In certain representative embodiments, a WTRU 102 may be configured with an AI / ML model (e.g., a first AI / ML model) that is associated with a set of PRS configurations (e.g., a first set of PRS configurations). The WTRU 102 may use the AI / ML model to determine the WTRU location. For example, if a PRS configuration is updated and the updated PRS configuration contains the set of PRS configurations, the WTRU 102 may determine to use the first AI / ML model for determination of the WTRU location. For example, if the updated PRS configuration is a subset of the first set of PRS configuration, the WTRU 102 may determine to use the first AI / ML model to determine the WTRU location.

[0503] For example, the WTRU 102 may determine to associate AI / ML model(s) with the configured frequency layers. When the WTRU 102 is configured with another set of frequency layers, the WTRU 102 may determine the AI / ML model in use can be used or not.

[0504] For example, the WTRU 102 may determine to use the same AI / ML model if the updated PRS configuration contains at least one of the positioning frequency layers associated with the AI / ML model.

[0505] FIG. 29 is a system diagram illustrating an example of a determination of an AI / ML model due to mobility.

[0506] In FIG. 29, the WTRU 102 is configured with three frequency layers in the area associated with TRP 1-1 (e.g., cell #1). The three frequency layers are PFL#1, PFL#2 and PFL#3. The WTRU 102 has an AI / ML model associated with PFL#1, PFL#2 and PFL#3 (e.g., trained with measurements made with PFL#1, PFL#2 and PFL#3). The WTRU 102 moves into another area associated with TRP 2-1 (e.g., cell #2). The WTRU 102 may be configured with a new set of frequency layers (e.g., only PFL#2). Since the AI / ML model is associated with PFL#2, the WTRU 102 may determine to (e.g., continue to) use the same model. The WTRU 102 may move to the area associated with TRP 3-1 (e.g., cell #3). In this area, the WTRU 102 may be configured with (e.g., only) PFL#3. Since the AI / ML model at the WTRU 102 is associated with PFL#3, the WTRU 102 may determine to (e.g., continue) to use the same model.

[0507] FIG. 30 is a system diagram illustrating another example of a determination of an AI / ML model due to mobility.

[0508] In FIG. 30, the WTRU 102 is configured with PFL#2 in the area associated with TRP 1- 1 (e.g., cell #1). The WTRU 102 may train the AI / ML model with measurements obtained using PFL#2. When the WTRU 102 moves to the (e.g., new) area associated with the TRP 2-1 (e.g., cell #2), the WTRU 102 may be configured with three frequency layers (e.g., PFL#1, PFL#2 and PFL#3). Since PFL#2, which was previously associated with the AI / ML model at the WTRU 102, is one of the configured PFLs, the WTRU 102 may determine to (e.g., continue to) use the same AI / ML model. The WTRU 102 may move into an area associated with TRP 3-1 where the WTRU 102 is configured with (e.g., only) PFL#3. Since PFL#3 is not associated with the AI / ML model at the WTRU 102, the WTRU 102 may determine to (e.g., switch to) use a fallback positioning method (e.g., DL-TDOA) which may be configured by the network.

[0509] FIG. 31 is a system diagram illustrating another example of a determination of an AI / ML model due to mobility. In FIG. 31, the WTRU 102 is configured with three frequency layers in the area associated with TRP 1-1 (e.g., cell #1). The three frequency layers are PFL#1, PFL#2 and PFL#3. The WTRU 102 has an AI / ML model associated with PFL#1, PFL#2 and PFL#3 (e.g., trained with measurements made with PFL#1, PFL#2 and PFL#3). The WTRU 102 may move into another (e.g., new) area associated with TRP 2-1 (e.g., cell #2). The WTRU 102 may be configured with a new set of frequency layers, namely PFL#1 and PFL#2. Since the AI / ML model is associated with both PFL#1 and PFL#2, the WTRU 102 may determine to (e.g., continue to) use the same model. The WTRU 102 may move to a (e.g., new) area associated with TRP 3-1 (e.g., cell #3). In this area, the WTRU 102 may be configured with PFL#3. Since the AI / ML modelat the WTRU 102 is associated with PFL#3, the WTRU 102 may determine to (e.g., continue to) use the same model.

[0510] For example, a WTRU 102 may determine to use the same AI / ML model if the input of the AI / ML model is a timing measurement.

[0511] For example, if the WTRU 102 determines to use the same AI / ML model, the WTRU 102 may send, to the network, information indicating the same AI / ML model, which may be configured at the initiating reference point (e.g., the cell where the AI / ML model is associated), is used.

[0512] For example, the WTRU 102 may determine to associate an AI / ML model to a PRS configuration at cell #1 based on an indication from the network (e.g., indication to associate an AI / ML model to the indicated PRS configuration) where cell #1 becomes the reference point. If the WTRU 102 moves to another cell, and the WTRU 102 determines to use the same AI / ML model based on a condition (e.g., PFLs in the new PRS configuration are a subset of the PFLs associated with the AI / ML model), the WTRU 102 may send, to the network, information indicating the same AI / ML model is used.

[0513] For example, the reference may be a first (e.g., initial) PRS configuration that is associated with the AI / ML model. The WTRU 102 may be configured with a PRS configuration. The WTRU 102 may determine to associate an AI / ML model with the PRS configuration (e.g., initial PRS configuration). The WTRU 102 may receive update to the first PRS configuration or a second (e.g., new) PRS configuration from the network. The WTRU 102 may determine to use the same AI / ML model if one or more PRS parameters, which are a part of the first PRS configuration associated with the AI / ML model, are included in or are part of the updated or second PRS configuration.

[0514] For example, if a fallback positioning method (e.g., RAT dependent positioning method) is used, the WTRU 102 may indicate that the fallback positioning method is used.

[0515] In certain representative embodiments, a WTRU 102 may indicate WTRU capability information (e.g., support for TRP -based AI / ML model) to the network. The WTRU 102 may be configured with a fallback positioning method (e.g., DL-TDOA). The WTRU 102 may be configured with AI / ML positioning by the network where an AI / ML model is associated with a set of PFLs (e.g., an initial PFL set). The WTRU 102 may receive PRS configurations from the network (e.g., supported PFL) for a current cell. The WTRU 102 may determine a positioning method according to one of the following. If the WTRU 102 is configured with aggregated PFLs and the initial PFL set is a subset of the aggregated PFLs, the WTRU 102 may determine to use the same AI / ML model. If the WTRU 102 is configured with aggregated PFLs and the aggregated PFLs contain the initial PFL set, the WTRU 102 may determine to use the same AI / ML model. Ifthe WTRU 102 is configured with a PFL which is not included in the initial PFL set, the WTRU 102 may determine to use the fallback positioning method.

[0516] FIG. 32 is a procedural diagram illustrating an example of AI / ML model verification. In certain representative embodiments, the procedure of FIG. 32 may be implemented (e.g., as a method) by a WTRU 102. At 3202 in FIG. 32, a WTRU 102 may send, to a network, a request for assistance information including any of a PRU location, a PRU inference of the PRU location, a set of PRSs associated with the PRU inference, a first set of measurements associated with the PRU inference, and / or a cell identifier associated with the PRU inference. At 3204, the WTRU 102 may receive the assistance information. At 3206, the WTRU 102 may obtain an inference of a WTRU location from an AI / ML model. At 3208, the WTRU 102 may verify the obtained inference based on the assistance information. At 3210, the WTRU 102 may send, to the network, a result of the verifying of the obtained inference.

[0517] For example, the WTRU 102 may send, to the network, WTRU capability information indicating support for AI / ML-based positioning (e.g., prior to 3202).

[0518] For example, the obtaining the inference from the AI / ML model at 3206 may include inputting measurement information associated with the first set of measurements to the AI / ML model.

[0519] For example, the WTRU 102 may perform a second set of measurements on the set of PRSs. At 3206, the obtaining of the inference from the AI / ML model may include inputting measurement information associated with the second set of measurements to the AI / ML model.

[0520] For example, the verifying of the obtained inference at 3208 may include determining a difference between (i) the obtained inference and (ii) the PRU location and / or the PRU inference. At 3210, the result may include information indicating tuning of the AI / ML model by the WTRU based on the determined difference being less than a threshold.

[0521] For example, the verifying the obtained inference at 3208 may include determining a difference between (i) the obtained inference and (ii) the PRU location and / or the PRU inference. At 3210, the result may include information indicating an identifier of the AI / ML model based on the determined difference being less than a threshold.

[0522] For example, the verifying the obtained inference at 3208 may include determining a difference between (i) the obtained inference and (ii) the PRU location and / or the PRU inference. At 3210, the result may include information indicating an identifier of another AI / ML model based on the determined difference being greater than or equal to a threshold.

[0523] For example, the verifying the obtained inference at 3208 may include determining a difference between (i) the obtained inference and (ii) the PRU location and / or the PRU inference.At 3210, the result may include information indicating an identifier of a fallback positioning method based on the determined difference being greater than or equal to a threshold.

[0524] FIG. 33 is a procedural diagram illustrating an example of switching AI / ML models. In certain representative embodiments, the procedure of FIG. 33 may be implemented (e.g., as a method) by a WTRU 102. At 3302, a WTRU 102 may receive configuration information indicating a plurality of sets of PRSs. At 3304, the WTRU 102 may obtain first measurement information associated with the plurality of sets of PRSs. At 3306, the WTRU 102 may select a first set of the plurality of sets of PRSs based on the first measurement information associated with the plurality of sets of PRSs. At 3308, the WTRU 102 may obtain an inference of a WTRU location from a first AI / ML model associated with the first set. At 3310, the WTRU 102 may obtain second measurement information associated with the plurality of sets of PRSs. At 3312, the WTRU 102 may send, to the network, information indicating a second AI / ML model based on the second measurement information associated with the first set being below a threshold. The second AI / ML model may be associated with a second set of the plurality of sets of PRSs.

[0525] For example, the obtaining of the inference of the WTRU location from the first AI / ML model at 3308 may use the first measurement information associated with the first set as an input to the first AI / ML model.

[0526] For example, the selecting the first set of the plurality of sets of PRSs at 3306 may be based on the first measurement information associated with the first set being highest among the plurality of sets of PRSs.

[0527] For example, the second set of the plurality of sets of PRSs may be selected by the WTRU 102 based on the second measurement information associated with the second set being highest among the plurality of sets of PRSs (e.g., other than the first set).

[0528] For example, the first measurement information may include reference signal received power (RSRP) values of each of the plurality of sets of PRSs during a first time interval.

[0529] For example, the second measurement information may include reference signal received power (RSRP) values of each of the plurality of sets of PRSs during a second time interval.

[0530] For example, the WTRU 102 may receive information indicating an association of the second AI / ML model and the second set.

[0531] FIG. 34 is a procedural diagram illustrating another example of switching AI / ML models. In certain representative embodiments, the procedure of FIG. 32 may be implemented (e.g., as a method) by a WTRU 102. At 3402, a WTRU 102 may receive, from a network, configuration information indicating a plurality of TA ranges which are associated with a plurality of AI / ML models. At 3404, the WTRU 102 may receive a TA command including information indicating a first TA value. At 3406, the WTRU 102 may select a first AI / ML model, from among the pluralityof AI / ML models, that is associated with a first TA range, of the plurality of TA ranges, which includes the first TA value. At 3408, the WTRU 102 may determine a second TA value (e.g., from another TA command which updates the first TA value). At 3410, the WTRU 102 may select a second AI / ML model, from among the plurality of AI / ML models, that is associated with a second TA range, of the plurality of TA ranges, which includes the second TA value.

[0532] For example, the WTRU 102 may obtain an inference of a WTRU location from the first AI / ML model.

[0533] For example, the WTRU 102 may obtain an inference of a WTRU location from the second AI / ML model.

[0534] For example, the TA command may include information indicating the first TA value which is associated with a first TRP and a third TA value which is associated with a second TRP. At 3406, the selecting of the first AI / ML model may be based on the first TA value being less than the third TA value.

[0535] For example, at 3408, the WTRU 102 may determine a fourth TA value. The second TA value may be associated with a third TRP and the fourth TA value may be associated with a fourth TRP. The WTRU 102 may select the second AI / ML model at 3410 based on the second TA value being less than the fourth TA value.

[0536] For example, the WTRU 102 may send, to the network, information indicating the selected first AI / ML model.

[0537] For example, the WTRU 102 may send, to the network, information indicating the selected second AI / ML model.

[0538] FIG. 35 is a procedural diagram illustrating another example of switching AI / ML models. In certain representative embodiments, the procedure of FIG. 32 may be implemented (e.g., as a method) by a WTRU 102. At 3502, the WTRU 102 may receive, from a network, first configuration information indicating a first set of PFLs (e.g., PRS configurations) which are associated with an AI / ML model. At 3504, after moving from a first cell to a second cell, the WTRU 102 may receive second configuration information indicating a second set of PFLs. At 3506, the WTRU 102 may send, to the network, information indicating the AI / ML model based on the first set and the second set having at least one PFL in common.

[0539] FIG. 36 is a procedural diagram illustrating another example of switching AI / ML models. In certain representative embodiments, the procedure of FIG. 36 may be implemented (e.g., as a method) by a WTRU 102. At 3602, the WTRU 102 may receive, from a network, first configuration information indicating a first set of PFLs (e.g., PRS configurations) which are associated with an AI / ML model. At 3604, after moving from a first cell to a second cell, the WTRU 102 may receive second configuration information indicating a second set of PFLs. At3606, the WTRU 102 may send, to the network, information indicating a fall back positioning method based on each of the PFLs of the first set being different than each of the PFLs of the second set.

[0540] For example, (in FIGs. 35 and / or 36) the WTRU 102 may obtain, while in the first cell, an inference of a WTRU location from the AI / ML model.

[0541] For example, (in FIG. 35) the WTRU 102 may obtain, while in the second cell, an inference of a WTRU location from the AI / ML model.

[0542] For example, (in FIGs. 35 and / or 36) the AI / ML model may be trained using measurement information associated with the plurality of PFLs.

[0543] For example, (in FIGs. 35 and / or 36) the first configuration information may be received from a first transmission / reception point (TRP).

[0544] For example, (in FIGs. 35 and / or 36) the second configuration information may be received from a second transmission / reception point (TRP).

[0545] FIG. 37 is a procedural diagram illustrating an example procedure, according to one or more embodiments of the present disclosure. As shown in FIG. 37, a WTRU 102 may send, to a base station associated with a first cell and based on the WTRU 102 moving to the first cell from a second cell, capability information indicating the WTRU supports AI / ML positioning at 3702. At 3704, the WTRU 102 may send, to the base station, a request for assistance information for a PRU inference. At 3706, the WTRU 102 may receive configuration information indicating a fallback positioning method and resources associated with a set of PRSs. At 3708, the WTRU 102 may measure the set of PRSs. At 3710, the WTRU 102 may receive assistance information indicating a location of a PRU and / or a set of measurement information associated with a PRU inference of the location. At 3712, the WTRU 102 may, based on a request from the base station, send, to the base station, reporting information indicating any of: (i) a first AI / ML model used at the WTRU for positioning in the second cell is to be used in the first cell, (ii) fine tuning of the first AI / ML model used at the WTRU for positioning in the second cell, (iii) a second AI / ML model to be used at the WTRU for positioning in the second cell, (iv) the fallback positioning method is to be used at the WTRU for positioning in the second cell, and / or (v) an inference generated based on the indicated set of measurement information and other measurement information associated with the measured set of PRSs.

[0546] For example, the request for assistance information may include information indicating any of a PRU location, a PRU inference of the PRU location, a time interval, and / or a type of PRU measurement information.

[0547] For example, the request for assistance information may include information indicating any of an identifier of the first cell, an identifier of the second cell, and / or a set of SSBs associated with the first cell.

[0548] For example, the fallback positioning method may be downlink time difference of arrival (DL-TDoA) positioning.

[0549] For example, the received assistance information may be associated with a first time interval.

[0550] For example, the set of PRSs may be measured during the first time interval.

[0551] For example, the WTRU 102 may obtain the inference from the first AI / ML model based on the indicated set of measurement information and other measurement information associated with the measured set of PRSs.

[0552] For example, the reporting information may include information indicating the first AI / ML model used at the WTRU for positioning in the second cell is to be used in the first cell based on a difference between the obtained inference from the first AI / ML model and the PRU inference being less than a first threshold.

[0553] For example, the reporting information may include information indicating the fine tuning of the first AI / ML model used at the WTRU for positioning in the second cell based on a difference between the obtained inference from the first AI / ML model and the PRU inference being greater than a first threshold and less than a second threshold.

[0554] For example, the reporting information may include information indicating the second AI / ML model to be used at the WTRU for positioning in the second cell or the fallback positioning method is to be used at the WTRU for positioning in the second cell based on a difference between the obtained inference from the first AI / ML model and the PRU inference being greater than a second threshold.

[0555] FIG. 38 is a procedural diagram illustrating an example procedure, according to one or more embodiments of the present disclosure. As shown in FIG. 38, a WTRU 102 may determine a location of the WTRU 102 at 3802. At 3804, the WTRU 102 may select (i) an AI / ML model from a set of AI / ML models or (ii) a fallback positioning method based on the determined location. Each AI / ML model of the set of AI / ML models may be associated with a respective area. At 3806, the WTRU 102 may send, to a base station, information indicating (e.g., one of) the selected AI / ML model or the selected fallback positioning method.

[0556] For example, the WTRU 102 may determine the location of the WTRU 102 upon the WTRU moving to a first cell from a second cell.

[0557] For example, the WTRU 102 may determine the location of the WTRU 102 upon reception of information indicating a set of positioning reference signals (PRSs).

[0558] For example, the WTRU 102 may determine the location of the WTRU 102 upon reception of information indicating a TA value.

[0559] For example, the WTRU 102 may determine the location of the WTRU 102 upon reception of information indicating a PFL.

[0560] For example, the WTRU 102 may select the AI / ML model from the set of AI / ML models based on the determined location (e.g., of the WTRU 102) being within the area associated with the AI / ML model.

[0561] For example, the WTRU 102 may send, to the base station, capability information indicating the WTRU 102 supports AI / ML positioning.

[0562] For example, the WTRU 102 may receive configuration information indicating any of a plurality of PRSs, a plurality of cells, and / or a plurality of TRPs. Each area may be associated with at least a portion of the configuration information. For example, a first area may be associated with one or more of the PRSs, cells, and / or TRPs. For example, a second area may be associated with another one or more of the PRSs, cells, and / or TRPs. For example, a third area may be associated with yet another one or more of the PRSs, cells, and / or TRPs.

[0563] For example, the WTRU 102 may determine the location (e.g., of the WTRU 102) based on the configuration information.

[0564] FIG. 39 is a procedural diagram illustrating an example procedure, according to one or more embodiments of the present disclosure. As shown in FIG. 39, a WTRU 102 may receive information indicating a first PRS configuration at 3902. For example, the first PRS configuration may associated with an AI / ML model. At 3904, the WTRU 102 may receive, upon the WTRU 102 moving from a first cell to a second cell, information indicating a second PRS configuration associated with the second cell. At 3906, the WTRU 102 may select (i) the AI / ML model or (ii) a fallback positioning method based on whether or not the second PRS configuration is included in the first PRS configuration. At 3908, the WTRU 102 may send information associated with (e.g., the one of) the selected AI / ML model or the selected fallback positioning method.

[0565] For example, the information indicating the first PRS configuration may be received from a base station associated with the first cell.

[0566] For example, the information indicating the second PRS configuration may be received from a base station associated with the second cell.

[0567] For example, the information associated with the selected AI / ML model or the selected fallback positioning method may be sent to the base station associated with the second cell.

[0568] For example, the first PRS configuration may include information associated with a first set of PFL s.

[0569] For example, the second PRS configuration may include information associated with a second set of PFLs. The first set of PFLs may include the second set of PFLs.

[0570] For example, the WTRU 102 may select the AI / ML model based on the second set of PFLs being a subset of the first set of PFLs.

[0571] For example, the WTRU 102 may select the fallback positioning method based on the second set of PFLs not being a subset of the first set of PFLs.

[0572] For example, the WTRU 102 may receive, from a base station associated with the second cell, information indicating the fallback positioning method.

[0573] For example, the WTRU 102 may receive, from a base station associated with the first cell, information indicating the fallback positioning method.

[0574] FIG. 40 is a procedural diagram illustrating an example procedure, according to one or more embodiments of the present disclosure. As shown in FIG. 40, a WTRU 102 may receive information indicating a set of AI / ML models at 4002. For example, each AI / ML model may be associated with a respective range of TA values. For example, a range of TA values may be associated with a particular base station. At 4004, the WTRU 102 may receive information indicating a TA value associated with a base station. At 4006, the WTRU may select an AI / ML model from the set of AI / ML models based on the indicated TA value falling within the range of TA values associated with the AI / ML model. For example, the indicated TA value may fall within the range of TA values associated with a first AI / ML model and may fall outside of the range of TA values associated with a second AI / ML model. At 4008, the WTRU 102 may send information associated with the selected AI / ML model. For example, the WTRU 102 may send an identifier of the selected AI / ML model and / or information associated with an inference of the selected AI / ML model.

[0575] For example, the information indicating the set of AI / ML models may be associated with a TRP.

[0576] For example, the set of AI / ML models may include a first AI / ML model associated with a first range of TA values and a second AI / ML model associated with a second range of TA values.

[0577] For example, the WTRU 102 may select one of the first AI / ML model or the second AI / ML model based on the indicated TA value falling within the first range of TA values or the second range of TA values.

[0578] For example, the WTRU 102 may select a fallback positioning method based on the indicated TA value falling outside the range of TA values associated with each of the set of AI / ML models.

[0579] For example, the WTRU 102 may send capability information indicating the WTRU supports AI / ML positioning.

[0580] For example, the WTRU 102 may send capability information indicating the WTRU supports the set of AI / ML models.

[0581] For example, each AI / ML model may be associated with a respective range of TA values and a respective base station and / or TRP.

[0582] For example, the WTRU 102 may select the AI / ML model from the set of AI / ML models based on the indicated TA value for the base station (or TRP) falling within the range of TA values which are associated with both the AI / ML model and the base station.

[0583] For example, each AI / ML model may be associated with a respective range of TA values and the base station (or TRP). In another example, each AI / ML model may be associated with a respective range of TA values and a particular base station (or TRP).

[0584] FIG. 41 is a procedural diagram illustrating an example procedure, according to one or more embodiments of the present disclosure. As shown in FIG. 41, a WTRU 102 may receive information indicating a first set of measurements associated with a PRU at 4102. At 4104, the WTRU 102 may obtain an inference of a location from a first AI / ML model using the first set of measurements. At 4106, the WTRU 102 may send, to a network, information associated with the obtained inference.

[0585] For example, the WTRU 102 may send, to the network, WTRU capability information indicating support for AI / ML-based positioning.

[0586] For example, the WTRU 102 may obtain the inference from the AI / ML model based on measurement information associated with the first set of measurements as an input to the AI / ML model.

[0587] For example, the WTRU 102 may perform a second set of measurements on a set of PRSs. The WTRU 102 may obtain the inference of the location from the AI / ML model based on measurement information associated with the first set of measurements and measurement information associated with the second set of measurements as inputs to the AI / ML model.

[0588] For example, the first set of measurements and / or the second set of measurements may be associated with any of timing information, phase information, power information, a channel impulse response and / or a delay profile.

[0589] For example, the WTRU 102 may receive information indicating a location of the PRU. The WTRU 102 may determine a difference between the obtained inference and the location of the PRU. The WTRU 102 may include the difference in the information reported to the network.

[0590] For example, the information associated with the obtained inference may include any of the obtained inference, the location of the PRU, and / or an identifier of the first AI / ML based on the determined difference being less than a threshold.

[0591] For example, the information associated with the obtained inference may include any of the obtained inference, the location of the PRU, and / or an identifier of a second AI / ML based on the determined difference being less than a threshold.

[0592] For example, the PRU may be associated with a cell in which the WTRU 102 is located.

[0593] For example, the information associated with the obtained inference may include any of an identifier of the cell, an identifier of the PRU, and / or an identifier of the first AI / ML model.

[0594] In certain representative embodiments, a WTRU 102 may send, to a network, a request for assistance information including any of a PRU location, a PRU inference of the PRU location, a set of PRSs associated with the PRU inference, a first set of measurements associated with the PRU inference, and / or a cell identifier associated with the PRU inference. The WTRU 102 may receive the assistance information. The WTRU 102 may obtain an inference of a WTRU location from an AI / ML model. The WTRU 102 may verify the obtained inference based on the assistance information. The WTRU 102 may send, to the network, a result of the verifying of the obtained inference.

[0595] For example, the WTRU 102 may send, to the network, WTRU capability information indicating support for AI / ML-based positioning.

[0596] For example, the WTRU 102 may obtain the inference from the AI / ML model after inputting measurement information associated with the first set of measurements to the AI / ML model.

[0597] For example, the WTRU 102 may perform a second set of measurements on the set of PRSs. The WTRU 102 may obtain the inference from the AI / ML model by inputting measurement information associated with the second set of measurements to the AI / ML model.

[0598] For example, the WTRU 102 may verify the obtained inference which includes to determine a difference between (i) the obtained inference and (ii) the PRU location and / or the PRU inference. The result of the verification may include information indicating tuning of the AI / ML model by the WTRU based on the determined difference being less than a threshold.

[0599] For example, the WTRU 102 may verify the obtained inference which includes to determine a difference between (i) the obtained inference and (ii) the PRU location and / or the PRU inference. The result of the verification may include information indicating an identifier of the AI / ML model based on the determined difference being less than a threshold.

[0600] For example, the WTRU 102 may verify the obtained inference which includes to determine a difference between (i) the obtained inference and (ii) the PRU location and / or the PRU inference. The result of the verification may include information indicating an identifier of another AI / ML model based on the determined difference being greater than or equal to a threshold.

[0601] For example, the WTRU 102 may verify the obtained inference which includes to determine a difference between (i) the obtained inference and (ii) the PRU location and / or the PRU inference. The result of the verification may include information indicating an identifier of a fallback positioning method based on the determined difference being greater than or equal to a threshold.

[0602] In certain representative embodiments, a WTRU 102 may receive configuration information indicating a plurality of sets of PRSs. The WTRU 102 may obtain first measurement information associated with the plurality of sets of PRSs. The WTRU 102 may select a first set of the plurality of sets of PRSs based on the first measurement information associated with the plurality of sets of PRSs. The WTRU 102 may obtain an inference of a WTRU location from a first AI / ML model associated with the first set. The WTRU 102 may obtain second measurement information associated with the plurality of sets of PRSs. The WTRU 102 may send, to the network, information indicating a second AI / ML model based on the second measurement information associated with the first set being below a threshold. For example, the second AI / ML model may be associated with a second set of the plurality of sets of PRSs.

[0603] For example, the WTRU 102 may obtain the inference of the WTRU location from the first AI / ML model using the first measurement information associated with the first set as an input to the first AI / ML model.

[0604] For example, the WTRU 102 may select the first set of the plurality of sets of PRSs based on the first measurement information associated with the first set being highest among the plurality of sets of PRSs.

[0605] For example, the WTRU 102 may select the second set of the plurality of sets of PRSs based on the second measurement information associated with the second set being highest among the plurality of sets of PRSs.

[0606] For example, the first measurement information may include RSRP values of each of the plurality of sets of PRSs during a first time interval.

[0607] For example, the second measurement information may include RSRP values of each of the plurality of sets of PRSs during a second time interval.

[0608] For example, the WTRU 102 may receive information indicating an association of the second AI / ML model and the second set.

[0609] In certain representative embodiments, a WTRU 102 may receive, from a network, configuration information indicating a plurality of TA ranges which are associated with a plurality of AI / ML models. The WTRU 102 may receive a TA command including information indicating a first TA value. The WTRU 102 may select a first AI / ML model, from among the plurality of AI / ML models, that is associated with a first TA range, of the plurality of TA ranges, whichincludes the first TA value. The WTRU 102 may determine a second TA value. The WTRU 102 may select a second AI / ML model, from among the plurality of AI / ML models, that is associated with a second TA range, of the plurality of TA ranges, which includes the second TA value.

[0610] For example, the WTRU 102 may obtain an inference of a WTRU location from the first AI / ML model.

[0611] For example, the WTRU 102 may obtain an inference of a WTRU location from the second AI / ML model.

[0612] For example, the TA command may include information indicating the first TA value which is associated with a first TRP and a third TA value which is associated with a second TRP. The selection of the first AI / ML model may be based on the first TA value being less than the third TA value.

[0613] For example, the WTRU 102 may determine the second TA value which includes to determine a fourth TA value, and the second TA value is associated with a third TRP and the fourth TA value is associated with a fourth TRP. The selection of the second AI / ML model may be based on the second TA value being less than the fourth TA value.

[0614] For example, the WTRU 102 may send, to the network, information indicating the selected first AI / ML model.

[0615] For example, the WTRU 102 may send, to the network, information indicating the selected second AI / ML model.

[0616] In certain representative embodiments, a WTRU 102 may receive, from a network, first configuration information indicating a first set of PFLs which are associated with an AI / ML model. After moving from a first cell to a second cell, the WTRU 102 may receive second configuration information indicating a second set of PFLs. The WTRU 102 may send, to the network, information indicating the AI / ML model based on the first set and the second set having at least one PFL in common.

[0617] In certain representative embodiments, a WTRU 102 may receive, from a network, first configuration information indicating a first set of PFLs which are associated with an AI / ML model. The WTRU 102 may, after moving from a first cell to a second cell, receive second configuration information indicating a second set of PFLs. The WTRU 102 may send, to the network, information indicating a fall back positioning method based on each of the PFLs of the first set being different than each of the PFLs of the second set.

[0618] For example, the WTRU 102 may obtain, while in the first cell, an inference of a WTRU location from the AI / ML model.

[0619] For example, the WTRU 102 may obtain, while in the second cell, an inference of a WTRU location from the AI / ML model.

[0620] For example, the AI / ML model may be trained using measurement information associated with the plurality of PFLs.

[0621] For example, the first configuration information may be received from a first TRP.

[0622] For example, the second configuration information may be received from a second TRP.

[0623] One or more embodiments provide a computer program comprising instructions which when executed by one or more processors cause such processors to perform the encoding and / or decoding methods according to any of the embodiments described above. One or more embodiments also provide a computer readable storage medium having stored thereon instructions for encoding or decoding video data according to the methods described above.

[0624] One or more embodiments provide a computer readable storage medium having stored thereon video data generated according to the methods described above. One or more embodiments also provide a method and apparatus for transmitting or receiving video data generated according to the methods described above.

[0625] The embodiments described herein may be implemented in, for example, a method or a process, an apparatus, a software program, a data stream, or a signal. Even if only discussed in the context of a single form of implementation (e.g., as a method), the implementation of such features may also be implemented in other forms. An apparatus may be implemented in, for example, appropriate hardware, software, and firmware. Corresponding methods may be implemented in, for example, a processor.

[0626] Various numeric values are used in the present application. Such specific values are for example purposes and the embodiments described are not limited to these specific values.

[0627] Various methods are described herein, and such methods comprise one or more steps or actions for achieving the described method. Unless a specific order of steps or actions is required for the proper operation of the method, the order and / or use of specific steps and / or actions may be modified or combined. Additionally, terms such as “first”, “second”, etc. may be used in various embodiments to modify an element, component, step, operation, etc., for example, a “first decoding” and a “second decoding”. Use of such terms does not imply an order to the operations unless specifically required.

[0628] The present disclosure may refer to “determining” various pieces of information. Determining information may include one or more of, for example, estimating, calculating, predicting, or retrieving (e.g., from memory) the information.

[0629] The present disclosure may refer to “accessing” various pieces of information. Accessing information may include one or more of, for example, receiving, retrieving (e.g., from memory), storing, moving, copying, calculating, determining, predicting, or estimating the information. Similarly, the present disclosure may refer to “receiving” various pieces of information. Receivinginformation may include one or more of, for example, accessing or retrieving (e.g., from memory) the information.

[0630] It is to be understood that use of any of the following“and / or”, and “at least one of’ is intended to encompass all possible selections of listed items, taken either individually or in any combination thereof.

[0631] While specific embodiments have been described in the foregoing description in connection with the accompanying drawings, it should be understood that embodiments described herein are examples only and should not be taken as limiting the scope of the present disclosure or the following claims. Although features and elements are described herein in particular combinations, those of ordinary skill in the art will appreciate that such features or elements may be used alone or in any combination with the other features and elements. It is understood, therefore, that the overall teachings of the present disclosure are not limited to the particular embodiments, implementations, and examples disclosed herein, but are intended to cover variations, modifications, and alternatives as defined by the appended claims and any and all equivalents thereof.

Claims

CLAIMSWhat is claimed is:

1. A wireless transmit / receive unit (WTRU) comprising: a transceiver, memory, and a processor which are configured to: send, to a base station associated with a first cell and based on the WTRU moving to the first cell from a second cell, capability information indicating the WTRU supports artificial intelligence / machine learning (AI / ML) positioning, send, to the base station, a request for assistance information for a positioning reference unit (PRU) inference, receive configuration information indicating a fallback positioning method and resources associated with a set of positioning reference signals (PRSs), measure the set of PRSs, receive assistance information indicating a location of a PRU and / or a set of measurement information associated with a PRU inference of the location, and send, based on a request from the base station, reporting information indicating any of: (i) a first AI / ML model used at the WTRU for positioning in the second cell is to be used in the first cell, (ii) fine tuning of the first AI / ML model used at the WTRU for positioning in the second cell, (iii) a second AI / ML model to be used at the WTRU for positioning in the second cell, (iv) the fallback positioning method is to be used at the WTRU for positioning in the second cell, and / or (v) an inference generated based on the indicated set of measurement information and other measurement information associated with the measured set of PRSs.

2. The WTRU of claim 1, wherein the request for assistance information includes information indicating any of a PRU location, a PRU inference of the PRU location, a time interval, and / or a type of PRU measurement information.

3. The WTRU of any of claims 1-2, wherein the request for assistance information includes information indicating any of an identifier of the first cell, an identifier of the second cell, and / or a set of synchronization signal blocks (SSBs) associated with the first cell.

4. The WTRU of any of claims 1-3, wherein the fallback positioning method is downlink time difference of arrival (DL-TDoA) positioning.

5. The WTRU of any of claims 1-4, wherein the received assistance information is associated with a first time interval.

6. The WTRU of claim 5, wherein the set of PRSs are measured during the first time interval.

7. The WTRU of any of claims 1-6, wherein the transceiver, the memory, and the processor are configured to: obtain the inference from the first AI / ML model based on the indicated set of measurement information and other measurement information associated with the measured set of PRSs.

8. The WTRU of claim 7, wherein the reporting information includes information indicating the first AI / ML model used at the WTRU for positioning in the second cell is to be used in the first cell based on a difference between the obtained inference from the first AI / ML model and the PRU inference being less than a first threshold.

9. The WTRU of claim 7, wherein the reporting information includes information indicating the fine tuning of the first AI / ML model used at the WTRU for positioning in the second cell based on a difference between the obtained inference from the first AI / ML model and the PRU inference being greater than a first threshold and less than a second threshold.

10. The WTRU of claim 7, wherein the reporting information includes information indicating the second AI / ML model to be used at the WTRU for positioning in the second cell or the fallback positioning method is to be used at the WTRU for positioning in the second cell based on a difference between the obtained inference from the first AI / ML model and the PRU inference being greater than a second threshold.I L A method implemented by a wireless transmit / receive unit (WTRU), the method comprising: sending, to a base station associated with a first cell and based on the WTRU moving to the first cell from a second cell, capability information indicating the WTRU supports artificial intelligence / machine learning (AI / ML) positioning; sending, to the base station, a request for assistance information for a positioning reference unit (PRU) inference;receiving configuration information indicating a fallback positioning method and resources associated with a set of positioning reference signals (PRSs); measuring the set of PRSs; receiving assistance information indicating a location of a PRU and / or a set of measurement information associated with a PRU inference of the location; and sending, based on a request from the base station, reporting information indicating any of (i) a first AI / ML model used at the WTRU for positioning in the second cell is to be used in the first cell, (ii) fine tuning of the first AI / ML model used at the WTRU for positioning in the second cell, (iii) a second AI / ML model to be used at the WTRU for positioning in the second cell, (iv) the fallback positioning method is to be used at the WTRU for positioning in the second cell, and / or (v) an inference generated based on the indicated set of measurement information and other measurement information associated with the measured set of PRSs.

12. The method of claim 11, wherein the request for assistance information includes information indicating any of a PRU location, a PRU inference of the PRU location, a time interval, and / or a type of PRU measurement information.

13. The method of any of claims 11-12, wherein the request for assistance information includes information indicating any of an identifier of the first cell, an identifier of the second cell, and / or a set of synchronization signal blocks (SSBs) associated with the first cell.

14. The method of any of claims 11-13, wherein the fallback positioning method is downlink time difference of arrival (DL-TDoA) positioning.

15. The method of any of claims 11-14, wherein the received assistance information is associated with a first time interval.

16. The method of claim 15, wherein the set of PRSs are measured during the first time interval.

17. The method of any of claims 11-16, further comprising: obtaining the inference from the first AI / ML model based on the indicated set of measurement information and other measurement information associated with the measured set of PRSs.

18. The method of claim 17, wherein the reporting information includes information indicating the first AI / ML model used at the WTRU for positioning in the second cell is to be used in the first cell based on a difference between the obtained inference from the first AI / ML model and the PRU inference being less than a first threshold.

19. The method of claim 17, wherein the reporting information includes information indicating the fine tuning of the first AI / ML model used at the WTRU for positioning in the second cell based on a difference between the obtained inference from the first AI / ML model and the PRU inference being greater than a first threshold and less than a second threshold.

20. The method of claim 17, wherein the reporting information includes information indicating the second AI / ML model to be used at the WTRU for positioning in the second cell or the fallback positioning method is to be used at the WTRU for positioning in the second cell based on a difference between the obtained inference from the first AI / ML model and the PRU inference being greater than a second threshold.

Images