Neural network functions for user equipment positioning

Abstract

In one aspect, the BS obtains at least one neural network function configured to facilitate the UE deriving a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, the at least one neural network function being dynamically generated based on machine learning associated with one or more historical measurement procedures. The BS transmits the at least one neural network function to the UE. In another aspect, the UE obtains positioning measurement data associated with the location of the UE (e.g., locally at the UE or remotely from the BS). The UE determines a positioning estimate for the UE based at least in part on the positioning measurement data and the at least one neural network function.

Description

Priority claims

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This patent application claims the benefit of U.S. Provisional Application No. 63 / 060,998, entitled "NEURAL NETWORK FUNCTIONS FOR POSITIONING OF A USER EQUIPMENT," filed August 4, 2020, and U.S. Non-Provisional Application No. 17 / 391,347, entitled "NEURAL NETWORK FUNCTIONS FOR POSITIONING OF A USER EQUIPMENT," filed August 2, 2021, both of which are assigned to the assignee of the present application and are expressly incorporated by reference in their entireties herein. [Technical Field]

[0002] Aspects of the present disclosure relate generally to wireless communications, and more particularly to neural network functions for positioning of user equipment (UE). [Background technology]

[0003] Wireless communication systems have evolved through various generations, including first-generation analog wireless telephone service (1G), second-generation (2G) digital wireless telephone service (including intermediate 2.5G networks), third-generation (3G) high-speed data, Internet-enabled wireless service, and fourth-generation (4G) service (e.g., LTE or WiMax). Currently, there are many different types of wireless communication systems in use, including cellular and personal communications services (PCS) systems. Examples of known cellular systems include the Cellular Analog Advanced Mobile Phone System (AMPS), and digital cellular systems based on code division multiple access (CDMA), frequency division multiple access (FDMA), time division multiple access (TDMA), Global System for Mobile Access (GSM) variants of TDMA, and the like.

[0004]

[0004] The fifth-generation (5G) wireless standard, known as New Radio (NR), promises higher data rates, a greater number of connections, and better coverage, among other improvements. The 5G standard from the Next Generation Mobile Network Alliance is designed to provide data rates of tens of megabits per second to each of tens of thousands of users, and 1 gigabit per second to dozens of workers on an office floor. To support large wireless sensor deployments, hundreds of thousands of simultaneous connections should be supported. Therefore, the spectral efficiency of 5G mobile communications should be significantly enhanced compared to the current 4G standard. Furthermore, signaling efficiency should be enhanced and latency should be significantly reduced compared to current standards. Summary of the Invention

[0005] The following presents a simplified summary related to one or more aspects disclosed herein. As such, the following summary is not intended to be an extensive overview related to all contemplated aspects, nor is it intended to identify key or critical elements related to all contemplated aspects or to delineate the scope related to particular aspects. As such, the following summary has the sole purpose of presenting some concepts related to one or more aspects related to the mechanisms disclosed herein in a simplified form as a prelude to the detailed description presented below.

[0006]

[0006] In one aspect, a method for operating a user equipment (UE) includes obtaining at least one neural network function configured to derive a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, the at least one neural network function being dynamically generated based on machine learning associated with one or more historical measurement procedures; obtaining positioning measurement data associated with a location of the UE; and determining a positioning estimate for the UE based at least in part on the positioning measurement data and the at least one neural network function.

[0007] In some aspects, the at least one neural network function comprises a UE feature processing neural network function.

[0008]

[0008] In some aspects, the positioning measurement data comprises a set of positioning measurements at the UE, and determining comprises detecting a set of positioning measurement features based on the set of positioning measurements at the UE, and deriving a likelihood that the set of positioning measurement features is present in a candidate set of positioning estimates for the UE based at least in part on a UE feature processing neural network function.

[0009] In some aspects, the at least one neural network function comprises at least one additional UE feature processing neural network function.

[0010]

[0010] In some aspects, the UE feature processing neural network function is configured to derive the likelihood based on at least one of clock drift in the UE, hardware group delay in the UE, a model of the UE, or a combination thereof.

[0011] In some aspects, the at least one neural network function comprises a base station (BS) feature processing neural network function.

[0012]

[0012] In some aspects, the positioning measurement data comprises a set of positioning measurement features based on a set of positioning measurements at one or more BSs, and determining comprises deriving a likelihood that the set of positioning measurement features is present in a candidate set of positioning estimates for the UE based at least in part on a BS feature processing neural network function, wherein the positioning estimates for the UE are based in part on the derived likelihoods.

[0013] In some aspects, the at least one neural network function comprises at least one additional BS feature processing neural network function.

[0014] In some aspects, the at least one neural network function further comprises a UE feature processing neural network function.

[0015]

[0015] In some aspects, the positioning measurement data comprises a first set of positioning measurement features based on a first set of positioning measurements at one or more BSs and a second set of positioning measurement features based on a second set of positioning measurements at the UE, and further comprises deriving a likelihood that the first set and the second set of positioning measurement features are present in a candidate set of positioning estimates for the UE based at least in part on the UE feature processing neural network function and the BS feature processing neural network function, wherein the positioning estimates for the UE are based in part on the derived likelihoods.

[0016]

[0016] In some aspects, the BS feature processing neural network function is configured to derive the likelihood based on at least one of the location of at least one BS, the downtilt of at least one BS, the transmit power of at least one BS, the clock synchronization error between two or more BSs, the clock drift of at least one BS, the hardware group delay of at least one BS, the base station almanac (BSA) error associated with at least one BS, or any combination thereof.

[0017]

[0017] In some aspects, the candidate set of positioning estimates is implicitly indicated to the UE in association with at least one neural network function, or the candidate set of positioning estimates is explicitly indicated to the UE in association with at least one neural network function.

[0018]

[0018] In some aspects, at least one neural network function is specific to a particular base station (BS) or group of BSs, carrier, location region, positioning measurement type or group of positioning measurement types, beam or group of beams, or any combination thereof.

[0019]

[0019] In some aspects, the positioning estimate comprises a wireless wide area network (WWAN) position estimate, a wireless local area network (WLAN) position estimate, a global navigation satellite system (GNSS) position estimate, a sensor-based position estimate, or any combination thereof.

[0020] In some aspects, obtaining comprises receiving the at least one neural network function from a base station, a server, or a combination thereof.

[0021]

[0021] In some aspects, at least one neural network function is configured to facilitate the UE deriving a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE relative to one or more other positioning measurement features.

[0022]

[0022] In one aspect, a method for operating a base station (BS) includes obtaining at least one neural network function configured to facilitate a user equipment (UE) deriving a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, the at least one neural network function being dynamically generated based on machine learning associated with one or more historical measurement procedures; and transmitting the at least one neural network function to the UE.

[0023] In some aspects, at least one neural network function is dynamically generated at the BS or another network component.

[0024] In some aspects, the at least one neural network function comprises a UE feature processing neural network function.

[0025] In some aspects, the at least one neural network function comprises at least one additional UE feature processing neural network function.

[0026]

[0026] In some aspects, the UE feature processing neural network function is configured to derive the likelihood based on at least one of clock drift in the UE, hardware group delay in the UE, a model of the UE, or a combination thereof.

[0027] In some aspects, the at least one neural network function comprises one or more base station (BS) feature processing neural network functions.

[0028] In some aspects, the at least one neural network function further comprises one or more UE feature processing neural network functions.

[0029]

[0029] In some aspects, the one or more BS feature processing neural network functions are configured to derive a likelihood based on at least one of the location of at least one BS, the downtilt of at least one BS, the transmit power of at least one BS, the clock synchronization error between two or more BSs, the clock drift of at least one BS, the hardware group delay of at least one BS, the base station almanac (BSA) error associated with at least one BS, or any combination thereof.

[0030]

[0030] In some aspects, the candidate set of positioning estimates is implicitly indicated to the UE in association with at least one neural network function, or the candidate set of positioning estimates is explicitly indicated to the UE in association with at least one neural network function.

[0031]

[0031] In some aspects, at least one neural network function is specific to a particular base station (BS) or group of BSs, carrier, location region, positioning measurement type or group of positioning measurement types, beam or group of beams, or any combination thereof.

[0032]

[0032] In some aspects, at least one neural network function is configured to facilitate the UE determining one or more wireless wide area network (WWAN) position estimates, wireless local area network (WLAN) position estimates, global navigation satellite system (GNSS) position estimates, sensor-based position estimates, or any combination thereof.

[0033]

[0033] In some aspects, the obtaining comprises generating at least one neural network function in the base station, or the obtaining comprises receiving at least one neural network function from a core network component or an external server.

[0034]

[0034] In one aspect, a user equipment (UE) includes a memory, at least one transceiver, and at least one processor communicatively coupled to the memory and the at least one transceiver, wherein the at least one processor is configured to: obtain at least one neural network function configured to derive a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, the at least one neural network function being dynamically generated based on machine learning associated with one or more historical measurement procedures; obtain positioning measurement data associated with the location of the UE; and determine a positioning estimate for the UE based at least in part on the positioning measurement data and the at least one neural network function.

[0035] In some aspects, the at least one neural network function comprises a UE feature processing neural network function.

[0036]

[0036] In some aspects, the positioning measurement data comprises a set of positioning measurements at the UE, and determining comprises detecting a set of positioning measurement features based on the set of positioning measurements at the UE, and deriving a likelihood that the set of positioning measurement features is present in a candidate set of positioning estimates for the UE based at least in part on a UE feature processing neural network function.

[0037] In some aspects, the at least one neural network function comprises at least one additional UE feature processing neural network function.

[0038]

[0038] In some aspects, the UE feature processing neural network function is configured to derive the likelihood based on at least one of clock drift in the UE, hardware group delay in the UE, a model of the UE, or a combination thereof.

[0039] In some aspects, the at least one neural network function comprises a base station (BS) feature processing neural network function.

[0040]

[0040] In some aspects, the positioning measurement data comprises a set of positioning measurement features based on a set of positioning measurements at one or more BSs, and determining comprises deriving a likelihood that the set of positioning measurement features is present in a candidate set of positioning estimates for the UE based at least in part on a BS feature processing neural network function, wherein the positioning estimates for the UE are based in part on the derived likelihoods.

[0041] In some aspects, the at least one neural network function comprises at least one additional BS feature processing neural network function.

[0042] In some aspects, the at least one neural network function further comprises a UE feature processing neural network function.

[0043]

[0043] In some aspects, the positioning measurement data comprises a first set of positioning measurement features based on a first set of positioning measurements at one or more BSs and a second set of positioning measurement features based on a second set of positioning measurements at the UE, and further comprising deriving a likelihood that the first set and the second set of positioning measurement features are present in a candidate set of positioning estimates for the UE based at least in part on the UE feature processing neural network function and the BS feature processing neural network function, wherein the positioning estimates for the UE are based in part on the derived likelihoods.

[0044]

[0044] In some aspects, the BS feature processing neural network function is configured to derive the likelihood based on at least one of the location of at least one BS, the downtilt of at least one BS, the transmit power of at least one BS, the clock synchronization error between two or more BSs, the clock drift of at least one BS, the hardware group delay of at least one BS, the base station almanac (BSA) error associated with at least one BS, or any combination thereof.

[0045]

[0045] In some aspects, the candidate set of positioning estimates is implicitly indicated to the UE in association with at least one neural network function, or the candidate set of positioning estimates is explicitly indicated to the UE in association with at least one neural network function.

[0046]

[0046] In some aspects, at least one neural network function is specific to a particular base station (BS) or group of BSs, carrier, location region, positioning measurement type or group of positioning measurement types, beam or group of beams, or any combination thereof.

[0047]

[0047] In some aspects, the positioning estimate comprises a wireless wide area network (WWAN) position estimate, a wireless local area network (WLAN) position estimate, a global navigation satellite system (GNSS) position estimate, a sensor-based position estimate, or any combination thereof.

[0048] In some aspects, obtaining comprises receiving the at least one neural network function from a base station, a server, or a combination thereof.

[0049]

[0049] In some aspects, at least one neural network function is configured to facilitate the UE deriving a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE relative to one or more other positioning measurement features.

[0050]

[0050] In one aspect, a base station (BS) includes a memory, at least one transceiver, and at least one processor communicatively coupled to the memory and the at least one transceiver, wherein the at least one processor is configured to: obtain at least one neural network function configured to facilitate a user equipment (UE) deriving a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, the at least one neural network function being dynamically generated based on machine learning associated with one or more historical measurement procedures; and transmit the at least one neural network function to the UE via the at least one transceiver.

[0051] In some aspects, at least one neural network function is dynamically generated at the BS or another network component.

[0052] In some aspects, the at least one neural network function comprises a UE feature processing neural network function.

[0053] In some aspects, the at least one neural network function comprises at least one additional UE feature processing neural network function.

[0054]

[0054] In some aspects, the UE feature processing neural network function is configured to derive the likelihood based on at least one of clock drift in the UE, hardware group delay in the UE, a model of the UE, or a combination thereof.

[0055] In some aspects, the at least one neural network function comprises one or more base station (BS) feature processing neural network functions.

[0056] In some aspects, the at least one neural network function further comprises one or more UE feature processing neural network functions.

[0057]

[0057] In some aspects, one or more BS feature processing neural network functions are configured to derive likelihoods based on at least one of the location of at least one BS, the downtilt of at least one BS, the transmit power of at least one BS, the clock synchronization error between two or more BSs, the clock drift of at least one BS, the hardware group delay of at least one BS, the base station almanac (BSA) error associated with at least one BS, or any combination thereof.

[0058]

[0058] In some aspects, the candidate set of positioning estimates is implicitly indicated to the UE in association with at least one neural network function, or the candidate set of positioning estimates is explicitly indicated to the UE in association with at least one neural network function.

[0059]

[0059] In some aspects, at least one neural network function is specific to a particular base station (BS) or group of BSs, carrier, location region, positioning measurement type or group of positioning measurement types, beam or group of beams, or any combination thereof.

[0060]

[0060] In some aspects, at least one neural network function is configured to facilitate the UE determining one or more wireless wide area network (WWAN) position estimates, wireless local area network (WLAN) position estimates, global navigation satellite system (GNSS) position estimates, sensor-based position estimates, or any combination thereof.

[0061]

[0061] In some aspects, the obtaining comprises generating at least one neural network function in the base station, or the obtaining comprises receiving at least one neural network function from a core network component or an external server.

[0062]

[0062] In one aspect, a user equipment (UE) includes means for obtaining at least one neural network function configured to derive a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, the at least one neural network function being dynamically generated based on machine learning associated with one or more historical measurement procedures; means for obtaining positioning measurement data associated with the location of the UE; and means for determining a positioning estimate for the UE based at least in part on the positioning measurement data and the at least one neural network function.

[0063] In some aspects, the at least one neural network function comprises a UE feature processing neural network function.

[0064]

[0064] In some aspects, the positioning measurement data comprises a set of positioning measurements at the UE, and determining comprises means for detecting a set of positioning measurement features based on the set of positioning measurements at the UE, and means for deriving a likelihood that the set of positioning measurement features is present in a candidate set of positioning estimates for the UE based at least in part on a UE feature processing neural network function.

[0065] In some aspects, the at least one neural network function comprises at least one additional UE feature processing neural network function.

[0066]

[0066] In some aspects, the UE feature processing neural network function is configured to derive the likelihood based on at least one of clock drift in the UE, hardware group delay in the UE, a model of the UE, or a combination thereof.

[0067] In some aspects, the at least one neural network function comprises a base station (BS) feature processing neural network function.

[0068]

[0068] In some aspects, the positioning measurement data comprises a set of positioning measurement features based on a set of positioning measurements at one or more BSs, and the determining comprises means for deriving a likelihood that the set of positioning measurement features is present in a candidate set of positioning estimates for the UE based at least in part on a BS feature processing neural network function, wherein the positioning estimates for the UE are based in part on the derived likelihoods.

[0069] In some aspects, the at least one neural network function comprises at least one additional BS feature processing neural network function.

[0070] In some aspects, the at least one neural network function further comprises a UE feature processing neural network function.

[0071]

[0071] In some aspects, the positioning measurement data comprises a first set of positioning measurement features based on a first set of positioning measurements at one or more BSs and a second set of positioning measurement features based on a second set of positioning measurements at the UE, and further comprises means for deriving a likelihood that the first set and the second set of positioning measurement features are present in a candidate set of positioning estimates for the UE based at least in part on the UE feature processing neural network function and the BS feature processing neural network function, wherein the positioning estimates for the UE are based in part on the derived likelihoods.

[0072]

[0072] In some aspects, the BS feature processing neural network function is configured to derive the likelihood based on at least one of the location of at least one BS, the downtilt of at least one BS, the transmit power of at least one BS, the clock synchronization error between two or more BSs, the clock drift of at least one BS, the hardware group delay of at least one BS, the base station almanac (BSA) error associated with at least one BS, or any combination thereof.

[0073]

[0073] In some aspects, the candidate set of positioning estimates is implicitly indicated to the UE in association with at least one neural network function, or the candidate set of positioning estimates is explicitly indicated to the UE in association with at least one neural network function.

[0074]

[0074] In some aspects, at least one neural network function is specific to a particular base station (BS) or group of BSs, carrier, location region, positioning measurement type or group of positioning measurement types, beam or group of beams, or any combination thereof.

[0075]

[0075] In some aspects, the positioning estimate comprises a wireless wide area network (WWAN) position estimate, a wireless local area network (WLAN) position estimate, a global navigation satellite system (GNSS) position estimate, a sensor-based position estimate, or any combination thereof.

[0076]

[0076] In some aspects, obtaining comprises receiving the at least one neural network function from a base station, a server, or a combination thereof.

[0077]

[0077] In some aspects, at least one neural network function is configured to facilitate the UE deriving a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE relative to one or more other positioning measurement features.

[0078]

[0078] In one aspect, a base station (BS) includes means for obtaining at least one neural network function configured to facilitate a user equipment (UE) deriving a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, the at least one neural network function being dynamically generated based on machine learning associated with one or more historical measurement procedures; and means for transmitting the at least one neural network function to the UE.

[0079] In some aspects, at least one neural network function is dynamically generated at the BS or another network component.

[0080] In some aspects, the at least one neural network function comprises a UE feature processing neural network function.

[0081] In some aspects, the at least one neural network function comprises at least one additional UE feature processing neural network function.

[0082]

[0082] In some aspects, the UE feature processing neural network function is configured to derive the likelihood based on at least one of clock drift in the UE, hardware group delay in the UE, a model of the UE, or a combination thereof.

[0083] In some aspects, the at least one neural network function comprises one or more base station (BS) feature processing neural network functions.

[0084] In some aspects, the at least one neural network function further comprises one or more UE feature processing neural network functions.

[0085]

[0085] In some aspects, one or more BS feature processing neural network functions are configured to derive likelihoods based on at least one of the location of at least one BS, the downtilt of at least one BS, the transmit power of at least one BS, the clock synchronization error between two or more BSs, the clock drift of at least one BS, the hardware group delay of at least one BS, the base station almanac (BSA) error associated with at least one BS, or any combination thereof.

[0086]

[0086] In some aspects, the candidate set of positioning estimates is implicitly indicated to the UE in association with at least one neural network function, or the candidate set of positioning estimates is explicitly indicated to the UE in association with at least one neural network function.

[0087]

[0087] In some aspects, at least one neural network function is specific to a particular base station (BS) or group of BSs, carrier, location region, positioning measurement type or group of positioning measurement types, beam or group of beams, or any combination thereof.

[0088]

[0088] In some aspects, at least one neural network function is configured to facilitate the UE determining one or more wireless wide area network (WWAN) position estimates, wireless local area network (WLAN) position estimates, global navigation satellite system (GNSS) position estimates, sensor-based position estimates, or any combination thereof.

[0089]

[0089] In some aspects, the obtaining comprises generating at least one neural network function in the base station, or the obtaining comprises receiving at least one neural network function from a core network component or an external server.

[0090]

[0090] In one aspect, a non-transitory computer-readable medium stores computer-executable instructions that, when executed by a user equipment (UE), cause the UE to: obtain at least one neural network function configured to derive a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, the at least one neural network function being dynamically generated based on machine learning associated with one or more historical measurement procedures; obtain positioning measurement data associated with the location of the UE; and determine a positioning estimate for the UE based at least in part on the positioning measurement data and the at least one neural network function.

[0091]

[0091] In some aspects, the at least one neural network function comprises a UE feature processing neural network function.

[0092]

[0092] In some aspects, the positioning measurement data comprises a set of positioning measurements at the UE, and determining comprises detecting a set of positioning measurement features based on the set of positioning measurements at the UE, and deriving a likelihood that the set of positioning measurement features is present in a candidate set of positioning estimates for the UE based at least in part on a UE feature processing neural network function.

[0093] In some aspects, the at least one neural network function comprises at least one additional UE feature processing neural network function.

[0094]

[0094] In some aspects, the UE feature processing neural network function is configured to derive the likelihood based on at least one of clock drift in the UE, hardware group delay in the UE, a model of the UE, or a combination thereof.

[0095] In some aspects, the at least one neural network function comprises a base station (BS) feature processing neural network function.

[0096]

[0096] In some aspects, the positioning measurement data comprises a set of positioning measurement features based on a set of positioning measurements at one or more BSs, and determining comprises deriving a likelihood that the set of positioning measurement features is present in a candidate set of positioning estimates for the UE based at least in part on a BS feature processing neural network function, wherein the positioning estimates for the UE are based in part on the derived likelihoods.

[0097] In some aspects, the at least one neural network function comprises at least one additional BS feature processing neural network function.

[0098] In some aspects, the at least one neural network function further comprises a UE feature processing neural network function.

[0099]

[0099] In some aspects, the positioning measurement data comprises a first set of positioning measurement features based on a first set of positioning measurements at one or more BSs and a second set of positioning measurement features based on a second set of positioning measurements at the UE, and further comprising deriving a likelihood that the first set and the second set of positioning measurement features are present in a candidate set of positioning estimates for the UE based at least in part on the UE feature processing neural network function and the BS feature processing neural network function, wherein the positioning estimates for the UE are based in part on the derived likelihoods.

[0100]

[0100] In some aspects, the BS feature processing neural network function is configured to derive the likelihood based on at least one of the location of at least one BS, the downtilt of at least one BS, the transmit power of at least one BS, the clock synchronization error between two or more BSs, the clock drift of at least one BS, the hardware group delay of at least one BS, the base station almanac (BSA) error associated with at least one BS, or any combination thereof.

[0101]

[0101] In some aspects, the candidate set of positioning estimates is implicitly indicated to the UE in association with at least one neural network function, or the candidate set of positioning estimates is explicitly indicated to the UE in association with at least one neural network function.

[0102]

[0102] In some aspects, at least one neural network function is specific to a particular base station (BS) or group of BSs, carrier, location region, positioning measurement type or group of positioning measurement types, beam or group of beams, or any combination thereof.

[0103]

[0103] In some aspects, the positioning estimate comprises a wireless wide area network (WWAN) position estimate, a wireless local area network (WLAN) position estimate, a global navigation satellite system (GNSS) position estimate, a sensor-based position estimate, or any combination thereof.

[0104]

[0104] In some aspects, obtaining comprises receiving the at least one neural network function from a base station, a server, or a combination thereof.

[0105]

[0105] In some aspects, at least one neural network function is configured to facilitate the UE deriving a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE relative to one or more other positioning measurement features.

[0106]

[0106] In one aspect, a non-transitory computer-readable medium stores computer-executable instructions that, when executed by a base station (BS), cause the BS to obtain at least one neural network function configured to facilitate a user equipment (UE) deriving a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, the at least one neural network function being dynamically generated based on machine learning associated with one or more historical measurement procedures; and transmit the at least one neural network function to the UE.

[0107]

[0107] In some aspects, at least one neural network function is dynamically generated at the BS or another network component.

[0108]

[0108] In some aspects, the at least one neural network function comprises a UE feature processing neural network function.

[0109]

[0109] In some aspects, the at least one neural network function comprises at least one additional UE feature processing neural network function.

[0110]

[0110] In some aspects, the UE feature processing neural network function is configured to derive the likelihood based on at least one of clock drift in the UE, hardware group delay in the UE, a model of the UE, or a combination thereof.

[0111]

[0111] In some aspects, the at least one neural network function comprises one or more base station (BS) feature processing neural network functions.

[0112]

[0112] In some aspects, the at least one neural network function further comprises one or more UE feature processing neural network functions.

[0113]

[0113] In some aspects, the one or more BS feature processing neural network functions are configured to derive a likelihood based on at least one of the location of at least one BS, the downtilt of at least one BS, the transmit power of at least one BS, the clock synchronization error between two or more BSs, the clock drift of at least one BS, the hardware group delay of at least one BS, the base station almanac (BSA) error associated with at least one BS, or any combination thereof.

[0114]

[0114] In some aspects, the candidate set of positioning estimates is implicitly indicated to the UE in association with at least one neural network function, or the candidate set of positioning estimates is explicitly indicated to the UE in association with at least one neural network function.

[0115]

[0115] In some aspects, at least one neural network function is specific to a particular base station (BS) or group of BSs, carrier, location region, positioning measurement type or group of positioning measurement types, beam or group of beams, or any combination thereof.

[0116]

[0116] In some aspects, at least one neural network function is configured to facilitate the UE determining one or more wireless wide area network (WWAN) position estimates, wireless local area network (WLAN) position estimates, global navigation satellite system (GNSS) position estimates, sensor-based position estimates, or any combination thereof.

[0117]

[0117] In some aspects, the obtaining comprises generating at least one neural network function in the base station, or the obtaining comprises receiving at least one neural network function from a core network component or an external server.

[0118]

[0118] Other objects and advantages associated with the embodiments disclosed herein will become apparent to those skilled in the art based on the accompanying drawings and detailed description.

[0119]

[0119] The accompanying drawings are presented to aid in the explanation of various aspects of the present disclosure and are provided merely to illustrate, not to limit, the aspects. [Brief explanation of the drawings]

[0120] [Figure 1]

[0120] FIG. 1 illustrates an example wireless communication system, in accordance with various aspects. [Figure 2A]

[0121] FIG. 1 illustrates an example wireless network structure, in accordance with various aspects. [Figure 2B] FIG. 1 illustrates an example wireless network structure, in accordance with various aspects. [Figure 3A]

[0122] 1 is a simplified block diagram of several sample aspects of components that may be employed in a wireless communication node and configured to support communication as taught herein; [Figure 3B] 1 is a simplified block diagram of several sample aspects of components that may be employed in a wireless communication node and configured to support communication as taught herein; [Figure 3C] 1 is a simplified block diagram of several sample aspects of components that may be employed in a wireless communication node and configured to support communication as taught herein; [Figure 4A]

[0123] 1 illustrates an example frame structure according to aspects of the present disclosure. [Figure 4B] 1 illustrates an example of channels within a frame structure, according to aspects of the present disclosure. [Figure 5]

[0124] FIG. 1 illustrates an example PRS configuration for a cell supported by a wireless node. [Figure 6]

[0125] FIG. 1 illustrates an example wireless communication system in accordance with various aspects of the present disclosure. [Figure 7]

[0126] FIG. 1 illustrates an example wireless communication system in accordance with various aspects of the present disclosure. [Figure 8A]

[0127] 10 is a graph illustrating RF channel response at a receiver over time, in accordance with an aspect of the present disclosure. [Figure 8B]

[0128] Diagram showing this separation of clusters in AoD. [Figure 9]

[0129] FIG. 1 illustrates a process for wireless communication according to aspects of the present disclosure. [Figure 10] FIG. 1 illustrates a process for wireless communication according to aspects of the present disclosure. [Figure 11]

[0130] FIG. 11 illustrates an exemplary implementation of the process of FIGS. 9-10, according to aspects of the present disclosure. [Figure 12]FIG. 11 illustrates an exemplary implementation of the process of FIGS. 9-10, according to aspects of the present disclosure. [Figure 13] FIG. 11 illustrates an exemplary implementation of the process of FIGS. 9-10, according to aspects of the present disclosure. [Figure 14]

[0131] FIG. 1 illustrates an example neural network, according to aspects of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0121]

[0132] Aspects of the present disclosure are provided in the following description and related drawings, directed to various examples provided for purposes of illustration. Alternative aspects may be devised without departing from the scope of the present disclosure. Additionally, well-known elements of the present disclosure will not be described in detail or will be omitted so as not to obscure the relevant details of the present disclosure.

[0122]

[0133] The words "exemplary" and / or "example" are used herein to mean "serving as an example, instance, or illustration." Any aspect described herein as "exemplary" and / or "example" is not necessarily to be construed as preferred or advantageous over other aspects. Likewise, the term "aspects of the present disclosure" does not require that all aspects of the present disclosure include the described feature, advantage or mode of operation.

[0123]

[0134] Those skilled in the art will appreciate that the information and signals described below may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips that may be referenced throughout the following description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof, depending in part on the particular application, desired design, corresponding technology, etc.

[0124]

[0135] Further, many aspects are described in terms of sequences of actions to be performed by, for example, elements of a computing device. It will be appreciated that various actions described herein may be performed by particular circuitry (e.g., an application-specific integrated circuit (ASIC)), by program instructions executed by one or more processors, or a combination of both. Furthermore, a sequence of actions described herein(s) may be considered to be embodied as a whole in any form of non-transitory computer-readable storage medium storing a corresponding set of computer instructions that, when executed, cause or instruct associated processors of a device to perform the functions described herein. Accordingly, various aspects of the present disclosure may be embodied in a number of different forms, all of which are contemplated to be within the scope of the claimed subject matter. Furthermore, for each aspect described herein, the corresponding form of any such aspect may be described herein, for example, as “logic configured to” perform the described actions.

[0125]

[0136] The terms “user equipment” (UE) and “base station,” as used herein, are not intended to be specific to or otherwise limited to any particular radio access technology (RAT) unless otherwise specified. Generally, a UE may be any wireless communication device (e.g., a mobile phone, a router, a tablet computer, a laptop computer, a tracking device, a wearable (e.g., a smart watch, glasses, an augmented reality (AR) / virtual reality (VR) headset, etc.), a vehicle (e.g., an automobile, a motorcycle, a bicycle, etc.), an Internet of Things (IoT) device, etc.) used by a user to communicate over a wireless communication network. A UE may be mobile or (e.g., at some times) stationary and may communicate with a radio access network (RAN). The term “UE” as used herein may be referred to interchangeably as an “access terminal” or “AT,” “client device,” “wireless device,” “subscriber device,” “subscriber terminal,” “subscriber station,” “user terminal” or UT,” “mobile terminal,” “mobile station,” or variations thereof. Generally, a UE may communicate with a core network via a RAN, through which the UE may be connected to external networks such as the Internet and other UEs. Of course, other mechanisms for connecting to the core network and / or the Internet are possible for the UE, such as via a wired access network, a wireless local area network (WLAN) network (eg, based on IEEE 802.11, etc.), etc.

[0126]

[0137] A base station may operate according to one of several RATs communicating with UEs depending on the network in which it is deployed and may alternatively be referred to as an access point (AP), network node, Node B, evolved Node B (eNB), new radio (NR) Node B (also referred to as gNB or gNode B), etc. Furthermore, in some systems, a base station may provide purely edge node signaling functionality, while in other systems, it may provide additional control and / or network management functions. In some systems, a base station may correspond to a customer premises equipment (CPE) or roadside unit (RSU). In some designs, a base station may correspond to a high-power UE (e.g., vehicular UE or VUE) that may provide functionality over limited infrastructure. The communication link through which a UE can send signals to a base station is called an uplink (UL) channel (e.g., a reverse traffic channel, a reverse control channel, an access channel, etc.). A communication link through which a base station may send signals to a UE is called a downlink (DL) or forward link channel (e.g., a paging channel, a control channel, a broadcast channel, a forward traffic channel, etc.). As used herein, the term traffic channel (TCH) can refer to either a UL / reverse traffic channel or a DL / forward traffic channel.

[0127]

[0138] The term "base station" may refer to a single physical transmit receiving point (TRP) or multiple physical TRPs, which may or may not be collocated. For example, when the term "base station" refers to a single physical TRP, the physical TRP may be an antenna of the base station corresponding to the base station's cell. When the term "base station" refers to multiple collocated physical TRPs, the physical TRP may be an array of antennas of the base station (e.g., as in a multiple-input multiple-output (MIMO) system or when the base station employs beamforming). When the term "base station" refers to multiple non-collocated physical TRPs, the physical TRP may be a distributed antenna system (DAS) (a network of spatially separated antennas connected to a common source via a transport medium) or a remote radio head (RRH) (a remote base station connected to a serving base station). Alternatively, the non-collocated physical TRP may be a serving base station that receives measurement reports from a UE and a neighbor base station whose reference RF signal the UE is measuring. A TRP is a point from which a base station transmits and receives wireless signals, and therefore, as used herein, references to transmission from or reception at a base station should be understood as referring to the particular TRP of the base station.

[0128]

[0139] An "RF signal" comprises electromagnetic waves of a given frequency that transport information through space between a transmitter and a receiver. As used herein, a transmitter may transmit a single "RF signal" or multiple "RF signals" to a receiver. However, a receiver may receive multiple "RF signals" corresponding to each transmitted RF signal due to the propagation characteristics of RF signals through a multipath channel. The same transmitted RF signal on different paths between a transmitter and a receiver is sometimes referred to as a "multipath" RF signal.

[0129]

[0140] According to various aspects, FIG. 1 illustrates an exemplary wireless communication system 100. The wireless communication system 100 (sometimes referred to as a wireless wide area network (WWAN)) may include various base stations 102 and various UEs 104. The base stations 102 may include macrocell base stations (high-power cellular base stations) and / or small cell base stations (low-power cellular base stations). In one aspect, the macrocell base stations may include eNBs where the wireless communication system 100 corresponds to an LTE network, or gNBs where the wireless communication system 100 corresponds to an NR network, or a combination of both, and the small cell base stations may include femtocells, picocells, microcells, etc.

[0130]

[0141] The base stations 102 collectively form a RAN and may interface with a core network 170 (e.g., Evolved Packet Core (EPC) or Next Generation Core (NGC)) through backhaul links 122, through which they may interface to one or more location servers 172. In addition to other functions, the base stations 102 may perform functions related to one or more of: forwarding user data, radio channel encryption and decryption, integrity protection, header compression, mobility control functions (e.g., handover, dual connectivity), inter-cell interference coordination, connection setup and release, load balancing, distribution for non-access stratum (NAS) messages, NAS node selection, synchronization, RAN sharing, Multimedia Broadcast Multicast Services (MBMS), subscriber and equipment tracing, RAN Information Management (RIM), paging, positioning, and delivery of alert messages. The base stations 102 may communicate with each other directly or indirectly (e.g., through EPC / NGC) via backhaul links 134, which may be wired or wireless.

[0131]

[0142] The base stations 102 may wirelessly communicate with the UEs 104. Each of the base stations 102 may provide communication coverage for a respective geographic coverage area 110. In one aspect, one or more cells may be supported by the base station 102 in each coverage area 110. A “cell” is a logical communication entity used for communication with a base station (e.g., over some frequency resource, referred to as a carrier frequency, component carrier, carrier, band, etc.) and may be associated with an identifier (e.g., physical cell identifier (PCI), virtual cell identifier (VCI)) to distinguish cells operating over the same or different carrier frequencies. In some cases, different cells may be configured according to different protocol types (e.g., machine type communication (MTC), narrowband IoT (NB-IoT), enhanced mobile broadband (eMBB), or others) that may provide access to different types of UEs. Because a cell is supported by a particular base station, the term “cell” may refer to either or both the logical communication entity and the base station that supports it, depending on the context. In some cases, the term "cell" may also refer to a geographic coverage area (e.g., a sector) of a base station, so long as the carrier frequency can be detected and used for communication within a portion of the geographic coverage area 110.

[0132]

[0143] The geographic coverage areas 110 of neighboring macrocell base stations 102 may partially overlap (e.g., in handover regions), but some of the geographic coverage areas 110 may be significantly overlapped by larger geographic coverage areas 110. For example, a small cell base station 102' may have a coverage area 110' that significantly overlaps with the coverage area 110 of one or more macrocell base stations 102. A network including both small cell base stations and macrocell base stations may be known as a heterogeneous network. A heterogeneous network may also include Home eNBs (HeNBs) that may serve restricted groups known as Closed Subscriber Groups (CSGs).

[0133]

[0144] The communication link 120 between the base station 102 and the UE 104 may include UL transmissions (also called reverse link) from the UE 104 to the base station 102, and / or downlink (DL) transmissions (also called forward link) from the base station 102 to the UE 104. The communication link 120 may use MIMO antenna techniques, including spatial multiplexing, beamforming, and / or transmit diversity. The communication link 120 may be over one or more carrier frequencies. The allocation of carriers may be asymmetric with respect to DL and UL (e.g., more or fewer carriers may be allocated for DL ​​than for UL).

[0134]

[0145] The wireless communication system 100 may further include a wireless local area network (WLAN) access point (AP) 150 communicating with a WLAN station (STA) 152 via a communication link 154 in an unlicensed frequency spectrum (e.g., 5 GHz). When communicating in the unlicensed frequency spectrum, the WLAN STA 152 and / or the WLAN AP 150 may perform a clear channel assessment (CCA) procedure or a listen-before-talk (LBT) procedure before communicating to determine whether a channel is available.

[0135]

[0146] The small cell base station 102' may operate in licensed and / or unlicensed frequency spectrums. When operating in the unlicensed frequency spectrum, the small cell base station 102' may employ LTE or NR technology and use the same 5 GHz unlicensed frequency spectrum used by the WLAN AP 150. A small cell base station 102' employing LTE / 5G in the unlicensed frequency spectrum may boost coverage to and / or increase the capacity of the access network. NR in the unlicensed spectrum may be referred to as NR-U. LTE in the unlicensed spectrum may be referred to as LTE-U, Licensed Assisted Access (LAA), or MultiFire.

[0136]

[0147] The wireless communication system 100 may further include a millimeter wave (mmW) base station 180 that may operate in mmW and / or near-mmW frequencies in communication with the UE 182. Extremely high frequency (EHF) is the RF portion of the electromagnetic spectrum. EHF has a range of 30 GHz to 300 GHz and a wavelength between 1 and 10 millimeters. Radio waves in this band are sometimes referred to as millimeter waves. Near-mmW may extend down to frequencies of 3 GHz, with wavelengths of 100 millimeters. The very high frequency (SHF) band, also referred to as centimeter wave, extends between 3 GHz and 30 GHz. Communications using the mmW / near-mmW radio frequency bands have high path loss and relatively short range. The mmW base station 180 and the UE 182 may utilize beamforming (transmit and / or receive) over the mmW communication link 184 to compensate for the extremely high path loss and short range. Furthermore, it will be appreciated that in alternative configurations, one or more base stations 102 may also transmit using mmW or near mmW and beamforming. Accordingly, it will be appreciated that the above description is by way of example only and should not be construed as limiting various aspects disclosed herein.

[0137]

[0148] Transmit beamforming is a technique for focusing an RF signal in a particular direction. Traditionally, when a network node (e.g., a base station) broadcasts an RF signal, it broadcasts the signal in all directions (omnidirectionally). With transmit beamforming, the network node determines where a given target device (e.g., UE) is located (relative to the transmitting network node) and projects a stronger downlink RF signal in that particular direction, thereby providing a faster (in terms of data rate) and stronger RF signal to the receiving device(s). To change the directionality of the RF signal when transmitting, the network node can control the phase and relative amplitude of the RF signal at each of one or more transmitters broadcasting the RF signal. For example, the network node may use an array of antennas (called a “phased array” or “antenna array”) that creates beams of RF waves that can be “steered” to point in different directions without actually moving the antennas. In particular, RF current from the transmitter is fed to individual antennas with the proper phase relationship so that radio waves from separate antennas add together to increase radiation in desired directions and cancel to suppress radiation in undesired directions.

[0138]

[0149] A transmit beam may be quasi-colocated, meaning that the transmit beam appears to a receiver (e.g., a UE) to have the same parameters regardless of whether the network node's transmit antennas themselves are physically colocated. In NR, there are four types of quasi-colocation (QCL) relationships. In particular, a given type of QCL relationship means that some parameters related to a second reference RF signal on a second beam can be derived from information about the source reference RF signal on the source beam. Thus, if the source reference RF signal is QCL Type A, the receiver can use the source reference RF signal to estimate the Doppler shift, Doppler spread, mean delay, and delay spread of the second reference RF signal transmitted on the same channel. If the source reference RF signal is QCL Type B, the receiver can use the source reference RF signal to estimate the Doppler shift and Doppler spread of the second reference RF signal transmitted on the same channel. If the source reference RF signal is QCL Type C, the receiver can use the source reference RF signal to estimate the Doppler shift and mean delay of the second reference RF signal transmitted on the same channel. If the source reference RF signal is QCL Type D, the receiver can use the source reference RF signal to estimate spatial reception parameters of a second reference RF signal transmitted on the same channel.

[0139]

[0150] In receive beamforming, a receiver uses receive beams to amplify RF signals detected on a given channel. For example, the receiver can increase the gain setting and / or adjust the phase setting of an antenna array in a particular direction to amplify (e.g., increase its gain level) an RF signal received from that direction. Thus, when a receiver is said to beamform in a direction, it means that the beam gain in that direction is higher relative to the beam gains along other directions, or that the beam gain in that direction is highest compared to the beam gains in that direction of all other receive beams available to the receiver. This results in a stronger received signal strength (e.g., reference signal received power (RSRP), reference signal received quality (RSRQ), signal-to-interference-plus-noise ratio (SINR), etc.) of the RF signal received from that direction.

[0140]

[0151] The receive beams may be spatially related. Spatial relationship means that parameters for a transmit beam for a second reference signal may be derived from information about the receive beam for the first reference signal. For example, a UE may use a particular receive beam to receive a reference downlink reference signal (e.g., a synchronization signal block (SSB)) from a base station. The UE can then form a transmit beam for sending an uplink reference signal (e.g., a sounding reference signal (SRS)) to that base station based on the parameters of the receive beam.

[0141]

[0152] Note that a "downlink" beam can be either a transmit beam or a receive beam, depending on the entity forming it. For example, if a base station forms a downlink beam to transmit a reference signal to a UE, the downlink beam is a transmit beam. However, if the UE forms a downlink beam, it is a receive beam to receive the downlink reference signal. Similarly, an "uplink" beam can be either a transmit beam or a receive beam, depending on the entity forming it. For example, if the base station forms an uplink beam, it is an uplink receive beam, and if the UE forms an uplink beam, it is an uplink transmit beam.

[0142]

[0153] In 5G, the frequency spectrum in which wireless nodes (e.g., base station 102 / 180, UE 104 / 182) operate is divided into multiple frequency ranges: FR1 (450 to 6000 MHz), FR2 (24250 to 52600 MHz), FR3 (above 52600 MHz), and FR4 (between FR1 and FR2). In a multi-carrier system such as 5G, one of the carrier frequencies is called the “primary carrier” or “anchor carrier” or “primary serving cell” or “PCell,” and the remaining carrier frequencies are called “secondary carriers” or “secondary serving cells” or “SCells.” In carrier aggregation, the anchor carrier is the carrier operating on the primary frequency (e.g., FR1) utilized by the UE 104 / 182 and the cell in which the UE 104 / 182 either performs an initial radio resource control (RRC) connection establishment procedure or initiates an RRC connection re-establishment procedure. The primary carrier carries all common and UE-specific control channels and may be a carrier in licensed frequencies (although this is not always the case). The secondary carrier is a carrier operating on a second frequency (e.g., FR2) that may be configured once an RRC connection is established between the UE 104 and the anchor carrier and may be used to provide additional radio resources. In some cases, the secondary carrier may be a carrier in unlicensed frequencies. The secondary carrier may contain only necessary signaling information and signals; for example, since both the primary uplink carrier and the primary downlink carrier are typically UE-specific, nothing UE-specific may be present in the secondary carrier. This means that different UEs 104 / 182 in a cell may have different downlink primary carriers. The same is true for the uplink primary carrier. The network can change the primary carrier of any UE 104 / 182 at any time. This is done, for example, to balance the load on different carriers.Since a "serving cell" (whether a PCell or an SCell) corresponds to the carrier frequency / component carrier over which some base station is communicating, terms such as "cell," "serving cell," "component carrier," and "carrier frequency" may be used interchangeably.

[0143]

[0154] For example, still referring to FIG. 1, one of the frequencies utilized by the macrocell base station 102 may be an anchor carrier (or “PCell”), and other frequencies utilized by the macrocell base station 102 and / or the mmW base station 180 may be secondary carriers (“SCells”). Simultaneous transmission and / or reception of multiple carriers allows the UE 104 / 182 to significantly increase its data transmission and / or reception rates. For example, two 20 MHz aggregated carriers in a multi-carrier system would theoretically lead to a doubling of the data rate (i.e., 40 MHz) compared to that achieved by a single 20 MHz carrier.

[0144]

[0155] The wireless communication system 100 may further include one or more UEs, such as a UE 190, that indirectly connect to one or more communication networks via one or more device-to-device (D2D) peer-to-peer (P2P) links. In the example of FIG. 1, the UE 190 has a D2D P2P link 192 with one of the UEs 104 connected to one of the base stations 102 (e.g., through which the UE 190 may indirectly obtain cellular connectivity) and a D2D P2P link 194 with a WLAN STA 152 connected to a WLAN AP 150 (through which the UE 190 may indirectly obtain WLAN-based Internet connectivity). In one example, the D2D P2P links 192 and 194 may be supported using any well-known D2D RAT, such as LTE Direct (LTE-D), WiFi Direct® (WiFi-D), Bluetooth®, etc.

[0145]

[0156] Wireless communications system 100 may further include a UE 164, which may communicate with macrocell base station 102 via communications link 120 and / or with mmW base station 180 via mmW communications link 184. For example, macrocell base station 102 may support a PCell and one or more SCells for UE 164, and mmW base station 180 may support one or more SCells for UE 164.

[0146]

[0157] According to various aspects, FIG. 2A illustrates an exemplary wireless network structure 200. For example, an NGC 210 (also referred to as a “5GC”) may be functionally considered to have control plane functions 214 (e.g., UE registration, authentication, network access, gateway selection, etc.) and user plane functions 212 (e.g., UE gateway functions, data network access, IP routing, etc.) that operate cooperatively to form a core network. A user plane interface (NG-U) 213 and a control plane interface (NG-C) 215 connect a gNB 222 to the NGC 210, specifically to the control plane function 214 and the user plane function 212. In an additional configuration, an eNB 224 may also be connected to the NGC 210 via the NG-C 215 to the control plane function 214 and the NG-U 213 to the user plane function 212. Additionally, the eNB 224 may communicate directly with the gNB 222 via a backhaul connection 223. In some configurations, the new RAN 220 may have only one or more gNBs 222, while other configurations include one or more of both eNBs 224 and gNBs 222. Either the gNBs 222 or the eNBs 224 may communicate with the UEs 204 (e.g., any of the UEs shown in FIG. 1). Another optional aspect may include a location server 230, which may be in communication with the NGC 210 to provide location assistance to the UEs 204. The location servers 230 may be implemented as multiple separate servers (e.g., physically separate servers, different software modules on a single server, different software modules spread across multiple physical servers, etc.), or alternatively, may each correspond to a single server. The location servers 230 may be configured to support one or more location services for UEs 204 that can connect to the location server 230 via the core network, the NGC 210, and / or the Internet (not shown). Furthermore, the location server 230 may be integrated into components of the core network or alternatively, may be external to the core network.

[0147]

[0158] 2B illustrates another exemplary wireless network structure 250. For example, an NGC 260 (also referred to as "5GC") may be considered functionally as a control plane function provided by an Access and Mobility Management Function (AMF) / User Plane Function (UPF) 264 and a user plane function provided by a Session Management Function (SMF) 262, which operate cooperatively to form a core network (i.e., NGC 260). A user plane interface 263 and a control plane interface 265 connect the eNB 224 to the NGC 260, specifically to the SMF 262 and the AMF / UPF 264, respectively. In an additional configuration, the gNB 222 may also be connected to the NGC 260 via the control plane interface 265 to the AMF / UPF 264 and the user plane interface 263 to the SMF 262. Additionally, eNB 224 may communicate directly with gNB 222 via backhaul connection 223, with or without gNB direct connectivity to NGC 260. In some configurations, new RAN 220 may have only one or more gNBs 222, while other configurations include one or more of both eNB 224 and gNB 222. Either gNB 222 or eNB 224 may communicate with UE 204 (e.g., any of the UEs shown in FIG. 1). Base stations of new RAN 220 communicate with the AMF side of AMF / UPF 264 via the N2 interface and with the UPF side of AMF / UPF 264 via the N3 interface.

[0148]

[0159] The AMF functions include registration management, connection management, reachability management, mobility management, lawful interception, transport for session management (SM) messages between the UE 204 and the SMF 262, a transparent proxy service for routing SM messages, access authentication and authorization, transport for short message service (SMS) messages between the UE 204 and a short message service function (SMSF) (not shown), and a security anchor function (SEAF). The AMF also interacts with an authentication server function (AUSF) (not shown) and the UE 204 to receive intermediate keys established as a result of the UE 204 authentication process. In the case of authentication based on a Universal Mobile Telecommunications System (UMTS) subscriber identity module (USIM), the AMF retrieves security material from the AUSF. The AMF's functions also include security context management (SCM). The SCM receives keys from the SEAF that it uses to derive access network-specific keys. The AMF functions also include location service management for barred services, transport for location service messages between the UE 204 and the Location Management Function (LMF) 270 and between the new RAN 220 and the LMF 270, EPS bearer identifier allocation for interworking with the Evolved Packet System (EPS), and UE 204 mobility event notification. Additionally, the AMF also supports functions for non-3GPP access networks.

[0149]

[0160] The functions of the UPF include acting as an anchor point for intra / inter-RAT mobility (when applicable), acting as an external protocol data unit (PDU) session point for interconnection to a data network (not shown), providing packet routing and forwarding, packet inspection, user plane policy rule enforcement (e.g., gating, redirection, traffic steering), lawful interception (user plane collection), traffic usage reporting, Quality of Service (QoS) handling for the user plane (e.g., UL / DL rate enforcement, reflective QoS marking in DL), UL traffic validation (Service Data Flow (SDF) to QoS flow mapping), transport level packet marking in UL and DL, DL packet buffering and DL data notification triggering, and sending and forwarding one or more "end markers" to the source RAN node.

[0150]

[0161] The functions of the SMF 262 include session management, UE Internet Protocol (IP) address allocation and management, selection and control of user plane functions, configuration of traffic steering in the UPF to route traffic to the appropriate destination, control of policy enforcement and parts of QoS, and downlink data notification. The interface through which the SMF 262 communicates with the AMF side of the AMF / UPF 264 is called the N11 interface.

[0151]

[0162] Another optional aspect may include an LMF 270, which may be in communication with the NGC 260 to provide location assistance to the UE 204. The LMF 270 may be implemented as multiple separate servers (e.g., physically separate servers, different software modules on a single server, different software modules spread across multiple physical servers, etc.), or alternatively, may each correspond to a single server. The LMF 270 may be configured to support one or more location services for the UE 204 that may connect to the LMF 270 via the core network, the NGC 260, and / or the Internet (not shown).

[0152]

[0163] 3A, 3B, and 3C illustrate several example components (represented by corresponding blocks) that may be incorporated in a UE 302 (which may correspond to any of the UEs described herein), a base station 304 (which may correspond to any of the base stations described herein), and a network entity 306 (which may correspond to or perform any of the network functions described herein, including location server 230 and LMF 270) to support file transmission operations as taught herein. It will be appreciated that these components may be implemented in different types of devices (e.g., in an ASIC, in a system-on-chip (SoC), etc.) in different implementations. The illustrated components may also be incorporated in other devices in a communication system. For example, other devices in the system may include similar components to those described to provide similar functionality. Also, a given device may include one or more of the components. For example, a device may include multiple transceiver components that enable the device to operate on multiple carriers and / or communicate via different technologies.

[0153]

[0164] The UE 302 and the base station 304 each include a wireless wide area network (WWAN) transceiver 310 and 350, respectively, configured to communicate via one or more wireless communications networks (not shown), such as an NR network, an LTE network, a GSM network, etc. The WWAN transceivers 310 and 350 may be connected to one or more antennas 316 and 356, respectively, for communicating with other network nodes, such as other UEs, access points, base stations (e.g., eNBs, gNBs), etc., via at least one designated RAT (e.g., NR, LTE, GSM, etc.) over a wireless communications medium of interest (e.g., some set of time / frequency resources in a particular frequency spectrum). The WWAN transceivers 310 and 350 may be variously configured to transmit and encode signals 318 and 358, respectively (e.g., messages, instructions, information, etc.), and conversely, to receive and decode signals 318 and 358, respectively (e.g., messages, instructions, information, pilots, etc.), in accordance with the designated RAT. In particular, transceivers 310 and 350 each include one or more transmitters 314 and 354, respectively, for transmitting and encoding signals 318 and 358, and one or more receivers 312 and 352, respectively, for receiving and decoding signals 318 and 358.

[0154]

[0165] The UE 302 and the base station 304 also, at least in some cases, include wireless local area network (WLAN) transceivers 320 and 360, respectively. The WLAN transceivers 320 and 360 may be connected to one or more antennas 326 and 366, respectively, for communicating with other network nodes, such as other UEs, access points, base stations, etc., via at least one designated RAT (e.g., WiFi, LTE-D, Bluetooth, etc.) over the wireless communications medium in question. The WLAN transceivers 320 and 360 may be variously configured to transmit and encode signals 328 and 368, respectively (e.g., messages, instructions, information, etc.), and conversely, to receive and decode signals 328 and 368, respectively (e.g., messages, instructions, information, pilots, etc.), in accordance with the designated RAT. In particular, transceivers 320 and 360 include one or more transmitters 324 and 364, respectively, for transmitting and encoding signals 328 and 368, and include one or more receivers 322 and 362, respectively, for receiving and decoding signals 328 and 368, respectively.

[0155]

[0166] The transceiver circuitry including the transmitter and receiver may in some implementations comprise an integrated device (e.g., implemented as transmitter and receiver circuitry in a single communications device), in some implementations comprise separate transmitter and receiver devices, or in other implementations may be implemented in other manners. In one aspect, the transmitter may include or be coupled to multiple antennas (e.g., antennas 316, 336, and 376), such as an antenna array, that enable each device to perform transmit “beamforming” as described herein. Similarly, the receiver may include or be coupled to multiple antennas (e.g., antennas 316, 336, and 376), such as an antenna array, that enable each device to perform receive beamforming as described herein. In one aspect, the transmitter and receiver may share the same multiple antennas (e.g., antennas 316, 336, and 376), such that each device can only receive or transmit at a given time, rather than both receive and transmit simultaneously. The wireless communication devices of apparatus 302 and / or 304 (e.g., one or both of transceivers 310 and 320 and / or 350 and 360) may also include a network listen module (NLM) or the like for performing various measurements.

[0156]

[0167] Devices 302 and 304 also, in at least some cases, include satellite positioning system (SPS) receivers 330 and 370. SPS receivers 330 and 370 may be connected to one or more antennas 336 and 376, respectively, for receiving SPS signals 338 and 378, respectively, such as Global Positioning System (GPS) signals, Global Navigation Satellite System (GLONASS) signals, Galileo signals, BeiDou signals, Indian Regional Navigation Satellite System (NAVIC), Quasi-Zenith Satellite System (QZSS), etc. SPS receivers 330 and 370 may comprise any suitable hardware and / or software for receiving and processing SPS signals 338 and 378, respectively. SPS receivers 330 and 370 request information and actions from other systems as appropriate and perform the calculations necessary to determine the positions of devices 302 and 304 using the acquired measurements via any suitable SPS algorithms.

[0157]

[0168] The base station 304 and the network entity 306 each include at least one network interface 380 and 390 for communicating with other network entities. For example, the network interfaces 380 and 390 (e.g., one or more network access ports) may be configured to communicate with one or more network entities via a wire-based or wireless backhaul connection. In some aspects, the network interfaces 380 and 390 may be implemented as transceivers configured to support wire-based or wireless signal communication. This communication may involve, for example, sending and receiving messages, parameters, or other types of information.

[0158]

[0169] The devices 302, 304, and 306 also include other components that may be used in conjunction with the operations disclosed herein. The UE 302 includes processor circuitry implementing a processing system 332, for example, for providing functionality related to false base station (FBS) detection as disclosed herein and for providing other processing functions. The base station 304 includes a processing system 384, for example, for providing functionality related to FBS detection as disclosed herein and for providing other processing functions. The network entity 306 includes a processing system 394, for example, for providing functionality related to FBS detection as disclosed herein and for providing other processing functions. In one aspect, the processing systems 332, 384, and 394 may include, for example, one or more general-purpose processors, multi-core processors, ASICs, digital signal processors (DSPs), field programmable gate arrays (FPGAs), or other programmable logic devices or processing circuits.

[0159]

[0170] Apparatus 302, 304, and 306 include memory circuitry implementing memory components 340, 386, and 396, respectively (e.g., each including a memory device) for maintaining information (e.g., information indicative of reserved resources, thresholds, parameters, etc.). In some cases, apparatus 302, 304, and 306 may include measurement modules 342 and 388, respectively. Measurement modules 342 and 388 may be hardware circuits that are part of or coupled to processing systems 332, 384, and 394, respectively, that, when executed, cause apparatus 302, 304, and 306 to perform the functions described herein. Alternatively, measurement modules 342 and 388 may be memory modules stored in memory components 340, 386, and 396, respectively (as shown in Figures 3A-3C), which, when executed by processing systems 332, 384, and 394, cause devices 302, 304, and 306 to perform the functions described herein.

[0160]

[0171] The UE 302 may include one or more sensors 344 coupled to the processing system 332 to provide movement and / or orientation information that is independent of movement data derived from signals received by the WWAN transceiver 310, the WLAN transceiver 320, and / or the GPS receiver 330. By way of example, the sensor(s) 344 may include an accelerometer (e.g., a microelectromechanical system (MEMS) device), a gyroscope, a geomagnetic sensor (e.g., a compass), an altimeter (e.g., a barometric altimeter), and / or any other type of movement detection sensor. Moreover, the sensor(s) 344 may include multiple different types of devices and combine their outputs to provide movement information. For example, the sensor(s) 344 may use a combination of a multi-axis accelerometer and an orientation sensor to provide the ability to calculate position in a 2D and / or 3D coordinate system.

[0161]

[0172] Additionally, the UE 302 includes a user interface 346 for providing instructions (e.g., audible and / or visual instructions) to a user and / or for receiving user input (e.g., upon user actuation of a sensing device such as a keypad, touchscreen, microphone, etc.). Although not shown, the devices 304 and 306 may also include user interfaces.

[0162]

[0173] Referring more particularly to the processing system 384, in the downlink, IP packets from the network entity 306 may be provided to the processing system 384. The processing system 384 may implement functionality for an RRC layer, a Packet Data Convergence Protocol (PDCP) layer, a Radio Link Control (RLC) layer, and a Medium Access Control (MAC) layer. The processing system 384 may provide RRC layer functions related to broadcasting of system information (e.g., Master Information Block (MIB), System Information Block (SIB)), RRC connection control (e.g., RRC connection paging, RRC connection establishment, RRC connection modification, and RRC connection release), inter-RAT mobility, and measurement configuration for UE measurement reporting; PDCP layer functions related to header compression / decompression, security (encryption, decryption, integrity protection, integrity verification), and handover support functions; RLC layer functions related to transfer of upper layer packet data units (PDUs), error correction via ARQ, concatenation, segmentation, and reassembly of RLC service data units (SDUs), re-segmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functions related to mapping between logical channels and transport channels, scheduling information reporting, error correction, priority handling, and logical channel prioritization.

[0163]

[0174] The transmitter 354 and receiver 352 may implement Layer 1 functions related to various signal processing functions. Layer 1, including the physical (PHY) layer, may include error detection on transport channels, forward error correction (FEC) coding / decoding of transport channels, interleaving, rate matching, mapping onto physical channels, modulation / demodulation of physical channels, and MIMO antenna processing. The transmitter 354 handles mapping to signal constellations based on various modulation schemes (e.g., binary phase shift keying (BPSK), quadrature phase shift keying (QPSK), M-phase shift keying (M-PSK), multi-level quadrature amplitude modulation (M-QAM)). The coded and modulated symbols may then be split into parallel streams. Each stream may then be mapped to a time-domain orthogonal frequency division multiplexing (OFDM) subcarrier, multiplexed with a reference signal (e.g., a pilot) in the time and / or frequency domain, and then combined with each other using an inverse fast Fourier transform (IFFT) to generate a physical channel carrying a time-domain OFDM symbol stream. The OFDM streams are spatially precoded to generate multiple spatial streams. Channel estimates from a channel estimator may be used to determine coding and modulation schemes and for spatial processing. The channel estimates may be derived from a reference signal and / or channel condition feedback transmitted by the UE 302. Each spatial stream may then be provided to one or more different antennas 356. The transmitter 354 may modulate an RF carrier with each spatial stream for transmission.

[0164]

[0175] At the UE 302, the receiver 312 receives signals through its respective antenna(s) 316. The receiver 312 recovers information modulated onto RF carriers and provides the information to the processing system 332. The transmitter 314 and receiver 312 implement Layer 1 functionality related to various signal processing functions. The receiver 312 may perform spatial processing on the information to recover spatial streams destined for the UE 302. If multiple spatial streams are destined for the UE 302, they may be combined into a single OFDM symbol stream by the receiver 312. The receiver 312 then converts the OFDM symbol stream from the time domain to the frequency domain using a fast Fourier transform (FFT). The frequency-domain signal comprises a separate OFDM symbol stream for each subcarrier of the OFDM signal. The symbols on each subcarrier and the reference signal are recovered and demodulated by determining the most likely signal constellation point transmitted by the base station 304. These soft decisions may be based on channel estimates calculated by a channel estimator. The soft decisions are then decoded and deinterleaved to recover the data and control signals originally transmitted on the physical channel by the base station 304. The data and control signals are then provided to a processing system 332 that implements Layer 3 and Layer 2 functions.

[0165]

[0176] In the UL, processing system 332 provides demultiplexing between transport and logical channels, packet reassembly, decryption, header recovery, and control signal processing to recover IP packets from the core network. Processing system 332 is also responsible for error detection.

[0166]

[0177] Similar to the functionality described with respect to DL transmission by the base station 304, the processing system 332 provides RRC layer functions related to system information (e.g., MIB, SIB) acquisition, RRC connection, and measurement reporting; PDCP layer functions related to header compression / decompression and security (encryption, decryption, integrity protection, integrity verification); RLC layer functions related to transfer of upper layer PDUs, error correction via ARQ, concatenation, segmentation, and reassembly of RLC SDUs, re-segmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functions related to mapping between logical channels and transport channels, multiplexing of MAC SDUs onto transport blocks (TBs), demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction via HARQ, priority handling, and logical channel prioritization.

[0167]

[0178] Channel estimates derived by the channel estimator from a reference signal or feedback transmitted by the base station 304 may be used by the transmitter 314 to select an appropriate coding and modulation scheme and to facilitate spatial processing. The spatial streams generated by the transmitter 314 may be provided to different antenna(s) 316. The transmitter 314 may modulate an RF carrier with each spatial stream for transmission.

[0168]

[0179] The UL transmission is processed at the base station 304 in a manner similar to that described with respect to the receiver function at the UE 302. The receiver 352 receives the signal through its respective antenna(s) 356. The receiver 352 recovers the information modulated onto the RF carrier and provides the information to the processing system 384.

[0169]

[0180] In the UL, the processing system 384 provides demultiplexing between transport and logical channels, packet reassembly, decryption, header recovery, and control signal processing to recover IP packets from the UE 302. The IP packets from the processing system 384 may be provided to the core network. The processing system 384 is also responsible for error detection.

[0170]

[0181] For convenience, devices 302, 304, and / or 306 are illustrated in Figures 3A-3C as including various components that may be configured according to various examples described herein, although it will be appreciated that the illustrated blocks may have different functions in different designs.

[0171]

[0182] The various components of devices 302, 304, and 306 may communicate with each other via data buses 334, 382, ​​and 392, respectively. The components of FIGS. 3A-3C may be implemented in various ways. In some implementations, the components of FIGS. 3A-3C may be implemented in one or more circuits, such as, for example, one or more processors and / or one or more ASICs (which may include one or more processors), where each circuit may use and / or incorporate at least one memory component for storing information or executable code used by the circuit to provide its functionality. For example, some or all of the functionality represented by blocks 310-346 may be implemented by the processor and memory component(s) of UE 302 (e.g., by execution of appropriate code and / or by appropriate configuration of the processor components). Similarly, some or all of the functionality represented by blocks 350-388 may be implemented by the processor and memory component(s) of base station 304 (e.g., by execution of appropriate code and / or by appropriate configuration of the processor components). Additionally, some or all of the functionality represented by blocks 390-396 may be implemented by a processor and memory component(s) of network entity 306 (e.g., by execution of appropriate code and / or by appropriate configuration of processor components). For simplicity, various operations, acts, and / or functions are described herein as being performed "by a UE," "by a base station," "by a positioning entity," etc. However, it will be appreciated that such operations, acts, and / or functions may actually be performed by a particular component or combination of components of a UE, base station, positioning entity, etc., such as processing systems 332, 384, 394, transceivers 310, 320, 350, and 360, memory components 340, 386, and 396, measurement modules 342 and 388, etc.

[0172]

[0183] 4A is a diagram 400 illustrating an example of a DL frame structure according to an embodiment of the present disclosure. FIG. 4B is a diagram 430 illustrating an example of channels within a DL frame structure according to an embodiment of the present disclosure. Other wireless communication technologies may have different frame structures and / or different channels.

[0173]

[0184] LTE, and possibly NR, utilizes OFDM on the downlink and single-carrier frequency-division multiplexing (SC-FDM) on the uplink. However, unlike LTE, NR has the option to use OFDM on the uplink as well. OFDM and SC-FDM partition the system bandwidth into multiple (K) orthogonal subcarriers, also commonly referred to as tones, bins, etc. Each subcarrier may be modulated with data. Generally, modulation symbols are sent in the frequency domain with OFDM and in the time domain with SC-FDM. The spacing between adjacent subcarriers may be fixed, and the total number of subcarriers (K) may depend on the system bandwidth. For example, the subcarrier spacing may be 15 kHz, and the minimum resource allocation (resource block) may be 12 subcarriers (or 180 kHz). Thus, the nominal FFT size may be equal to 128, 256, 512, 1024, or 2048 for a system bandwidth of 1.25, 2.5, 5, 10, or 20 megahertz (MHz), respectively. The system bandwidth may also be partitioned into subbands. For example, a subband may cover 1.08 MHz (i.e., 6 resource blocks), and there may be 1, 2, 4, 8, or 16 subbands for a system bandwidth of 1.25, 2.5, 5, 10, or 20 MHz, respectively.

[0174]

[0185] LTE supports a single numerology (subcarrier spacing, symbol length, etc.). In contrast, NR may support multiple numerologies; for example, subcarrier spacings of 15 kHz, 30 kHz, 60 kHz, 120 kHz, and 204 kHz or greater may be available. Table 1, provided below, lists some various parameters for different NR numerologies.

[0175] [Table 1]

[0176]

[0186] In the example of Figures 4A and 4B, a 15 kHz numerology is used. Thus, in the time domain, a frame (e.g., 10 ms) is divided into 10 equally sized subframes of 1 ms each, with each subframe containing one time slot. In Figures 4A and 4B, time is represented horizontally (e.g., on the X-axis), with time increasing from left to right, and frequency is represented vertically (e.g., on the Y-axis), with frequency increasing (or decreasing) from bottom to top.

[0177]

[0187] A resource grid may be used to represent a time slot, with each time slot including one or more time-parallel resource blocks (RBs) (also referred to as physical RBs (PRBs)) in the frequency domain. The resource grid is further divided into multiple resource elements (REs). An RE may correspond to one symbol length in the time domain and one subcarrier in the frequency domain. In the numerology of FIGS. 4A and 4B, for a normal cyclic prefix, an RB may include 12 consecutive subcarriers in the frequency domain and 7 consecutive symbols (OFDM symbols for DL, SC-FDMA symbols for UL) in the time domain, for a total of 84 REs. For an extended cyclic prefix, an RB may include 12 consecutive subcarriers in the frequency domain and 6 consecutive symbols in the time domain, for a total of 72 REs. The number of bits carried by each RE depends on the modulation scheme.

[0178]

[0188] As shown in Figure 4A, some of the REs carry DL reference (pilot) signals (DL-RS) for channel estimation at the UE. The DL-RS may include demodulation reference signals (DMRS) and channel state information reference signals (CSI-RS), whose example locations are labeled "R" in Figure 4A.

[0179]

[0189] 4B shows an example of various channels in a DL subframe of a frame. The physical downlink control channel (PDCCH) carries DL control information (DCI) in one or more control channel elements (CCEs), each containing nine RE groups (REGs), with each REG containing four consecutive REs in one OFDM symbol. The DCI carries information about UL resource allocation (persistent and non-persistent) and a description of the DL data to be transmitted to the UE. Multiple (e.g., up to eight) DCIs may be configured in the PDCCH, and these DCIs may have one of multiple formats. For example, there are different DCI formats for UL scheduling, for non-MIMO DL scheduling, for MIMO DL scheduling, and for UL power control.

[0180]

[0190] The primary synchronization signal (PSS) is used by the UE to determine subframe / symbol timing and physical layer identity. The secondary synchronization signal (SSS) is used by the UE to determine the physical layer cell identity group number and radio frame timing. Based on the physical layer identity and the physical layer cell identity group number, the UE can determine the PCI. Based on the PCI, the UE can determine the location of the above-mentioned DL-RS. The physical broadcast channel (PBCH) carrying the MIB can be logically grouped using the PSS and SSS to form an SSB (also called SS / PBCH). The MIB provides the number of RBs in the DL system bandwidth and the system frame number (SFN). The physical downlink shared channel (PDSCH) carries user data, broadcast system information not transmitted over the PBCH, such as system information blocks (SIBs), and paging messages.

[0181]

[0191] In some cases, the DL RS shown in Figure 4A may be a positioning reference signal (PRS). Figure 5 shows an example PRS configuration 500 for a cell supported by a wireless node (such as base station 102). Figure 5 illustrates how the PRS positioning occasion may be configured with a system frame number (SFN), a cell-specific subframe offset (Δ PRS )552, and PRS periodicity (T PRS ) 520. Generally, the cell-specific PRS subframe configuration is determined by the "PRS configuration index" I PRS The PRS periodicity (T PRS ) 520 and cell-specific subframe offset (Δ PRS ) is the PRS configuration index I as shown in Table 2 below. PRS It is defined based on

[0182] [Table 2]

[0183]

[0192] A PRS configuration is defined with reference to the SFN of the cell transmitting the PRS. A PRS instance is the N SFN with the first PRS positioning occasion. PRS For a first subframe of the downlink subframes,

[0184]

number

[0185] , where n f is 0≦n f SFN ≦ 1023, n s is 0≦n s n ≦ 19 f is the slot number in the radio frame defined by T PRS is the PRS periodicity 520, and Δ PRS is the cell-specific subframe offset 552.

[0186]

[0193] As shown in Figure 5, the cell-specific subframe offset Δ PRS 552 may be defined in terms of the number of subframes transmitted starting from system frame number 0 (slot "number 0," marked as slot 550) until the start of the first (subsequent) PRS positioning occasion. In the example in FIG. 5, the number of consecutive positioning subframes (N PRS ) is equal to 4, that is, each shaded block representing PRS positioning occasions 518a, 518b, and 518c represents four subframes.

[0187]

[0194] In some aspects, the UE may include a PRS configuration index I in the OTDOA assistance data for a particular cell. PRS When receiving the PRS, the UE uses Table 2 to determine the PRS periodicity T PRS 520 and PRS subframe offset Δ PRS The UE may then determine (e.g., using equation (1)) the radio frame, subframe, and slot when the PRS is scheduled in the cell. The OTDOA assistance data may be determined, for example, by a location server (e.g., location server 230, LMF 270) and includes assistance data for the reference cell and several neighbor cells supported by various base stations.

[0188]

[0195] Generally, PRS occasions from all cells in a network using the same frequency may be aligned in time and have a fixed, known time offset (e.g., cell-specific subframe offset 552) relative to other cells in networks using different frequencies. In an SFN synchronous network, all wireless nodes (e.g., base stations 102) may be aligned with respect to both frame boundaries and system frame numbers. Thus, in an SFN synchronous network, all cells supported by various wireless nodes may use the same PRS configuration index for a particular frequency of PRS transmission. On the other hand, in an SFN asynchronous network, various wireless nodes may be aligned with respect to frame boundaries but not with system frame numbers. Thus, in an SFN asynchronous network, the PRS configuration index for each cell may be configured separately by the network such that PRS occasions are aligned in time.

[0189]

[0196] A UE may determine the timing of PRS occasions of the reference cell and neighbor cells for OTDOA positioning if the UE can acquire the cell timing (e.g., SFN) of at least one of the cells, e.g., the reference cell or the serving cell. The timing of other cells may then be derived by the UE, e.g., based on the assumption that PRS occasions from different cells overlap.

[0190]

[0197] A set of resource elements used for transmitting a PRS is called a "PRS resource." The set of resource elements can span multiple PRBs in the frequency domain and N (e.g., one or more) consecutive symbols 460 within a slot 430 in the time domain. In a given OFDM symbol 460, the PRS resource occupies consecutive PRBs. A PRS resource is described by at least the following parameters: a PRS resource identifier (ID), a sequence ID, a comb size N, a resource element offset in the frequency domain, a starting slot and symbol, the number of symbols per PRS resource (i.e., the duration of the PRS resource), and QCL information (e.g., QCL with respect to other DL reference signals). In some designs, one antenna port is supported. The comb size indicates the number of subcarriers in each symbol carrying a PRS. For example, a comb size of comb 4 means that every fourth subcarrier in a given symbol carries a PRS.

[0191]

[0198] A "PRS resource set" is a set of PRS resources used for transmitting PRS signals, where each PRS resource has a PRS resource ID. Furthermore, PRS resources in a PRS resource set are associated with the same transmit reception point (TRP). A PRS resource ID in a PRS resource set is associated with a single beam transmitted from a single TRP (where a TRP may transmit one or more beams). That is, each PRS resource in a PRS resource set may be transmitted on a different beam; therefore, a "PRS resource" may also be referred to as a "beam." Note that this does not imply whether the TRP and the beam on which the PRS is transmitted are known to the UE. A "PRS occasion" is one instance of a periodically repeating time window (e.g., a group of one or more consecutive slots) in which a PRS is expected to be transmitted. A PRS occasion may also be referred to as a "PRS positioning occasion," a "positioning occasion," or simply an "occasion."

[0192]

[0199] Note that the terms "positioning reference signal" and "PRS" may sometimes refer to specific reference signals used for positioning in LTE or NR systems. However, unless otherwise specified, the terms "positioning reference signal" and "PRS" as used herein refer to any type of reference signal that may be used for positioning, such as, but not limited to, a PRS signal in LTE or NR, a navigation reference signal (NRS) in 5G, a transmitter reference signal (TRS), a cell-specific reference signal (CRS), a channel state information reference signal (CSI-RS), a primary synchronization signal (PSS), a secondary synchronization signal (SSS), or an SSB.

[0193]

[0200] SRS is an uplink-only signal transmitted by UEs to help the base station obtain channel state information (CSI) for each user. Channel state information describes how the RF signal propagates from the UE to the base station and accounts for the combined effects of scattering, fading, and power attenuation over distance. Systems use SRS for resource scheduling, link adaptation, massive MIMO, beam management, etc.

[0194]

[0201] Several extensions over the previous definition of SRS have been proposed for SRS for positioning (SRS-P), including a new staggered pattern within SRS resources, a new comb type for SRS, a new sequence for SRS, a higher number of SRS resource sets per component carrier, and a higher number of SRS resources per component carrier. Furthermore, the parameters "SpatialRelationInfo" and "PathLossReference" should be configured based on DL RS from neighboring TRPs. Furthermore, one SRS resource may be transmitted outside the active bandwidth portion (BWP), and one SRS resource may span multiple component carriers. Finally, a UE may transmit from multiple SRS resources for UL-AoA through the same transmission beam. All of these are features added to the current SRS framework, configured through RRC upper layer signaling (and potentially triggered or activated through MAC control element (CE) or downlink control information (DCI)).

[0195]

[0202] As mentioned above, SRS in NR is a UE-specific configured reference signal transmitted by the UE for the purpose of sounding the uplink radio channel. Similar to CSI-RS, such sounding provides various levels of knowledge of radio channel characteristics. At one extreme, SRS may be used in the gNB simply to obtain signal strength measurements, e.g., for the purpose of UL beam management. At the other extreme, SRS may be used in the gNB to obtain detailed amplitude and phase estimates as a function of frequency, time, and space. In NR, channel sounding with SRS supports a more diverse set of use cases compared to LTE (e.g., downlink CSI acquisition for reciprocity-based gNB transmit beamforming (downlink MIMO), uplink CSI acquisition for link adaptation and codebook / non-codebook-based precoding for uplink MIMO, uplink beam management, etc.).

[0196]

[0203] The SRS can be configured using various options: The time / frequency mapping of the SRS resource is defined by the following characteristics:

[0197] Duration N symb SRS The duration of an SRS resource can be one, two, or four consecutive OFDM symbols within a slot, in contrast to LTE, which only allows a single OFDM symbol per slot.

[0198] Starting symbol location l0 - The starting symbol of the SRS resource can be located anywhere within the last six OFDM symbols of the slot, provided that the resource does not cross a slot end boundary.

[0199] Repetition factor R—For SRS resources configured with frequency hopping, repetition allows the same set of subcarriers to be sounded in R consecutive OFDM symbols before the next hop occurs ("hop" as used herein specifically refers to a frequency hop). For example, values ​​of R are 1, 2, 4, where R≦N symb SRS is.

[0200] Transmission comb spacing K TC and Com Offset k TC - SRS resources may occupy resource elements (REs) of a frequency-domain comb structure, where the comb spacing is either two REs or four REs, as in LTE. Such a structure allows frequency-domain multiplexing of different SRS resources of the same or different users on different combs, where the different combs are offset from each other by an integer number of REs. Comb offsets are defined with respect to PRB boundaries and are in the range 0, 1, ..., K. TC -1 RE. Therefore, the comb spacing K TC = 2, there are two different combs available for multiplexing if needed, with comb spacing K TC If =4, there are four different combs available.

[0201] Periodicity and slot offset in case of periodic / semi-persistent SRS.

[0202] · Sounding bandwidth within the bandwidth portion.

[0203]

[0204] For low-latency positioning, the gNB may trigger a UL SRS-P via DCI (e.g., the transmitted SRS-P may include repetition or beam sweeping to enable several gNBs to receive the SRS-P). Alternatively, the gNB may send information regarding aperiodic PRS transmissions to the UE (e.g., this configuration may include information regarding PRSs from multiple gNBs to enable the UE to perform timing calculations for positioning (UE-based) or reporting (UE-assisted)). While various aspects of the present disclosure relate to DL PRS-based positioning procedures, some or all of such aspects may also apply to UL SRS-P-based positioning procedures.

[0204]

[0205] Note that the terms "sounding reference signal," "SRS," and "SRS-P" may sometimes refer to specific reference signals used for positioning in LTE or NR systems. However, unless otherwise specified, the terms "sounding reference signal," "SRS," and "SRS-P" as used herein refer to any type of reference signal that may be used for positioning, such as, but not limited to, an SRS signal in LTE or NR, a navigation reference signal (NRS) in 5G, a transmitter reference signal (TRS), a random access channel (RACH) signal for positioning (e.g., a RACH preamble, such as Msg-1 in a four-step RACH procedure or Msg-A in a two-step RACH procedure).

[0205]

[0206] 3GPP Rel. 16 introduced various NR positioning aspects aimed at increasing the location accuracy of positioning schemes involving measurement(s) associated with one or more UL or DL ​​PRS (e.g., higher bandwidth (BW), FR2 beam sweeping, angle-based measurements such as angle-of-arrival (AoA) and angle-of-radiation (AoD) measurements, multi-cell round-trip time (RTT) measurements, etc.). When latency reduction is a priority, UE-based positioning techniques (e.g., DL-only techniques without UL location measurement reporting) are generally used. However, when latency is less of a concern, UE-assisted positioning techniques may be used, whereby UE measurement data is reported to a network entity (e.g., location server 230, LMF 270, etc.). The latency associated with UE-assisted positioning techniques can be somewhat reduced by implementing an LMF in the RAN.

[0206]

[0207] Layer 3 (L3) signaling (e.g., RRC or Location Positioning Protocol (LPP)) is generally used to transport reports comprising location-based data in connection with UE-assisted positioning techniques. L3 signaling is associated with relatively high latency (e.g., greater than 100 ms) compared to Layer 1 (L1, or PHY layer) signaling or Layer 2 (L2, or MAC layer) signaling. In some cases, lower latency (e.g., less than 100 ms, less than 10 ms, etc.) between the UE and the RAN for location-based reporting may be desired. In such cases, L3 signaling may not be able to reach these lower latency levels. L3 signaling for positioning measurements may comprise any combination of the following:

[0207] One or more TOA, TDOA, RSRP, or Rx-Tx measurements; · One or more AoA / AoD measurements (e.g., currently only DL AoA and UL AoD are agreed upon for gNB->LMF reporting), One or more multipath reporting measurements, e.g., per-path ToA, RSRP, AoA / AoD (e.g., currently only per-path ToA is enabled in LTE), One or more movement states (e.g., walking, driving, etc.) and trajectories (e.g., currently for the UE), and / or One or more reported quality instructions.

[0208] More recently, L1 and L2 signaling has been contemplated for use in connection with PRS-based reporting. For example, L1 and L2 signaling is currently used in some systems to transport CSI reports (e.g., reports of Channel Quality Indicator (CQI), Precoding Matrix Indicator (PMI), Layer Indicator (Li), L1-RSRP, etc.). A CSI report may comprise a set of fields in a predefined order (e.g., defined by the relevant standard). A single UL transmission (e.g., on the PUSCH or PUCCH) may include multiple reports, referred to herein as “sub-reports,” organized according to a predefined priority (e.g., defined by the relevant standard). In some designs, the predefined order may be based on the associated sub-report periodicity (e.g., aperiodic / semi-persistent / periodic (A / SP / P) over PUSCH / PUCCH), measurement type (e.g., L1-RSRP or not), serving cell index (e.g., in the case of carrier aggregation (CA)), and reportconfigID. In two-part CSI reporting, Part 1 of all reports is grouped together, Part 2 is grouped separately, and each group is coded separately (e.g., Part 1 payload size is fixed based on configuration parameters, while Part 2 size is variable and depends on the configuration parameters and on the associated Part 1 content). The number of coded bits / symbols to be output after encoding and rate matching is calculated based on the number of input bits and a beta factor for each relevant standard. A linkage (e.g., a time offset) is defined between the instance of the RS being measured and the corresponding report. In some designs, CSI-like reporting of PRS-based measurement data using L1 and L2 signaling may be implemented.

[0209] FIG. 6 illustrates an exemplary wireless communications system 600 in accordance with various aspects of the present disclosure. In the example of FIG. 6, a UE 604, which may correspond to any of the UEs described above with respect to FIG. 1 (e.g., UE 104, UE 182, UE 190, etc.), is attempting to calculate an estimate of its location or to assist another entity (e.g., a base station or core network component, another UE, a location server, a third-party application, etc.) in calculating an estimate of its location. The UE 604 may communicate wirelessly with multiple base stations 602a-d (collectively, base stations 602), which may correspond to any combination of base stations 102 or 180 and / or WLAN AP 150 in FIG. 1, using RF signals and standardized protocols for modulation of RF signals and exchange of information packets. By extracting different types of information from the exchanged RF signals and utilizing the layout of the wireless communications system 600 (i.e., base station locations, geometry, etc.), the UE 604 may determine, or assist in determining, its location in a predefined reference frame. In one aspect, the UE 604 may specify its location using a two-dimensional coordinate system, although the aspects disclosed herein are not so limited and may be applicable to determining location using a three-dimensional coordinate system if additional dimensions are desired. Additionally, while FIG. 6 shows one UE 604 and four base stations 602, it will be appreciated that there may be more UEs 604 and more or fewer base stations 602.

[0210] To support location estimation, base stations 602 may be configured to broadcast reference RF signals (e.g., positioning reference signals (PRS), cell-specific reference signals (CRS), channel state information reference signals (CSI-RS), synchronization signals, etc.) to UEs 604 in their coverage areas to enable the UEs 604 to measure reference RF signal timing differences (e.g., OTDOA or RSTD) between pairs of network nodes and / or identify the beam that best excites LOS or the shortest radio path between the UE 604 and the transmitting base station 602. Identifying the LOS / shortest path beam(s) is interesting because not only can these beams be subsequently used for OTDOA measurements between pairs of base stations 602, but identifying these beams can also directly provide some positioning information based on the beam direction. Moreover, these beams can subsequently be used for other location estimation methods that require accurate ToA, such as round-trip time estimation-based methods.

[0211]

[0211] As used herein, a "network node" may be a base station 602, a cell of a base station 602, a remote radio head, an antenna of a base station 602 when the location of the antenna of the base station 602 is separate from the location of the base station 602 itself, or any other network entity capable of transmitting a reference signal. Furthermore, as used herein, a "node" may refer to either a network node or a UE.

[0212] A location server (e.g., location server 230) may send assistance data to the UE 604, including identification information of one or more neighbor cells of the base station 602 and configuration information for the reference RF signal transmitted by each neighbor cell. Alternatively, the assistance data may originate directly from the base station 602 itself (e.g., in a periodically broadcast overhead message, etc.). Alternatively, the UE 604 may detect neighbor cells of the base station 602 on its own without using assistance data. The UE 604 may measure and (optionally) report (e.g., based in part on assistance data, if provided) the OTDOA from individual network nodes and / or the RSTD between reference RF signals received from pairs of network nodes. Using these measurements and the known location of the measured network node (i.e., the base station(s) 602 or antenna(s) that transmitted the reference RF signal measured by the UE 604), the UE 604 or location server may determine the distance between the UE 604 and the measured network node, thereby calculating the location of the UE 604.

[0213] The term “position estimate” is used herein to refer to an estimate of a position for a UE 604, which may be geographic (e.g., may comprise latitude, longitude, and possibly altitude) or urban (e.g., may comprise a street address, a building designation, or a precise point or area within or near a building or street address, such as a particular entrance to a building, a particular room or suite within a building, or a landmark such as a town square). A position estimate may also be referred to as a “location,” “position,” “fix,” “position fix,” “location fix,” “location estimate,” “fix estimate,” or some other term. Means of obtaining a location estimate may be generally referred to as “positioning,” “locating,” or “position fixing.” A particular solution for obtaining a position estimate may be referred to as a “position solution.” A particular method for obtaining a position estimate as part of a position solution may be referred to as a “position method” or “positioning method.”

[0214] The term "base station" may refer to a single physical transmission point or multiple physical transmission points, which may or may not be collocated. For example, when the term "base station" refers to a single physical transmission point, the physical transmission point may be an antenna of the base station corresponding to the cell of the base station (e.g., base station 602). When the term "base station" refers to multiple collocated physical transmission points, the physical transmission point may be an array of antennas of the base station (e.g., as in a MIMO system or when the base station employs beamforming). When the term "base station" refers to multiple non-collocated physical transmission points, the physical transmission point may be a distributed antenna system (DAS) (a network of spatially separated antennas connected to a common source via a transport medium) or a remote radio head (RRH) (a remote base station connected to a serving base station). Alternatively, the non-collocated physical transmission points may be a serving base station that receives measurement reports from a UE (e.g., UE 604) and a neighbor base station whose reference RF signal the UE is measuring. 6 illustrates an aspect in which base stations 602a and 602b form a DAS / RRH 620. For example, base station 602a may be a serving base station for UE 604, and base station 602b may be a neighbor base station for UE 604. Thus, base station 602b may be an RRH for base station 602a. Base stations 602a and 602b may communicate with each other via a wired or wireless link 622.

[0215] To accurately determine the location of a UE 604 using the OTDOA and / or RSTD between RF signals received from a pair of network nodes, the UE 604 needs to measure a reference RF signal received over the LOS path (or the shortest NLOS path if no LOS path is available) between the UE 604 and the network node (e.g., base station 602, antenna). However, the RF signal not only travels by the LOS / shortest path between the transmitter and receiver, but also travels via several other paths as the RF signal spreads from the transmitter and reflects off other objects, such as hills, buildings, water, etc., on its way to the receiver. Thus, FIG. 6 shows several LOS paths 610 and several NLOS paths 612 between the base station 602 and the UE 604. In particular, FIG. 6 shows base station 602a transmitting via LOS path 610a and NLOS path 612a, base station 602b transmitting via LOS path 610b and two NLOS paths 612b, base station 602c transmitting via LOS path 610c and NLOS path 612c, and base station 602d transmitting via two NLOS paths 612d. As shown in FIG. 6, each NLOS path 612 reflects off some object 630 (e.g., a building). As will be appreciated, each LOS path 610 and NLOS path 612 transmitted by base station 602 may be transmitted by a different antenna of base station 602 (e.g., as in a MIMO system) or may be transmitted by the same antenna of base station 602 (thereby illustrating RF signal propagation). Furthermore, the term “LOS path” as used herein refers to the shortest path between the transmitter and receiver, which may not be the actual LOS path, but rather the shortest NLOS path.

[0216] In one aspect, one or more of the base stations 602 may be configured to use beamforming to transmit RF signals. In that case, some of the available beams may focus the transmitted RF signals along the LOS path 610 (e.g., the beam producing the highest antenna gain along the LOS path), while other available beams may focus the transmitted RF signals along the NLOS path 612. A beam that has high gain along one path and therefore focuses the RF signals along that path may still have some RF signals propagating along other paths, the strength of which, of course, depends on the beam gain along those other paths. An "RF signal" comprises electromagnetic waves that transport information through space between a transmitter and a receiver. As used herein, a transmitter may transmit a single "RF signal" or multiple "RF signals" to a receiver. However, as explained further below, a receiver may receive multiple "RF signals" corresponding to each transmitted RF signal due to the propagation characteristics of RF signals through a multipath channel.

[0217]

[0217] If the base station 602 uses beamforming to transmit RF signals, the beam of interest for data communication between the base station 602 and the UE 604 will be the beam carrying the RF signal that arrives at the UE 604 with the highest signal strength (e.g., as indicated by received signal received power (RSRP) or SINR in the presence of directional interfering signals), while the beam of interest for position estimation will be the beam carrying the RF signal that excites the shortest path or LOS path (e.g., LOS path 610). In some frequency bands and for commonly used antenna systems, this will be the same beam. However, in other frequency bands, such as mmW, where multiple antenna elements may typically be used to create a narrow transmit beam, they may not be the same beam. As described below with reference to FIG. 7, in some cases, the signal strength of the RF signal on the LOS path 610 may be weaker (e.g., due to interference) than the signal strength of the RF signal on the NLOS path 612, where the RF signal arrives later due to propagation delay.

[0218] FIG. 7 illustrates an exemplary wireless communications system 700 in accordance with various aspects of the present disclosure. In the example of FIG. 7, a UE 704, which may correspond to the UE 604 of FIG. 6, is attempting to calculate an estimate of its location or to assist another entity (e.g., a base station or core network component, another UE, a location server, a third-party application, etc.) in calculating an estimate of its location. The UE 704 may communicate wirelessly with a base station 702, which may correspond to one of the base stations 602 in FIG. 6, using RF signals and standardized protocols for modulation of the RF signals and exchange of information packets.

[0219] As shown in Figure 7, the base station 702 utilizes beamforming to transmit multiple beams 711-715 of RF signals. Each beam 711-715 may be formed and transmitted by an array of antennas at the base station 702. While Figure 7 shows the base station 702 transmitting five beams 711-715, it will be appreciated that there may be more or fewer than five beams, the beam shapes, such as peak gain, width, and sidelobe gain, may vary among the transmitted beams, and some of the beams may be transmitted by different base stations.

[0220]

[0220] A beam index may be assigned to each of the multiple beams 711-715 to distinguish RF signals associated with one beam from RF signals associated with another beam. Moreover, RF signals associated with a particular beam among the multiple beams 711-715 may carry a beam index indicator. The beam index may also be derived from the time of transmission of the RF signal, e.g., frame, slot, and / or OFDM symbol number. The beam index indicator may be, for example, a 3-bit field for uniquely distinguishing up to eight beams. If two different RF signals with different beam indices are received, this indicates that the RF signals were transmitted using different beams. If two different RF signals share a common beam index, this indicates that the different RF signals are transmitted using the same beam. Another way to describe two RF signals being transmitted using the same beam is to say that the antenna port(s) used for transmission of the first RF signal are quasi-colocated in space with the antenna port(s) used for transmission of the second RF signal.

[0221] In the example of FIG. 7, UE 704 receives NLOS data stream 723 of RF signals transmitted on beam 713 and LOS data stream 724 of RF signals transmitted on beam 714. While FIG. 7 illustrates NLOS data stream 723 and LOS data stream 724 as single lines (dashed and solid lines, respectively), it will be appreciated that NLOS data stream 723 and LOS data stream 724 may each comprise multiple rays (i.e., "clusters") by the time they reach UE 704, for example, due to the propagation characteristics of RF signals through a multipath channel. For example, when an electromagnetic wave is reflected off multiple surfaces of an object, a cluster of RF signals is formed, with the reflections arriving at the receiver (e.g., UE 704) from approximately the same angle, each traveling a few wavelengths (e.g., centimeters) more or less than the others. A "cluster" of received RF signals generally corresponds to a single transmitted RF signal.

[0222] In the example of FIG. 7, NLOS data stream 723 is not initially directed to UE 704, but as can be appreciated, it may be directed to UE 704, much like the RF signal on NLOS path 612 in FIG. 6 is. However, it may be reflected off a reflector 740 (e.g., a building) and reach UE 704 unimpeded, and thus still be a relatively strong RF signal. In contrast, LOS data stream 724 is directed to UE 704 but passes through obstructions 730 (e.g., vegetation, buildings, hills, clouds, smoke, or other confusing environments) that may significantly degrade the RF signal. As can be appreciated, LOS data stream 724 is weaker than NLOS data stream 723, but because LOS data stream 724 follows a shorter path from base station 702 to UE 704, it arrives at UE 704 before NLOS data stream 723.

[0223]

[0223] As mentioned above, the beam of interest for data communication between a base station (e.g., base station 702) and a UE (e.g., UE 704) is the beam carrying the RF signal that arrives at the UE with the highest signal strength (e.g., highest RSRP or SINR), and the beam of interest for position estimation is the beam carrying the RF signal that excites the LOS path and has the highest gain along the LOS path among all other beams (e.g., beam 714). That is, even if beam 713 (an NLOS beam) weakly excites the LOS path (not focused along the LOS path but due to the propagation characteristics of RF signals), the weak signal, if any, of the LOS path of beam 713 may not be as reliably detectable (compared to that from beam 714), thus leading to larger errors in performing positioning measurements.

[0224]

[0224] The beam of interest for data communication and the beam of interest for position estimation may be the same beam in some frequency bands, but may not be the same beam in other frequency bands, such as mmW. Thus, referring to Figure 7, if UE 704 is engaged in a data communication session with base station 702 (e.g., base station 702 is the serving base station for UE 704) and is simply not attempting to measure a reference RF signal transmitted by base station 702, the beam of interest for the data communication session may be beam 713 because beam 713 carries unobstructed NLOS data stream 723. However, the beam of interest for position estimation will be beam 714 because beam 714 carries the strongest LOS data stream 724 despite being obstructed.

[0225] FIG. 8A is a graph 800A illustrating an RF channel response over time at a receiver (e.g., UE 704) in accordance with an aspect of the present disclosure. Under the channel shown in FIG. 8A, the receiver receives a first cluster of two RF signals on the channel tap at time T1, a second cluster of five RF signals on the channel tap at time T2, a third cluster of five RF signals on the channel tap at time T3, and a fourth cluster of four RF signals on the channel tap at time T4. In the example of FIG. 8A, because the first cluster of RF signals at time T1 arrives first, it is inferred to be a line-of-sight (LOS) data stream (i.e., a data stream arriving via line-of-sight or shortest path) and may correspond to LOS data stream 724. The third cluster at time T3 is composed of the strongest RF signals and may correspond to NLOS data stream 723. From the transmitter's perspective, each cluster of received RF signals may comprise a portion of the RF signal transmitted at a different angle; therefore, each cluster may be said to have a different angle of departure (AoD) from the transmitter. FIG. 8B is a diagram 800B illustrating this separation of clusters in the AoD. An RF signal transmitted in AoD range 802a may correspond to one cluster (e.g., "Cluster 1") in FIG. 8A, and an RF signal transmitted in AoD range 802b may correspond to a different cluster (e.g., "Cluster 3") in FIG. 8A. Note that while the AoD ranges of the two clusters shown in FIG. 8B are spatially separated, the AoD ranges of some clusters may also partially overlap, although the clusters are separated in time. For example, this may occur when two separate buildings at the same AoD from the transmitter reflect a signal toward the receiver. Note that while FIG. 8A shows clusters of 2 to 5 channel taps (or "peaks"), it will be appreciated that the clusters may have more or fewer channel taps than shown.

[0226] As explained above, for positioning in cellular systems, the gNB typically transmits a reference signal (e.g., PRS), and the UE is configured to measure and report several predefined metrics, such as Reference Signal Received Power (RSRP), Time of Arrival (TOA), Round Trip Time (RTT), and Reference Signal Time Difference (RSTD). To enable UE-based positioning, the gNB typically transmits additional information, such as the gNB location (also known as the base station almanac or BSA). The UE then maps the measurements to an estimate of the UE position using models based on physics and statistical techniques. This approach relies on the ability to reliably mathematically model the measurements.

[0227]

[0227] Various parameters can affect the accuracy of the mapping from measurements to UE location likelihood, some of which may not be easy to obtain or to mathematically model in a reliable manner.

[0228] Parameters that are neutral with respect to the UE or gNB, such as physics-based models (e.g., round trip times have circular contours), gNB-specific parameters, such as gNB properties (e.g., location, downtilt, transmit power), gNB-side implementation issues (e.g., gNB time synchronization error, clock drift, antenna-to-baseband delay or hardware group delay), and BSA errors (e.g., some eNB locations are wrong or inaccurate), UE-specific parameters (e.g. clock drift, antenna-to-baseband delay or hardware group delay, device type such as vehicle or phone, or specific brand of vehicle or phone, chipset type, etc.).

[0229]

[0228] Therefore, mathematical modeling for mapping from positioning measurements to positioning estimates for a UE can be difficult. Moreover, some information required for such mathematical modeling may not be available (e.g., BSA, gNB time synchronization error, etc.).

[0230]

[0229] Accordingly, one or more aspects of the present disclosure are directed to applying dynamically generated neural network function(s) based on machine learning (ML) based on historical measurement procedures to new positioning measurement data. In some designs, the neural network function(s) may be fine-tuned (or optimized) based on ML for various operating conditions, as described in more detail below. In some designs, such aspects may facilitate various technical advantages, such as more accurate UE positioning estimates, faster UE positioning estimates, etc.

[0231] Hereinafter, references are made to positioning measurement “features.” As used herein, a positioning measurement “feature” is a processed (e.g., compressed) representation of raw positioning measurement data. In some designs, processing (e.g., or refinement or compression) of raw positioning measurement data into (one or more) respective positioning measurement features may be implemented for various reasons, such as reducing the amount of positioning measurement data to be transported over a physical channel between the UE and the gNB. Examples of positioning measurement features include time of arrival (e.g., TOA, TDOA, OTDOA, etc.), reference signal time difference, angle of radiation (AoD), angle of arrival (AoA), timing and magnitude of a predefined number of peaks in the channel estimate, other channel estimate information such as a power delay profile (PDP), etc.

[0232] 9 illustrates an example process 900 for wireless communication according to an aspect of the present disclosure. In one aspect, the process 900 may be performed by a UE, such as the UE 302 of FIG.

[0233] At 910, the UE 302 (e.g., receiver 312, receiver 322, etc.) obtains at least one neural network function configured to derive a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE. In other words, given values ​​for some positioning measurement features (e.g., which may be measured at various locations), the neural network function(s) will indicate the likelihood of those particular assumed values ​​at various candidate locations (or positioning estimates). In some designs, the at least one neural network function is dynamically generated based on machine learning associated with one or more historical measurement procedures. In some designs, the at least one neural network function may be received from a network entity (e.g., BS 304). In some designs, the at least one neural network function may be generated by a network entity (e.g., network entity 306, such as LMF) or an external server and then relayed to the UE 302 via the serving BS. For example, one or more historical measurement procedures may be filtered based on one or more criteria (e.g., location, gNB, carrier, etc.) and input as training data to a machine learning algorithm that outputs a set of offsets, algorithms, and / or processing rules, referred to herein as a “neural network function,” which may be used to derive the likelihood that a particular positioning measurement feature is present at a particular candidate location (or region). In some designs, the one or more historical measurement procedures may be associated with different UEs (e.g., crowdsourcing), and UE model types or operating conditions may also be used to filter the training data fed to the machine learning algorithm that generates the neural network function(s).

[0234] At 920, the UE 302 (e.g., receiver 312, receiver 322, receiver 336, sensor 344, measurement module 342, etc.) acquires positioning measurement data associated with a location of the UE. For example, the positioning measurement data may comprise wireless wide area network (WWAN) positioning measurement data, WLAN positioning measurement data, global navigation satellite system (GNSS) positioning measurement data, sensor measurement data, etc. In some designs, the positioning measurement data may be acquired by performing a set of positioning measurements on a reference signal for positioning (e.g., PRS, etc.). In some designs, the positioning measurement data may be received from a gNB (e.g., based on SRS-P measurements, etc.). With respect to sensor measurement data, in some designs, the positioning measurement data may comprise sensor data captured by one or more sensors, such as sensor 344 (e.g., visual data or image data captured by a camera of the UE 302, from which landmarks may be identified in association with a particular location, etc.). In one example, the positioning measurement data may comprise an estimate of a channel response associated with a reference signal (e.g., a PDP that may be measured on one antenna or beam or across multiple antennas or beams; in the case of multiple antennas or beams, different PDPs may be used to jointly estimate time and angle measurements, such as AoA or AoD measurements).

[0235] At 930, the UE 302 (e.g., processing system 332, measurement module 342, etc.) determines a positioning estimate (e.g., a WWAN position estimate, a WLAN position estimate, a GNSS position estimate, a sensor-based position estimate, etc.) for the UE based at least in part on the positioning measurement data and at least one neural network function. In some designs, the UE 302 may provide the channel estimate directly as an input to the neural network function(s) at 930. In other designs, the UE 302 may first extract certain features, such as time of arrival, reference signal time difference, radiation angle, timing and magnitude of a predefined number of peaks in the channel estimate, and provide such features to the neural network function(s). In some designs, the neural network function(s) may output a likelihood that a particular feature(s) is / are present at a particular candidate location(s), in which case a post-processing function may be calculated that combines the likelihood(s) across all measurements (or features) into a combined likelihood function, as described in more detail below with respect to Figures 11-13. For example, if the neural network function(s) indicates that the positioning measurement data has a 99.9% likelihood of being present at a given candidate location and a less than 1% chance of being present at other candidate locations, the given candidate location may be determined as the positioning estimate (e.g., or at least the given candidate location may be weighted more favorably as a positioning estimate in a positioning algorithm).

[0236] 10 illustrates an example process 1000 for wireless communication according to an aspect of the present disclosure. In one aspect, the process 1000 may be performed by a BS, such as the BS 304 of FIG.

[0237] At 1010, the BS 304 (e.g., network interface(s) 380, processing system 384, measurement module 388, etc.) obtains at least one neural network function configured to facilitate the UE deriving a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE. In other words, given values ​​for several positioning measurement features (e.g., which may be measured at various locations), the neural network function(s) will indicate the likelihood of those particular assumed values ​​at various candidate locations (or positioning estimates). In some designs, the at least one neural network function is dynamically generated based on machine learning associated with one or more historical measurement procedures. In some designs, the at least one neural network function is generated at the BS 304. In other designs, the at least one neural network function may be generated at another network entity, such as the network entity 306 (e.g., the LMF) or an external server. For example, one or more historical measurement procedures may be filtered based on one or more criteria (e.g., location, gNB, carrier, etc.) and input as training data to a machine learning algorithm that outputs a set of offsets, algorithms, and / or processing rules, referred to herein as a “neural network function,” which may be used to derive the likelihood that a particular positioning measurement feature is present at a particular candidate location (or region). In some designs, the one or more historical measurement procedures may be associated with different UEs (e.g., crowdsourcing), and UE model types or operating conditions may also be used to filter the training data fed to the machine learning algorithm that generates the neural network function(s).In one example, the positioning measurement data may comprise an estimate of a channel response associated with a reference signal (e.g., a PDP that may be measured on one antenna or beam or across multiple antennas or beams; in the case of multiple antennas or beams, different PDPs may be used to jointly estimate time and angle measurements, such as AoA or AoD measurements).

[0238]

[0237] At 1020, the BS 304 (eg, transmitter 354, transmitter 364, etc.) transmits at least one neural network function to the UE.

[0239] 9-10 , in some designs, the at least one neural network function may comprise at least one UE feature processing neural network function. The UE feature processing neural network function is used to process positioning measurement features based on a set of positioning measurements (e.g., PRS measurements, etc.) measured at the UE. In some designs, the UE feature processing neural network function may receive one or more UE-side positioning measurement features, and the UE feature processing neural network function may output a likelihood that the one or more UE-side positioning measurement features are present in one or more candidate positioning estimates for the UE. The output (or derived) likelihoods may then be included as factors in the positioning estimates for the UE (e.g., low-likelihood positioning estimates are excluded or weighted more lightly, high-likelihood positioning estimates are weighted more heavily, etc.). In some designs, the input to the UE feature processing neural network function is Clock drift in the UE, Hardware group delay in the UE, a model of the UE (e.g., some UE models may have some characteristics that may skew positioning measurements, in which case the UE feature processing neural network function(s) may be configured to offset this skew); Channel estimate information, such as PDPs (e.g., PDPs measured on one antenna or beam or across multiple antennas or beams; in the case of multiple antennas or beams, different PDPs may be used to jointly estimate time and angle measurements, such as AoA or AoD measurements), or Any combination thereof It may comprise:

[0240] 9-10 , in some designs, the candidate set of positioning estimates for the UE may correspond to configured or predefined candidate areas. In one simple example, the configured or predefined candidate areas may correspond to a coverage area associated with a serving cell, a coverage area associated with a cross-section of the coverage areas of two or more cells within range of the UE, etc. In some designs, the candidate set of positioning estimates is implicitly indicated to the UE in association with at least one neural network function (e.g., the UE may include a table of coverage areas associated with various BSs or cells and may use the detected BSs / cells to filter the candidate areas). In other designs, the candidate set of positioning estimates is explicitly indicated to the UE in association with at least one neural network function (e.g., via RRC signaling, etc.).

[0241] 9-10 , in some designs, at 910, the UE receives at least one neural network function from a base station, a server, or a combination thereof (e.g., the server may send the at least one neural network function to the base station, which then transmits or forwards the at least one neural network function to the UE). In some designs, at 1010, the base station may obtain the at least one neural network function by generating the at least one neural network function at the base station itself. In other designs, the base station may receive at 1010 the at least one neural network function from a core network component or an external server.

[0242] 9-10 , in some designs, the at least one neural network function may be configured to facilitate the UE deriving a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE relative to one or more other positioning measurement features (e.g., an estimated channel response such as the magnitude and delay of a certain number of peaks in the estimated channel response). In a particular example, the at least one neural network function may output, based on the channel response estimated using a reference signal, how likely it is to observe a measured value of the ToA of the reference signal at a given candidate location.

[0243] 9-10 , in some designs, the at least one neural network function may comprise at least one BS feature processing neural network function. The BS feature processing neural network function is used to process positioning measurement features based on a set of positioning measurements (e.g., SRS-P measurements, etc.) measured at a network side, such as a serving BS or one or more non-serving BSs for the UE. In some designs, the BS feature processing neural network function may receive one or more BS-side positioning measurement features, and the BS feature processing neural network function may output a likelihood that the one or more BS-side positioning measurement features are present in one or more candidate positioning estimates for the UE. The output (or derived) likelihoods may then be included as factors in a positioning estimate for the UE (e.g., low-likelihood positioning estimates are excluded or weighted more lightly, high-likelihood positioning estimates are weighted more heavily, etc.). In some designs, the input to the BS feature processing neural network function is · the location of at least one BS; Downtilt of at least one BS, the transmission power of at least one BS; Clock synchronization error between two or more BSs; Clock drift of at least one BS, the hardware group delay of at least one BS; the Base Station Almanac (BSA) error associated with at least one BS, or Any combination thereof It may comprise:

[0244] 9-10 , in some designs, the at least one neural network function may comprise at least one UE feature processing neural network function and at least one BS feature processing neural network function. In this case, the positioning measurement data may comprise a first set of positioning measurement features based on a first set of positioning measurements at one or more BSs and a second set of positioning measurement features based on a second set of positioning measurements at the UE. A likelihood that the first and second sets of positioning measurement features are present in a candidate set of positioning estimates for the UE may then be derived based at least in part on the UE feature processing neural network function and the BS feature processing neural network function, whereby the positioning estimate for the UE is based in part on the derived likelihood.

[0245] 9-10, in some designs, the UE feature processing neural network function(s) or the BS feature processing neural network function may be: a particular base station (BS) or group of BSs (e.g., based on cell ID(s) etc.); career, Location area, a positioning measurement type or a group of positioning measurement types, a beam or group of beams, or Any combination thereof may be specific to

[0246]

[0245] Referring to Figures 9-10, in some designs, the LMF may send some inputs to the neural network function(s) to the network, which are then provided to the UE by the gNB based on local conditions, while other inputs to the neural network function(s) are supplied by the UE.

[0247] 9-10 , in some designs, a version of a neural network function may be obtained by the BS at 1010 and sent to the UE at 1020, whereby the neural network undergoes further refinement or modification at the UE. In this case, the neural network function obtained at 910 may correspond to an initial version received from the BS or a version of the neural network function further refined at the UE. For example, an initial version of the neural network function (e.g., comprising default weights, a set of offsets, etc. for processing measurement data into features) may be sent by the BS to the UE along with training data to be applied by the UE according to machine learning. In some designs, the initial version of the neural network function may be conservatively configured to avoid overriding UE-specific parameters that may already be implemented. In this case, the training data may be used to adapt to these UE-specific parameters (e.g., the training data may be used to refine such parameters rather than simply overriding UE-specific parameters with different values).

[0248]

[0247] Figure 11 illustrates an example implementation 1100 of the processes 900-1000 of Figures 9-10 according to one aspect of the present disclosure.

[0249]

[0248] Referring to Figure 11, UE side positioning measurement features Z1...Z m are input to UE feature processing neural network function 1102 and UE feature processing neural network function 1104, along with BSA information (e.g., gNB location, etc.). For example, UE feature processing neural network function 1102 and UE feature processing neural network function 1104 may be specific to positioning measurement features for different beams, measurement types, etc. The likelihood of each positioning measurement feature(s) across a candidate set (or candidate region) of positioning estimates for the UE

[0250]

number

[0251] ...

[0252]

number

[0253] 1106-1108 are output by the UE feature processing neural network functions 1102-1104, thereby

[0254]

number

[0255] represents the UE location (e.g., the candidate UE location under consideration), and Z k represents the value for the kth feature.

[0256]

number

[0257] ...

[0258]

number

[0259] 1106-1108 are then input to a feature fusion module 1110. The feature fusion module 1110 generates a likelihood

[0260]

number

[0261] ...

[0262]

number

[0263] 1106-1108 are processed (eg, aggregated) and at 1112 an overall likelihood across all evaluated positioning measurement features is output.

[0264] FIG. 12 illustrates an exemplary implementation 1200 of the processes 900-1000 of FIGS. 9-10 according to another aspect of the disclosure.

[0265]

[0250] Referring to Figure 12, UE side positioning measurement features Z1...Z m are input to UE feature processing neural network function 1202 and UE feature processing neural network function 1204. In contrast to example implementation 1100, assume that BSA information is not available. In this case, a different mapping (i.e., a different set of neural network functions) may be developed for each gNB. For example, UE feature processing neural network function 1202 and UE feature processing neural network function 1204 may be specific to positioning measurement features for different beams, measurement types, etc., associated with a particular gNB. The likelihood of each positioning measurement feature(s) over a candidate set (or candidate region) of positioning estimates for the UE

[0266]

number

[0267] ...

[0268]

number

[0269] 1206-1208 are output by the UE feature processing neural network functions 1202-1204, thereby

[0270]

number

[0271] represents the UE location (e.g., the candidate UE location under consideration), and Z k represents the value for the kth feature.

[0272]

number

[0273] ...

[0274]

number

[0275] 1206-1208 are then input to a feature fusion module 1210. The feature fusion module 1210 generates a likelihood

[0276]

number

[0277] ...

[0278]

number

[0279] 1206-1208 are processed (eg, aggregated) and at 1212 an overall likelihood across all evaluated positioning measurement features is output.

[0280]

[0251] Figure 13 illustrates an example implementation 1300 of the processes 900-1000 of Figures 9-10 according to another aspect of the present disclosure. In particular, the example implementation 1300 illustrates a scenario in which at least one neural network function comprises both a UE-based neural network function and a BS-based neural network function.

[0281]

[0252] Referring to Figure 13, gNB side measurements y1...y n are input to the gNB measurement processing neural network function 1302 and the BS measurement processing neural network function 1304. The neural network functions 1302 and 1304 process the gNB side measurements y1...y n into a set of gNB-side positioning measurement features (e.g., values) suitable for transmission to the UE. The resulting gNB-side positioning measurement features may be transmitted by the gNB (or BS) to the UE as part of gNB assistance information at 1306.

[0282]

[0253] gNB side positioning measurement characteristics Z1...Z m are input to BS feature processing neural network function 1308 and BS feature processing neural network function 1310, along with BSA information (e.g., gNB location, etc.). For example, BS feature processing neural network function 1310 and UE feature processing neural network function 1312 may be specific to positioning measurement features for different beams, measurement types, etc. The likelihood of each positioning measurement feature(s) across a candidate set (or candidate region) of positioning estimates for the UE

[0283]

number

[0284] ...

[0285]

number

[0286] is output by the BS feature processing neural network function, which results in

[0287]

number

[0288] represents the UE location (e.g., the candidate UE location under consideration), and Z k is the kth feature (k th Represents the value for the feature.

[0289]

[0254] UE side positioning measurement characteristics Z1...Z m are also input to UE feature processing neural network function 1314 and UE feature processing neural network function 1316, along with BSA information (e.g., gNB location, etc.). For example, UE feature processing neural network function 1314 and UE feature processing neural network function 1316 may be specific to positioning measurement features for different beams, measurement types, etc. The likelihood of each positioning measurement feature(s) across a candidate set (or candidate region) of positioning estimates for the UE

[0290]

number

[0291] ...

[0292]

number

[0293] is output by the UE feature processing neural network functions 1314-1316, thereby

[0294]

number

[0295] represents the UE location (e.g., the candidate UE location under consideration), and Z k represents the value for the kth feature.

[0296]

[0255] Likelihood

[0297]

number

[0298] ...

[0299]

number

[0300] and

[0301]

number

[0302] ...

[0303]

number

[0304] is then input to the feature fusion module 1318. The feature fusion module 1318

[0305]

number

[0306] ...

[0307]

number

[0308] and

[0309]

number

[0310] ...

[0311]

number

[0312] , and outputs 1320 an overall likelihood across all evaluated positioning measurement features.

[0313]

[0256] Next, additional explanation of neural networks and machine learning in general is provided.

[0314] Machine learning can be used to generate models that can be used to facilitate various aspects related to processing data. One particular application of machine learning relates to generating measurement models for processing reference signals (e.g., PRS) for positioning, such as feature extraction, reporting reference signal measurements (e.g., selecting which extracted features to report), and the like.

[0315]

[0258] Machine learning models are generally categorized as either supervised or unsupervised. Supervised models may be further subcategorized as either regression models or classification models. Supervised learning involves learning a function that maps inputs to outputs based on example input-output pairs. For example, given a training dataset with two variables, age (input) and height (output), a supervised learning model can be generated to predict a person's height based on their age. In regression models, the output is continuous. One example of a regression model is linear regression, which simply attempts to find a line that best fits the data. Extensions of linear regression include multiple linear regression (e.g., finding a plane of best fit) and polynomial regression (e.g., finding a curve of best fit).

[0316] Another example of a machine learning model is a decision tree model. In a decision tree model, a tree structure is defined by multiple nodes. Decisions are used to move from a root node at the top of the decision tree to leaf nodes (i.e., nodes with no further child nodes) at the bottom of the decision tree. Generally, a higher number of nodes in a decision tree model correlates with higher decision accuracy.

[0317] Another example of a machine learning model is a decision forest. A random forest is an ensemble learning technique that builds from decision trees. Random forests involve creating multiple decision trees using a bootstrapped dataset of the original data and randomly selecting a subset of variables at each step in the decision tree. The model then selects the most frequent value of all predictions for each decision tree. By relying on a "majority wins" model, the risk of error from individual trees is reduced.

[0318] Another example of a machine learning model is a neural network (NN). A neural network is essentially a network of mathematical formulas. A neural network accepts one or more input variables and, by passing them through a network of formulas, produces one or more output variables. In other words, a neural network takes in a vector of inputs and returns a vector of outputs.

[0319] FIG. 14 illustrates an exemplary neural network 1400 according to aspects of the present disclosure. The neural network 1400 includes an input layer “i” that receives “n” (one or more) inputs (denoted as “Input 1,” “Input 2,” and “Input n”), one or more hidden layers (denoted as hidden layers “h1,” “h2,” and “h3”) for processing the inputs from the input layer, and an output layer “o” that provides “m” (one or more) outputs (labeled “Output 1” and “Output m”). The number of inputs “n,” hidden layers “h,” and outputs “m” may be the same or different. In some designs, the hidden layer “h” may include linear function(s) and / or activation function(s) that the nodes (denoted as circles) of each successive hidden layer process from the nodes of the previous hidden layer.

[0320]

[0263] In classification models, the output is discrete. One example of a classification model is logistic regression. Logistic regression is similar to linear regression, but is used to model the probability of a finite number of outcomes, typically two. Essentially, a logistic equation is created so that the output value can only be between "0" and "1." Another example of a classification model is a support vector machine. For example, given two classes of data, a support vector machine finds a hyperplane or boundary between the two classes that maximizes the margin between the two classes. There are many planes that can separate the two classes, but only one plane can maximize the margin or distance between the classes. Another example of a classification model is naive Bayes, which is based on Bayes' theorem. Other examples of classification models include decision trees, random forests, and neural networks, which are similar to the examples described above, except that the output is discrete rather than continuous.

[0321]

[0264] Unlike supervised learning, unsupervised learning is used to draw inferences and find patterns from input data without reference to labeled results. Two examples of unsupervised learning models include clustering and dimensionality reduction.

[0322]

[0265] Clustering is an unsupervised technique that involves grouping or clustering data points. Clustering is frequently used for customer segmentation, fraud detection, and document classification. Common clustering techniques include k-means clustering, hierarchical clustering, mean-shift clustering, and density-based clustering. Dimensionality reduction is the process of reducing the number of random variables under consideration by obtaining a set of key variables. More simply, dimensionality reduction is the process of reducing the dimensionality of a feature set (or even more simply, reducing the number of features). Most dimensionality reduction techniques can be categorized as either feature removal or feature extraction. One example of dimensionality reduction is called principal component analysis (PCA). In the simplest sense, PCA involves projecting higher-dimensional data (e.g., three dimensions) into a smaller space (e.g., two dimensions). This results in lower-dimensional data (e.g., two dimensions instead of three) while preserving all original variables in the model.

[0323]

[0266] Regardless of which machine learning model is used, at a high level, the machine learning module (implemented by a processing system, e.g., processor 332, 384, or 394) may be configured to iteratively analyze training input data (e.g., measurements of reference signals to / from various target UEs) and associate this training input data with an output dataset (e.g., a set of possible or likely candidate locations for various target UEs), thereby enabling subsequent determination of the same output dataset when presented with similar input data (e.g., from other target UEs at the same or similar locations).

[0324]

[0267] In the above detailed description, it can be seen that different features are grouped together in examples. This mode of disclosure should not be understood as an intention that the exemplary clauses have more features than are expressly set forth in each clause. Rather, various aspects of the present disclosure may include fewer than all features of each disclosed exemplary clause. Thus, the following clauses should be considered incorporated herein, with each clause standing as a separate example by itself. While each dependent clause may refer to a specific combination with one of the other clauses in the clause, the aspect(s) of that dependent clause are not limited to that specific combination. It will be appreciated that other exemplary clauses may also include combinations of the dependent clause aspect(s) with the subject matter of any other dependent clause or independent clause, or any combination of features with other dependent and independent clauses. The various aspects disclosed herein expressly include combinations of specific combinations (e.g., inconsistent aspects, such as defining an element as both an insulator and a conductor) unless these combinations are expressly expressed or can be readily inferred to be unintended. Furthermore, it is also contemplated that aspects of a clause may be included in any other independent clause, even if that clause is not directly dependent on that independent clause.

[0325]

[0268] Example implementations are described in the following numbered clauses.

[0326]

[0269] Clause 1. A method for operating a user equipment (UE), comprising: obtaining at least one neural network function configured to derive a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, the at least one neural network function being dynamically generated based on machine learning associated with one or more historical measurement procedures; obtaining positioning measurement data associated with a location of the UE; and determining a positioning estimate for the UE based at least in part on the positioning measurement data and the at least one neural network function.

[0327]

[0270] Clause 2. The method of clause 1, wherein the at least one neural network function comprises a UE feature processing neural network function.

[0328]

[0271] Clause 3. The method described in Clause 2, wherein the positioning measurement data comprises a set of positioning measurements at the UE, and determining comprises detecting a set of positioning measurement features based on the set of positioning measurements at the UE, and deriving a likelihood that the set of positioning measurement features is present in a candidate set of positioning estimates for the UE based at least in part on a UE feature processing neural network function.

[0329]

[0272] Clause 4. The method of clause 2 or 3, wherein the at least one neural network function comprises at least one additional UE feature processing neural network function.

[0330]

[0273] Clause 5. A method according to any one of clauses 2 to 4, wherein the UE feature processing neural network function is configured to derive likelihood based on at least one of clock drift in the UE, hardware group delay in the UE, a model of the UE, or a combination thereof.

[0331]

[0274] Clause 6. The method of any one of clauses 1 to 5, wherein at least one neural network function comprises a base station (BS) feature processing neural network function.

[0332]

[0275] Clause 7. The method of clause 6, wherein the positioning measurement data comprises a set of positioning measurement features based on a set of positioning measurements at one or more BSs, and determining comprises deriving a likelihood that the set of positioning measurement features is present in a candidate set of positioning estimates for the UE based at least in part on a BS feature processing neural network function, wherein the positioning estimates for the UE are based in part on the derived likelihoods.

[0333]

[0276] Clause 8. The method of clause 7, wherein the at least one neural network function comprises at least one additional BS feature processing neural network function.

[0334]

[0277] Clause 9. The method of any one of clauses 6 to 8, wherein the at least one neural network function further comprises a UE feature processing neural network function.

[0335]

[0278] Clause 10. The method of clause 9, wherein the positioning measurement data comprises a first set of positioning measurement features based on a first set of positioning measurements at one or more BSs and a second set of positioning measurement features based on a second set of positioning measurements at the UE, and further comprising deriving a likelihood that the first set and the second set of positioning measurement features are present in a candidate set of positioning estimates for the UE based at least in part on the UE feature processing neural network function and the BS feature processing neural network function, wherein the positioning estimates for the UE are based in part on the derived likelihoods.

[0336]

[0279] Clause 11. A method according to any one of clauses 6 to 10, wherein the BS feature processing neural network function is configured to derive likelihood based on at least one of the location of at least one BS, the downtilt of at least one BS, the transmit power of at least one BS, the clock synchronization error between two or more BSs, the clock drift of at least one BS, the hardware group delay of at least one BS, the Base Station Almanac (BSA) error associated with at least one BS, or any combination thereof.

[0337]

[0280] Clause 12. A method according to any one of clauses 1 to 11, wherein a candidate set of positioning estimates is implicitly indicated to the UE in association with at least one neural network function, or wherein a candidate set of positioning estimates is explicitly indicated to the UE in association with at least one neural network function.

[0338]

[0281] Clause 13. A method according to any one of clauses 1 to 12, wherein at least one neural network function is specific to a particular base station (BS) or group of BSs, carrier, location region, positioning measurement type or group of positioning measurement types, beam or group of beams, or any combination thereof.

[0339]

[0282] Clause 14. A method according to any one of clauses 1 to 13, wherein the positioning estimate comprises a wireless wide area network (WWAN) position estimate, a wireless local area network (WLAN) position estimate, a global navigation satellite system (GNSS) position estimate, a sensor-based position estimate, or any combination thereof.

[0340]

[0283] Clause 15. The method of any one of clauses 1 to 14, wherein obtaining comprises receiving at least one neural network function from a base station, a server, or a combination thereof.

[0341]

[0284] Clause 16. A method according to any one of clauses 1 to 15, wherein at least one neural network function is configured to facilitate the UE deriving the likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE relative to one or more other positioning measurement features.

[0342]

[0285] Clause 17. A method of operating a base station (BS), comprising: obtaining at least one neural network function configured to facilitate a user equipment (UE) deriving a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, the at least one neural network function being dynamically generated based on machine learning associated with one or more historical measurement procedures; and transmitting the at least one neural network function to the UE.

[0343]

[0286] Clause 18. The method of clause 17, wherein at least one neural network function is dynamically generated at the BS or another network component.

[0344]

[0287] Clause 19. The method of clause 17 or 18, wherein at least one neural network function comprises a UE feature processing neural network function.

[0345]

[0288] Clause 20. The method of clause 19, wherein the at least one neural network function comprises at least one additional UE feature processing neural network function.

[0346]

[0289] Clause 21. A method as described in clause 19 or 20, wherein the UE feature processing neural network function is configured to derive likelihood based on at least one of clock drift in the UE, hardware group delay in the UE, a model of the UE, or a combination thereof.

[0347]

[0290] Clause 22. The method of any one of clauses 19 to 21, wherein at least one neural network function comprises one or more base station (BS) feature processing neural network functions.

[0348]

[0291] Clause 23. The method of clause 22, wherein the at least one neural network function further comprises one or more UE feature processing neural network functions.

[0349]

[0292] Clause 24. A method as described in Clause 22 or 23, wherein the one or more BS feature processing neural network functions are configured to derive likelihood based on at least one of the location of at least one BS, the downtilt of at least one BS, the transmit power of at least one BS, the clock synchronization error between two or more BSs, the clock drift of at least one BS, the hardware group delay of at least one BS, the Base Station Almanac (BSA) error associated with at least one BS, or any combination thereof.

[0350]

[0293] Clause 25. A method according to any one of clauses 17 to 24, wherein a candidate set of positioning estimates is implicitly indicated to the UE in association with at least one neural network function, or wherein a candidate set of positioning estimates is explicitly indicated to the UE in association with at least one neural network function.

[0351]

[0294] Clause 26. A method according to any one of clauses 17 to 25, wherein at least one neural network function is specific to a particular base station (BS) or group of BSs, carrier, location region, positioning measurement type or group of positioning measurement types, beam or group of beams, or any combination thereof.

[0352]

[0295] Clause 27. A method according to any one of clauses 17 to 26, wherein at least one neural network function is configured to facilitate the UE determining one or more of a wireless wide area network (WWAN) position estimate, a wireless local area network (WLAN) position estimate, a global navigation satellite system (GNSS) position estimate, a sensor-based position estimate, or any combination thereof.

[0353]

[0296] Clause 28. A method according to any one of clauses 17 to 27, wherein obtaining comprises generating at least one neural network function in the base station, or wherein obtaining comprises receiving at least one neural network function from a core network component or an external server.

[0354]

[0297] Clause 29. A user equipment (UE) comprising a memory, at least one transceiver, and at least one processor communicatively coupled to the memory and the at least one transceiver, wherein the at least one processor is configured to: obtain at least one neural network function configured to derive a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, the at least one neural network function being dynamically generated based on machine learning associated with one or more historical measurement procedures; obtain positioning measurement data associated with a location of the UE; and determine a positioning estimate for the UE based at least in part on the positioning measurement data and the at least one neural network function.

[0355]

[0298] Clause 30. The UE described in clause 29, wherein at least one neural network function comprises a UE feature processing neural network function.

[0356]

[0299] Clause 31. A UE as described in Clause 30, wherein the positioning measurement data comprises a set of positioning measurements at the UE, and determining comprises detecting a set of positioning measurement features based on the set of positioning measurements at the UE, and deriving a likelihood that the set of positioning measurement features is present in a candidate set of positioning estimates for the UE based at least in part on a UE feature processing neural network function.

[0357]

[0300] Clause 32. A UE as described in clause 30 or 31, wherein the at least one neural network function comprises at least one additional UE feature processing neural network function.

[0358]

[0301] Clause 33. A UE described in any one of clauses 30 to 32, wherein the UE feature processing neural network function is configured to derive likelihood based on at least one of clock drift in the UE, hardware group delay in the UE, a model of the UE, or a combination thereof.

[0359]

[0302] Clause 34. A UE as described in any one of clauses 29 to 33, wherein at least one neural network function comprises a base station (BS) feature processing neural network function.

[0360]

[0303] Clause 35. A UE as described in Clause 34, wherein the positioning measurement data comprises a set of positioning measurement features based on a set of positioning measurements at one or more BSs, and determining comprises deriving a likelihood that the set of positioning measurement features is present in a candidate set of positioning estimates for the UE based at least in part on a BS feature processing neural network function, wherein the positioning estimates for the UE are based in part on the derived likelihoods.

[0361]

[0304] Clause 36. The UE of clause 35, wherein the at least one neural network function comprises at least one additional BS feature processing neural network function.

[0362]

[0305] Clause 37. A UE described in any one of clauses 34 to 36, wherein the at least one neural network function further comprises a UE feature processing neural network function.

[0363]

[0306] Clause 38. A UE as described in Clause 37, wherein the positioning measurement data comprises a first set of positioning measurement features based on a first set of positioning measurements at one or more BSs and a second set of positioning measurement features based on a second set of positioning measurements at the UE, and further comprising deriving a likelihood that the first set and the second set of positioning measurement features are present in a candidate set of positioning estimates for the UE based at least in part on the UE feature processing neural network function and the BS feature processing neural network function, wherein the positioning estimates for the UE are based in part on the derived likelihoods.

[0364]

[0307] Clause 39. A UE described in any one of clauses 34 to 38, wherein the BS feature processing neural network function is configured to derive a likelihood based on at least one of the location of at least one BS, the downtilt of at least one BS, the transmit power of at least one BS, the clock synchronization error between two or more BSs, the clock drift of at least one BS, the hardware group delay of at least one BS, the base station almanac (BSA) error associated with at least one BS, or any combination thereof.

[0365]

[0308] Clause 40. A UE as described in any one of clauses 29 to 39, wherein a candidate set of positioning estimates is implicitly indicated to the UE in association with at least one neural network function, or wherein a candidate set of positioning estimates is explicitly indicated to the UE in association with at least one neural network function.

[0366]

[0309] Clause 41. A UE described in any one of clauses 29 to 40, wherein at least one neural network function is specific to a particular base station (BS) or group of BSs, carrier, location area, positioning measurement type or group of positioning measurement types, beam or group of beams, or any combination thereof.

[0367]

[0310] Clause 42. A UE as described in any one of clauses 29 to 41, wherein the positioning estimate comprises a wireless wide area network (WWAN) position estimate, a wireless local area network (WLAN) position estimate, a global navigation satellite system (GNSS) position estimate, a sensor-based position estimate, or any combination thereof.

[0368]

[0311] Clause 43. A UE as described in any one of clauses 29 to 42, wherein obtaining comprises receiving at least one neural network function from a base station, a server, or a combination thereof.

[0369]

[0312] Clause 44. A UE as described in any one of clauses 29 to 43, wherein at least one neural network function is configured to facilitate the UE deriving the likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE relative to one or more other positioning measurement features.

[0370]

[0313] Clause 45. A base station (BS) comprising a memory, at least one transceiver, and at least one processor communicatively coupled to the memory and the at least one transceiver, wherein the at least one processor is configured to: obtain at least one neural network function configured to facilitate a user equipment (UE) deriving a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, the at least one neural network function being dynamically generated based on machine learning associated with one or more historical measurement procedures; and transmit the at least one neural network function to the UE via the at least one transceiver.

[0371]

[0314] Clause 46. The BS of clause 45, wherein at least one neural network function is dynamically generated at the BS or another network component.

[0372]

[0315] Clause 47. The BS of clause 45 or 46, wherein at least one neural network function comprises a UE feature processing neural network function.

[0373]

[0316] Clause 48. The BS described in clause 47, wherein the at least one neural network function comprises at least one additional UE feature processing neural network function.

[0374]

[0317] Clause 49. A BS described in clause 47 or 48, wherein the UE feature processing neural network function is configured to derive likelihood based on at least one of clock drift in the UE, hardware group delay in the UE, a model of the UE, or a combination thereof.

[0375]

[0318] Clause 50. The BS described in any one of clauses 47 to 49, wherein at least one neural network function comprises one or more base station (BS) feature processing neural network functions.

[0376]

[0319] Clause 51. The BS described in clause 50, wherein the at least one neural network function further comprises one or more UE feature processing neural network functions.

[0377]

[0320] Clause 52. A BS as described in Clause 50 or 51, wherein one or more BS feature processing neural network functions are configured to derive likelihood based on at least one of the location of at least one BS, the downtilt of at least one BS, the transmit power of at least one BS, the clock synchronization error between two or more BSs, the clock drift of at least one BS, the hardware group delay of at least one BS, the base station almanac (BSA) error associated with at least one BS, or any combination thereof.

[0378]

[0321] Clause 53. A BS as described in any one of clauses 45 to 52, wherein a candidate set of positioning estimates is implicitly indicated to the UE in association with at least one neural network function, or wherein a candidate set of positioning estimates is explicitly indicated to the UE in association with at least one neural network function.

[0379]

[0322] Clause 54. A BS described in any one of clauses 45 to 53, wherein at least one neural network function is specific to a particular base station (BS) or group of BSs, carrier, location region, positioning measurement type or group of positioning measurement types, beam or group of beams, or any combination thereof.

[0380]

[0323] Clause 55. A BS as described in any one of clauses 45 to 54, wherein at least one neural network function is configured to facilitate the UE determining one or more of a wireless wide area network (WWAN) position estimate, a wireless local area network (WLAN) position estimate, a global navigation satellite system (GNSS) position estimate, a sensor-based position estimate, or any combination thereof.

[0381]

[0324] Clause 56. A BS as described in any one of clauses 45 to 55, wherein obtaining comprises generating at least one neural network function in the base station, or wherein obtaining comprises receiving at least one neural network function from a core network component or an external server.

[0382]

[0325] Clause 57. A user equipment (UE) comprising: means for obtaining at least one neural network function configured to derive a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, the at least one neural network function being dynamically generated based on machine learning associated with one or more historical measurement procedures; means for obtaining positioning measurement data associated with a location of the UE; and means for determining a positioning estimate for the UE based at least in part on the positioning measurement data and the at least one neural network function.

[0383]

[0326] Clause 58. The UE described in clause 57, wherein at least one neural network function comprises a UE feature processing neural network function.

[0384]

[0327] Clause 59. A UE as described in Clause 58, wherein the positioning measurement data comprises a set of positioning measurements at the UE, and wherein determining comprises means for detecting a set of positioning measurement features based on the set of positioning measurements at the UE, and means for deriving a likelihood that the set of positioning measurement features is present in a candidate set of positioning estimates for the UE based at least in part on a UE feature processing neural network function.

[0385]

[0328] Clause 60. A UE as described in clause 58 or 59, wherein the at least one neural network function comprises at least one additional UE feature processing neural network function.

[0386]

[0329] Clause 61. A UE described in any one of clauses 58 to 60, wherein the UE feature processing neural network function is configured to derive likelihood based on at least one of clock drift in the UE, hardware group delay in the UE, a model of the UE, or a combination thereof.

[0387]

[0330] Clause 62. A UE as described in any one of clauses 57 to 61, wherein at least one neural network function comprises a base station (BS) feature processing neural network function.

[0388]

[0331] Clause 63. A UE as described in Clause 62, wherein the positioning measurement data comprises a set of positioning measurement features based on a set of positioning measurements at one or more BSs, and wherein determining comprises means for deriving a likelihood that the set of positioning measurement features is present in a candidate set of positioning estimates for the UE based at least in part on a BS feature processing neural network function, wherein the positioning estimate for the UE is based in part on the derived likelihood.

[0389]

[0332] Clause 64. The UE described in clause 63, wherein the at least one neural network function comprises at least one additional BS feature processing neural network function.

[0390]

[0333] Clause 65. A UE described in any one of clauses 62 to 64, wherein at least one neural network function further comprises a UE feature processing neural network function.

[0391]

[0334] Clause 66. A UE as described in Clause 65, wherein the positioning measurement data comprises a first set of positioning measurement features based on a first set of positioning measurements at one or more BSs and a second set of positioning measurement features based on a second set of positioning measurements at the UE, and further comprising means for deriving a likelihood that the first set and the second set of positioning measurement features are present in a candidate set of positioning estimates for the UE based at least in part on the UE feature processing neural network function and the BS feature processing neural network function, wherein the positioning estimates for the UE are based in part on the derived likelihoods.

[0392]

[0335] Clause 67. A UE described in any one of clauses 62 to 66, wherein the BS feature processing neural network function is configured to derive a likelihood based on at least one of the location of at least one BS, the downtilt of at least one BS, the transmit power of at least one BS, the clock synchronization error between two or more BSs, the clock drift of at least one BS, the hardware group delay of at least one BS, the base station almanac (BSA) error associated with at least one BS, or any combination thereof.

[0393]

[0336] Clause 68. A UE described in any one of clauses 57 to 67, wherein a candidate set of positioning estimates is implicitly indicated to the UE in association with at least one neural network function, or wherein a candidate set of positioning estimates is explicitly indicated to the UE in association with at least one neural network function.

[0394]

[0337] Clause 69. A UE described in any one of clauses 57 to 68, wherein at least one neural network function is specific to a particular base station (BS) or group of BSs, carrier, location area, positioning measurement type or group of positioning measurement types, beam or group of beams, or any combination thereof.

[0395]

[0338] Clause 70. A UE described in any one of clauses 57 to 69, wherein the positioning estimate comprises a wireless wide area network (WWAN) position estimate, a wireless local area network (WLAN) position estimate, a global navigation satellite system (GNSS) position estimate, a sensor-based position estimate, or any combination thereof.

[0396]

[0339] Clause 71. A UE as described in any one of clauses 57 to 70, wherein obtaining comprises receiving at least one neural network function from a base station, a server, or a combination thereof.

[0397]

[0340] Clause 72. A UE as described in any one of clauses 57 to 71, wherein at least one neural network function is configured to facilitate the UE deriving the likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE relative to one or more other positioning measurement features.

[0398]

[0341] Clause 73. A base station (BS), comprising: means for obtaining at least one neural network function configured to facilitate a user equipment (UE) deriving a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, the at least one neural network function being dynamically generated based on machine learning associated with one or more historical measurement procedures; and means for transmitting the at least one neural network function to the UE.

[0399]

[0342] Clause 74. The BS of clause 73, wherein at least one neural network function is dynamically generated at the BS or another network component.

[0400]

[0343] Clause 75. The BS described in clause 73 or 74, wherein at least one neural network function comprises a UE feature processing neural network function.

[0401]

[0344] Clause 76. The BS described in Clause 75, wherein the at least one neural network function comprises at least one additional UE feature processing neural network function.

[0402]

[0345] Clause 77. A BS as described in clause 75 or 76, wherein the UE feature processing neural network function is configured to derive likelihood based on at least one of clock drift in the UE, hardware group delay in the UE, a model of the UE, or a combination thereof.

[0403]

[0346] Clause 78. The BS described in any one of clauses 75 to 77, wherein at least one neural network function comprises one or more base station (BS) feature processing neural network functions.

[0404]

[0347] Clause 79. The BS described in Clause 78, wherein the at least one neural network function further comprises one or more UE feature processing neural network functions.

[0405]

[0348] Clause 80. A BS as described in Clause 78 or 79, wherein the one or more BS feature processing neural network functions are configured to derive likelihood based on at least one of the location of at least one BS, the downtilt of at least one BS, the transmit power of at least one BS, the clock synchronization error between two or more BSs, the clock drift of at least one BS, the hardware group delay of at least one BS, the Base Station Almanac (BSA) error associated with at least one BS, or any combination thereof.

[0406]

[0349] Clause 81. A BS described in any one of clauses 73 to 80, wherein a candidate set of positioning estimates is implicitly indicated to the UE in association with at least one neural network function, or wherein a candidate set of positioning estimates is explicitly indicated to the UE in association with at least one neural network function.

[0407]

[0350] Clause 82. A BS described in any one of clauses 73 to 81, wherein at least one neural network function is specific to a particular base station (BS) or group of BSs, carrier, location region, positioning measurement type or group of positioning measurement types, beam or group of beams, or any combination thereof.

[0408]

[0351] Clause 83. A BS as described in any one of clauses 73 to 82, wherein at least one neural network function is configured to facilitate the UE determining one or more of a wireless wide area network (WWAN) position estimate, a wireless local area network (WLAN) position estimate, a global navigation satellite system (GNSS) position estimate, a sensor-based position estimate, or any combination thereof.

[0409]

[0352] Clause 84. A BS as described in any one of clauses 73 to 83, wherein obtaining comprises generating at least one neural network function in the base station, or wherein obtaining comprises receiving at least one neural network function from a core network component or an external server.

[0410]

[0353] Clause 85. A non-transitory computer-readable medium storing computer-executable instructions that, when executed by a user equipment (UE), cause the UE to: obtain at least one neural network function configured to derive a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, the at least one neural network function being dynamically generated based on machine learning associated with one or more historical measurement procedures; obtain positioning measurement data associated with a location of the UE; and determine a positioning estimate for the UE based at least in part on the positioning measurement data and the at least one neural network function.

[0411]

[0354] Clause 86. The non-transitory computer-readable medium of clause 85, wherein at least one neural network function comprises a UE feature processing neural network function.

[0412]

[0355] Clause 87. A non-transitory computer-readable medium as described in Clause 86, wherein the positioning measurement data comprises a set of positioning measurements at the UE, and determining comprises detecting a set of positioning measurement features based on the set of positioning measurements at the UE, and deriving a likelihood that the set of positioning measurement features is present in a candidate set of positioning estimates for the UE based at least in part on a UE feature processing neural network function.

[0413]

[0356] Clause 88. A non-transitory computer-readable medium as described in clause 86 or 87, wherein the at least one neural network function comprises at least one additional UE feature processing neural network function.

[0414]

[0357] Clause 89. A non-transitory computer-readable medium described in any one of clauses 86 to 88, wherein the UE feature processing neural network function is configured to derive likelihood based on at least one of clock drift in the UE, hardware group delay in the UE, a model of the UE, or a combination thereof.

[0415]

[0358] Clause 90. The non-transitory computer-readable medium of any one of clauses 85 to 89, wherein at least one neural network function comprises a base station (BS) feature processing neural network function.

[0416]

[0359] Clause 91. A non-transitory computer-readable medium as described in Clause 90, wherein the positioning measurement data comprises a set of positioning measurement features based on a set of positioning measurements at one or more BSs, and determining comprises deriving a likelihood that the set of positioning measurement features is present in a candidate set of positioning estimates for the UE based at least in part on a BS feature processing neural network function, wherein the positioning estimates for the UE are based in part on the derived likelihoods.

[0417]

[0360] Clause 92. The non-transitory computer-readable medium of clause 91, wherein the at least one neural network function comprises at least one additional BS feature processing neural network function.

[0418]

[0361] Clause 93. A non-transitory computer-readable medium described in any one of clauses 90 to 92, wherein at least one neural network function further comprises a UE feature processing neural network function.

[0419]

[0362] Clause 94. A non-transitory computer-readable medium as described in Clause 93, wherein the positioning measurement data comprises a first set of positioning measurement features based on a first set of positioning measurements at one or more BSs and a second set of positioning measurement features based on a second set of positioning measurements at the UE, and further comprising deriving, based at least in part on the UE feature processing neural network function and the BS feature processing neural network function, a likelihood that the first set and the second set of positioning measurement features are present in a candidate set of positioning estimates for the UE, wherein the positioning estimates for the UE are based in part on the derived likelihoods.

[0420]

[0363] Clause 95. A non-transitory computer-readable medium described in any one of clauses 90 to 94, wherein the BS feature processing neural network function is configured to derive a likelihood based on at least one of the location of at least one BS, the downtilt of at least one BS, the transmit power of at least one BS, the clock synchronization error between two or more BSs, the clock drift of at least one BS, the hardware group delay of at least one BS, the Base Station Almanac (BSA) error associated with at least one BS, or any combination thereof.

[0421]

[0364] Clause 96. A non-transitory computer-readable medium described in any one of clauses 85 to 95, wherein a candidate set of positioning estimates is implicitly indicated to the UE in association with at least one neural network function, or wherein a candidate set of positioning estimates is explicitly indicated to the UE in association with at least one neural network function.

[0422]

[0365] Clause 97. A non-transitory computer-readable medium described in any one of clauses 85 to 96, wherein at least one neural network function is specific to a particular base station (BS) or group of BSs, carrier, location region, positioning measurement type or group of positioning measurement types, beam or group of beams, or any combination thereof.

[0423]

[0366] Clause 98. A non-transitory computer-readable medium described in any one of clauses 85 to 97, wherein the positioning estimate comprises a wireless wide area network (WWAN) position estimate, a wireless local area network (WLAN) position estimate, a global navigation satellite system (GNSS) position estimate, a sensor-based position estimate, or any combination thereof.

[0424]

[0367] Clause 99. A non-transitory computer-readable medium described in any one of clauses 85 to 98, wherein obtaining comprises receiving at least one neural network function from a base station, a server, or a combination thereof.

[0425]

[0368] Clause 100. A non-transitory computer-readable medium described in any one of clauses 85 to 99, wherein at least one neural network function is configured to facilitate the UE deriving a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE relative to one or more other positioning measurement features.

[0426]

[0369] Clause 101. A non-transitory computer-readable medium storing computer-executable instructions, which, when executed by a base station (BS), cause the BS to: obtain at least one neural network function configured to facilitate a user equipment (UE) deriving a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, the at least one neural network function being dynamically generated based on machine learning associated with one or more historical measurement procedures; and transmit the at least one neural network function to the UE.

[0427]

[0370] Clause 102. The non-transitory computer-readable medium of clause 101, wherein at least one neural network function is dynamically generated at a BS or another network component.

[0428]

[0371] Clause 103. The non-transitory computer-readable medium of clause 101 or 102, wherein at least one neural network function comprises a UE feature processing neural network function.

[0429]

[0372] Clause 104. The non-transitory computer-readable medium of clause 103, wherein the at least one neural network function comprises at least one additional UE feature processing neural network function.

[0430]

[0373] Clause 105. A non-transitory computer-readable medium described in clause 103 or 104, wherein the UE feature processing neural network function is configured to derive likelihood based on at least one of clock drift in the UE, hardware group delay in the UE, a model of the UE, or a combination thereof.

[0431]

[0374] Clause 106. A non-transitory computer-readable medium described in any one of clauses 103 to 105, wherein at least one neural network function comprises one or more base station (BS) feature processing neural network functions.

[0432]

[0375] Clause 107. The non-transitory computer-readable medium of clause 106, wherein the at least one neural network function further comprises one or more UE feature processing neural network functions.

[0433]

[0376] Clause 108. A non-transitory computer-readable medium as described in Clause 106 or 107, wherein the one or more BS feature processing neural network functions are configured to derive a likelihood based on at least one of the location of at least one BS, the downtilt of at least one BS, the transmit power of at least one BS, the clock synchronization error between two or more BSs, the clock drift of at least one BS, the hardware group delay of at least one BS, the Base Station Almanac (BSA) error associated with at least one BS, or any combination thereof.

[0434]

[0377] Clause 109. A non-transitory computer-readable medium described in any one of clauses 101 to 108, wherein a candidate set of positioning estimates is implicitly indicated to the UE in association with at least one neural network function, or wherein a candidate set of positioning estimates is explicitly indicated to the UE in association with at least one neural network function.

[0435]

[0378] Clause 110. A non-transitory computer-readable medium described in any one of clauses 101 to 109, wherein at least one neural network function is specific to a particular base station (BS) or group of BSs, carrier, location region, positioning measurement type or group of positioning measurement types, beam or group of beams, or any combination thereof.

[0436]

[0379] Clause 111. A non-transitory computer-readable medium described in any one of clauses 101 to 110, wherein at least one neural network function is configured to facilitate the UE determining one or more of a wireless wide area network (WWAN) position estimate, a wireless local area network (WLAN) position estimate, a global navigation satellite system (GNSS) position estimate, a sensor-based position estimate, or any combination thereof.

[0437]

[0380] Clause 112. A non-transitory computer-readable medium described in any one of clauses 101 to 111, wherein obtaining comprises generating at least one neural network function in a base station, or wherein obtaining comprises receiving at least one neural network function from a core network component or an external server.

[0438] Those skilled in the art will appreciate that information and signals may be represented using any of a variety of different technologies and techniques. For example, the data, instructions, commands, information, signals, bits, symbols, and chips that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

[0439]

[0382] Furthermore, those skilled in the art will appreciate that the various illustrative logic blocks, modules, circuits, and algorithm steps described in connection with the aspects disclosed herein may be implemented as electronic hardware, computer software, or a combination of both. To clearly illustrate this interchangeability between hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the particular application and design constraints imposed on the overall system. Those skilled in the art may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

[0440] The various example logic blocks, modules, and circuits described in connection with aspects disclosed herein may be implemented or performed using a general-purpose processor, a DSP, an ASIC, an FPGA, or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but alternatively, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.

[0441] The methods, sequences, and / or algorithms described in connection with the aspects disclosed herein may be embodied directly in hardware, in software modules executed by a processor, or in a combination of the two. The software modules may reside in random access memory (RAM), flash memory, read-only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such that the processor can read information from, and write information to, the storage medium. Alternatively, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal (e.g., UE). Alternatively, the processor and the storage medium may reside as discrete components in the user terminal.

[0442] In one or more exemplary aspects, the functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media, including any medium that facilitates transfer of a computer program from one place to another. Storage media may be any available medium that can be accessed by a computer. By way of example, and not limitation, such computer-readable media may comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. Also, any connection is properly termed a computer-readable medium. For example, if software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of medium. As used herein, disk and disc include compact discs (CDs), laser discs, optical discs, digital versatile discs (DVDs), floppy discs, and Blu-ray discs, where disks typically reproduce data magnetically and discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0443]

[0386] While the above disclosure sets forth exemplary embodiments of the present disclosure, it should be noted that various changes and modifications can be made herein without departing from the scope of the present disclosure, as defined by the appended claims. The functions, steps, and / or actions of the method claims in accordance with the embodiments of the present disclosure described herein need not be performed in any particular order. Furthermore, although elements of the present disclosure may be described or claimed in the singular, the plural is contemplated unless limitation to the singular is explicitly stated. The inventions described in the claims of the present application as originally filed are set forth below. [C1] 1. A method of operating a user equipment (UE), comprising: obtaining at least one neural network function configured to derive a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, wherein the at least one neural network function is dynamically generated based on machine learning associated with one or more historical measurement procedures; obtaining positioning measurement data relating to a location of the UE; determining a positioning estimate for the UE based at least in part on the positioning measurement data and the at least one neural network function; A method comprising: [C2] The method of C1, wherein the at least one neural network function comprises a UE feature processing neural network function. [C3] the positioning measurement data comprises a set of positioning measurements at the UE; The determining step comprises: Detecting a set of positioning measurement features based on the set of positioning measurements at the UE; and deriving a likelihood that the set of positioning measurement features is present in the candidate set of positioning estimates for the UE based at least in part on the UE feature processing neural network function; the positioning estimate for the UE is based in part on the derived likelihood. The method described in C2. [C4] The method of C2, wherein the at least one neural network function comprises at least one additional UE feature processing neural network function. [C5] The UE feature processing neural network function: clock drift at the UE; hardware group delay at the UE; UE model, or combinations of these, The method of claim 2, configured to derive the likelihood based on at least one of: [C6] The method of C1, wherein the at least one neural network function comprises a base station (BS) feature processing neural network function. [C7] the positioning measurement data comprises a set of positioning measurement features based on a set of positioning measurements at one or more BSs; The determining step comprises: deriving a likelihood that the set of positioning measurement features is present in the candidate set of positioning estimates for the UE based at least in part on the BS feature processing neural network function; Equipped with the positioning estimate for the UE is based in part on the derived likelihood. The method described in C6. [C8] The method of C7, wherein the at least one neural network function comprises at least one additional BS feature processing neural network function. [C9] The method of C6, wherein the at least one neural network function further comprises a UE feature processing neural network function. [C10] the positioning measurement data comprises a first set of positioning measurement features based on a first set of positioning measurements at one or more BSs and a second set of positioning measurement features based on a second set of positioning measurements at the UE; deriving a likelihood that the first and second sets of positioning measurement features are present in the candidate set of positioning estimates for the UE based at least in part on the UE feature processing neural network function and the BS feature processing neural network function; the positioning estimate for the UE is based in part on the derived likelihood. The method described in C9. [C11] The BS feature processing neural network function is: Location of at least one BS, downtilt of said at least one BS; the transmit power of the at least one BS; clock synchronization error between two or more BSs; a clock drift of the at least one BS; a hardware group delay of the at least one BS; a Base Station Almanac (BSA) error associated with the at least one BS; or any combination thereof, deriving the likelihood based on at least one of: [C12] the candidate set of positioning estimates is implicitly indicated to the UE in association with the at least one neural network function; or the candidate set of positioning estimates is explicitly indicated to the UE in association with the at least one neural network function. The method described in C1. [C13] The at least one neural network function is a specific base station (BS) or group of BSs, Career, Location area, a positioning measurement type or a group of positioning measurement types, a beam or group of beams, or any combination thereof, The method according to claim 1, wherein the method is specific to [C14] The position estimate is Wireless Wide Area Network (WWAN) position estimates, Wireless Local Area Network (WLAN) location estimates, Global Navigation Satellite System (GNSS) position estimates, a sensor-based position estimate, or any combination thereof, The method of claim C1, comprising: [C15] The method of C1, wherein the obtaining comprises receiving the at least one neural network function from a base station, a server, or a combination thereof. [C16] The method of claim 1, wherein the at least one neural network function is configured to facilitate the UE deriving the likelihood that the at least one set of positioning measurement features is present in the candidate set of positioning estimates for the UE relative to one or more other positioning measurement features. [C17] 1. A method of operating a base station (BS), comprising: obtaining at least one neural network function configured to facilitate a user equipment (UE) deriving a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, the at least one neural network function being dynamically generated based on machine learning associated with one or more historical measurement procedures; transmitting the at least one neural network function to the UE; A method comprising: [C18] The method of C17, wherein the at least one neural network function is dynamically generated at the BS or another network component. [C19] The method of C17, wherein the at least one neural network function comprises a UE feature processing neural network function. [C20] The method of C19, wherein the at least one neural network function comprises at least one additional UE feature processing neural network function. [C21] The UE feature processing neural network function: clock drift at the UE; hardware group delay at the UE; UE model, or combinations of these, deriving the likelihood based on at least one of: [C22] The method of C19, wherein the at least one neural network function comprises one or more base station (BS) feature processing neural network functions. [C23] The method of C22, wherein the at least one neural network function further comprises one or more UE feature processing neural network functions. [C24] The one or more BS feature processing neural network functions include: Location of at least one BS, downtilt of said at least one BS; the transmit power of the at least one BS; clock synchronization error between two or more BSs; a clock drift of the at least one BS; a hardware group delay of the at least one BS; a Base Station Almanac (BSA) error associated with the at least one BS; or any combination thereof, The method of claim 22, configured to derive the likelihood based on at least one of: [C25] the candidate set of positioning estimates is implicitly indicated to the UE in association with the at least one neural network function; or the candidate set of positioning estimates is explicitly indicated to the UE in association with the at least one neural network function. The method described in C17. [C26] The at least one neural network function is a specific base station (BS) or group of BSs, Career, Location area, a positioning measurement type or a group of positioning measurement types, a beam or group of beams, or any combination thereof, The method according to C17, which is specific to [C27] The at least one neural network function is configured by the UE: Wireless Wide Area Network (WWAN) position estimates, Wireless Local Area Network (WLAN) location estimates, Global Navigation Satellite System (GNSS) position estimates, a sensor-based position estimate, or any combination thereof, configured to facilitate determining one or more of: The method described in C17. [C28] said obtaining comprising generating said at least one neural network function at said base station; or obtaining comprises receiving the at least one neural network function from a core network component or an external server. The method described in C17. [C29] Memory and at least one transceiver; at least one processor communicatively coupled to the memory and the at least one transceiver; 1. A user equipment (UE) comprising: obtaining at least one neural network function configured to derive a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, wherein the at least one neural network function is dynamically generated based on machine learning associated with one or more historical measurement procedures; obtaining positioning measurement data relating to a location of the UE; determining a positioning estimate for the UE based at least in part on the positioning measurement data and the at least one neural network function; A user equipment (UE) configured to perform the following: [C30] Memory and at least one transceiver; at least one processor communicatively coupled to the memory and the at least one transceiver; a base station (BS), wherein the at least one processor obtaining at least one neural network function configured to facilitate a user equipment (UE) deriving a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, the at least one neural network function being dynamically generated based on machine learning associated with one or more historical measurement procedures; transmitting the at least one neural network function to the UE via the at least one transceiver; A base station (BS) configured to perform the above.

Claims

1. 1. A method of operating a user equipment (UE), comprising: receiving at least one neural network function from a base station, a server, or a combination thereof, wherein the at least one neural network function is configured to derive a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, the at least one neural network function being dynamically generated based on machine learning associated with one or more historical measurement procedures, and the at least one set of positioning measurement features comprising channel estimate information based on an estimate of a channel response associated with a reference signal; obtaining positioning measurement data related to a location of the UE, the positioning measurement data comprising the at least one set of positioning measurement features; determining a positioning estimate for the UE based at least in part on the positioning measurement data and the at least one neural network function; A method comprising:

2. the at least one neural network function comprises a UE feature processing neural network function; the positioning measurement data comprises a set of positioning measurements at the UE; The determining step comprises: Detecting a set of positioning measurement features based on the set of positioning measurements at the UE; deriving a likelihood that the set of positioning measurement features is present in the candidate set of positioning estimates for the UE based at least in part on the UE feature processing neural network function; the positioning estimate for the UE is based in part on the derived likelihood; The UE feature processing neural network function is: clock drift at the UE; hardware group delay at the UE; the model of the UE, or combinations of these, configured to derive the likelihood based on at least one of The method of claim 1.

3. the at least one neural network function comprises a base station (BS) feature processing neural network function; the positioning measurement data comprises a set of positioning measurement features based on a set of positioning measurements at one or more BSs; The determining step comprises: deriving a likelihood that the set of positioning measurement features is present in the candidate set of positioning estimates for the UE based at least in part on the BS feature processing neural network function; Equipped with the positioning estimate for the UE is based in part on the derived likelihood. The method of claim 1.

4. the at least one neural network function further comprises a UE feature processing neural network function; the positioning measurement data comprises a first set of positioning measurement features based on a first set of positioning measurements at one or more BSs and a second set of positioning measurement features based on a second set of positioning measurements at the UE; deriving a likelihood that the first and second sets of positioning measurement features are present in the candidate set of positioning estimates for the UE based at least in part on the UE feature processing neural network function and the BS feature processing neural network function; the positioning estimate for the UE is based in part on the derived likelihood. The method of claim 3.

5. The BS feature processing neural network function is: the location of at least one BS; downtilt of the at least one BS; the transmit power of the at least one BS; clock synchronization error between two or more BSs; clock drift of said at least one BS; the hardware group delay of the at least one BS; a Base Station Almanac (BSA) error associated with the at least one BS; or any combination thereof, The method of claim 3 , configured to derive the likelihood based on at least one of:

6. 2. The method of claim 1, wherein the at least one neural network function is configured to derive, for the UE, the likelihood that the at least one set of positioning measurement features is present in the candidate set of positioning estimates for the UE relative to one or more other positioning measurement features.

7. 1. A method of operating a base station (BS), comprising: obtaining at least one neural network function for a user equipment (UE) configured to derive a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, the at least one neural network function being dynamically generated based on machine learning associated with one or more historical measurement procedures, and the at least one set of positioning measurement features comprising channel estimate information based on an estimate of a channel response associated with a reference signal; transmitting the at least one neural network function to the UE; A method comprising:

8. The method of claim 7 , wherein the at least one neural network function is dynamically generated at the BS or another network element.

9. the at least one neural network function comprises a UE feature processing neural network function; the at least one neural network function comprises at least one additional UE feature processing neural network function; The UE feature processing neural network function is: clock drift at the UE; hardware group delay at the UE; the model of the UE, or combinations of these, configured to derive the likelihood based on at least one of The method of claim 7.

10. the at least one neural network function comprises one or more base station (BS) feature processing neural network functions; the at least one neural network function further comprises one or more UE feature processing neural network functions; The one or more BS feature processing neural network functions include: the location of at least one BS; downtilt of the at least one BS; the transmit power of the at least one BS; clock synchronization error between two or more BSs; clock drift of said at least one BS; the hardware group delay of the at least one BS; a Base Station Almanac (BSA) error associated with the at least one BS; or any combination thereof, configured to derive the likelihood based on at least one of 10. The method of claim 9.

11. the candidate set of positioning estimates is provided to the UE in association with the at least one neural network function; or the candidate set of positioning estimates is indicated to the UE via signaling in association with the at least one neural network function.

10. The method of claim 1 or 8.

12. The at least one neural network function is a particular base station (BS) or group of BSs; Career, Location area, a positioning measurement type or a group of positioning measurement types, a beam or group of beams, or any combination thereof, The method of claim 1 or 8, wherein the method is specific to

13. said obtaining comprising generating said at least one neural network function at said base station; or obtaining comprises receiving the at least one neural network function from a core network component or an external server. The method of claim 7.

14. Memory and at least one transceiver; at least one processor communicatively coupled to the memory and the at least one transceiver; 1. A user equipment (UE) comprising: receiving at least one neural network function from a base station, a server, or a combination thereof, wherein the at least one neural network function is configured to derive a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, the at least one neural network function being dynamically generated based on machine learning associated with one or more historical measurement procedures, and the at least one set of positioning measurement features comprising channel estimate information based on an estimate of a channel response associated with a reference signal; obtaining positioning measurement data related to a location of the UE, the positioning measurement data comprising the at least one set of positioning measurement features; determining a positioning estimate for the UE based at least in part on the positioning measurement data and the at least one neural network function; configured to: User Equipment (UE).

15. Memory and at least one transceiver; at least one processor communicatively coupled to the memory and the at least one transceiver; 1. A base station (BS) comprising: obtaining, for a user equipment (UE), at least one neural network function configured to derive a likelihood that at least one set of positioning measurement features is present in a candidate set of positioning estimates for the UE, the at least one neural network function being dynamically generated based on machine learning associated with one or more historical measurement procedures, the at least one set of positioning measurement features comprising channel estimate information based on estimates of responses associated with a reference signal; transmitting the at least one neural network function to the UE via the at least one transceiver; a base station (BS) configured to:

Images