Positioning with estimated measurements

Abstract

Systems, methods, and / or apparatuses are provided herein for locating devices in a network using estimated measurements. A wireless transmit / receive unit (WTRU) may determine positioning accuracy based on one or more actual and / or inferred measurements. The WTRU or network entity may train and / or implement one or more artificial intelligence (AI) and / or machine learning (ML) models to determine the positioning accuracy.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to U.S. Provisional Patent Application No. 63 / 390,440 filed in the United States on July 19, 2022, U.S. Provisional Patent Application No. 63 / 444,638 filed in the United States on February 10, 2023, and U.S. Provisional Patent Application No. 63 / 465,052 filed in the United States on May 9, 2023, each of which is incorporated herein by reference in its entirety. Background Art

[0003] Downlink positioning methods, uplink positioning methods, and / or combined downlink and uplink positioning methods may be described and / or used herein with respect to positioning. One or more of the methods described herein may use positioning reference signals and / or sounding reference signals for positioning. The environment may play a (e.g., critical) role in the measurement of positioning reference signals and / or sounding reference signals, which may (e.g., subsequently) affect (e.g., enable) the positioning accuracy of one or more of the positioning techniques described herein. Summary of the invention

[0004] A WTRU may be unable to obtain and / or measure one or more measurements, for example, based on WTRU capabilities and / or (e.g., lack of) one or more types of configured positioning methods (e.g., angle-based, timing-based, WTRU-based, etc.). For example, depending on the configured positioning methods, one or more (e.g., certain) positioning methods (e.g., angle-based positioning methods such as downlink (DL) angle of arrival (AoA), timing-based positioning methods such as DL time difference of arrival (TDOA), network-based positioning methods, WTRU-based positioning methods, etc.) may not be available at a wireless transmit / receive unit (WTRU). For example, when the WTRU is configured with angle-based positioning, the WTRU may not be able to obtain one or more timing measurements (e.g., the WTRU may not be able to measure timing) due to limited WTRU capabilities. Additionally or alternatively, the WTRU may not receive one or more configurations related to timing synchronization between transmit-receive points (TRPs), which may prevent the WTRU from calculating an accurate reference signal time difference (RSTD). The WTRU may obtain one or more measurements that are not observable. The one or more measurements that the WTRU is unable to measure (e.g., due to limited WTRU capabilities, unconfigured positioning reference signals (PRS), one or more different time instances, and / or unconfigured TRPs) may be referred to herein as unobservable measurements and / or unobserved measurements. Additionally or alternatively, the WTRU may perform one or more measurements (e.g., only) on PRS sent from a configured TRP, and / or the amount of one or more measurements may be limited to achieve a target accuracy.

[0005] The measurements may include one or more anomalies (e.g., non-line of sight (NLOS), unexpected timing errors, etc.). Thus, the WTRU may detect one or more (e.g., anomaly) measurements to isolate one or more error sources (e.g., timing errors) that cause the one or more anomalies. A WTRU with reduced capability (e.g., reduced bandwidth (BW), reduced number of antenna elements, etc.) may collect one or more measurements that may be unreliable (e.g., large variations in RSTD and / or large variations in one or more reference signal received power (RSRP) measurements). The WTRU may enhance the quality of the one or more measurements for the reduced capability (RedCap) WTRU to improve positioning accuracy.

[0006] The WTRU may determine an estimate (e.g., RSTD) based on one or more actual measurements (e.g., RSRP). The WTRU may receive one or more configurations from the network to determine the estimate. The WTRU may transmit a request for one or more configurations to the network to enable a function to generate the estimate, for example, based on one or more conditions herein (e.g., if at least one condition is met); the input to the function may include one or more measurements made by the WTRU. For example, if the maximum RSRP in the PRS is below a threshold and / or if the WTRU receives an indication from the network to determine an estimate of a measurement that cannot be observed (e.g., RSTD), the WTRU may transmit the request to the network. The WTRU may determine its position based on the estimated measurement and / or the actual measurement (e.g., both). Based on the difference between the actual measurement and the inferred / estimated measurement, the WTRU may determine whether there are one or more errors in the one or more measurements. The WTRU may determine a first position estimate (e.g., absolute positioning) based on, for example, the one or more actual measurements. The WTRU may determine a second position estimate (e.g., absolute positioning) based on, for example, one or more inferred measurements obtained based on the one or more actual measurements. The WTRU may report the relative position of the first position and / or the second position relative to the first position. For example, if the WTRU is configured with WTRU-based positioning, the WTRU may report the determined position to the network, indicating that the estimate was used. For example, if the WTRU is configured with WTRU-assisted positioning, the WTRU may report both the estimate and the measurement to the network. The WTRU may determine the RSTD based on RSRP measurements and / or an artificial intelligence / machine learning (AI / ML) model, wherein the AI / ML model may be trained using one or more ideal measurements. The WTRU may indicate a quality metric of the one or more estimated measurements in a measurement report.

[0007] The WTRU may determine the estimated measurement (e.g., RSTD) based on a first measurement (e.g., RSRP). The WTRU may determine a difference (e.g., an absolute value of the difference between the two values) between the estimated measurement and a second measurement (e.g., RSTD) and / or an actual measurement. If the difference is above a preconfigured threshold, the WTRU may transmit a request to the network to change the PRS configuration. The WTRU may determine one or more anomalies, for example, by using an AI / ML model specifically configured for anomaly detection.

[0008] A WTRU may receive configuration information, for example, where the configuration information indicates positioning reference signal (PRS) configuration information for one or more (e.g., each) of a plurality of transmit / receive points (TRPs). The configuration information may indicate one or more criteria for requesting PRS measurement assistance information. The configuration information may indicate a minimum number of TRPs for which one or more PRS measurements are to be reported. The WTRU may determine that at least one of the one or more criteria for requesting the PRS measurement assistance information is satisfied based on one or more measurements performed on one or more of the plurality of TRPs. The WTRU may transmit a request for the PRS measurement assistance information. The request may indicate, for example, a location of the WTRU determined based on one or more measurements performed on one or more of the plurality of TRPs. The WTRU may receive the PRS measurement assistance information. The WTRU may estimate one or more measurements of at least one TRP based on the PRS measurement assistance information and / or at least one measurement performed using the PRS configuration information for at least one of the plurality of TRPs. The WTRU may transmit a positioning measurement report. The positioning measurement report may include a set of one or more PRS measurements performed on a first subset of TRPs in the plurality of TRPs and / or an estimated measurement set determined for a second subset of TRPs in the plurality of TRPs. For example, the total number of TRPs may be included in the first subset of TRPs and / or the second subset of TRPs. For example, the total number of TRPs included in the first subset of TRPs and / or the second subset of TRPs may be at least the minimum number of TRPs for which PRS measurements are to be reported.

[0009] The WTRU may determine the estimated measurement of the first type of measurement, for example, based on one or more actual measurements of the second type of measurement and / or the PRS measurement assistance information. The WTRU may determine one or more estimated measurements with relatively lower estimated quality for at least one additional TRP, such that the total number of TRPs associated with actual PRS measurements, associated with the estimated measurements with relatively higher estimated quality, and / or associated with the estimated measurements with relatively lower estimated quality is at least the minimum number of TRPs for which one or more measurements are to be reported. Determining the one or more estimated measurements with relatively lower estimated quality for at least one additional TRP may be responsive to determining that the total number of TRPs associated with one or more actual PRS measurements and / or associated with one or more estimated measurements with relatively higher estimated quality is less than the minimum number of TRPs for which PRS measurements are to be reported.

[0010] The WTRU may request PRS measurement assistance information based on determining that one or more TRPs among the multiple TRPs include a non-line-of-sight TRP.

[0011] The WTRU may determine a reference signal time difference (RSTD) based on, for example, one or more reference signal received power (RSRP) measurements and / or the PRS measurement assistance information.

[0012] The WTRU may receive an indication of a time window and / or may transmit a first measurement report and / or a second measurement report, for example, based on the time window. The WTRU may estimate one or more measurements of at least one TRP based on one or more artificial intelligence (AI) and / or machine learning (ML) models. The WTRU may receive one or more parameters for the AI / ML model.

[0013] The WTRU may determine one or more anomalies associated with the set of PRS measurements performed on the first subset of the plurality of TRPs and / or the estimated set of measurements determined for the second subset of the plurality of TRPs. The WTRU may transmit an indication to a network to indicate the one or more anomalies associated with the set of PRS measurements performed on the first subset of the plurality of TRPs and / or the estimated set of measurements determined for the second subset of the plurality of TRPs. The WTRU may transmit a request to update the PRS measurement assistance information to estimate one or more measurements of at least one TRP. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1A is a system diagram illustrating an example communication system in which one or more disclosed embodiments may be implemented.

[0015] Figure 1B is an example of a method that can be used according to an embodiment of the present invention. Figure 1A A system diagram of an example wireless transmit / receive unit (WTRU) for use within an illustrated communication system.

[0016] Figure 1C is an example of a method that can be used according to an embodiment of the present invention. Figure 1A System diagram of an example Radio Access Network (RAN) and an example Core Network (CN) for use within an illustrated communication system.

[0017] Figure 1D is an example of a method that can be used according to an embodiment of the present invention. Figure 1A System diagram of another example RAN and another example CN for use within the illustrated communication system.

[0018] Figure 2A is a schematic diagram of an example system environment in which artificial intelligence (AI) and / or machine learning (ML) models may be implemented.

[0019] Figure 2B An example of a neural network is illustrated.

[0020] Figure 2C is a schematic diagram of an example system environment for training and / or implementing an AI / ML model including a neural network (NN).

[0021] Figure 3 An example is shown where the network trains an AI / ML model based on measurements reported by the WTRU.

[0022] Figure 4 An example system is shown in which a WTRU receives one or more AI / ML parameters (eg, weights) from a network entity (eg, LMF).

[0023] Figure 5 An example of inference generation using the system is illustrated.

[0024] Figure 6 An example signal flow diagram between the WTRU, gNB and the Location Management Function (LMF) is illustrated.

[0025] Figure 7 An example system for enabling RSTD prediction based on one or more actual RSTD measurements is shown.

[0026] Fig. 8A An example system is illustrated in which the reference TRP is a predictable region of TRP1.

[0027] Figure 8B An example system is illustrated for determining whether a TRP is within a predicted / inferred coverage area, where the center of the coverage area is the location of the WTRU.

[0028] Fig. 9 An example system showing arrival times in the presence of reflected signals is illustrated.

[0029] Fig.10 An example graph of estimates of arrival time for using narrowband PRS and wideband PRS is shown.

[0030] Fig.11 An example system for training an AI / ML model to generate inferences is shown.

[0031] Fig.12 An example system illustrating inference generation from a trained model (e.g., an AI / ML model) is shown.

[0032] Fig.13 An example system for anomaly detection is illustrated.

[0033] Fig.14 An example process of using AI for anomaly detection is illustrated.

[0034] Fig.15An example system for network-assisted anomaly detection is illustrated.

[0035] Fig.16 An example system including a WTRU and a network entity (eg, LMF) from which a request to receive assistance information may be issued is illustrated.

[0036] Fig.17 An example system is illustrated in which a WTRU may determine (eg, estimate) one or more RSRP measurements for an unobserved TRP.

[0037] Fig.18 An example system is illustrated in which a WTRU may determine one or more RSRP measurements for one or more unobserved TRPs (eg, in an extended area).

[0038] 19 depicts a process flow diagram of an example procedure for determining one or more measurements and / or one or more position measurements. DETAILED DESCRIPTION

[0039] Figure 1A 1 is a diagram illustrating an example communication system 100 in which one or more disclosed embodiments may be implemented. The communication system 100 may be a multiple access system that provides content such as voice, data, video, messaging, broadcast, etc. to multiple wireless users. The communication system 100 may enable multiple wireless users to access such content through sharing of system resources (including wireless bandwidth). For example, the communication system 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), single carrier FDMA (SC-FDMA), zero tail unique word DFT spread OFDM (ZT UW DTS-s OFDM), unique word OFDM (UW-OFDM), resource block filtered OFDM, and filter bank multi-carrier (FBMC), etc.

[0040] like Figure 1AAs shown, the communication system 100 may include wireless transmit / receive units (WTRUs) 102a, 102b, 102c, 102d, RAN 104 / 113, CN 106 / 115, public switched telephone network (PSTN) 108, Internet 110 and other networks 112, but it should be understood that the disclosed embodiments contemplate any number of WTRUs, base stations, networks, and / or network elements. Each of the WTRUs 102a, 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 “STA”) may be configured to send and / or receive wireless signals and may include user equipment (UE), a mobile station, a fixed or mobile subscriber unit, a subscription-based unit, a pager, a cellular phone, a personal digital assistant (PDA), a smart phone, a laptop, a netbook, a personal computer, a wireless sensor, a hotspot or Mi-Fi device, an Internet of Things (IoT) device, a watch or other wearable device, a head-mounted display (HMD), a vehicle, a drone, medical devices and applications (e.g., remote surgery), industrial devices and applications (e.g., robots and / or other wireless devices operating in an industrial and / or automated process chain environment), consumer electronic devices, and devices operating on a commercial and / or industrial wireless network, etc. Any of the WTRUs 102a, 102b, 102c, and 102d may be interchangeably referred to as a UE.

[0041] The communication system 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 that is configured to wirelessly interface with at least one of the WTRUs 102a, 102b, 102c, 102d to facilitate access to one or more communication networks, such as the CN 106 / 115, the Internet 110, and / or other networks 112. By way of example, the base stations 114a, 114b may be a base transceiver station (BTS), a Node B, an eNode B, a Home Node B, a Home eNode B, a gNB, an NR Node B, a site controller, an access point (AP), a wireless router, and the like. Although the base stations 114a, 114b are each depicted as a single element, it should be appreciated that the base stations 114a, 114b may include any number of interconnected base stations and / or network elements.

[0042] Base station 114a may be part of RAN 104 / 113, which may also include other base stations and / or network elements (not shown), such as base station controllers (BSC), radio network controllers (RNC), relay nodes, etc. Base station 114a and / or base station 114b may be configured to send and / or receive wireless signals on one or more carrier frequencies (which may be referred to as cells (not shown)). These frequencies may be in a licensed spectrum, an unlicensed spectrum, or a combination of a licensed spectrum and an unlicensed spectrum. A cell may provide coverage of wireless services to a specific geographic area, which may be relatively fixed or may change over time. A cell may be further divided into cell sectors. For example, a cell associated with base station 114a may be divided into three sectors. Therefore, in one embodiment, base station 114a may include three transceivers, i.e., one transceiver for each sector of the cell. In an embodiment, base station 114a may employ multiple-input multiple-output (MIMO) technology and may utilize multiple transceivers for each sector of the cell. For example, beamforming may be used to send and / or receive signals in a desired spatial direction.

[0043] 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).

[0044] More specifically, as noted above, the communication system 100 may be a multiple access system and may employ one or more channel access schemes such as CDMA, TDMA, FDMA, OFDMA, and SC-FDMA, among others. 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 use Wideband CDMA (WCDMA) to establish the air interface 115 / 116 / 117. WCDMA may include communication protocols such as High Speed ​​Packet Access (HSPA) and / or Evolved HSPA (HSPA+). HSPA may include High Speed ​​Downlink (DL) Packet Access (HSDPA) and / or High Speed ​​UL Packet Access (HSUPA).

[0045] 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 Advanced LTE (LTE-A) and / or Advanced LTE Pro (LTE-A Pro).

[0046] 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).

[0047] 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 together implement LTE radio access and NR radio access, for example using the dual connectivity (DC) principle. Thus, the air interface utilized by the WTRUs 102a, 102b, 102c may be characterized by multiple types of radio access technologies and / or transmissions transmitted to / from multiple types of base stations (e.g., eNBs and gNBs).

[0048] In other embodiments, the base station 114a and the WTRUs 102a, 102b, 102c may implement radio technologies such as IEEE 802.11 (i.e., Wireless Fidelity (WiFi)), IEEE 802.16 (i.e., Worldwide Interoperability for Microwave Access (WiMAX)), CDMA2000, CDMA2000 1X, 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), and GSM EDGE (GERAN).

[0049] Figure 1AThe base station 114b in the may be, for example, a wireless router, a Home NodeB, a Home eNodeB, or an access point, and may utilize any suitable RAT to facilitate wireless connectivity in local areas such as commercial venues, homes, vehicles, campuses, industrial facilities, sky corridors (e.g., for use by drones), and roads. In one 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 another 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 a picocell or a femtocell. As Figure 1A As shown, base station 114b may have a direct connection to Internet 110. Therefore, base station 114b may not need to access Internet 110 via CN 106 / 115.

[0050] 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 different quality of service (QoS) requirements, such as different throughput requirements, latency requirements, error tolerance requirements, reliability requirements, data throughput requirements, mobility requirements, etc. The CN 106 / 115 may provide call control, billing services, mobile location-based services, prepaid calling, Internet connectivity, video distribution, etc., and / or perform high-level security functions, such as user authentication. Although not described in detail in the text and video, the CN 106 / 115 may be 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 different quality of service (QoS) requirements, such as different throughput requirements, latency requirements, error tolerance requirements, reliability requirements, data throughput requirements, mobility requirements, etc. The CN 106 / 115 may provide call control, billing services, mobile location-based services, prepaid calling, Internet connectivity, video distribution, etc., and / or perform high-level security functions, such as user authentication. Figure 1A Although not shown in the figure, it will be appreciated that the RAN 104 / 113 and / or 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 utilize NR radio technology, the CN 106 / 115 may also be in communication with another RAN (not shown) that employs GSM, UMTS, CDMA2000, WiMAX, E-UTRA, or WiFi radio technology.

[0051] The CN 106 / 115 may also act 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 a circuit-switched telephone network that provides 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), the User Datagram Protocol (UDP), and / or the Internet Protocol (IP) in the TCP / IP Internet protocol suite. The networks 112 may include wired communication networks and / or wireless communication 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 / 113 or a different RAT.

[0052] Some or all of the WTRUs 102a, 102b, 102c, 102d in the communication 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 via different wireless links). Figure 1A The illustrated WTRU 102c 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.

[0053] Figure 1B is a system diagram illustrating an example WTRU 102. Figure 1B As shown, the WTRU 102 may include, among other things, 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 peripherals 138. It will be appreciated that the WTRU 102 may include any sub-combination of the foregoing elements while remaining consistent with an embodiment.

[0054] 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 associated with a DSP core, a controller, a microcontroller, an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) circuit, any other type of integrated circuit (IC) and state machine, etc. The processor 118 may perform signal decoding, 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. Although Figure 1B The processor 118 and the transceiver 120 are depicted as separate components, but it is understood that the processor 118 and the transceiver 120 may be integrated together in an electronic package or chip.

[0055] The send / receive element 122 may be configured to send a signal to a base station (e.g., base station 114a) or receive a signal from the base station via an air interface 116. For example, in one embodiment, the send / receive element 122 may be an antenna configured to send and / or receive an RF signal. In an embodiment, the send / receive element 122 may be a transmitter / detector configured to send and / or receive, for example, an IR, UV or visible light signal. In another embodiment, the send / receive element 122 may be configured to send and / or receive both an RF signal and an optical signal. It should be understood that the send / receive element 122 may be configured to send and / or receive any combination of wireless signals.

[0056] Although the transmit / receive element 122 Figure 1B Although depicted as a single element in the figure, the WTRU 102 may include any number of transmit / receive elements 122. More specifically, the WTRU 102 may employ MIMO technology. Thus, in one embodiment, the WTRU 102 may include two or more transmit / receive elements 122 (e.g., multiple antennas) for transmitting and receiving wireless signals over the air interface 116.

[0057] The transceiver 120 may be configured to modulate signals to be transmitted by the transmit / receive element 122 and to demodulate signals received by the transmit / receive element 122. As noted above, the WTRU 102 may have multi-mode capabilities. For example, the transceiver 120 may include multiple transceivers for enabling the WTRU 102 to communicate via multiple RATs, such as NR and IEEE 802.11.

[0058] The processor 118 of the WTRU 102 may be coupled to and may receive user input data from a speaker / microphone 124, a keypad 126, and / or a display / touchpad 128 (e.g., a liquid crystal display (LCD) display unit or an 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 a non-removable memory 130 and / or a removable memory 132. The non-removable memory 130 may include a random access memory (RAM), a read-only 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, and a secure digital (SD) memory card, among others. In other embodiments, the processor 118 may access information from and store data in a memory that is not physically located on the WTRU 102, such as on a server or a home computer (not shown).

[0059] The processor 118 may receive power from the power source 134, and may be configured to distribute and / or control 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, etc.

[0060] 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 from a base station (e.g., base stations 114a, 114b) over the air interface 116 and / or determine its location based on the timing of signals received from two or more nearby base stations. It will be appreciated that the WTRU 102 may acquire location information by any suitable location-determination method while remaining consistent with an embodiment.

[0061] The processor 118 may be further coupled to other peripherals 138, which may include one or more software modules and / or hardware modules that provide additional features, functionality, and / or wired or wireless connectivity. For example, the peripherals 138 may include an accelerometer, an electronic compass, a satellite transceiver, a digital camera (for photos and / or video), a universal serial bus (USB) port, a vibration device, a television transceiver, a hands-free headset, module, FM radio unit, digital music player, media player, video game player module, Internet browser, virtual reality and / or augmented reality (VR / AR) device and activity tracker, etc. Peripheral device 138 may include one or more sensors, which may be one or more of the following: 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.

[0062] The WTRU 102 may include a full-duplex radio for which transmission and reception of some or all signals (e.g., associated with specific subframes for both UL (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 139 for reducing and / or substantially eliminating self-interference via signal processing performed via hardware (e.g., a choke) or via a processor (e.g., a separate processor (not shown) or via processor 118). In an embodiment, the WRTU 102 may include a half-duplex radio for which transmission and reception of some or all signals (e.g., associated with specific subframes for both UL (e.g., for transmission) or downlink (e.g., for reception)) may be concurrent and / or simultaneous.

[0063] Figure 1C 1 is a system diagram illustrating the RAN 104 and the CN 106 in accordance with an embodiment. As noted above, the RAN 104 may employ an E-UTRA radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 104 may also be in communication with the CN 106.

[0064] The RAN 104 may include evolved Node-Bs 160a, 160b, 160c, though it will be appreciated that the RAN 104 may include any number of evolved Node-Bs while remaining consistent with an embodiment. The evolved Node-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 one embodiment, the evolved Node-Bs 160a, 160b, 160c may implement MIMO technology. Thus, the evolved Node-B 160a, for example, may use multiple antennas to transmit wireless signals to and / or receive wireless signals from the WTRU 102a.

[0065] Each of the evolved Node Bs 160a, 160b, 160c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, and scheduling of users in the UL and / or DL, among other things. Figure 1C As shown, the eNode-Bs 160a, 160b, 160c may communicate with one another via an X2 interface.

[0066] Figure 1C The illustrated CN 106 may include a mobility management entity (MME) 162, a serving gateway (SGW) 164, and a packet data network (PDN) gateway (or PGW) 166. While each of the foregoing elements is depicted as being part of the CN 106, it should be understood that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0067] The MME 162 may be connected to each of the evolved Node-Bs 162a, 162b, 162c in the RAN 104 via an S1 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, and selecting a particular serving gateway during an initial attach of the WTRUs 102a, 102b, 102c. 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.

[0068] The SGW 164 may be connected to each of the evolved Node-Bs 160a, 160b, 160c in the RAN 104 via an S1 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 the user plane during an inter-evolved Node-B handover, triggering paging when DL data is available for the WTRUs 102a, 102b, 102c, and managing and storing the context of the WTRUs 102a, 102b, 102c.

[0069] 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.

[0070] 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 be in communication with, an IP gateway (e.g., an IP Multimedia Subsystem (IMS) server) that acts 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 other networks 112, which may include other wired networks and / or wireless networks owned and / or operated by other service providers.

[0071] Although the WTRU Figures 1A to 1D Although described as wireless terminals, it is contemplated that in certain representative embodiments, such terminals may (eg, temporarily or permanently) use a wired communications interface with a communications network.

[0072] In a representative embodiment, the other network 112 may be a WLAN.

[0073] A WLAN in infrastructure basic service set (BSS) mode may have an access point (AP) for a BSS and one or more stations (STAs) associated with the AP. The AP may have access or an interface to a distribution system (DS) or another type of wired / wireless network that carries traffic to and / or out of the BSS. Traffic originating from outside the BSS to a STA may be reached by the AP and may be delivered to the STA. Traffic originating from a STA to a destination outside the BSS may be transmitted to the AP to be delivered to the corresponding destination. Traffic between STAs within the BSS may be transmitted by the AP, for example, wherein the source STA may transmit traffic to the AP, and the AP may deliver traffic to the destination STA. Traffic between STAs within the BSS may be considered and / or referred to as point-to-point traffic. Direct link establishment (DLS) may be utilized to transmit point-to-point traffic between a source STA and a destination STA (e.g., directly between them). In certain representative embodiments, the DLS may use 802.11e DLS or 802.11z tunnel DLS (TDLS). A WLAN using an independent BSS (IBSS) mode may not have an AP, and STAs within or using the IBSS (eg, all STAs in the STA) may communicate directly with each other. The IBSS communication mode may sometimes be referred to herein as an "ad hoc" communication mode.

[0074] When using the 802.11ac infrastructure operation mode or a similar operation mode, the AP may send beacons on a fixed channel (such as a primary channel). The primary channel may be a fixed width (e.g., a 20 MHz wide bandwidth) or a width dynamically set via signaling. The primary channel may be an operating channel of the BSS and may be used by the STA to establish a connection with the AP. In certain representative embodiments, carrier sense multiple access / collision avoidance (CSMA / CA) may be implemented, for example, in an 802.11 system. For CSMA / CA, a STA (e.g., each 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.

[0075] High throughput (HT) STAs may communicate using a 40 MHz wide channel, for example, via a combination of a primary 20 MHz channel and adjacent or non-adjacent 20 MHz channels to form a 40 MHz wide channel.

[0076] Very high throughput (VHT) STA can support 20MHz, 40MHz, 80MHz and / or 160MHz wide channels. 40MHz channels and / or 80MHz channels can be formed by combining continuous 20MHz channels. 160MHz channels can be formed by combining 8 continuous 20MHz channels, or by combining two non-continuous 80MHz channels (this can be called 80+80 configuration). For 80+80 configuration, after channel coding, the data can pass through a segment parser that can divide the data into two streams. Each stream can be processed by inverse fast Fourier transform (IFFT) and time domain processing separately. These streams can be mapped to two 80MHz channels, and data can be sent by the transmitter STA. At the receiver of the receiver STA, the operations for the 80+80 configuration described above can be reversed, and the combined data can be transmitted to the medium access control (MAC).

[0077] 802.11af and 802.11ah support operating modes below 1GHz. Channel operating bandwidths and carriers are reduced in 802.11af and 802.11ah relative to those used in 802.11n and 802.11ac. 802.11af supports 5MHz, 10MHz, and 20MHz bandwidths in the TV White Space (TVWS) spectrum, and 802.11ah supports 1MHz, 2MHz, 4MHz, 8MHz, and 16MHz bandwidths using non-TVWS spectrum. According to a representative embodiment, 802.11ah may support instrument type control / machine type communications, such as MTC devices in macro coverage areas. MTC devices may have certain capabilities, such as limited capabilities, including support for (e.g., only support for) certain bandwidths and / or limited bandwidths. MTC devices may include batteries with battery life above a threshold (e.g., to maintain very long battery life).

[0078] WLAN systems that can support multiple channels and channel bandwidths (such as 802.11n, 802.11ac, 802.11af, and 802.11ah) include channels that can be designated as primary channels. The primary channel may have a bandwidth equal to the maximum 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 (which supports the minimum bandwidth operating mode) from all STAs operating in the BSS. In the example of 802.11ah, for STAs (e.g., MTC-type devices) that support (e.g., only support) 1MHz mode, the primary channel may be 1MHz wide, even if the AP and other STAs in the BSS support 2MHz, 4MHz, 8MHz, 16MHz, and / or other channel bandwidth operating modes. Carrier sensing and / or network allocation vector (NAV) settings may depend on the state of the primary channel. If the primary channel is busy, for example, because a STA (supporting only the 1MHz operating mode) is sending to the AP, the entire available band may be considered busy even if most of the band remains idle and may be available.

[0079] In the United States, the available frequency band for 802.11ah is 902MHz to 928MHz. In South Korea, the available frequency band is 917.5MHz to 923.5MHz. In Japan, the available frequency band is 916.5MHz to 927.5MHz. The total bandwidth available for 802.11ah is 6MHz to 26MHz, depending on the country code.

[0080] Figure 1D 1 is a system diagram illustrating the RAN 113 and the CN 115 in accordance with an embodiment. As noted above, the RAN 113 may employ 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.

[0081] 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. The gNBs 180a, 180b, 180c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In one embodiment, the gNBs 180a, 180b, 180c may implement MIMO technology. For example, the gNBs 180a, 180b may utilize beamforming to send signals to and / or receive signals from the gNBs 180a, 180b, 180c. Thus, the gNB 180a may, for example, use multiple antennas to send 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 an unlicensed spectrum, while the remaining component carriers may be on a licensed spectrum. In an embodiment, the gNBs 180a, 180b, 180c may implement coordinated multi-point (CoMP) technology. For example, the WTRU 102a may receive coordinated transmissions from the gNB 180a and the gNB 180b (and / or the gNB 180c).

[0082] The WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c using transmissions associated with parameter sets that may be scalable. 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 the gNBs 180a, 180b, 180c using subframes or transmit time intervals (TTIs) of varying or scalable lengths (e.g., containing different numbers of OFDM symbols and / or varying absolute time lengths over time).

[0083] 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 a standalone configuration, the WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c while not accessing other RANs (e.g., such as the eNodeBs 160a, 160b, 160c). In a standalone configuration, the WTRUs 102a, 102b, 102c may use one or more of the gNBs 180a, 180b, 180c as mobility anchor points. In a standalone configuration, the WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c using signals in an unlicensed band. In a non-standalone configuration, the WTRUs 102a, 102b, 102c may communicate / connect with the gNB 180a, 180b, 180c while also communicating / connecting with another RAN, such as the eNode-B 160a, 160b, 160c. For example, the WTRUs 102a, 102b, 102c may implement the DC principle to communicate with one or more gNBs 180a, 180b, 180c and one or more eNode-Bs 160a, 160b, 160c substantially simultaneously. In a non-standalone configuration, the eNode-B 160a, 160b, 160c may act as a mobility anchor for the WTRUs 102a, 102b, 102c, and the gNB 180a, 180b, 180c may provide additional coverage and / or throughput for serving the WTRUs 102a, 102b, 102c.

[0084] Each of the gNBs 180a, 180b, 180c may be associated with a specific cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, scheduling of users in UL and / or DL, support of network slicing, dual connectivity, interworking between NR and E-UTRA, routing of user plane data towards a user plane function (UPF) 184a, 184b and routing of control plane information towards an access and mobility management function (AMF) 182a, 182b, etc. Figure 1D As shown, gNBs 180a, 180b, and 180c may communicate with each other via an Xn interface.

[0085] Figure 1DThe illustrated CN 115 may include at least one AMF 182a, 182b, at least one UPF 184a, 184b, at least one session management function (SMF) 183a, 183b, and possible data networks (DNs) 185a, 185b. Although each of the foregoing elements is depicted as part of the CN 115, it should be understood that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0086] The AMF 182a, 182b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via the N2 interface and may act as a control node. For example, the AMF 182a, 182b may be responsible for authenticating users of the WTRU 102a, 102b, 102c, support of network slicing (e.g., handling of different PDU sessions with different requirements), selecting a specific SMF 183a, 183b, management of registration areas, termination of NAS signaling and mobility management, etc. The AMF 182a, 182b may use network slicing to customize CN support for the WTRU 102a, 102b, 102c based on the type of services utilized by the WTRU 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 mobile broadband (eMBB) access, and / or services for machine type communication (MTC) access, etc. 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.

[0087] The SMF 183a, 183b may be connected to the AMF 182a, 182b in the CN 115 via the N11 interface. The SMF 183a, 183b may also be connected to the UPF 184a, 184b in the CN 115 via the N4 interface. The SMF 183a, 183b may select and control the UPF 184a, 184b, and configure the service routing performed by the UPF 184a, 184b. The SMF 183a, 183b may perform other functions, such as managing and allocating UE IP addresses, managing PDU sessions, controlling policy implementation and QoS, and providing downlink data notifications. The PDU session type may be IP-based, non-IP-based, Ethernet-based, etc.

[0088] The UPF 184a, 184b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via the N3 interface, 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. The UPF 184, 184b may perform other functions, such as routing and forwarding packets, enforcing user plane policies, supporting multi-homed PDU sessions, handling user plane QoS, buffering downlink packets, and providing mobility anchoring, etc.

[0089] 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 acts 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 other networks 112, which may include other wired networks and / or wireless networks owned and / or operated by other service providers. In one embodiment, the WTRUs 102a, 102b, 102c may be connected to local data networks (DNs) 185a, 185b via the UPF 184a, 184b via the N3 interface to the UPF 184a, 184b and the N6 interface between the UPF 184a, 184b and the DN 185a, 185b.

[0090] Given that Figures 1A to 1D as well as Figures 1A to 1D Corresponding to the description of the present invention, one or more or all of the functions described herein for one or more of the following items may be performed by one or more simulation devices (not shown): WTRU102a-102d, base station 114a-114b, evolved Node B 160a-160c, MME 162, SGW 164, PGW 166, gNB 180a-180c, AMF 182a-182ab, UPF 184a-184b, SMF 183a-183b, DN 185a-185b and / or any other device described herein. The simulation device may be one or more devices configured to mimic one or more or all of the functions described herein. For example, the simulation device can be used to test other devices and / or simulate network and / or WTRU functions.

[0091] The simulation device may be designed to implement one or more tests of other devices in a laboratory environment and / or in an operator network environment. For example, one or more simulation devices may perform one or more functions 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. One or more simulation devices may perform one or more functions or all functions while being temporarily implemented / deployed as part of a wired and / or wireless communication network. The simulation device may be directly coupled to another device for testing purposes and / or may use over-the-air wireless communications to perform testing.

[0092] One or more simulation devices may perform one or more (including all) functions without being implemented / deployed as part of a wired and / or wireless communication network. For example, the simulation device may be used in a test scenario in a test lab and / or a non-deployed (e.g., test) wired and / or wireless communication network to implement testing of one or more components. One or more simulation devices may be test equipment. Direct RF coupling and / or wireless communication via an RF circuit (e.g., which may include one or more antennas) may be used by the simulation device to send and / or receive data. Downlink (DL) positioning methods, uplink positioning methods, and / or combined downlink and uplink positioning methods may be used herein. For example, as described herein, one or more measurements may be used (e.g., by a WTRU and / or by a network) to determine location information. One or more measurements may be used to determine a position estimate (e.g., of a WTRU) using one or more AI / ML models as described herein. As used herein, the term "downlink positioning method" and / or "DL positioning method" may refer to one or more (e.g., any) positioning methods using a downlink reference signal such as a positioning reference signal (PRS). The WTRU may receive one or more (e.g., multiple) reference signals from a transmission point (TP) and / or may measure a DL reference signal time difference (RSTD) and / or a reference signal received power (RSRP). Examples of DL positioning methods may include downlink-angle of departure (DL-AoD) positioning and / or downlink-time difference of arrival (DL-TDOA) positioning. The RSTD may be determined based on a difference between the arrival times of a reference PRS and a target PRS with which the WTRU is configured (e.g., which TRP may transmit the reference PRS and / or the target PRS, one or more PRS configurations for the target PRS and / or the reference PRS). For example, for WTRU-based DL-TDOA or DL-AoD, the WTRU may return a position estimate of the WTRU to the network. The WTRU may determine its position, for example, using one or more RSRP measurements and / or one or more RSTD measurements. For example, for network-based DL-TDOA or DL-AoD, the WTRU may return one or more measurements (e.g., RSRP of the received PRS, RSTD determined based on the arrival time of the target PRS and the reference PRS) to the network. The network may determine the location of the WTRU, for example, using one or more reported measurements (e.g., one or more RSRP measurements and / or one or more RSTD measurements).

[0093] As used herein, the terms "uplink (UL) positioning method" and / or "UL positioning method" may refer to one or more (e.g., any) positioning methods that use one or more uplink reference signals, such as a sounding reference signal (SRS) for positioning (SRSp) and / or an SRS. The WTRU may send an SRS to one or more (e.g., multiple) reception points (RPs), and / or the one or more RPs may measure UL relative time of arrival (RTOA) and / or RSRP. Examples of UL positioning methods may include uplink-time difference of arrival (UL-TDOA) positioning and / or uplink-angle of arrival (UL-AoA) positioning. The network may determine the position of the WTRU, for example, by using one or more measurements (e.g., RSRP, RTOA, difference between RTOA) obtained from a received SRS and / or an SRS for positioning.

[0094] As used herein, the term "combined downlink and uplink positioning method" and / or "DL and UL positioning method" may refer to one or more (e.g., any) positioning methods that use both uplink reference signals and downlink reference signals for positioning. For example, in round trip time (RTT) based positioning, the WTRU may receive a PRS transmitted by one or more TRPs and / or may transmit an SRS and / or an SRS for positioning to the network. The WTRU may perform one or more measurements on the received PRS and / or may determine a receive (Rx)-transmit (Tx) time based on the transmit time of the SRS and / or the SRS for positioning and / or the arrival time of the received PRS. In an example, the WTRU may transmit the SRS to one or more (e.g., multiple) transmit / receive points (TRPs), and / or the network (e.g., gNB) may measure the receive (Rx) minus transmit (Tx) (e.g., Rx-Tx) time difference. The gNB may measure the RSRP of the received SRS. The WTRU may measure the Rx-Tx time difference of the PRS sent from one or more (e.g., multiple) TRPs. The WTRU may report the Rx-Tx time difference to the network. The Rx-Tx time may be defined by the difference between the arrival time of the PRS and the time when the WTRU sends the SRS and / or SRSp. The above time may be defined by the following: absolute time; relative time relative to a reference; subframe number and / or subframe index; frame number and / or frame index; time slot number and / or time slot index; and / or symbol number or index. The WTRU may measure the RSRP of the received PRS. The Rx-TX difference and / or the RSRP that may be measured at the WTRU and / or gNB may be used to calculate the round trip time. Here, the Rx and Tx difference may refer to the difference between the arrival time of the reference signal sent by the TRP and the transmission time of the reference signal sent from the WTRU. Examples of DL and UL positioning methods may include multi-round trip time (multi-RTT) positioning. The network may determine the location of the WTRU, for example, using one or more reported measurements (eg, RSRP, Rx-Tx time difference reported by the WTRU).

[0095] The PRS configuration may include one or more of the following: a PRS resource ID; a PRS sequence ID (e.g., and / or other IDs used to generate a PRS sequence); a PRS resource element offset; a PRS resource slot offset; a PRS symbol offset; PRS quasi-colocation (QCL) information; a PRS resource set ID; a list of PRS resources in a resource set; one or more (e.g., a certain number of) PRS symbols; a muting pattern, a muting parameter (e.g., a repetition factor), and / or a muting option for a PRS; a PRS resource power; a periodicity of PRS transmission; spatial direction information for PRS transmission (e.g., beam information, one or more transmission angles, etc.); spatial direction information for UL RS reception (e.g., a beam ID, an angle of arrival, etc. for receiving a UL RS); a frequency layer ID, a TRP ID; and / or a PRS ID. For example, the QCL may indicate that one or more (e.g., two) RSs are transmitted over similar channels (e.g., the two RSs are transmitted from similar locations). In an example, the spatial QCL may indicate that one or more (e.g., two) RSs are transmitted over one or more similar channels (e.g., the two RSs may be colocated).

[0096] The SRS (SRSp) configuration for positioning may include one or more of the following: a resource ID; a comb offset value and / or a cyclic shift value; a starting position in the frequency domain; one or more (e.g., a certain number of) SRSp symbols; a shift in the frequency domain for the SRSp; a frequency hopping pattern; a type of SRSp (e.g., aperiodic, semi-persistent, periodic, etc.); a sequence ID for generating the SRSp (e.g., and / or other IDs for generating the SRSp sequence); spatial relationship information indicating which reference signal (e.g., DL RS, UL RS, CSI-RS, SRS, DM-RS) and / or synchronization signal block (SSB) (e.g., SSB) the SRSp is spatially aligned with. ID, cell ID of SSB); QCL information (for example, QCL relationship between SRSp and other reference signals or SSB), QCL type (for example, QCL type A, QCL type B, QCL type C, QCL type D); resource set ID; a list of SRSp resources in the resource set; information related to transmit power; path loss reference information (for example, which may include indexes for SSB, CSI-RS and / or PRS); periodicity of SRSp transmission; spatial direction information of SRSp transmission (for example, beam information, transmission angle, etc.); and / or spatial direction information of DL RS reception (for example, beam ID, arrival angle, etc. for receiving DL RS).

[0097] The embodiments described herein may implement artificial intelligence (AI) and / or machine learning (ML) algorithms (e.g., models). For example, the WTRU and / or the network may use one or more AI / ML models to determine the location (e.g., position) of the WTRU, one or more unobserved measurements, and / or the location of one or more TRPs (e.g., as described herein). As used herein, the terms "artificial intelligence" and / or "AI" may include behavior exhibited by one or more machines that simulate one or more cognitive functions (e.g., for sensing, reasoning, adaptation, and / or action). The terms "unobserved" and "unobservable" may be used interchangeably herein.

[0098] As used herein, the term "machine learning" and / or "ML" may refer to an algorithm that solves problems based on learning through experience ("data") without explicit programming ("configuration rule set"). Machine learning may be considered a subset of AI. Different machine learning paradigms may be envisioned based on the nature of the data and / or feedback available for the learning algorithm. For example, supervised learning methods may involve learning a function that maps inputs to outputs based on labeled training examples, where one or more (e.g., each) training examples may be pairs including inputs and corresponding outputs. Unsupervised learning methods may involve detecting patterns in data without pre-existing labels. Reinforcement learning methods may involve performing a series of actions in an environment to maximize cumulative rewards. In an example, it is possible to apply one or more machine learning algorithms using a combination and / or interpolation of the methods mentioned herein (e.g., the above methods). For example, a semi-supervised learning method may use a combination of a small amount of labeled data and a large amount of unlabeled data during training. In this regard, semi-supervised learning may fall between unsupervised learning (e.g., no labeled training data) and supervised learning (e.g., only labeled training data).

[0099] Figure 2A2 is a diagram of an example system environment 201 in which an AI / ML 209 model may be implemented. The AI / ML model 209 may be implemented at a WTRU and / or a network (e.g., a location management function). The AI / ML 209 model may include model data and one or more algorithms and / or functions configured to learn from received input data 207 to train the AI / ML 209 and / or generate output 215. The input data 207 may be input in one or more formats, such as an image format, an audio format (e.g., a spectrogram or other audio format), a tensor format (e.g., including a one-dimensional or multi-dimensional array), and / or another data type capable of being input into the AI / ML 209 algorithm. The input data 207 may be the result of pre-processing 205 that may be performed on the raw data 203, or the input data 207 may include the raw data 203 itself. The raw data 203 may include image data, text data, audio data, or another information sequence (such as a network information sequence associated with a communication network), and / or other types of data. Pre-processing 205 may include format changes or other types of processing (e.g., averaging, filtering in the time and / or frequency domain) to generate input data 207 in a format for input into the AI / ML 209 algorithm. Output 215 may be generated by the AI / ML 209 algorithm in one or more formats, such as a tensor, a text format (e.g., words, sentences, or other text sequences), a numerical format (e.g., predictions), an audio format, an image format (e.g., including video formats), another data sequence format, or / another output format.

[0100] AI / ML 209 may be implemented using software and / or hardware as described herein. AI / ML 209 may be stored as computer executable instructions on a computer readable medium that can be accessed by one or more processors for execution as described herein. Example AI / ML environments and / or libraries include TENSORFLOW, TORCH, PYTORCH, MATLAB, GOOGLE CLOUD AI and AUTOML, AMAZON SAGEMAKER, AZURE MACHINE LEARNING STUDIO, and / or ORACLE MACHINE LEARNING.

[0101] The AI / ML 209 may include one or more algorithms configured for unsupervised learning. Unsupervised learning may be implemented using AI / ML 209 algorithms that learn from input data 207 without being trained for a specific target output. For example, during unsupervised learning, the AI / ML 209 algorithm may receive unlabeled data as input data 207 and determine patterns or similarities in the input data 207 without additional intervention (e.g., updating parameters and / or hyperparameters). The AI / ML 209 algorithms configured to implement unsupervised learning may include algorithms configured to identify patterns, groupings, clusters, anomalies, and / or similarities or other associations in the input data 207. For example, the AI / ML may implement a hierarchical clustering algorithm, a k-means clustering algorithm, a k-nearest neighbor (K-NN) algorithm, an anomaly detection algorithm, a principal component analysis algorithm, and / or a priori algorithms. The AI / ML 209 algorithm configured for unsupervised learning may be implemented on a single device or distributed across multiple devices such that the output 215 or portions thereof may be aggregated at one or more devices for further processing and / or implementation in other downstream algorithms or processes, as may be further described herein.

[0102] AI / ML 209 may include one or more algorithms configured for supervised learning. Supervised learning may be implemented using an AI / ML 209 algorithm trained during a training process to determine a predictive model using known results. The AI / ML 209 algorithm may be characterized by parameters and / or hyperparameters that may be trained during the training process. These parameters may include values ​​derived during the training process. These parameters may include weights or coefficients and / or biases. AI / ML 209 may also include hyperparameters. These hyperparameters may include values ​​for controlling the learning process. These hyperparameters may include a learning rate, the number of time periods, a batch size, the number of layers, the number of nodes in each layer, the number of kernels (e.g., CNN), the stride size (e.g., CNN), the kernel size in the pooling layer (e.g., CNN), and / or other hyperparameters. In some cases, certain parameters and hyperparameters may be used interchangeably.

[0103] The AI / ML 209 may be trained during supervised learning by inputting training data into the AI / ML 209 algorithm and adjusting parameters and / or hyperparameters toward a known target output 215 while minimizing the loss or error in the output 215 generated by the AI / ML 209 algorithm. The raw data 203 may include or be divided into training data, validation data, and / or test data, which are used to train, validate, and / or test the AI / ML 209 algorithm during supervised learning, respectively. The training data, validation data, and / or test data may be pre-processed from the raw data 103 for input into the AI / ML 209 algorithm. During supervised learning, the training data may be labeled before being input into the AI / ML 209. The training data may be labeled to teach the AI / ML 209 algorithm to learn from the labeled data and to test the accuracy of the AI / ML 109 implemented on unlabeled input data 207 during production / implementation of the AI / ML 209 algorithm or a similar AI / ML 209 algorithm utilizing similar parameters and / or hyperparameters. The training data may be used to fit the parameters of the AI / ML 209 model using an optimization function, such as a loss or error function. Typically, the training data includes pairs of input data 207 and corresponding target outputs 215, and the parameters may be trained to generate these input data and target outputs (e.g., within a threshold loss or error). The trained or fitted AI / ML 209 model may receive validation data as input to evaluate the fit of the model to the training data set while tuning the hyperparameters of the AI / ML 209 model. The AI / ML 209 model may receive test data to evaluate the fit of the final model to the training data set and to evaluate the performance of the AI / ML 209 model. One or more of training, validation, and / or testing may be performed during supervised learning for different types of AI / ML 209 models.

[0104] Supervised learning can be implemented for various types of AI / ML 209 algorithms, including algorithms that implement linear regression, logistic regression, neural networks (NNs), decision trees, Bayesian logic, random forests, and / or support vector machines (SVMs). NNs and deep NNs (DNNs) are commonly used examples of algorithms utilized in AI / ML models that can be trained using supervised learning. However, the AI / ML 209 model may implement one or more NN-based and / or non-NN-based algorithms. Various examples of NNs include: perceptrons, multilayer perceptrons (MLPs), feedforward NNs, fully connected NNs, convolutional neural networks (CNNs), recursive NNs (RNNs), long short-term memory (LSTM) NNs, and / or residual NNs (ResNets). A perceptron is a NN that includes a function that multiplies its input by a learned weight coefficient to generate an output value. A feedforward NN is a NN that receives input at one or more nodes of an input layer and moves information in a direction through one or more hidden layers to one or more nodes of an output layer. In a feedforward NN, one or more nodes of a given layer may be connected to one or more nodes of another layer. A fully connected NN is a NN that includes an input layer, one or more hidden layers, and an output layer. In a fully connected NN, each node in one layer is connected to each node in another layer of the NN. MLP is a feedforward NN of the fully connected class. CNN is a NN with one or more convolutional layers that are configured to perform convolutions. Various types of NNs may have elements including one or more CNNs or convolutional layers, such as generative adversarial networks (GANs). GANs may include conditional GANs (CGANs), cycle-consistent GANs (CycleGANs), StyleGANs, DiscoGANs, and / or IsGANs. GANs may include a generator submodel and a discriminator submodel. The generator submodel may be configured to receive input data and pass real, independently generated data to the discriminator submodel. The discriminator submodel may be configured to receive real, independently generated data from the generator, discriminate real, independently generated data, and provide feedback to the generator submodel during training to improve the function of the generator submodel in independently generating outputs based on the received input. For example, GANs are models commonly used to generate data types or data sequences (such as image data, audio data, and / or text). RNNs are NNs that are recursive in nature because nodes include feedback connections and internal hidden states (e.g., memories) that allow outputs from nodes in the NN to affect subsequent inputs to the same node. LSTM NNs may be similar to RNNs because nodes have feedback connections and internal hidden states (e.g., memories). However, LSTM NNs may include additional gates to allow LSTM NNs to learn long-term dependencies between data sequences. ResNets are NNs that may include skip connections to skip one or more layers of the NN.An autoencoder may be a form of AI / ML 109 that may be implemented for supervised learning such that parameters and / or hyperparameters may be updated during the training process. These parameters and / or hyperparameters may be associated with the encoder portion and / or decoder portion of the autoencoder. Some NNs include one or more attention layers or functions to enhance or focus on some portions of the input data while attenuating or de-emphasizing other portions.

[0105] Different types of NNs and / or layers may be implemented to process different types of data and / or produce different types of outputs. For example, a NN may include one or more convolutional layers (e.g., for CNNs or GANs), which may be commonly used to process image data and / or audio data (e.g., spectrograms). Each convolutional layer may vary according to various convolutional layer parameters or hyperparameters, such as kernel size (e.g., the field of view of the convolution), stride (e.g., the step size of the kernel when traversing the image), padding (e.g., for processing image boundaries), and / or input and output sizes. The image being processed may include one or more dimensions (e.g., rows of pixels or a two-dimensional array of pixels). These pixels may be represented according to one or more values ​​(e.g., one or more integer values ​​representing color and / or intensity) that may be received by the convolutional layer. A kernel, which may also be referred to as a convolution matrix or mask, may be a matrix for extracting and / or transforming features from the input data being received. Kernels may be used for blurring, sharpening, and / or edge detection, among others. Example kernel sizes may include matrices such as 3×3, 5×5, 10×10 (e.g., in units of pixels for a 2D image). The stride can be a parameter used to identify the amount by which the kernel moves on the image data. Example default strides have a size of 1 or 2 within the matrix (e.g., in pixels of a 2D image). Padding can include the amount of data added to the border of the image data as it is processed by the kernel (e.g., in pixels of a 2D image). The kernel can move on the input image data (e.g., according to the stride length) and perform a dot product with the overlapping input region to obtain an activation value for the region. The output of each convolutional layer can be provided to the next layer of the NN, or as the output of the NN itself (e.g., image data, feature maps, etc.) with convolution-based updated features.

[0106] The NN may include layers of similar types (e.g., convolutional layers, feed-forward layers, fully connected layers, etc.) and / or layers having similar or different configurations (e.g., size, number of nodes, etc.). The NN may also or alternatively include one or more layers of the NN of different types or different subsets, which may be interconnected for training and / or implementation as described herein. For example, the NN may include both convolutional layers and feed-forward layers or fully connected layers.

[0107] Figure 2BAn example of a neural network 209a is illustrated. The purpose of training can be to use input 207a as training data and / or adjust the Figure 2B One or more weights indicated as w and x in 209a (e.g., these weights may be referred to as neuron weights and / or link weights) are used to make the output 215 from the neural network 209a close to the desired target value associated with the input 207a values ​​used for the training data. In an example, the neural network may include three layers (e.g., Figure 2B ). During training, for a given input, the difference between the output and the expected value can be calculated, and / or the difference can be used to update one or more weights in the neural network. For example, if the difference between the output and the expected value is observed to be significant (e.g., large), one or more changes in one or more weights can be expected to be relatively significant (e.g., large); a small difference (e.g., between the output and the expected value) can include one or more changes in one or more weights being relatively small. For example, for positioning, the input 207a can be a reference signal parameter, and / or the output 215 can be an estimated positioning. The expected value can be location information acquired with high accuracy by a global navigation satellite system (GNSS).

[0108] Once the neural network 209a completes its training, the difference between the output 215 and the expected value may be below a threshold. The neural network 209a may be applied or implemented after positioning training by feeding the input data 207a and / or by estimating or predicting the output 215 as the expected result of the associated input 207a. The output 215 may be an estimated position and / or location of the WTRU.

[0109] Training the neural network 209a may include identifying one or more of the following information: an input to the neural network; an expected output associated with the input; and / or an actual output from the neural network that is compared to a target value.

[0110] In an example, a neural network model may be characterized by one or more parameters and / or hyperparameters, which may include: the number of weights and / or the number of layers in the neural network.

[0111] As used herein, the term "deep learning" may refer to a class of machine learning algorithms that employ artificial neural networks (e.g., deep neural networks (DNNs)) that are loosely inspired from biological systems and / or include at least one hidden layer. DNNs may be a special class of machine learning models inspired by the human brain, in which inputs are linearly transformed and / or passed through a nonlinear activation function one or more times (e.g., multiple times). DNNs may include one or more (e.g., multiple) layers, in which one or more (e.g., each) layer includes a linear transformation and / or a given nonlinear activation function. DNNs may be trained using training data via a back-propagation algorithm. Recently, DNNs have demonstrated state-of-the-art performance in various fields (e.g., speech, vision, natural language, etc.) and / or for various machine learning settings (e.g., supervised, unsupervised, and / or semi-supervised).

[0112] Figure 2C 201a for training and implementing an AI / ML model including a NN 209a. However, other types of AI / ML models (e.g., including NN and / or non-NN models) may be similarly trained and / or implemented. NN 209a may be trained and / or implemented on one or more devices to determine and / or update parameters and / or hyperparameters 217 of NN 209a. Raw data 203a may be generated from one or more sources. For example, raw data 203a may include image data, text data, audio data, or another information sequence (such as a network information sequence associated with a communication network) and / or other types of data. Raw data 203a may be pre-processed at 205a (e.g., averaging, filtering in the time domain and / or frequency domain) to generate training data 207a. The pre-processing may include formatting or other types of processing of the changes so as to generate training data 207a in a format for input into NN 209a.

[0113] NN 209a may include one or more layers 211. The configuration of NN 209a and / or layer 211 may be based on parameters and / or hyperparameters 217. As described herein, these parameters may include weights or coefficients and / or biases for nodes or functions in layer 211. These hyperparameters may include learning rate, number of epochs, batch size, number of layers, number of nodes in each layer, number of kernels (e.g., CNN), stride size (e.g., CNN), kernel size in pooling layer (e.g., CNN), and / or other hyperparameters. As described herein, NN 109a may include a feedforward NN, a fully connected NN, a CNN, a GAN, an RNN, a ResNet, and / or one or more other types of NNs. NN 209a may be composed of one or more different types of NNs or different layers for different types of NNs. For example, NN 109a may include one or more separate layers with one or more configurations.

[0114] During the training process, training data 207a may be input into the NN 209a and may be used to learn parameters and / or tune hyperparameters 217. Training may be performed by initializing parameters and / or hyperparameters of the NN 209a; generating and / or accessing training data 207a; inputting training data 207a into the NN 209a; calculating the error or loss from the output of the NN 209a to the target output 215a via a loss function 213 (e.g., using gradient descent and / or associated back propagation); and / or updating parameters and / or hyperparameters 217.

[0115] The loss function 213 may be implemented using a back-propagation based gradient update and / or gradient descent technique, such as stochastic gradient descent (SGD), synchronous SGD, asynchronous SGD, batch gradient descent, and / or mini-batch gradient descent. Examples of loss or error functions may include functions for determining squared error loss, mean squared error (MSE) loss, mean absolute error loss, mean absolute percentage error loss, mean squared logarithmic error loss, pixel-based loss, pixel-by-pixel loss, cross entropy loss, logarithmic loss, and / or benchmark-based loss. These loss functions may be implemented based on one or more quality metrics, such as a signal-to-noise ratio (SNR) metric or another signal or image quality metric.

[0116] An optimizer may be implemented with the loss function 213. The optimizer may be an algorithm or function configured to adapt properties of the NN 209a, such as learning rate and / or weights, to improve the accuracy of the NN 209a and / or reduce loss or error. The optimizer may be implemented to update parameters and / or hyperparameters 217 of the NN 209a.

[0117] The training process may be iterated to update parameters and / or hyperparameters 217 until an end condition is met. The end condition may be met when the output of the NN 209a is within a predefined threshold of the target output 215a.

[0118] After the training process is completed, the trained NN 209a or a portion thereof may be stored for implementation by one or more devices. The trained NN 209a or a portion thereof may be implemented in other downstream algorithms or processes, as may be further described herein. The trained NN 209a or a portion thereof may be implemented on the same device that performs the training. The trained NN 209a or a portion thereof may be sent or otherwise provided to another device for implementation. For example, NN 209b, 209c may include one or more portions of the trained NN 209a. NN 209b and NN 209c receive corresponding input data 207b, 207c and generate corresponding outputs 215b, 215c. The outputs 215b, 215c may be generated in one or more formats, such as tensors, text formats (e.g., words, sentences, or other text sequences), numerical formats (e.g., predictions), audio formats, image formats (e.g., including video formats), another data sequence format, and / or another output format. The outputs 215b, 215c may be aggregated at one or more devices for further processing and / or implementation in other downstream algorithms or processes, as may be further described herein.

[0119] Alternatively or additionally, after the training process is completed, the trained parameters and / or tuned hyperparameters 217 or portions thereof may be stored for implementation by one or more devices. The trained parameters and / or tuned hyperparameters 217 or portions thereof may be implemented in other downstream algorithms or processes, as may be further described herein. The trained parameters and / or tuned hyperparameters 217 or portions thereof may be implemented on the same device that performs the training. The trained parameters and / or tuned hyperparameters 217 or portions thereof may be sent or otherwise provided to another device for implementation, for example, based on the trained parameters and / or tuned hyperparameters 217 being sent or otherwise provided to another one or more devices that can implement NN209b, 209c. For example, NN 209b, 209c may be constructed at another device based on the trained parameters and / or tuned hyperparameters 217 or portions thereof. NN 209b and NN 209c may be configured according to parameters / hyperparameters 217 or portions thereof to receive respective input data 207b, 207c and generate respective outputs 215b, 215c. Outputs 215b, 215c may be generated in one or more formats, such as tensors, text formats (e.g., words, sentences, or other text sequences), numerical formats (e.g., predictions), audio formats, image formats (e.g., including video formats), another data sequence format, and / or another output format. Outputs 215b, 215c may be aggregated at one or more devices for further processing and / or implementation in other downstream algorithms or processes, as may be further described herein.

[0120] The AI / ML models and / or algorithms described herein may be implemented on one or more devices. For example, the AI / ML 209 may be implemented in whole or in part on one or more devices, such as one or more WTRUs, one or more base stations, and / or one or more other network entities, such as network servers. An example network in which the AI / ML may be distributed may include a federated network. A federated network may include a group of dispersed devices, each device including an AI / ML. Figure 2C As shown, AI / ML 209b and AI / ML 209c may be distributed on separate devices. Figure 2C Two models are shown (e.g., AI / ML 209b and AI / ML 209c), but any number of models may be implemented across any number of devices. AI / ML may be implemented for collaborative learning, where the AI / ML is trained across multiple devices. In another example, the AI / ML may be trained at a centralized location or device, and one or more portions of the AI / ML or trained parameters and / or tuned hyperparameters may be distributed to decentralized locations. For example, updated parameters or hyperparameters may be transmitted to one or more devices to update and / or implement the AI / ML thereon.

[0121] AI / ML may be used to estimate positioning (e.g., the location of the WTRU). For example, the WTRU and / or the network may use AI / ML to estimate positioning (e.g., the location of the WTRU). The WTRU and / or the network may estimate positioning based on one or more measurements (e.g., one or more measurements of received PRSs sent from one or more TRPs and / or based on the location of one or more TRPs). For example, the WTRU and / or the network may train an AI / ML model based on one or more actual and / or estimated measurements, as described herein. As used herein, the term "network" may include an application management function (AMF), a location management function (LMF), a base station (e.g., a gNB), and / or a next generation radio access network (NG-RAN).

[0122] The following pairs of terms may be used interchangeably: event and opportunity; preconfiguration and configuration; non-serving gNB and neighboring gNB; gNB and TRP; PRS and PRS resource; PRS and PRS resource; PRS and DL-PRS or DL ​​PRS; and / or measurement gap and measurement gap pattern. The aforementioned terms "PRS" or "PRS resource" may belong to one or more different PRS resource sets. The measurement gap pattern may include one or more parameters such as measurement gap duration, measurement gap repetition period, and / or measurement gap periodicity.

[0123] A Positioning Reference Unit (PRU) may be a WTRU or TRP whose location (e.g., altitude, latitude, geographic coordinates, and / or local coordinates) is known to the network (e.g., gNB, LMF). One or more capabilities of the PRU may be the same as the WTRU or TRP (e.g., ability to receive PRS and / or transmit SRS and / or SRS for positioning, one or more return measurements, and / or transmit PRS). One or more WTRUs acting as PRUs may be used by the network for one or more calibration purposes (e.g., correcting unknown timing offsets, correcting unknown angle offsets).

[0124] The LMF may be a non-limiting example of a node and / or entity (eg, a network node and / or entity) that may be used for and / or support positioning. The LMF may be replaced by one or more (eg, any) other nodes and / or entities.

[0125] AI may be a branch of science that solves problems by enabling one or more machines to simulate human behavior. ML may be a subset of artificial intelligence that focuses on solving problems by learning from data and / or making predictions. As used herein, the terms "AI" and "ML" are used interchangeably.

[0126] A mathematical model can be a mathematical formula that approximates the relationship between one or more variables (eg, inputs) and another variable (eg, output). The model can be created by one or more ML techniques.

[0127] Model training may include the process of providing input variables and / or output variables to a model to learn from.

[0128] Model deployment can be the process of deploying a trained model in the real world to perform one or more predictions and / or estimate outputs. Model inference can be the process of providing input variables to a model and / or predicting / calculating outputs. The terms "model deployment" and "model inference" are used interchangeably in this article.

[0129] Model monitoring can be the process of monitoring the accuracy of a particular model's output predictions. Model accuracy can be a metric for comparing one or more different classification models (e.g., defined as the ratio of the number of correct predictions made by a model to the total sample size).

[0130] Model updating can be a process where one model is replaced by another model for prediction.

[0131] Depending on the configured positioning methods, one or more (e.g., certain) types of methods may not be available at a given WTRU. For example, when the WTRU is configured with angle-based positioning, the WTRU may not be able to obtain one or more timing measurements. For example, due to one or more limited WTRU capabilities (e.g., the WTRU cannot measure timing), the WTRU may not be able to obtain one or more timing measurements. The WTRU may not receive one or more configurations related to timing synchronization between TRPs, which may prevent the WTRU from calculating an accurate RSTD (reference signal time difference). Therefore, the WTRU may obtain one or more unobservable measurements. Measurements that the WTRU cannot measure (e.g., due to limited WTRU capabilities, unconfigured PRS, different time instances and / or unconfigured TRPs) may be referred to as unobservable measurements and / or unobserved measurements.

[0132] Additionally or alternatively, the WTRU may perform one or more measurements on (e.g., only) PRS sent from a configured TRP, and the amount of measurements may be limited to achieve a target accuracy.

[0133] The measurements may include one or more anomalies (e.g., sudden non-line of sight (NLOS), one or more unexpected timing errors). The WTRU may detect the one or more anomalous measurements to isolate one or more error sources (e.g., timing errors) that caused the one or more anomalies.

[0134] A WTRU with reduced capability (e.g., reduced bandwidth (BW), reduced number of antenna elements) may collect one or more measurements that may be unreliable (e.g., large variations in RSTD and / or RSRP measurements). In this case, for example, the WTRU may enhance the quality of one or more measurements for the reduced capability (RedCap) WTRU to improve positioning accuracy.

[0135] AI / ML-based predictions may be used to determine estimates and / or inferences (e.g., RSTD) based on one or more actual measurements (e.g., RSRP). The WTRU may receive one or more configurations from the network to determine the estimate. The WTRU may transmit a request for one or more configurations to the network to enable a function to generate an estimate, for example, based on one or more of the conditions in the present document (e.g., if at least one condition is met). The input to the function may include one or more measurements made by the WTRU. The WTRU may determine its location, for example, based on estimates and / or actual measurements (e.g., both). For example, if the WTRU is configured with WTRU-based positioning, the WTRU may report the determined location to the network, indicating that the estimate was used. For example, if the WTRU is configured with WTRU-assisted positioning, the WTRU may report the estimate and / or one or more measurements (e.g., both) to the network.

[0136] When the WTRU receives one or more configurations for DL-AoD, the WTRU may measure the RSRP of the received PRS. The WTRU may not need to measure timing information (e.g., time of arrival, RSTD). The WTRU may have the capability to measure timing information. The timing information may improve positioning accuracy by enabling hybrid positioning methods that combine angle-based positioning methods and timing-based positioning methods. Therefore, obtaining measurements that cannot be observed may be a challenge.

[0137] An AI / ML model may be trained (e.g., as described herein, with respect to supervised learning, etc.) to predict one or more measurements. A network (e.g., LMF, gNB) may train an AI / ML model (e.g., as described herein, with respect to supervised learning, etc.) based on one or more measurements reported by a WTRU. A network (e.g., LMF, gNB) may implement a trained AI / ML model to predict one or more measurements, as described herein. The trained network may be implemented at one or more network entities. The trained model and / or one or more trained model parameters may be transmitted to another entity based on the training (e.g., before being implemented). In an example, the trained AI / ML model may be transferred from a serving gNB to a neighboring gNB. In another example, the trained network may be transferred from a gNB to an LMF, or vice versa.

[0138] Figure 3 An example is shown where the network trains an AI / ML model 300 based on measurements reported by WTRUs (e.g., WTRU1 310 and / or WTRU2 312). Figure 3 In the example shown, one or more RSRP measurements observed from one or more PRSs sent from TRP1 302, TRP2 304, and / or TRP3 306 may be used as input to an AI / ML model 308 (e.g., as described herein). Figure 3As shown, the network may use one or more TRP locations as part of the training data 301. The training data may include training data 301a and / or training data 301b. The training data 301 may include one or more RSRP measurements and / or TRP locations (e.g., location of TRP1, location of TRP2, location of TRP3, etc.). For example, WTRU1 may provide input 302a (e.g., RSRP1, RSRP2, RSRP3, location of TRP1, location of TRP2, and / or location of TRP3) to train the AI / ML model 308. For example, WTRU2 may provide input 301b (e.g., RSRP1, RSRP2, RSRP3, location of TRP1, location of TRP2, and / or location of TRP3) to train the AI / ML model 308. The training data 301a, 301b may be used to learn / determine one or more parameters of the AI / ML model 308 and / or tune one or more hyperparameters of the AI / ML model, as described herein. The WTRUs (e.g., WTRU1 310 and / or WTRU2 312) may receive corresponding configurations for PRSs (e.g., PRS resources) from the network. Each WTRU may measure RSRPs corresponding to PRS1, PRS2, and / or PRS3 sent from TRP1 302, TRP2 304, and / or TRP3 306, respectively. The corresponding timing information (e.g., RSTD 351a, 351b) may be used as a target. The target output 351a may be a target for training the AI / ML model 308 based on the training data 301a. The target output 351a may include RSTD12 and / or RSTD13 based on one or more training data 301a provided, for example, by WTRU1 310. The target output 351b may include RSTD12 and / or RSTD13 based on one or more training data 301b provided, for example, by WTRU2 312. The training process may be iterated to update one or more parameters and / or hyperparameters 217 until an end condition is met. For example, one or more parameters and / or hyperparameters of the AI / ML model 308 may be iteratively updated until the target output 351a, 351b is achieved. A WTRU (e.g., WTRU1 310 and / or WTRU2 312) may measure one or more RSTDs as follows. First, a WTRU (e.g., WTRU1 310 and / or WTRU2 312) may receive a configuration from a network indicating which TRP and / or PRS to use as a reference. The WTRU (e.g., WTRU1 310 and / or WTRU2 312) may receive an indication from the network that PRS1 is used as a reference. The WTRU may measure the time of arrival (ToA) for PRS1 and / or PRS2, namely, ToA1 and ToA2, respectively. For example, the ToA for PRS1 may be referred to as ToA1, and / or the ToA for PRS2 may be referred to as ToA2.For example, the ToA for PRS3 may be referred to as ToA3. RSTD12 may be calculated by subtracting ToA2 from ToA1 (e.g., RSTD12=ToA1-ToA2). Subsequently, the WTRU (e.g., WTRU1 310 and / or WTRU2 312) may calculate RSTD13 by subtracting ToA3 from ToA1 (e.g., where RSTD13=ToA1-ToA3). The WTRU (e.g., WTRU1 310 and / or WTRU2 312) may report RSRP and / or RSTD information to the network, and / or the network may train the AI / ML model 308 using one or more reported measurements. In one or more examples described herein, the term "RSRP" may be used interchangeably with the term "absolute RSRP" and / or "relative RSRP", where the relative RSRP may be determined based on a reference RSRP.

[0139] The WTRU may start using the trained AI / ML model based on one or more triggers (e.g., 308). In an example, the WTRU may not be able to measure RSTD and / or may measure (e.g., only measure) the RSRP of one or more received PRSs. In such a case, for example, the WTRU may transmit a request for assistance information to the network to obtain one or more assistance measurements based on one or more of the following conditions (e.g., if one or more of the following conditions are met): the highest RSRP of the received PRSs is below a preconfigured threshold; the highest RSRP of the received SSBs is below a preconfigured threshold; the average of the RSRP of the configured TRP of the received PRSs is below a preconfigured threshold; the standard deviation of the WTRU position information obtained from the configured angle-based positioning is above a preconfigured threshold (e.g., for WTRU-based positioning); the WTRU receives a periodic or semi-persistent trigger; and / or the WTRU receives an indication from the network (e.g., LMF, gNB) that one or more unobserved measurements from the (e.g., trained) AI / ML model are determined.

[0140] If the WTRU receives a periodic and / or semi-persistent trigger, the WTRU may transmit a request for assistance information to the network. For example, the WTRU may be configured with periodic occasions and / or semi-persistent occasions, where the semi-persistent occasions occur periodically during a time window and / or until the WTRU receives a deactivation command from the network. The semi-persistent occasion may be initiated with an activation command from the network. At one or more (e.g., each) periodic and / or semi-persistent occasions, the WTRU may determine one or more estimated measurements based on actual measurements, and / or the WTRU may determine its position using one or more estimated measurements.

[0141] In an example, a WTRU may receive an indication that a network has an AI / ML model trained based on one or more TRPs and / or PRSs that are within a line of sight (LOS) relative to the WTRU from which the network collected measurements. For example, if the WTRU determines that one or more received PRSs and / or configured TRPs are within the LOS with the WTRU, the WTRU may determine to transmit a request to the network for configuration of the trained AI / ML model. The WTRU may determine whether one or more TRPs and / or PRSs are within the LOS based on one or more measurements (e.g., RSRP).

[0142] The WTRU may transmit a request for auxiliary information (e.g., one or more AI / ML model parameters) to the network, for example, based on one or more of the conditions herein (e.g., if one or more of the conditions indicated herein are met). For example, if the request is granted, the WTRU may receive the information from the network. Examples of AI / ML model parameters may include one or more weights, one or more (e.g., multiple) layers in the network, an AI / ML model index, and / or an ID number.

[0143] Figure 4An example system 400 is shown in which a WTRU receives one or more AI / ML parameters 401 from a network entity 403 (e.g., an LMF). The WTRU (e.g., 402a) may receive one or more of the following AI / ML parameters 401 from the network 403 as auxiliary information: one or more weights in an AI / ML model; one or more input attributes of the AI / ML model 408 (e.g., the number of TRPs, the RSRP for each TRP, the location of each TRP, a TRP ID, a reference TRP ID, a PRS ID, and / or a PRS reference ID for calculating RSTD and / or differential RSRP, where the differential RSRP may be calculated by calculating the difference between a target RSRP and a reference RSRP); one or more output attributes of the AI / ML model 408 (e.g., the number of inferred measurements); one or more configurations related to the one or more input attributes (e.g., PRS configuration, reference TRP ID, PRS ID, and / or PRS reference ID for calculating RSTD and / or differential RSRP, where the differential RSRP may be calculated by calculating the difference between a target RSRP and a reference RSRP); 402a, 402b); a mapping function, wherein the WTRU (e.g., 402a, 402b) receives information related to parameters and outputs for the function; and / or a list of one or more AI / ML models 408 (e.g., the WTRU may receive one or more AI / ML models, each of which corresponds to one or more different characteristics of an input measurement (e.g., RSRP)). The WTRU (e.g., 402a, 402b) may receive a configuration from the AI / ML models 408 indicating how much RSTD and / or RSRP the WTRU expects to obtain. The WTRU may determine the RSRP from PRS1. The WTRU may perform a correlation between a sequence of PRS1 received in a configuration (e.g., provided by the network) and a received signal (e.g., which may include PRS1). The WTRU may perform a correlation operation in the frequency domain and / or time domain, and / or may determine the RSRP, for example, based on the result of the correlation operation.

[0144] The WTRU (e.g., 402a) may receive a mapping function, wherein the WTRU 402a receives information related to parameters and outputs for the function from the network as auxiliary information. Examples of parameters may include RSRP and / or TRP position, and / or the output of the function may be RSTD. The WTRU (e.g., 402a) may receive one or more parameters related to the function, and one or more examples of these parameters may include one or more coefficients and / or constants for a polynomial.

[0145] The WTRU (e.g., 402a) may receive a list of AI / ML models 408 from the network as auxiliary information. Examples of characteristics of measurements may include one or more granularities of measurements (e.g., granularity of RSRP values), one or more (e.g., a certain number of) TRPs corresponding to the measurements, and / or LOS / NLOS indicators associated with one or more measurements. For example, the WTRU (e.g., 402a) may receive one or more (e.g., two) AI / ML models 408, wherein one AI / ML model generates an RSTD measurement based on an RSRP measurement made in a LOS environment, and / or another AI / ML model generates an RSTD measurement 415 based on an RSRP measurement 401 made in a NLOS environment. In an example, the WTRU (e.g., 402a) may receive one or more AI / ML models, wherein the models generate RSTD measurements 415 based on RSRP measurements 401, and one or more (e.g., each) models correspond to one or more different ranges of average RSRP measurements.

[0146] The determination of the estimated measurement 415 may be performed, wherein the estimated measurement 415 is of a different type than the actual measurement 401. In an example, based on the assistance information, the WTRU (e.g., 402a) may determine one or more estimated measurements 415 (e.g., RSTD) based on one or more actual measurements 401 (e.g., RSRP) made by the WTRU (e.g., 402a). Figure 4 As shown, the WTRU 402a may use the received AI / ML model 408 parameters, RSRP measurements 401 (e.g., the RSRP for each PRS received by the WTRU), and / or the location of the TRP from which the WTRU 402a received the PRS to determine one or more RSTDs 415. The terms "actual measurements" and "observed measurements" may be used interchangeably herein.

[0147] Figure 5 An example of inference generation using system 500 is illustrated. Figure 5 As shown, the WTRU 502 may determine RSTD12 504 based on input data 501 (e.g., RSRP1 and RSRP2). For example, the WTRU 502 may determine RSTD12 504 based on one or more similar methods as described herein. RSRP1, RSRP2, and / or RSTD12 may be associated with a PRS resource ID.

[0148] One or more measurements (e.g., RSTD) obtained from the AI / ML model and / or one or more other (e.g., configured or predicted) functions may be estimated and / or inferred by the AI / ML model 508 and / or other functions, for example, based on one or more input measurements 501 (e.g., RSRP). Examples of the one or more functions may include interpolation and / or extrapolation functions. The parameters of these functions may not be trained because they may be preconfigured. The one or more other functions may not use AI / ML. In an example, the function may utilize coefficients trained to perform predictions / estimations herein. In an example, the AI / ML model 508 and / or configured functions may be trained at the network 503 (e.g., LMF) so that the model 508 generates one or more inferred measurements 515 (e.g., RSTD12 504). The AI / ML model 508 may include trained parameters and / or tuned hyperparameters to determine one or more inferred measurements 515 (e.g., RSTD). In an example, the function may generate one or more interpolated and / or extrapolated measurements 515 (eg, RSTD) based on one or more input measurements (eg, RSRP and / or RSTD).The terms "inferred measurement," "output," and "estimated measurement" may be used interchangeably herein.

[0149] The WTRU 502 may determine one or more estimated measurements 515 (e.g., unobserved measurements) based on one or more of: actual measurements (e.g., RSTD, RSRP); the location of the TRP (e.g., absolute and / or relative positioning, where the relative positioning may be relative to a reference TRP); the location of the WTRU (e.g., the WTRU obtains a coarse location of the WTRU based on one or more measurement and / or positioning methods such as DL-TDOA and / or DL-AoD; and / or a TRP ID, PRS resource, and / or PRS ID associated with the one or more measurements.

[0150] The WTRU may determine which inferred / estimated measurement to use. In an example, the WTRU may use one or more inferred / estimated measurements for one or more radio access technology (RAT) related positioning methods (e.g., DL-TDOA, DL-AoD). For example, if the WTRU determines an inferred / estimated measurement (e.g., RSTD) based on an actual measurement (e.g., RSRP), the WTRU may use the inferred / estimated measurement (e.g., RSTD) for the RAT related positioning method (e.g., DL-TDOA). For example, if the WTRU obtains an inferred / estimated timing measurement (e.g., RSTD), the WTRU may use one or more measurements for one or more timing based positioning methods (e.g., DL-TDOA).

[0151] For example, if the WTRU is unable to obtain the minimum number of measurements required for positioning, the WTRU may determine to use a default positioning method to determine the WTRU's location and / or report one or more available measurements to the network. For example, if the WTRU is unable to obtain the minimum number of inferred / estimated timing measurements for a timing positioning method based on one or more RSRP measurements, the WTRU may determine to use a positioning method that uses RSRP measurements (e.g., DL-AoD). For example, the WTRU may stop using a timing-based method and use a positioning-based method, where the positioning-based method may be based on RSRP (e.g., based only on RSRP). For example, if the WTRU is configured with a WTRU-based positioning method, the WTRU may determine to use a default positioning method (e.g., DL-AoD) to determine the WTRU's location. For example, if the WTRU is configured with a WTRU-assisted positioning method, the WTRU may determine to report one or more available measurements (e.g., RSRP) to the network.

[0152] The terms "observed TRP" and "unobserved TRP" may include one or more of the following. For example, if the WTRU performs one or more measurements on the PRS sent from one or more TRPs, then these TRPs may be referred to as observed TRPs. For example, if the WTRU does not perform one or more measurements on the PRS sent from the TRPs, then these TRPs may be referred to as unobserved TRPs. The WTRU may receive one or more configurations related to observed and / or unobserved TRPs (e.g., configurations related to PRS, TRP locations) from the network (e.g., LMF, gNB).

[0153] In an example, the WTRU may use both inferred / estimated measurements and actual measurements for RAT-dependent positioning methods (e.g., DL-TDOA, DL-AoD). For example, if the WTRU determines one or more inferred / estimated measurements (e.g., RSRP for PRS of unobserved TRP) based on one or more actual measurements (e.g., RSRP for PRS of observed TRP), the WTRU may use both actual measurements and inferred / estimated measurements for RAT-dependent positioning methods (e.g., DL-AoD).

[0154] In an example, the WTRU may use inferred / estimated measurements and actual measurements, in part, for a RAT-dependent positioning method (e.g., DL-TDOA, DL-AoD). For example, the WTRU may determine one or more inferred / estimated measurements (e.g., RSRP for PRS of unobserved TRP) based on actual measurements (e.g., RSRP for PRS of observed TRP). If the RAT-dependent positioning method accepts N measurements (e.g., RSRP), and the number of actual measurements and inferred / estimated measurements is greater than N, the WTRU may determine one or more measurements to be used for positioning, for example, by sorting the measurements (e.g., RSRP) in descending order, and / or may select one or more measurements with the N highest RSRP measurements. In an example, the WTRU may determine the N measurements (e.g., RSTD, RSRP) based on one or more LOS indicators associated with the one or more measurements. For example, if the LOS indicator is greater than a preconfigured threshold, the WTRU may determine to use RSRP measurements (e.g., use RSRP measurements associated with LOS). In an example, the WTRU may determine the N closest TRPs relative to the estimated WTRU position and / or a reference TRP, and / or may select N inferred / estimated RSTDs associated with one or more selected (e.g., determined) TRPs.

[0155] If the WTRU is configured with WTRU-based positioning, the WTRU may determine its position (e.g., the position of the WTRU in global coordinates) based on one or more actual measurements (e.g., RSRP) and / or one or more estimated measurements (e.g., RSTD) (e.g., both). The WTRU may report the determined location information to the network. For example, if the WTRU receives a request from the network, the WTRU may indicate to the network that one or more unobserved measurements were used to determine (e.g., derive) the location information.

[0156] For example, if the WTRU is configured with WTRU-assisted positioning, the WTRU may transmit a measurement report to the network, the measurement report including one or more actual measurements (e.g., RSRP) and / or one or more estimated / inferred measurements (e.g., RSTD estimated by an AI / ML model) (e.g., both). The WTRU may include one or more details related to one or more PRS configurations (e.g., PRS resource ID) in the measurement report.

[0157] Inferred / estimated measurements may be used as expected values. The WTRU may determine to use one or more inferred / estimated measurements as expected values ​​for one or more measurements. The WTRU may determine one or more inferred / estimated measurements of TRP that are not part of the configuration (e.g., RSRP, RSTD). The WTRU may receive an indication from the network (e.g., gNB, LMF) to use one or more inferred / estimated measurements as expected values ​​for a measurement.

[0158] The WTRU may use the expected value to prepare for one or more PRS measurements. For example, the WTRU may expect to receive PRS within a time window whose duration and / or center is determined (e.g., derived) based on the expected value and / or configured duration.

[0159] For example, RSTD may be defined as RSTD=t1-t0, where t1 and t0 are the arrival times of the target PRS and the reference PRS, respectively. For example, based on the expected value of RSTD (e.g., E_rstd) and the arrival time of the reference PRS (e.g., t0), the WTRU may determine (e.g., derive) the expected arrival time of the target PRS as E_rstd+t0. Additionally or alternatively, if the WTRU is configured with an uncertainty value d, the WTRU may determine a (e.g., time) window including a start time and / or an end time. The window may have a start time, which is represented as E_rstd+t0-d. For example, the window may have an end time, which may be represented as E_rstd+t0+d. During the time window, the WTRU may expect to receive the target PRS. Once the WTRU receives the target PRS, the WTRU may record the arrival time t1 and / or may determine (e.g., calculate) the RSTD, which is t1-t0. The time window may be associated with a PRS resource and / or TRP, measurements of which are used to determine (e.g., derive) one or more inferred / estimated measurements such that the WTRU may use a (e.g., appropriate) time window to receive the PRS.

[0160] The WTRU may determine the content of the measurement report according to (e.g., based on) whether the WTRU receives the target PRS during the time window. For example, if the WTRU receives the target PRS during the time window, the WTRU may report the actual RSTD. For example, if the WTRU does not receive the target PRS during the time window, the WTRU may report the inferred RSTD.

[0161] The WTRU may use the inferred / estimated RSRP to determine a range of RSRPs that the WTRU may use to receive the PRS. The WTRU may use this range to determine the quantization granularity and / or the range in which to receive the PRS.

[0162] The WTRU may receive one or more PRS configurations (e.g., reference TRP, PRS resource ID) from a network (e.g., LMF). The WTRU may receive an indication from the network (e.g., LMF) to determine (e.g., derive) a time window. The WTRU may receive a configuration for a window duration and / or one or more AI / ML models associated with one or more unobserved TRPs. The WTRU may perform one or more measurements on the PRS and / or may obtain one or more RSRP measurements. The WTRU may obtain one or more measurements of one or more unobserved TRPs (e.g., RSTD inferred from the AI / ML model based on the measurements). The WTRU may determine (e.g., derive) the time window based on the inferred RSTD and / or uncertainty value. The WTRU may receive a reference PRS from an unobserved TRP. The WTRU may determine one or more measurements to report. For example, if the WTRU receives a target PRS during the time window, the WTRU may transmit a measurement report including an actual RSTD and / or one or more RSRP measurements, and / or may indicate that the one or more measurements are actual measurements. For example, if the WTRU does not receive the target PRS during the time window, the WTRU may transmit a measurement report including an inferred RSTD and / or one or more RSRP measurements, and may indicate that the one or more measurements are inferred measurements.

[0163] Figure 6An example signal flow diagram 600 between a WTRU 602, a gNB 604, and a LMF 606 is illustrated. The AI / ML model may be trained at the network (e.g., the LMF and / or the gNB) and / or the WTRU. The trained AI / ML model may be implemented at the network and / or the WTRU (e.g., either, both). At 608, the LMF 606 may transmit assistance information to the WTRU 602. The assistance information may include one or more parameters for characterizing the AI / ML model and / or other functions. These other functions may include configuration functions and / or prediction functions that may not use AI / ML. In an example, the function may utilize coefficients that are trained to perform prediction / estimation herein. At 610, the LMF may transmit an indication to the WTRU 602. The indication 610 may indicate determining (e.g., deriving) a time window. At 612, the gNB 604 may transmit a PRS to the WTRU 602. At 614, the WTRU 602 may measure one or more RSRPs (e.g., as described herein). At 616, the WTRU 602 may determine one or more inferred RSTDs (e.g., as described herein). For example, the WTRU 602 may determine the one or more inferred RSTDs using an AI / ML model or other (e.g., configured) function based on parameters in the assistance information. At 618, the WTRU 602 may determine a window (e.g., determine a time window as described herein). At 620, the gNB 604 may transmit a PRS to the WTRU 602. At 622, the WTRU 602 may determine one or more RSTD measurements (e.g., as described herein). At 624, the WTRU 602 may transmit a measurement report (e.g., as described herein).

[0164] RSRP may be estimated based on RSTD. For example, the WTRU may determine RSRP based on one or more measured RSTDs. For example, the WTRU may determine RSRP based on one or more measured RSTDs by using an (e.g., trained) AI / ML model. The network may train an AI / ML model that accepts input (e.g., RSTD and / or TRP location information) and / or generates an RSRP corresponding to a PRS received from a TRP. The content of the request to the AI / ML model and / or another (e.g., configuration) function may be based on (e.g., dependent on) the positioning method configured for the WTRU. For example, if the WTRU is configured with a timing-based positioning method (e.g., DL-TDOA) and the maximum and / or minimum standard deviation of the measured RSTD is above a configured threshold, the WTRU may transmit a request to the network to configure an AI / ML model that generates RSRP based on the measured RSTD. For example, if the WTRU is configured with WTRU-based positioning, the WTRU may use the measured RSTD and / or the estimated RSRP to determine its position. Additionally or alternatively, if the WTRU is configured with WTRU-assisted positioning, the WTRU may transmit a report to the network including the estimated RSRP, the measured RSTD and / or the corresponding PRS resource ID.

[0165] The WTRU may receive one or more configurations for a WTRU-based angle-based positioning method (e.g., DL-AoD with TRP location) and / or one or more PRS configurations. The WTRU may receive, for example, a configuration for a reference TRP from a network node. The WTRU may receive one or more (e.g., multiple) AI / ML models, wherein one or more (e.g., each) AI / ML model may be associated with one or more different ranges of maximum RSRP values. The WTRU may perform one or more measurements on the PRS and / or may determine (e.g., obtain) one or more RSRP measurements. For example, if the measured maximum RSRP value is below a threshold, the WTRU may request the AI / ML model based on the range in which the maximum RSRP value falls. The WTRU may receive one or more parameters (e.g., weights) for the AI / ML model. The WTRU may determine one or more measurements (e.g., RSTD from the AI / ML model based on the measured RSRP measurement and / or TRP location information), wherein the RSTD is based on the reference TRP. The WTRU may determine a position estimate based on one or more inferred RSTDs, one or more RSRP measurements, and / or TRP information, for example, by using the AI / ML model. For example, the WTRU may use both one or more inferred measurements and one or more actual measurements to determine the WTRU location. The WTRU may report the determined location information to the network. In an example, the WTRU may use at least one or more inferred measurements (e.g., in addition to one or more actual measurements) to determine the WTRU location using a positioning method (e.g., WTRU-based DL-TDOA, WTRU-based DL-AoD, etc.).

[0166] The WTRU and / or the network may determine one or more unobservable measurements based on measurements of the same type. For example, the WTRU and / or the network may determine one or more unobservable measurements based on one or more (e.g., trained) AI / ML models (e.g., as described herein). One or more unobservable measurements may be generated based on measurements of the same type. For example, the WTRU may determine an unobserved portion of a measurement based on one or more actual measurements of the same type. The WTRU may determine one or more RSRP measurements from a TRP at a next measurement occasion (e.g., using an AI / ML model, a configuration function, and / or a prediction function) based on one or more RSRP measurements up to and including the current measurement occasion. Additionally or alternatively, the WTRU may determine one or more RSRP measurements from a TRP at a next measurement occasion based on the last N measurement occasions (wherein the WTRU receives a value of N from the network (e.g., LMF, gNB)). The WTRU may be configured with a range of measurement occasions, and / or other functions and / or AI / ML models may make predictions based on the N measurements and the associated TRP. Assuming that the current time index is indicated as k (e.g., symbol, slot, frame index), the WTRU may be configured with one or more future measurement opportunities (Ne) and / or one or more past measurement opportunities (Nr). For example, Ne=2 and Nr=3 may indicate that the AI / ML model may predict 2 future measurement opportunities (e.g., with time indices k+1, k+2) based on Nr=3 past measurement opportunities (e.g., with time indices k-3, k-2, k-1).

[0167] In an example, the WTRU may receive a configuration for a set of one or more TRPs. The WTRU may determine measurements of TRPs not included in the configured set based on one or more actual measurements (e.g., RSTD) from the configured set of TRPs. The WTRU may receive location information for one or more TRPs (e.g., location information for TRP1, location information for TRP2, etc.). The WTRU may determine one or more unobserved measurements (e.g., RSTD) of a target TRP, for example, based on one or more of the following measurements and / or information: one or more RSTD measurements and / or associated TRPs; TRP and / or reference TRP location information (e.g., absolute and / or relative locations of the TRPs, where the relative location may be determined / derived relative to the absolute location of a reference TRP); absolute and / or relative locations of one or more target TRPs, where the target TRP refers to a TRP used to calculate RSTD and / or where at least one of the TRPs used to calculate RSTD belongs to a configured set of TRPs; one or more RSRP measurements and / or associated TRPs; PRS resource IDs and / or TRP / PRS IDs associated with one or more measurements; and / or the location of the WTRU (e.g., the WTRU may obtain a coarse location of the WTRU based on one or more measurements and / or positioning methods (e.g., DL-TDOA, DL-AoD)).

[0168] The WTRU may determine, for example, an unobserved measurement of a target TRP based on an absolute and / or relative position of the target TRP, wherein the target TRP refers to a TRP used to calculate RSTD, and wherein at least one of the TRPs used to calculate RSTD belongs to a configured set of TRPs. For example, the WTRU and / or the network may determine (e.g., derive) a relative position of the WTRU and / or the target TRP or a selected TRP relative to an absolute position of a reference TRP.

[0169] Figure 7 An example system 700 is shown for enabling RSTD prediction based on one or more actual RSTD measurements. Figure 7As shown, the WTRU 702 may be configured with one or more (e.g., three) TRPs, namely TRP1 704, TRP2 706, and / or TRP3 708, where TRP1 704 is used as a reference. The WTRU 702 may receive one or more PRS configurations from the network, may perform one or more timing measurements, and / or may determine one or more RSTDs, such as RSTD12 711 and / or RSTD13 714. The WTRU 702 may receive information about the location of other TRPs (e.g., TRP4 710) from the network (e.g., via broadcast). For example, the WTRU may receive assistance information, which may include one or more parameters for an AI / ML model 718. The WTRU 702 may be configured with an AI / ML model 718, which may generate an RSTD measurement 715 for a given input 701. The WTRU 702 may use RSTD12 712 and / or RSTD13 714, location information of TRP1 704, location information of TRP2 706, location information of TRP3 708, and / or location information of TRP4 710, which may be a target TRP. The WTRU 702 may obtain RSTD value 715 (e.g., RSTD14 716) from AI / ML model 718, for example, based on one or more inputs 701. In an example, the WTRU may determine RSTD14 716 based on RSTD12 712, RSTD13 713, and / or TRP location information (e.g., location information of TRP1 704, TRP2 706, TRP3 708, and TRP1 704). The one or more inputs 701 may include one or more RSTD values ​​and / or one or more TRP locations.

[0170] The AI / ML model 718 may determine (e.g., predict, as described herein) one or more measurements that are valid for a predefined and / or preconfigured area. In an example, the WTRU may determine that one or more predicted measurements made by the AI / ML model are valid for a preconfigured group of cells. For example, the WTRU may receive one or more configurations of the AI / ML model 718 related to predicted coverage ranges. For example, the WTRU may be configured with a coverage range within which the AI / ML model 718 may determine (e.g., predict) one or more measurements (e.g., a radius and / or area within which a target TRP may be located relative to a reference TRP).

[0171] Fig. 8AAn example system 800a is depicted in which a reference TRP is a predictable area 802a of TRP1 804a. The AI / ML model and / or other functions may determine / predict one or more measurements (e.g., RSTD, RSRP) associated with TRP1 804a, TRP2 806a, TRP3 808a, and / or TRP4 810a. The other function may be a configuration function or a prediction function that may not use AI / ML. In an example, the function may utilize coefficients trained to perform the prediction / estimation herein. For example, since TRP5 812a is outside the coverage area, one or more measurements associated with TRP5 812a may not be predicted by the AI / ML model.

[0172] Figure 8B An example system 800b is illustrated for determining whether a TRP is within a predicted / inferred coverage area 802b, where the center of the coverage area is the location of the WTRU 801. In the example, the WTRU 801 may receive a configuration of an AI / ML model associated with a predicted / inferred coverage area 802b, where the coverage area is defined based on the location of the WTRU 801. For example, once the WTRU 801 determines its location, the WTRU 801 may transmit to the network a request for an AI / ML model associated with the WTRU location and / or the region / area in which the WTRU 801 is located. The WTRU 801 may determine the location of the WTRU 801 based on one or more measurements made on the PRS and / or a WTRU-based positioning method (e.g., DL-TDOA, DL-AoD). The WTRU 801 may determine whether one or more TRPs are within the predicted / inferred coverage area. Figure 8B An example is illustrated in FIG. 8 , where the center of the coverage area is the location of the WTRU 801. One or more measurements associated with TRP1 804b, TRP2 806b, TRP3 808b, and / or TRP4 810b (e.g., RSTD, RSRP) may be predictable by the AI / ML model and / or another function. For example, one or more measurements associated with TRP5 812b may not be predictable by the AI / ML model (e.g., and / or another function) because TRP5 812b is outside the coverage area 802b (e.g., the area that can be predicted).

[0173] The WTRU may determine in which region / area the WTRU is located based on the estimated WTRU location. The WTRU may receive information related to one or more locations of a region / area, based on which the WTRU determines in which region / area the WTRU is located. The WTRU may determine that an AI / ML model associated with the region to which the WTRU belongs may predict / infer one or more measurements associated with one or more TRPs located in the region.

[0174] In an example, if the WTRU does not find one or more (e.g., any) TRPs within the coverage area, the WTRU may determine to extend the coverage area by a configured extension factor. For example, if the extended coverage area is below a threshold, the WTRU may determine to search for one or more TRPs using the extended coverage area. For example, if the extended coverage area is above a threshold, the WTRU may report one or more measurements to the network. In an example, the WTRU may (e.g., continue to) extend the coverage area until the WTRU finds N TRPs, where N is an integer configured by the network, and / or until an expiration time of the search.

[0175] The WTRU may receive one or more of the LMF PRS configurations including a first set of TRPs and / or a reference TRP. The WTRU may receive assistance information (e.g., one or more parameters for an AI / ML model) and / or an associated coverage area (e.g., represented as a circle) from the network, for example, based on a reference TRP, an expansion factor, and / or a threshold (e.g., a diameter of a circle expressed in meters). The WTRU may receive a second set of TRPs and / or associated location information via a broadcast. The WTRU may perform one or more measurements on the PRS received from the first set of TRPs. The WTRU may determine one or more TRPs from the second set of TRPs that fall within the coverage area. For one or more (e.g., each) TRPs within the coverage area, the WTRU may determine a corresponding RSRP (e.g., an inference generated from the AI / ML model based on one or more RSRP measurements from the first set). The WTRU may report one or more RSRP measurements and / or corresponding TRP IDs to the network. If the WTRU does not find one or more (e.g., any) TRPs within the coverage area, the WTRU may determine an extended coverage area based on the expansion factor. If the WTRU does not find one or more (e.g., any) TRPs within the extended coverage area, the WTRU may compare the extended coverage area (e.g., the diameter of the extended coverage area) with a threshold. If the extended coverage area (e.g., the diameter) is below the threshold, the WTRU may again determine the TRPs that fall within the coverage area from the second set of TRPs. If the extended coverage area is above the threshold, the WTRU may report the RSRPs from the first set of TRPs to the network. For example, the coverage area may be represented as a circle (e.g., 802a, 802b). The WTRU (e.g., 801) may compare the size of the coverage area (e.g., the diameter of the corresponding circle) with a threshold and / or may determine whether the WTRU (e.g., 801) may further expand the coverage area (e.g., 802a, 802b). The expansion of the coverage area may be achieved by multiplying the diameter by an expansion factor, thereby expanding the coverage area.

[0176] Ideal measurement estimation can be performed. For example, as described herein, one or more ideal measurements can be determined.

[0177] The WTRU may determine the ideal measurement from the AI / ML model. The WTRU may determine the ideal measurement based on the location of the WTRU and / or the location of one or more TRPs. Additionally or alternatively, the WTRU may determine the ideal measurement (e.g., one or more time measurements) based on different types of measurements (e.g., power measurements) and / or the AI / ML model. The WTRU may determine the ideal measurement based on one or more of the following. For example, the WTRU may determine the ideal time of arrival (ToA) of the received PRS based on one or more RSRP measurements and / or the AI / ML model for the received PRS. The WTRU may determine the ideal RSTD for one or more received PRSs based on one or more RSRP measurements and / or the AI / ML model for the received PRS.

[0178] As described herein, the ideal RSTD may include the RSTD that the WTRU measures in the absence of any obstacles and / or elements that create a NLOS and / or multipath environment. The terms "ideal RSTD" and "ideal measurement" may be used interchangeably herein.

[0179] The WTRU may determine an ideal RSTD. For example, the WTRU may determine an ideal RSTD without reflections. For example, the WTRU may determine an ideal RSTD with reflections.

[0180] Fig. 9 An example system 900 is illustrated showing the arrival time in the presence of reflected signals. Fig. 9 As shown, the WTRU 902 may receive PRS (e.g., 906a, 906b) from the TRP 904. For example, the WTRU 902 may receive the PRS 906a directly from the TRP 904 that is within the LOS. The time of arrival in this example may be ToA=T (e.g., ideal ToA). For example, the WTRU 902 may receive the PRS 904b that is reflected by the obstacle 908. The time of arrival in the case where the PRS 904b is reflected by the obstacle 908 may be ToA=T+Tr, where Tr may be the additional time that the PRS 904b takes to reach the WTRU 902 due to the reflection. For example, due to the nature of the reflection, there may be one or more uncertainties (e.g., which may be represented as Tr). Therefore, the time of arrival in the presence of obstacles and / or NLOS may be unpredictable and / or may include inaccuracies in positioning performance.

[0181] For example, the ideal ToA may be calculated based on the WTRU location and / or the TRP location. For example, if the WTRU determines the distance between the WTRU and the TRP based on their respective locations, the WTRU may determine the propagation time by t=d / c, where d represents the distance between the WTRU and the TRP (e.g., expressed in meters), and c represents the speed of light (e.g., meters / second). The WTRU may determine the ideal RSTD. For example, the WTRU may determine the ideal RSTD by using the ideal ToA between the WTRU and the target TRP. In an example, the WTRU may determine the ideal ToA (e.g., time of flight, the time it takes for the PRS to reach the WTRU from the TRP) based on the WTRU's location (e.g., determined based on GNSS / GPS and / or one or more RAT-related or -independent positioning methods) and / or the TRP (e.g., provided in assistance information) and / or the speed at which the reference signal travels (e.g., the speed of light c). For example, if the distance between the TRP and the WTRU is represented as d, the ToA may be the distance divided by the speed of light (e.g., d / c), where the speed of light may be represented as 3×10^8 meters per second (e.g., c=3e8). The WTRU may determine the ideal RSTD by using the ideal ToA between the WTRU and a reference TRP. For example, the WTRU may determine the ideal RSTD by using the ideal ToA between the WTRU and a target TRP and / or by using the ideal ToA between the WTRU and a reference TRP.

[0182] The WTRU may determine the ideal RSTD as follows. For example, in a LOS scenario, if the ToAs from the reference TRP and the target TRP are T1 and T2, respectively, the RSTD may be calculated as RSTD=T1-T2 (e.g., "ideal RSTD"). In a LOS scenario, if the ToAs from the reference TRP and the target TRP are T1+Tr1 and T2+Tr2, respectively, the RSTD may be calculated as RSTD=T1-T2+Tr1-Tr2, which may be the measured / actual RSTD. In the presence of NLOS, one or more uncertainties in RSTD may increase.

[0183] In an example, the WTRU may train an AI / ML model based on one or more RSRP measurements using an ideal RSTD measurement as a target (e.g., an example of a target during training). The WTRU may obtain the ideal RSTD measurement based on knowledge of the WTRU's location. The WTRU may determine its location based on one or more GNSS / GPS, RAT-related positioning methods (e.g., DL-TDOA, RTT), and / or configuration from a network, where the network knows the location of the WTRU. The WTRU may determine the ideal RSTD, for example, based on knowledge of the WTRU's location and / or one or more locations of the TRP.

[0184] For example, once the WTRU obtains a trained AI / ML model and / or one or more parameters thereof, the WTRU may use the AI / ML model to determine the RSTD. For example, the WTRU may use the AI / ML model to determine the RSTD using one or more methods as described herein. In an example, the WTRU may perform one or more measurements (e.g., RSRP) on the PRS. The WTRU may determine the RSTD from the trained AI / ML model, for example, based on one or more RSRP measurements. The WTRU may use the determined RSTD with the configured positioning method (e.g., DL-TDOA) to determine the WTRU position. Based on the configuration for the AI / ML model (e.g., input parameters, output parameters), the WTRU may determine to use one or more of the following parameters and / or measurements as input to the AI / ML model to determine the RSTD: one or more measurements (e.g., RSRP for each path of the RSRP / PRS resource); a TRP index; and / or one or more locations of the TRP.

[0185] The WTRU may request an AI / ML model and / or one or more parameters thereof trained with one or more ideal measurements. In an example, the WTRU may determine to use one or more AI / ML models trained with one or more ideal measurements based on one or more of the following criteria: the WTRU determines that a LOS indicator associated with a TRP and / or a PRS resource is less than or equal to a preconfigured threshold; the WTRU determines that the uncertainty of one or more measurements (e.g., ToA, RSTD) is greater than or equal to a preconfigured threshold; the WTRU determines that there are one or more (e.g., multiple) paths (e.g., more than one ToA measurement of a PRS resource); the WTRU determines that the RSRP of the PRS resource is less than a preconfigured threshold; and / or the WTRU determines that the number of NLOS TRPs is greater than or equal to a preconfigured threshold. In an example, the WTRU may determine to transmit a request to the network for an AI / ML model trained with the ideal measurement as a target based on one or more of the conditions herein (e.g., at least one of the conditions being met).

[0186] In an example, the WTRU may determine to transmit a request to the network for an AI / ML model trained using one or more ideal measurements (e.g., ideal RSTD) and / or actual measurements (e.g., actual RSTD) as targets. The WTRU may determine which AI / ML model to request based on one or more of the following conditions: if the WTRU determines that the LOS indicator associated with the TRP and / or PRS resource is less than or equal to a preconfigured threshold, the WTRU may transmit a request for an AI / ML model that is trained using one or more ideal measurements; if the WTRU determines that the uncertainty of one or more measurements (e.g., ToA, RSTD) is greater than or equal to a preconfigured threshold, the WTRU may transmit a request for an AI / ML model that is trained using one or more ideal measurements; if the WTRU determines that there are one or more (e.g., multiple) paths (e.g., more than one ToA measurement for a PRS resource), the WTRU may transmit a request for an AI / ML model that is trained using one or more actual measurements; if the WTRU determines that the RSRP of the PRS resource is less than a preconfigured threshold, the WTRU may transmit a request for an AI / ML model that is trained using one or more ideal measurements; and / or if the WTRU determines that the NLOS If the number of TRPs is greater than or equal to a preconfigured threshold, the WTRU may transmit a request for an AI / ML model that is trained using one or more actual measurements.

[0187] The terms “AI / ML model trained using actual measurements” and “AI / ML model trained using ideal measurements” are used interchangeably herein.

[0188] The AI / ML model may be trained at the WTRU using an ideal target. The WTRU may determine during training to use an ideal RSTD as the target metric rather than a measured RSTD, for example, because the arrival time measurement may be affected by a multipath channel (e.g., the uncertainty in the arrival time may increase in the presence of multipath).

[0189] In an example, the WTRU may train an AI / ML model based on an ideal RSTD and / or measured RSRP. The AI / ML model may be trained to estimate the correct or ideal RSTD, for example, based on one or more RSRP measurements. The one or more RSRP measurements may serve as a fingerprint.

[0190] During training, the WTRU may determine to use one or more ideal measurements (e.g., instead of actual measurements) as target metrics based on one or more of the following criteria: the WTRU receives an indication from the network to train the AI / ML model using one or more ideal measurements; the WTRU determines that the LOS indicator associated with the TRP and / or PRS resources is less than (e.g., below) or equal to a preconfigured threshold; the WTRU determines that the uncertainty of one or more measurements (e.g., ToA, RSTD) is greater than or equal to a preconfigured threshold; and / or the WTRU determines that there are one or more (e.g., multiple) paths (e.g., more than one ToA measurement of a PRS resource).

[0191] A trained AI / ML model may be identified. In an example, the WTRU may train an AI / ML model for each TRP (e.g., and / or TRP pair). Thus, the AI / ML model may be associated with a TRP index (e.g., ID) and / or a pair index (e.g., a pair may include two TRPs). The WTRU may determine the AI / ML model index for determining the RSTD, for example, based on the TRP and / or TRP pair from which the PRS for which the WTRU makes one or more measurements is sent.

[0192] In an example, the WTRU may train an AI / ML model for a set of TRPs. In this case, the AI / ML model may be associated with a group index. The WTRU may receive one or more configurations (e.g., TRP IDs in the set) for the TRPs included in the set from the network.

[0193] In an example, the WTRU may receive one or more configurations (e.g., PRS resource ID and / or periodicity) and / or thresholds for a PRS from a network. The WTRU may receive one or more (e.g., more than one) thresholds, each of which may be an RSRP threshold and / or may be associated with a group of PRS resources or a PRS resource. The WTRU may perform one or more measurements on a PRS from one or more TRPs. The WTRU may be configured with a DL-TDOA positioning method (e.g., the WTRU may determine RSTD). For example, if the WTRU determines that the RSRP of a PRS resource is less than a threshold, the WTRU may transmit a request to the network for an AI / ML model that is trained using one or more ideal RSTD measurements. The WTRU may determine one or more ideal RSTD measurements based on the measured RSRP (e.g., based on the AI / ML model that the WTRU received from the network). The WTRU may use the ideal RSTD measurements to determine its location. The WTRU may report its location to the network.

[0194] A differential position reporting may be performed. The WTRU may determine its position information, for example, by using WTRU-based positioning. In an example, when the WTRU is configured with WTRU-based positioning, the WTRU may include differential position information in the report. More than one position information associated with the WTRU may be included in the report if one or more of the following conditions are met: the WTRU is configured with more than one positioning method, and the WTRU determines (e.g., derives) its position according to one or more (e.g., each) method respectively; one or more uncertainties exist in one or more measurements (e.g., multipath channel, reflected PRS), and the WTRU determines (e.g., derives) more than one position; the WTRU obtains one or more unobserved measurements (e.g., inferred / estimated measurements obtained from an AI / ML model), based on which the WTRU may determine (e.g., derive) (e.g., new) position information; and / or the WTRU receives an indication from the network to report one or more differential positions.

[0195] If the WTRU obtains unobserved measurements (e.g., inferred / estimated measurements obtained from an AI / ML model), more than one location information associated with the WTRU may be included in the report, and the WTRU may derive new location information based on these unobserved measurements. The WTRU may derive new location information based on only the unobserved measurements or based on a combination of observed and unobserved measurements.

[0196] The differential position may include one or more of the following: Given two locations with coordinates, e.g., (x1, y1, z1) and (x2, y2, z2), the differential position relative to a reference point (x1, y1, z1) may be given by (x2-x1, y2-y1, z2-z1). For example, if the WTRU determines more than one location, the WTRU may determine a reference location (e.g., based on a configuration) and / or a relative position of one or more (e.g., each) locations relative to the reference location. In an example, the WTRU may determine three locations (x1, y1, z1), (x2, y2, z2), and (x3, y3, z3) based on one or more measurements and / or estimated / inferred locations. In an example, the WTRU may be configured to use (x1, y1, z1) as a reference location because the location is determined (e.g., derived) based on one or more measurements (e.g., based only on one or more measurements). The first differential position and / or the second differential position may be determined as p21 = (x2-x1, y2-y1, z2-z1) and p31 = (x3-x1, y3-y1, z3-z1), respectively. Positions (x2, y2, z2) and (x3, y3, z3) may be estimated positions for which the WTRU may use differential positions relative to reference points and / or positions.

[0197] The WTRU may determine and / or derive a reference location based on one or more of the following criteria: one or more actual measurements; an indication from the network (e.g., the WTRU is indicated to use a reference location derived from an AI / ML model, the WTRU is indicated to use a reference location derived using a WTRU-based positioning method (such as DL-TDOA, DL-AoD)); a configured default positioning method; a first position estimate determined / derived by the WTRU; one or more measurements of a PRS sent from a reference TRP; and / or the WTRU is indicated to use location information derived at an indicated time (e.g., N slots / frames / subframes / seconds before the current slot, at time T, where T may be indicated by an absolute time, a slot / frame / subframe ID, etc.).

[0198] The WTRU may receive from a network (e.g., LMF) one or more configurations for a WTRU-based angle-based positioning method (e.g., DL-AoD with TRP locations) and / or one or more PRS configurations including a first set of TRPs and / or a reference TRP. The WTRU may receive from the network an indication to use a determined (e.g., derived) location as a reference location. The WTRU may receive a second set of TRPs and / or associated location information via a broadcast. The WTRU may determine a first set of one or more measurements (e.g., RSRP) of the PRS received from the first set of TRPs. The WTRU may determine the first location information based on the first set of measurements, for example, using the configured WTRU-based positioning method. The WTRU may transmit to the network a request for an AI / ML model associated with the first location. The WTRU may receive from the network assistance information (e.g., one or more parameters for the AI / ML model) and / or associated coverage areas. The WTRU may determine from the second set of TRPs one or more TRPs that fall within the coverage area. For one or more (e.g., all) TRPs within the coverage area, the WTRU may determine a second measurement set (e.g., one or more inferred RSRP measurements for each TRP obtained from the AI / ML model) based on the first RSRP measurement set. The WTRU may determine the second location information based on the first measurement set and / or the second measurement set, for example, by using a configured positioning method. The WTRU may report the first location information as a reference location and / or relative location information between the first location information and the second location information.

[0199] AI / ML-based predictions may be performed for a WTRU with one or more reduced capabilities, as described herein. The WTRU may determine an estimated / inferred measurement (e.g., RSTD) based on one or more actual measurements (e.g., RSRP). The WTRU may receive a configuration from the network to determine one or more estimated measurements. For example, if one or more conditions are met, the WTRU may transmit a request for one or more configurations to the network to enable a function to generate one or more estimated measurements. The input to the function for generating one or more estimated measurements may include one or more actual measurements made by the WTRU. The WTRU may determine its location based on one or more actual measurements and / or one or more estimated measurements (e.g., both). For example, if the WTRU is configured with WTRU-based positioning, the WTRU may report the determined location to the network; the report may indicate the use of one or more unobserved measurements. For example, if the WTRU is configured with WTRU-assisted positioning, the WTRU may report both actual measurements and estimated measurements to the network.

[0200] Fig.10 Example graphs 1000a, 1000b are shown for estimation of arrival time using narrowband PRS and wideband PRS. Fig.10 A comparison of one or more correlator outputs for narrowband and wideband orthogonal frequency division multiplexing (OFDM) is depicted to illustrate the enhanced resolution that may be included with narrowband measurements. Fig.10 As illustrated in graph 1000a of , using one or more measurements obtained from the PRS over a relatively small (e.g., reduced) bandwidth, for example due to coarse resolution in the time domain, may include determining an arrival time that becomes uncertain. An example of a relatively small bandwidth may be 2.5 MHz, 5 MHz, 20 MHz, etc. For example, another or relatively large bandwidth may be 100 MHz, 200 MHz, 1 GHz. Compared to one or more measurements obtained using a narrow bandwidth, for example, due to its fine time resolution, one or more measurements obtained from an increased bandwidth of the PRS may provide a more accurate estimate of the arrival time. Fig.10 Graph 1000b in FIG. 1 depicts an example of estimation of arrival time using a relatively large bandwidth.

[0201] Trainable AI / ML models. Fig.11 An example system 1100 for training an AI / ML model to generate inferences 1100 is depicted. The AI / ML model may use one or more measurements obtained from one or more (e.g., various) bandwidths as inputs to the AI / ML model. A target value for the AI / ML model may include one or more measurements obtained from one or more larger bandwidths. For example, one or more measurements obtained from one or more larger bandwidths may be used as a target value for the AI / ML model.

[0202] like Fig.11 As shown, one or more RSTD measurements (e.g., RSTD2 1102 and / or RSTD1 1104) may be presented as input to the AI / ML model 1106. One or more RSTD measurements (e.g., RSTD1 1104 and / or RSTD2 1102) may be reported by one or more WTRUs having different bandwidths (BW). For example, RSTD1 1104 may be associated with BW1, and / or RSTD2 1102 may be associated with BW2. One or more RSTD measurements may be associated with one or more different TRPs, wherein the association information is included in the measurement report. The network may train the AI / ML model 1106, wherein the target (output 215) may be an RSTD value determined (e.g., derived) from one or more WTRU positions obtained from GNSS, for example based on one or more measurements. For example, the RSTD value may be determined based on the trained AI / ML model 1106 (e.g., as described herein). Additionally or alternatively, one or more outputs 1108 may include one or more RSTD measurements obtained using a relatively wide bandwidth, which may be used as target values. For example, the target value may include an RSTD determined based on WTRU positioning, TRP location, and / or an RSTD based on (e.g., wideband) PRS. The network may calculate the difference between the target RSTD and the estimated RSTD, and / or may calculate one or more parameters for the AI / ML model 1106 (e.g., to train the one or more parameters and / or tune the one or more hyperparameters 217). The AI / ML model may be used in a specific implementation (e.g., after training). The trained AI / ML model may receive input data to determine one or more outputs; the one or more outputs may be used as one or more inferences.

[0203] One or more inputs to the AI / ML model 1106 during training may include one or more measurements (e.g., RSTD, RSRP) from one or more adjacent and / or neighboring frequency bands and / or adjacent bandwidth parts (BWPs).

[0204] Fig.12 An example system 1200 illustrating inference generation from a trained model (e.g., AI / ML model 1210) is shown. Fig.12 As shown, the WTRU may obtain an estimated RSTD (e.g., RSTD1 of input 1202) based on measurements obtained from a reduced bandwidth (e.g., 1204). For example, a trained A / ML model may predict one or more outputs (e.g., inferred output 1250) using trained parameters and / or tuned hyperparameters, as described herein.

[0205] The WTRU may receive one or more configurations for one or more inputs to the AI / ML model. The one or more configurations may be included as one or more inputs 207 to the AI / ML model 1210, as described herein. For example, the WTRU may determine one or more estimation measurements based on one or more of the following configurations and / or measurements (e.g., input 1202): RSTD measurement; bandwidth; center frequency; location of the TRP from which the PRS is transmitted; frequency layer ID; PRS ID; PRS resource ID; and / or reference information for calculating RSTD and / or differential RSRP (e.g., reference PRS resource ID, reference PRS ID, reference TRP ID, etc.).

[0206] One or more conditions may trigger AI / ML-based measurement estimates. The WTRU may transmit a request for AI / ML to the network to generate one or more estimated measurements, for example, based on one or more of the following conditions: the WTRU has reduced capability (e.g., reduced bandwidth, reduced number of antennas, etc.) compared to non-reduced capability; the maximum RSRP of the PRS is below a threshold; the average PRS of the PRS is below a threshold; the standard deviation and / or variance of the PRS is below a threshold; and / or one or more TRPs sent from the PRS are within LOS (line of sight) and / or a soft LOS indicator for the TRP (e.g., a value indicating the likelihood of LOS between the TRP and the WTRU) is above a threshold.

[0207] The WTRU may receive one or more PRS configurations from the network and / or may perform one or more measurements on the PRS. If the average RSRP of the measured PRS is below a threshold, the WTRU may transmit a request to the network for a configuration for the AI / ML model. Based on the AI / ML model, the WTRU may determine an estimated RSTD. The WTRU may use the estimated RSTD to determine its positioning.

[0208] The WTRU may receive one or more PRS configurations (e.g., BW, center frequency, TRP position). For example, the WTRU may receive one or more PRS configurations from the network. The WTRU may perform one or more measurements on the PRS. For example, if the average RSRP of the PRS is below a threshold, the WTRU may request the AI / ML model. For example, the WTRU may transmit a request for one or more configurations for the AI / ML model to the network. The WTRU may receive the AI / ML model from the network. For example, the WTRU may determine an estimated RSTD from the AI / ML model based on one or more measured RSTDs and / or one or more PRS configurations. The WTRU may determine its positioning based on the (e.g., estimated) RSTD.

[0209] AI / ML based anomaly detection may be performed. Anomaly detection associated with WTRU behavior may be provided herein. For example, one or more methods may be provided herein for a WTRU to determine / detect anomalies associated with one or more measurements and / or one or more (e.g., various) anomaly detection triggers.

[0210] The WTRU may determine an estimated measurement (e.g., RSTD) based on a first measurement (e.g., RSRP). The WTRU may determine a difference (e.g., an absolute value of the difference between the two values) between the estimated measurement and a second measurement (e.g., RSTD) or an actual measurement. For example, if the difference (e.g., the difference between the estimated measurement and the second measurement) is above a preconfigured threshold, the WTRU may determine to transmit a request to the network to change the PRS configuration.

[0211] The WTRU may determine one or more anomalies. For example, the WTRU may determine one or more anomalies using an AI / ML model (e.g., specifically) configured for anomaly detection. One or more (e.g., various) details regarding model inputs, outputs, and / or one or more model training aspects and / or WTRU reporting aspects may be provided herein.

[0212] One or more (eg, various) triggers, detection criteria, and / or WTRU behaviors may be included (eg, common) across one or more (eg, multiple) examples (eg, implementations) provided herein.

[0213] During communication, one or more unexpected errors may occur in one or more measurements. The one or more errors may be based on one or more different aspects (e.g., error sources). For example, one or more changes in the environment may cause one or more changes to one or more measurements. One or more changes to the measurements may (e.g., subsequently) change one or more (e.g., various) downstream quantities derived and / or determined based on one or more measurements. For example, the sudden presence of an obstacle between transmitters (e.g., a moving vehicle and / or pedestrian, one or more fallen objects) may result in reduced RSRP and / or one or more (e.g., multiple) arrival time measurements due to multipath. The transmitter and / or receiver may change its transmission and / or reception hardware during communication, which may introduce unexpected timing errors in one or more timing-based measurements. For example, if an anomaly (e.g., an unexpected error) is detected in one or more measurements, the WTRU may detect the anomaly and / or notify the network of the anomaly.

[0214] Anomalies may be detected based on differences between one or more estimated measurements and actual measurements.Generation of estimates and / or inferences of one or more measurements may be performed as provided herein.

[0215] The WTRU may determine a difference between one or more actual measurements and the estimated measurements, for example, based on one or more estimated measurements obtained by the WTRU. For example, after the WTRU obtains the one or more estimated measurements, the WTRU may determine a difference between the one or more actual measurements and the estimated measurements. For example, if the difference is above a threshold, the WTRU may determine that there is an anomaly (e.g., and / or a source of error) in the one or more measurements. The difference may include an absolute value of the difference between the one or more (e.g., two) values ​​and / or a square value of the absolute difference.

[0216] The WTRU may use thresholds to determine one or more anomalies in one or more measurements. The thresholds used by the WTRU to determine whether an anomaly exists in one or more measurements may be based on (e.g., dependent on) the type of measurement. For example, the WTRU may receive one or more different thresholds for timing-based and / or RSRP-based measurements and / or may use one or more separate thresholds based on (e.g., dependent on) whether one or more timing-based and / or RSRP-based measurements are used to calculate the error. For example, the WTRU may use a (e.g., first) threshold for one or more timing-based measurements. For example, the WTRU may use a (e.g., second) threshold for RSRP-based measurements.

[0217] Since one or more actual measurements and / or estimated measurements may include noise, the WTRU may determine to calculate an average of the estimated measurements and / or actual measurements, for example, if the WTRU receives a configuration from the network. The one or more actual measurements and / or estimated measurements may be averaged for the error between the estimated measurement and the actual measurement. For example, the WTRU may be configured by the network with a number of measurement occasions N over which the WTRU may be expected to calculate the average. For example, the error δ may be an average of one or more measurements collected over N occasions, where the measurement and / or estimated measurement at the i-th occasion is denoted as y, respectively. i and

[0218]

[0219] Additionally or alternatively, the WTRU may calculate the average of the absolute errors as follows:

[0220]

[0221] Additionally or alternatively, the WTRU may calculate the RMS error as follows:

[0222]

[0223] Anomaly detection may be performed based on an AI / ML model specifically configured for anomaly detection. In an example, the WTRU may be configured with an AI / ML model for anomaly detection purposes, which AI / ML model may be referred to as an anomaly detection AI / ML model. The WTRU may obtain the AI / ML model and / or one or more configuration parameters thereof from the network. Such AI / ML models may be pre-trained. For example, one or more AI / ML models may be pre-trained specifically for the geographic area in which the WTRU is located. The AI / ML model for anomaly detection may be implemented specifically based on the WTRU. In an example, the WTRU may be configured to train and / or fine-tune the AI / ML model. For example, the WTRU may be configured to train and / or fine-tune the AI / ML model based on one or more WTRU measurements and / or auxiliary data from the network. For example, the WTRU may receive auxiliary data including one or more training labels for training anomaly detection models. For example, based on one or more WTRU reports, the network may determine whether an anomaly exists. The WTRU may receive an indication of an anomaly from the network, and / or such an indication may be associated with a previous WTRU report. The WTRU may (e.g., subsequently) use the indication as a training label and / or use the previous report as an input to train the AI / ML model. The WTRU may receive a training data set including a plurality of input data and / or one or more corresponding output / training label pairs. The WTRU may request training data from the network. For example, the WTRU may request training data from the network, the training data including information about the input to the AI / ML model, the size of the training data, and / or the output of the AI / ML model, etc. The WTRU may be configured to report the training status associated with the anomaly detection AI / ML model. For example, the WTRU may be implicitly and / or explicitly configured to start anomaly detection. For example, the WTRU may be configured to start anomaly detection based on the training status of the AI / ML model. For example, the WTRU may report that the AI / ML model is successfully trained and / or (e.g., subsequently) receive an activation command from the network to start anomaly monitoring. Additionally or alternatively, the WTRU may be configured by the network with training completion criteria (e.g., when the AI / ML model successfully detects an anomaly given a preconfigured training data set). The WTRU may be configured to autonomously activate anomaly detection when training criteria are met.

[0224] The AI / ML model of the model for anomaly detection can be a classification model (e.g., a task that can perform binary classification). For example, given a set of one or more inputs described herein, the inference output of the AI / ML model can indicate whether an anomaly is detected.

[0225] In an example, an AI / ML model for a model for anomaly detection may include a regression model, wherein an inferred output of the AI / ML model may indicate a probability of detecting an anomaly given a set of one or more inputs described herein.

[0226] In an example, the AI / ML model may perform a prediction task where, given a set of one or more inputs, at time t as described herein, the inference output of the AI / ML model may indicate a probability of detecting an anomaly at a future time instance (e.g., t+n). For example, t may be a current time slot (e.g., or frame, subframe) index, and / or n may be the number of time slots (e.g., or frames, subframes) where an anomaly may occur.

[0227] The AI / ML model for anomaly detection may include one or more observed measurements as input. The terms "observed measurements" and "actual measurements" are used interchangeably herein. Such observed measurements may include one or more of the following: one or more (e.g., a certain number of) TRPs; one or more (e.g., RSRPs of each) TRP; one or more SSB / CSI-RS measurements; channel impulse response (CIR); channel frequency response (CFR); and / or one or more Doppler measurements, etc. Additionally or alternatively, the AI / ML model input may include one or more parameters based on a configuration and / or value (e.g., one or more measurements, such as time of flight, ToA RSTD, RSRP) determined from the measurement, including but not limited to: one or more TRP identifiers, one or more (e.g., RSRPs of each) TRP, location of the TRP, reference TRP ID, PRS ID, PRS resource ID, reference PRS ID, one or more RSTD values, differential RSTD, frequency layer ID, bandwidth configuration, etc. In an example, the AI / ML model may take one or more historical measurements as input. For example, the one or more historical measurements may include one or more of RSRP, CIR, and / or CFR, etc., from a previous time instance. For example, in a recurrent AI / ML model architecture, the AI / ML model output from time tn may be provided as an input to the AI / ML at time t. The WTRU may be configured to pre-process one or more inputs to the AI / ML model, including but not limited to one or more (e.g., various) transformations applied to the inputs (e.g., scaling, sampling, filtering outliers, etc.).

[0228] WTRU reporting may be performed as described herein. For example, if the AI / ML model determines that an anomaly is detected, the WTRU may be configured to send an indication to the network. In an example, the anomaly detection criteria may be based on the instantaneous output of the AI / ML model. For example, if the AI / ML model determines that the probability of an anomaly is above a preconfigured threshold, the WTRU may be configured to send a report of the anomaly. The anomaly detection criteria may be based on post-processing the output of the AI / ML model within a preconfigured time period. For example, if one or more (e.g., a certain number) of anomalies detected within a certain time period are above a threshold, the post-processing may include determining one or more statistical values ​​of the AI / ML model output.

[0229] The AI / ML model may generate one or more additional outputs characterizing the source of the anomaly. For example, in addition to indicating that an anomaly was detected, the AI / ML model may also indicate the source of the anomaly. One or more (e.g., each) sources of the anomaly may be abstracted as a specific cause value. If the AI / ML model determines that an anomaly is detected, and / or if the probability of an anomaly is above a preconfigured threshold, the WTRU may be configured to report the source of the error (e.g., and / or in other words a specific cause value).

[0230] Fig.13 An example system 1300 for anomaly detection is illustrated. Fig.13 As shown, the WTRU 1302 may apply an AI / ML model 1306 to detect one or more anomalies. The WTRU 1302 may receive a trained AI / ML 1306 and / or one or more parameters thereof from the network and / or apply an AI / ML model 1306 based on a WTRU specific implementation. For example, based on one or more inputs 1304 (e.g., one or more actual RSRP measurements, one or more RSTD measurements and / or TRP location information, etc.), the AI / ML model 1306 may determine (e.g., generate) a probability of detecting an anomaly as an output 1308. For example, the anomaly detection model 1306 may determine one or more outputs 1308 (e.g., anomaly probabilities) using the AI / ML model and one or more inputs 1304 (e.g., RSRP1, RSRP2, RSRP3, RSTD12, RSTD13, TRP location 1, TRP location 2, TRP location 3, etc.). The WTRU may be configured to send a report to the network, for example, based on the output 1308 of the post-processing AI / ML model 1306.

[0231] One or more examples described herein may be applied to the first example process and / or the second example process (eg, both), which are used for anomaly detection.

[0232] The WTRU may be configured with a time window during which the WTRU monitors errors between one or more actual measurements and one or more estimated measurements. Examples of details of the configuration of the time window may include a start time and / or end time of the window and / or a duration of the window in terms of number of symbols, time slots, frames, and / or absolute time (e.g., seconds). For example, once the time window expires, the WTRU may stop anomaly detection. During the window, the WTRU may (e.g., continue to) monitor errors even after the WTRU detects an anomaly and / or reports the anomaly to the network.

[0233] The WTRU may be configured with one or more (e.g., a certain number of) iterations that the WTRU is expected to perform anomaly detection. For example, the WTRU may be configured by the network with an integer M, and / or the WTRU may be expected to repeat the anomaly detection process M iterations. The WTRU may include in the measurement report the number of occasions when the error was greater than a threshold. Additionally or alternatively, for example, upon discovery of an error, the WTRU may terminate the process (e.g., iteration). Upon discovery of an error, the WTRU may perform anomaly reporting (e.g., transmit a report to the network indicating discovery of an anomaly), and / or transmit a request to the network to reconfigure the PRS.

[0234] Anomaly detection may be triggered. For example, one or more conditions may trigger anomaly detection. The WTRU may initiate anomaly detection based on one or more of the following: an indication from the network to initiate anomaly detection; availability of reference / actual / expected measurements (e.g., when the WTRU receives one or more expected RSTD measurements from the network); training status of the anomaly detection AI / ML model (e.g., when the anomaly detection AI / ML model is successfully trained, the WTRU may start anomaly detection); variance and / or standard deviation greater than a preconfigured threshold; measured RSRP of the PRS resource less than a preconfigured threshold; change in the timing error group (TEG) in the PRS since the last time the WTRU received configuration of the TEG; an NLOS indicator (e.g., a soft indicator indicating whether the channel is NLOS) greater than a preconfigured threshold; and / or a periodic trigger or a semi-persistent trigger.

[0235] The WTRU may initiate anomaly detection based on the NLOS indicator. For example, 0.5 may indicate that the channel may or may not be NLOS, while values ​​0 and 1 may indicate that the channel is LOS or NLOS, respectively.

[0236] The WTRU may initiate anomaly detection based on a periodic trigger or a semi-persistent trigger. For example, the WTRU may be configured with one or more periodic opportunities and / or semi-persistent opportunities, where the semi-persistent opportunities occur periodically during a time window or until the WTRU receives a deactivation command from the network. One or more semi-persistent opportunities may be initiated with an activation command from the network. The WTRU may perform anomaly detection by, for example, calculating an error at one or more (e.g., each) periodic opportunity and / or semi-persistent opportunity and / or comparing the error to a threshold.

[0237] The WTRU may initiate an anomaly detection process, for example, based on one or more of the conditions herein (e.g., one or more of the conditions herein are met). The WTRU may initiate anomaly detection by starting a time window based on one or more preconfigured parameters related to the time window. For example, if the WTRU does not have one or more configurations for the time window, the WTRU may transmit a request to the network to transmit one or more configurations to the WTRU. The WTRU may initiate a time window and / or (e.g., in other words) anomaly detection at a preconfigured timing offset relative to a timing. The timing may be a timing at which the WTRU determines that the conditions for initiating anomaly detection are met. For example, if the WTRU is not configured with an AI / ML model for estimating one or more measurements, the WTRU may transmit a request to the network to configure the AI / ML model.

[0238] The WTRU may determine to perform one or more actions based on determining that one or more errors are above a preconfigured threshold. For example, after the WTRU determines that one or more errors are above a preconfigured threshold, the WTRU may determine to perform one or more of the following actions: reconfigure one or more PRS parameters; notify the network of detected anomalies and / or measurement reports.

[0239] The WTRU may perform reconfiguration of one or more PRS parameters, for example, based on whether the WTRU determines that the error is above a preconfigured threshold. For example, after the WTRU determines that the error is above a preconfigured threshold, the WTRU may perform reconfiguration of one or more PRS parameters. The WTRU may transmit a request to reconfigure one or more PRS parameters. The WTRU may determine to reconfigure one or more different PRS parameters based on (e.g., depending on) the error and / or associated measurements. For example, if the error associated with one or more timing measurements (e.g., RSTD) of the measured PRS resource is greater than a threshold, the WTRU may determine to transmit a request to the network to change the TEG associated with the PRS resource so that potential sources of error can be avoided. In an example, the WTRU may be preconfigured with a list of one or more TEGs for one or more PRS resources.

[0240] For example, if the error is associated with one or more power (e.g., RSRP) measurements and / or one or more timing measurements are greater than a threshold, the WTRU may determine to transmit a request to the network to change the transmission source (e.g., TRP) by specifying the associated PRS ID, TRP ID, and / or PRS resource ID. In an example, the WTRU may receive one or more pre-configurations from the network that include a list of TRP IDs, PRS IDs, and / or PRS resource IDs based on which the WTRU determines to make the request.

[0241] The WTRU may notify the network of the detection of one or more anomalies (e.g., transmit a report to the network indicating the detection of anomalies), for example, based on whether the WTRU determines that the error is above a preconfigured threshold. For example, after the WTRU determines that the error is above a preconfigured threshold, the WTRU may notify the network of the detection of one or more anomalies. The WTRU may transmit an indication of the detection of an anomaly to the network. The WTRU may transmit a report indicating the error source that caused the anomaly. For example, the WTRU may indicate to the network the presence of a timing-based error source (e.g., timing offset, calibration error, clock drift, and / or inter-TRP synchronization error) in one or more measurements based on a difference calculated using one or more timing-based measurements. For example, the WTRU may indicate the presence of a multipath and / or NLOS-related error source in one or more measurements based on a difference calculated using one or more power-based measurements. For example, the WTRU may indicate the presence of one or more transmitter-side error sources (e.g., TRP position, antenna offset, etc.).

[0242] The WTRU may perform measurement reporting based on determining whether one or more errors are above a preconfigured threshold. For example, after the WTRU determines that the error is above a preconfigured threshold, the WTRU may perform measurement reporting. For example, if the error is greater than the preconfigured threshold, the WTRU may report both the actual measurement and the associated error to the network. The WTRU may include a timestamp associated with the one or more actual measurements.

[0243] Fig.14 An example process 1400 for using AI for anomaly detection is illustrated. Fig.14As shown, the WTRU 1402 may receive a trained AI / ML 1404 and / or one or more parameters thereof from the network. The WTRU 1402 may obtain one or more estimated RSTD measurements from the AI / ML model 1404, for example, based on one or more actual RSTD measurements and / or location information of one or more TRp. The WTRU 1402 may (e.g., further) calculate an average of one or more actual and estimated RSTD measurements over N occasions, and / or an absolute difference between one or more (e.g., two) averaged actual and estimated measurements (e.g., at 1406). For example, averaging one or more actual and estimated RSTD measurements over N occasions, and / or an absolute difference between one or more (e.g., two) averaged actual and estimated measurements may reduce one or more errors in the AI / ML estimation and / or measurement (e.g., at 1406). At 1408, for example, if the error is less than or equal to a preconfigured threshold, the WTRU 1402 may report the one or more actual measurements to the network. At 1410, the WTRU may report the actual measurement and the associated error to the network, for example, if the error is greater than a preconfigured threshold.

[0244] The WTRU may receive one or more configurations for a WTRU-based angle-based positioning method (e.g., DL-AoD with TRP location), N (e.g., number of measurement opportunities), a threshold, and / or one or more PRS configurations. The WTRU may receive one or more parameters for an AI / ML model. The WTRU may perform one or more measurements on the PRS and / or may obtain one or more RSRPs. The WTRU may obtain one or more RSTDs (e.g., RSTDs estimated from the AI / ML model based on measured RSRP measurements and TRP location information). The WTRU may, for example, calculate an average based on N opportunities of RSTD measurements and / or one or more inferred RSTDs. The WTRU may calculate a difference between one or more averaged RSTD measurements and one or more estimated RSTDs. For example, if the difference is greater than a threshold, the WTRU may determine to transmit a request to the network to switch to the indicated TxTEG. For example, if the difference is less than a threshold, the WTRU may determine to transmit the RSTD measurement to the network.

[0245] As described herein, network-assisted anomaly detection can be performed. Fig.15 An example system 1500 for network-assisted anomaly detection is illustrated. Fig.15As shown, the WTRU 1502 may receive one or more estimated measurements from the network based on one or more actual measurements reported by the WTRU 1502. For example, the WTRU 1502 may report one or more RSRP measurements to the network, and / or the network may determine one or more estimated RSTDs. The network may use an AI / ML model to obtain one or more estimated RSTDs based on one or more actual measurements reported by the WTRU 1502. The AI / ML model may be trained by the network and / or by the WTRU 1502. The network may (e.g., subsequently) indicate to the WTRU 1502 that the WTRU 1502 will receive an estimated RSTD and / or may request that anomaly detection be performed in one or more RSTD measurements. The WTRU 1502 may receive one or more estimated measurements from the network, and / or may calculate the difference between the estimated RSTD and the measured RSTD, for example, to determine whether there is an anomaly in one or more measurements.

[0246] The WTRU 1502 may use the information provided in the network assistance to train an anomaly detection AI / ML model at the WTRU, for example, to support one or more of the processes described herein.

[0247] The WTRU 1502 may include a quality indication in the measurement report. The WTRU 1502 may perform one or more measurements on one or more configured TRPs. The WTRU may determine that one or more measurements are performed on one or more TRPs that are within the LOS relative to the WTRU 1502. The WTRU 1502 may determine that one or more TRPs are in the LOS relationship with the WTRU 1502 based on one or more measurements (e.g., RSTD, RSRP) and / or an indication from the network.

[0248] The WTRU 1502 may determine that one or more RSRP measurements obtained by the WTRU 1502 from one or more PRSs sent from one or more TRPs are insufficient to determine its position. Additionally or alternatively, the WTRU 1502 may determine that one or more (e.g., a certain number of) measurements and / or one or more (e.g., a certain number of) observed TRPs are below a configured threshold (e.g., a minimum number) of measurements and / or TRPs. The WTRU 1502 may use the AI / ML model 1504 to obtain one or more estimated RSRP measurements for one or more unobserved TRPs.

[0249] The WTRU 1502 may determine to use the configured AI / ML model 1504 based on one or more of the following (e.g., if one or more of the following conditions are met): one or more (e.g., a certain number) of NLOS TRPs are above a configured threshold (e.g., where the threshold may be a function of the number of TRPs); the average, minimum, or maximum RSRP measurement of the TRPs is below a configured threshold; and / or the average, minimum, or maximum number of paths in the measurement is above a threshold.

[0250] For example, if the WTRU 1502 is not configured with the AI / ML model 1504 and / or based on one or more of the conditions herein (e.g., the WTRU determines that one or more of the conditions herein are satisfied), the WTRU 1502 may determine to transmit a request for assistance information (e.g., the AI / ML model 1504). The WTRU 1502 may determine to include coarse location information in the request, where the location may be determined based on one or more measurements.

[0251] One of the parameters of the AI / ML model 1504 may be a coverage range (e.g., the AI / ML model 1504 may estimate one or more measurements within the coverage range). The coverage range may be represented by a radius (e.g., in meters), an area (e.g., in square meters), a predefined area, and / or a predefined region and / or a cell (e.g., defined by a cell ID).

[0252] The AI / ML model 1504 may be associated with a region. The WTRU and / or the network (e.g., LMF, gNB) may determine the AI / ML model 1504 to use and / or transmit, for example, based on the coarse location information about the WTRU 1502. For example, the WTRU 1502 and / or the NW may determine the AI / ML model 1504 whose center of coverage is within a threshold based on the coarse location information of the WTRU 1502. In an example, one or more AI / ML models 1504 may not be associated with a region and / or location. In this case, for example, the AI / ML model 1504 may be based on the coverage area.

[0253] Fig.16 An example system 1600 is illustrated that includes a WTRU 1602 and a network entity (e.g., LMF 1605) from which a request to receive assistance information may be issued. Fig.16As shown, the WTRU 1602 may perform one or more measurements of the TRP and / or transmit a request 1604 to the network (e.g., LMF) for assistance information 1606 (e.g., an AI / ML model and / or one or more parameters thereof). In response to the request 1604, the LMF 1605 may send the assistance information, which includes the AI / ML model and / or one or more parameters thereof. The assistance information may be based on the measurements performed and / or included in the request 1604. The WTRU may determine the assistance information in the request. For example, the WTRU may determine which assistance information to request from the network. Based on the request, for example, the network may determine the content of the assistance information to be transmitted (e.g., provided) to the WTRU (e.g., an AI / ML model index and / or ID). One or more AI / ML models may be trained by the network and / or by the WTRU. In an example, the network may have one or more AI / ML models and / or may provide one or more details of model parameters (e.g., weights, model indexes) to the WTRU.

[0254] The AI / ML model may be associated with a region and / or a cell. The WTRU 1602 may determine that the AI / ML model may estimate one or more measurements (e.g., RSRP) of one or more TRPs within the region. The WTRU 1602 may determine one or more estimated measurements of a target TRP, for example, based on one or more actual measurements of one or more TRPs, the locations of these TRPs, and / or the location of the target TRP.

[0255] Fig.17 An example system 1700 is illustrated in which a WTRU 1702 may estimate one or more RSRP measurements for an unobserved TRP (e.g., the unobserved TRP may be one that is not part of one or more configurations provided to the WTRU). For example, the WTRU 1702 may estimate one or more RSRP measurements for an unobserved TRP (e.g., the unobserved TRP may be one that is not part of one or more configurations provided to the WTRU). Fig.17 The unobserved TRP (e.g., Fig.17 One or more RSRP measurements of TRP4 1710 and TRP5 1712) shown.

[0256] The WTRU 1702 may be configured with more than one model, where one or more (e.g., each) model may be associated with a model ID (e.g., a model index). The one or more (e.g., each) model may correspond to different sizes (e.g., number of neurons) and / or applicable locations of the AI / ML model, for example, where one or more (e.g., each) model may be associated with a region and / or a cell. For example, when the WTRU requests a model, the WTRU 1702 may receive the model ID from the network.

[0257] The WTRU 1702 may be configured with an expansion factor associated with the AI / ML model. The WTRU 1702 may determine to expand the area associated with the AI / ML model by the expansion factor, for example, based on one or more of the conditions herein (e.g., if the WTRU 1702 determines that at least one of the following conditions is satisfied): one or more (e.g., a certain number) of actual measurements and / or estimated measurements are below a threshold; and / or an uncertainty associated with location information determined based on the actual and / or estimated measurements is below a threshold. For example, the WTRU may determine to expand the area associated with the AI / ML model by the expansion factor, r new =r×e x , where r new can be the new radius of the region, r can be the radius of the current region, and / or e x Can be an expansion factor.

[0258] The WTRU 1702 may determine one or more measurements of one or more TRPs within an estimated extended area (e.g., a second area). The WTRU 1702 may determine one or more TRP measurements of TRPs within the second area but outside the first area 1750. The WTRU may determine one or more measurements of one or more TRPs within the second area, for example, based on one or more actual measurements and / or estimated measurements within the first area 1750.

[0259] When the WTRU 1702 reports fine location information (e.g., determined based on one or more actual and / or estimated measurements) and / or measurements to the network, the WTRU 1702 may indicate one or more of the following in the report: a quality indication associated with the estimated measurement (e.g., an area ID, and / or the number of iterations that the area has been extended, one or more statistical characteristics such as a standard deviation, whether one or more estimated measurements are associated with the first area 1750 and / or the second area, etc.); and / or a quality indication associated with the estimated location information (e.g., the number of iterations that the area has been extended, whether one or more estimated measurements from the first area 1750 and / or the second area have been used, etc.).

[0260] Fig.18 An example system 1800 is illustrated in which a WTRU 1802 may determine one or more RSRP measurements for one or more unobserved TRPs. For example, the WTRU 1802 may determine one or more RSRP measurements for one or more unobserved TRPs (e.g., TRP4 1804 and / or TRP5 1806) within an area (e.g., a second area 1850, which may be an area extending from the first area 1825). Fig.18As shown, the WTRU 1802 may determine one or more estimated measurements of a TRP (e.g., TRP6 1810) within the second area 1850 but outside the first area 1825. The WTRU 1802 may report the one or more measurements to the network (e.g., LMF 1808), where the WTRU 1802 may indicate quality information for the measurements. The quality indication in the measurements may be useful for the network to determine the quality associated with the one or more estimated measurements and / or location information (e.g., because the quality of the one or more estimated measurements may degrade as the area expands).

[0261] For example, the WTRU may receive one or more configurations for a first TRP set, wherein the one or more configurations may include a PRS from the network (e.g., a PRS resource ID, a periodicity), one or more TRP locations, a value N, and / or a threshold value (e.g., a function of the total number of TRPs). The WTRU may perform a first set of measurements (e.g., RSRP) on the PRS from the first TRP set, for example, based on the configurations received from the network. The WTRU may determine its coarse position, for example, based on one or more measurements made on the first TRP set. For example, if the WTRU determines that the number of NLOS TRPs is greater than or equal to a threshold, the WTRU may request assistance information (e.g., an AI / ML model); the request may include the determined coarse WTRU position. The WTRU may obtain assistance information having a first area and / or an area expansion factor. The WTRU may determine a second TRP set, for example, based on the first area associated with the AI / ML model. The WTRU may estimate the RSRP of the target TRPs in the first set of measurements and / or the first TRP set and / or the second TRP set, for example, based on one or more locations of the target TRPs. For example, if the total number of measured and / or estimated TRPs (e.g., from the first TRP set and / or the target TRP) is less than N, the WTRU may determine to expand the coverage area by an expansion factor (e.g., to a second area). The WTRU may repeat this process, for example, until the WTRU obtains one or more measurements (e.g., RSRPs) from N TRPs. The WTRU may determine and / or report a fine WTRU location based on the measurements. The WTRU may (e.g., also) report the quality of one or more RSRP measurements and / or one or more estimated measurements (e.g., whether from the first area and / or the second area).

[0262] 19 depicts a process flow diagram of an example procedure for determining one or more measurements and / or one or more position measurements.

[0263] At 1902, the WTRU may receive configuration information from a network (e.g., LMF, gNB), as described herein. The configuration information may include PRS configuration information for each of a plurality of TRPs. For example, the configuration information may indicate one or more criteria for requesting PRS measurement assistance information. For example, the configuration may indicate a minimum number of TRPs for which one or more PRS measurements are to be reported. For example, the configuration information may include one or more parameters for an AI / ML model. The configuration information may be included in a PRS configuration. One or more parameters for an AI / ML model may be included in a PRS configuration or a dedicated AI / ML-related configuration, and / or the network may indicate to the WTRU how to configure the AI / ML-related parameters (e.g., via a PRS configuration and / or AI / ML-dedicated signaling or configuration).

[0264] At 1904, the WTRU may determine that one or more criteria for requesting PRS measurement assistance information are met, as described herein. For example, the WTRU determines that one or more criteria for requesting PRS measurement assistance are met based on one or more measurements performed on one or more TRPs in a plurality of TRPs.

[0265] At 1906, the WTRU may transmit (e.g., to the network 1904) a request for PRS measurement assistance information, as described herein. The WTRU may request the PRS measurement assistance information based on, for example, a determination that one or more of the plurality of TRPs include a non-line-of-sight TRP. The request may indicate a location of the WTRU. For example, the request may indicate a location of the WTRU determined based on one or more measurements performed on one or more of the plurality of TRPs.

[0266] At 1908, the WTRU may receive PRS measurement assistance information from the network (e.g., LMF, gNB), as described herein. For example, the WTRU may receive one or more parameters (e.g., one or more weights, PRS configuration for training) for one or more AI / ML models. Additionally or alternatively, the WTRU may receive one or more parameters (e.g., weights, PRS configuration for training) for one or more AI / ML models from the network via receiving configuration information (e.g., via signaling, indication, and / or configuration information associated with the AI / ML model configuration).

[0267] At 1910, the WTRU may determine (e.g., estimate) one or more measurements of at least one TRP, as described herein. For example, the WTRU may estimate the one or more measurements of at least one TRP based on PRS measurement assistance information and / or at least one measurement performed using PRS configuration information for at least one TRP of the plurality of TRPs. For example, the WTRU may estimate the one or more measurements of at least one TRP based on one or more AI / ML models. The WTRU may estimate the one or more measurements of the first type of measurement based on one or more actual measurements of the second type of measurement and / or PRS measurement assistance information. For example, the WTRU may determine the RSRP based on one or more RSRP measurements and / or PRS measurement assistance information. The WTRU may determine one or more estimated measurements with relatively lower estimated quality for at least one additional TRP, such that the total number of TRPs associated with actual PRS measurements, with estimated measurements with relatively higher estimated quality, and / or with estimated measurements with relatively lower estimated quality is at least the minimum number of TRPs for which measurements are to be reported. Determining one or more estimated measurements having relatively lower estimation quality for at least one additional TRP may be responsive to determining that a total number of TRPs associated with one or more actual PS measurements and / or associated with one or more estimated measurements having relatively higher estimation quality is less than a minimum number of TRPs for which PRS measurements are to be reported.

[0268] At 1912, the WTRU may transmit a positioning measurement report, as described herein. The positioning measurement report may include a set of PRS measurements performed on a first subset of TRPs in a plurality of TRPs and / or an estimated set of measurements determined for a second subset of TRPs in a plurality of TRPs. The first subset of TRPs and / or the second subset of TRPs may include a total number of TRPs. For example, the total number of TRPs included in the first subset of TRPs and / or the second subset of TRPs may be at least the minimum number of TRPs for which PRS measurements are to be reported. In an example, the WTRU may receive an indication of a time window. The WTRU may receive a configuration related to a time window in a dedicated configuration and / or a PRS configuration. The WTRU may receive an indication from the network that the WTRU may receive a configuration of parameters related to a window (e.g., between a PRS configuration and a dedicated window configuration). The WTRU may transmit a first (e.g., positioning) measurement report and / or a second (e.g., positioning) measurement report, for example, based on a time window. The WTRU may include one or more measurements (eg, RSTD, RSRP, time of flight, ToA, Rx-Tx time difference) in the first measurement report and / or the second measurement report.

[0269] At 1914, as described herein, the WTRU may determine one or more anomalies associated with a set of PRS measurements performed on a first subset of TRPs among a plurality of TRPs and / or a set of estimated measurements determined for a second subset of TRPs among a plurality of TRPs.

[0270] At 1916, the WTRU may transmit an indication to the network (e.g., as described herein) indicating one or more anomalies associated with a set of PRS measurements performed on a first subset of TRPs among a plurality of TRPs and / or a set of estimated measurements determined for a second subset of TRPs among a plurality of TRPs.

[0271] At 1918, the WTRU may transmit a request to update PRS measurement assistance information (e.g., as described herein) to estimate one or more measurements of at least one TRP.

[0272] The processes and approaches described herein may be applied in any combination, may be applied to other wireless technologies, and may be used for other services.

[0273] The WTRU may refer to an identity of a physical device, or to an identity of a user, such as a subscription-related identity, for example, an MSISDN, a SIP URI, etc. The WTRU may refer to an application-based identity, such as a user name that may be used for each application.

[0274] The processes described above may be implemented in a computer program, software, and / or firmware incorporated in a computer-readable medium for execution by a computer and / or processor. Examples of computer-readable media include, but are not limited to, electronic signals (sent via wired and / or wireless connections) and / or computer-readable storage media. Examples of computer-readable storage media include, but are not limited to, read-only memory (ROM), random access memory (RAM), registers, cache memory, semiconductor memory devices, magnetic media (such as, but not limited to, built-in hard disks and removable disks), magneto-optical media, and / or optical media (such as CD-ROM disks and / or digital versatile disks (DVDs)). A processor associated with the software may be used to implement a radio frequency transceiver for a WTRU, UE, terminal, base station, RNC, and / or any host computer.

Claims

1. A wireless transmit / receive unit (WTRU), the wireless transmit / receive unit (WTRU) comprising: A processor, the processor being configured to: receiving configuration information, wherein the configuration information indicates positioning reference signal (PRS) configuration information for each of a plurality of transmit / receive points (TRPs), wherein the configuration information indicates one or more criteria for requesting PRS measurement assistance information, and wherein the configuration information indicates a minimum number of TRPs for which one or more PRS measurements are to be reported; determining, based on one or more measurements performed on one or more TRPs of the plurality of TRPs, that at least one of the one or more criteria for requesting the PRS measurement assistance information is satisfied; transmitting a request for the PRS measurement assistance information, wherein the request indicates a location of the WTRU determined based on the one or more measurements performed on one or more TRPs of the plurality of TRPs; Receiving the PRS measurement assistance information; estimating one or more measurements of at least one TRP based on the PRS measurement assistance information and at least one measurement performed using the PRS configuration information for at least one TRP of the plurality of TRPs; as well as Transmitting a positioning measurement report, wherein the positioning measurement report includes a PRS measurement set performed on a first TRP subset among the multiple TRPs and an estimated measurement set determined for a second TRP subset among the multiple TRPs, wherein the total number of TRPs included in the first TRP subset and the second TRP subset is at least the minimum number of TRPs for which PRS measurements are to be reported.

2. The WTRU of claim 1 , wherein the processor is further configured to determine an estimated measurement of the first type of measurement based on one or more actual measurements of the second type of measurement and the PRS measurement assistance information.

3. The WTRU of claim 1 or 2, wherein the processor is further configured to: determine, for at least one additional TRP, one or more estimated measurements having a relatively lower estimated quality, such that the total number of TRPs associated with actual PRS measurements, associated with the estimated measurements having a relatively higher estimated quality, or associated with the estimated measurements having the relatively lower estimated quality is at least the minimum number of TRPs for which measurements are to be reported; Wherein determining one or more estimated measurements having relatively lower estimated quality for at least one additional TRP is in response to determining that a total number of TRPs associated with one or more actual PRS measurements or associated with one or more estimated measurements having relatively higher estimated quality is less than the minimum number of TRPs for which PRS measurements are to be reported.

4. A WTRU according to any one of claims 1 to 3, wherein the processor is further configured to: request the PRS measurement assistance information based on determining that one or more TRPs among the multiple TRPs include a non-line-of-sight TRP.

5. The WTRU of any one of claims 1 to 4, wherein the processor is further configured to determine a reference signal time difference (RSRP) based on one or more reference signal received power (RSRP) measurements and the PRS measurement assistance information.

6. The WTRU of any one of claims 1 to 5, wherein the processor is further configured to: receiving an indication of a time window; and The first measurement report or the second measurement report is transmitted based on the time window.

7. A WTRU according to any one of claims 1 to 6, wherein the processor is further configured to estimate one or more measurements of at least one TRP based on an artificial intelligence (AI) or machine learning (ML) (AI / ML) model.

8. The WTRU of claim 7, wherein the processor is further configured to receive one or more parameters for the AI / ML model.

9. A WTRU according to any one of claims 1 to 8, wherein the processor is further configured to: determine one or more anomalies associated with the PRS measurement set performed on the first TRP subset among the multiple TRPs or the estimated measurement set determined for the second TRP subset among the multiple TRPs.

10. The WTRU of claim 9, wherein the processor is further configured to: transmitting an indication to a network to indicate the one or more anomalies associated with the set of PRS measurements performed on the first subset of the plurality of TRPs or the set of estimated measurements determined for the second subset of the plurality of TRPs; or Transmitting a request to update the PRS measurement assistance information to estimate one or more measurements of at least one TRP.

11. A method performed by a wireless transmit / receive unit (WTRU), the method comprising: receiving configuration information, wherein the configuration information indicates positioning reference signal (PRS) configuration information for each of a plurality of transmit / receive points (TRPs), wherein the configuration information indicates one or more criteria for requesting PRS measurement assistance information, and wherein the configuration information indicates a minimum number of TRPs for which one or more PRS measurements are to be reported; determining, based on one or more measurements performed on one or more TRPs of the plurality of TRPs, that at least one of the one or more criteria for requesting the PRS measurement assistance information is satisfied; transmitting a request for the PRS measurement assistance information, wherein the request indicates a location of the WTRU determined based on the one or more measurements performed on one or more TRPs of the plurality of TRPs; Receiving the PRS measurement assistance information; estimating one or more measurements of at least one TRP based on the PRS measurement assistance information and at least one measurement performed using the PRS configuration information for at least one TRP of the plurality of TRPs; as well as Transmitting a positioning measurement report, wherein the positioning measurement report includes a PRS measurement set performed on a first TRP subset among the multiple TRPs and an estimated measurement set determined for a second TRP subset among the multiple TRPs, wherein the total number of TRPs included in the first TRP subset and the second TRP subset is at least the minimum number of TRPs for which PRS measurements are to be reported.

12. The method according to claim 11, further comprising: An estimated measurement of the first type of measurement is determined based on one or more actual measurements of the second type of measurement and the PRS measurement assistance information.

13. The method according to claim 11 or 12, further comprising: determining, for at least one additional TRP, one or more estimated measurements having a relatively lower estimated quality, such that the total number of TRPs associated with actual PRS measurements, associated with the estimated measurements having a relatively higher estimated quality, or associated with the estimated measurements having the relatively lower estimated quality is at least the minimum number of TRPs for which measurements are to be reported; Wherein determining one or more estimated measurements having relatively lower estimated quality for at least one additional TRP is in response to determining that a total number of TRPs associated with one or more actual PRS measurements or associated with one or more estimated measurements having relatively higher estimated quality is less than the minimum number of TRPs for which PRS measurements are to be reported.

14. The method according to any one of claims 11 to 13, further comprising: The PRS measurement assistance information is requested based on determining that one or more TRPs among the multiple TRPs include a non-line-of-sight TRP.

15. The method according to any one of claims 11 to 14, further comprising: A reference signal time difference (RSRP) is determined based on one or more reference signal received power (RSRP) measurements and the PRS measurement assistance information.

16. The method according to any one of claims 11 to 15, further comprising: receiving an indication of a time window; as well as The first measurement report or the second measurement report is transmitted based on the time window.

17. The method according to any one of claims 11 to 16, further comprising: One or more measurements of at least one TRP are estimated based on an artificial intelligence (AI) or machine learning (ML) (AI / ML) model.

18. The method according to claim 17, further comprising: One or more parameters for the AI / ML model are received.

19. The method according to any one of claims 11 to 18, further comprising: Determine one or more anomalies associated with the set of PRS measurements performed on the first subset of the multiple TRPs or the set of estimated measurements determined for the second subset of the multiple TRPs.

20. The method according to claim 19, further comprising: transmitting an indication to a network to indicate the one or more anomalies associated with the set of PRS measurements performed on the first subset of the plurality of TRPs or the set of estimated measurements determined for the second subset of the plurality of TRPs; or Transmitting a request to update the PRS measurement assistance information to estimate one or more measurements of at least one TRP.

Images