Space aircraft geometry based machine learning for classification and location estimation

Abstract

Aspects presented herein may enable a positioning device or positioning entity to estimate the positioning of a UE based on a machine learning (ML) classifier and an SV geometry. In one aspect, a UE or a location server determines, for each SV in a set of SVs, at least one geometric orientation relative to the UE. The UE or the location server determines a relative PR weight for each SV in the set of SVs based on an ML classifier and a determined geometric orientation relative to the UE for each SV in at least a subset of the set of SVs. The UE or the location server estimates the location of the UE based on the PR measurement for each SV of the set of SV and the relative PR weight for each SV of the set of SV.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of U.S. non-provisional patent application serial number 17 / 804,849, filed on May 31, 2022, entitled “SPACE VEHICLE GEOMETRY BASED MACHINE LEARNING FOR MEASUREMENT ERROR DETECTION AND CLASSIFICATION,” which is expressly incorporated herein by reference in its entirety. Technical Field

[0003] The present disclosure relates generally to positioning systems, and more particularly to machine learning related positioning. Background Art

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

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

[0006] A simplified summary of one or more aspects is presented below to provide a basic understanding of these aspects. This summary is not an extensive review of all contemplated aspects. This summary is neither intended to identify key or important elements of all aspects, nor to describe the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to a more detailed description presented later.

[0007] In one aspect of the present disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus determines at least one geometric orientation relative to a user equipment (UE) for each SV in a set of space vehicles (SVs). The apparatus determines a relative pseudorange (PR) weight for each SV in the set of SVs based on a machine learning (ML) classifier and the geometric orientation relative to the UE determined for each SV in at least one subset of the set of SVs. The apparatus estimates the positioning of the UE based on the PR measurement of each SV in the set of SVs and the relative PR weight of each SV in the set of SVs.

[0008] To achieve the aforementioned and related purposes, one or more aspects include the features fully described below and particularly pointed out in the claims. The following description and the accompanying drawings set forth in detail some exemplary features of one or more aspects. However, these features are only indicative of only some of the various ways in which the principles of the various aspects can be employed. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 is a diagram illustrating an example of a wireless communication system and an access network.

[0010] Figure 2A is a diagram illustrating an example of a first frame according to various aspects of the present disclosure.

[0011] Figure 2B is a diagram illustrating an example of DL channels within a subframe according to various aspects of the present disclosure.

[0012] Figure 2C is a diagram illustrating an example of a second frame according to various aspects of the present disclosure.

[0013] Figure 2D is a diagram illustrating an example of UL channels within a subframe according to various aspects of the present disclosure.

[0014] Figure 3 is a diagram illustrating an example of a base station and a user equipment (UE) in an access network.

[0015] Figure 4 is a diagram illustrating an example of UE positioning based on reference signal measurement.

[0016] Figure 5 is a diagram illustrating an example of global navigation satellite system (GNSS) positioning according to various aspects of the present disclosure.

[0017] Figure 6 is a diagram illustrating an example of non-line-of-sight (NLOS) GNSS measurements in an urban area in accordance with various aspects of the present disclosure.

[0018] Figure 7 is a diagram of an example architecture illustrating a functional framework of RAN intelligence implemented through data collection according to various aspects of the present disclosure.

[0019] Fig. 8A is a diagram illustrating example machine learning (ML) training for a classifier capable of classifying GNSS pseudorange (PR) measurements in accordance with various aspects of the present disclosure.

[0020] Figure 8B is a diagram illustrating example ML inference for an ML classifier capable of classifying GNSS PR measurements in accordance with various aspects of the present disclosure.

[0021] Fig. 9 is a diagram illustrating example space vehicle (SV) geometry in accordance with various aspects of the present disclosure.

[0022] Fig.10 is a diagram illustrating example ML training based on a graph convolutional network (GCN) according to various aspects of the present disclosure.

[0023] Fig.11 is a diagram illustrating an example architecture of a multi-layer perceptron (MLP) based near-GCN classifier according to various aspects of the present disclosure.

[0024] Fig.12 is a diagram illustrating an example of a horizontal error cumulative distribution function (CDF) for an MLP-based ML classifier and a GCN-based ML classifier according to various aspects of the present disclosure.

[0025] Fig.13 is a diagram illustrating examples of receiver operating characteristics of an MLP-based ML classifier and a GCN-based ML classifier according to various aspects of the present disclosure.

[0026] Fig.14 is a diagram illustrating an example of known and unknown parameters of a GNSS device during a warm start according to various aspects of the present disclosure.

[0027] Fig.15 is a diagram illustrating an example of identifying a location of a GNSS device based on a positioning grid method according to various aspects of the present disclosure.

[0028] Fig.16 is a diagram illustrating an example ML model for inferring whether a grid point is close to an actual position of a GNSS device in accordance with various aspects of the present disclosure.

[0029] Fig.17 A flow chart of a wireless communication method.

[0030] Fig.18 are diagrams illustrating examples of hardware implementations of example devices and / or network entities. DETAILED DESCRIPTION

[0031] Various aspects presented herein can improve the performance and accuracy of GNSS-based positioning. Various aspects presented herein provide an ML model that utilizes SV geometry and raw GNSS observables to classify GNSS PR measurements in terms of relative NLOS errors (e.g., excess delay). Based on the ML classification, a GNSS device (e.g., UE or location server) can determine appropriate weights for PR measurements in a GNSS positioning estimator (e.g., weighted least squares (WLS), Kalman filter (KF), etc.).

[0032] The detailed description set forth below in conjunction with the accompanying drawings is a description of various configurations and does not represent the only configurations with which the concepts described herein can be practiced. In order to provide a thorough understanding of the various concepts, the specific embodiments include specific details. However, these concepts can be practiced without these specific details. In some instances, well-known structures and components are shown in block diagram form to avoid obscuring these concepts.

[0033] Several aspects of the telecommunication system are also presented with reference to various apparatus and methods. These apparatus and methods are described in the following detailed description and illustrated in the accompanying drawings by various blocks, components, circuits, processes, algorithms, etc. (collectively referred to as "elements"). These elements can be implemented using electronic hardware, computer software, or any combination thereof. Whether these elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system.

[0034] As an example, an element or any part of an element or any combination of elements can be implemented as a "processing system", which includes one or more processors. The example of a processor includes a microprocessor, a microcontroller, a graphics processing unit (GPU), a central processing unit (CPU), an application processor, a digital signal processor (DSP), a reduced instruction set computing (RISC) processor, a system on a chip (SoC), a baseband processor, a field programmable gate array (FPGA), a programmable logic device (PLD), a state machine, a gate logic piece, a discrete hardware circuit and other suitable hardware configured to perform various functionalities described throughout the present disclosure. One or more processors in a processing system can execute software. Whether referred to as software, firmware, middleware, microcode, hardware description language or other terms, software should be broadly interpreted as meaning an instruction, an instruction set, a code, a code segment, a program code, a program, a subroutine, a software component, an application, a software application, a software package, a routine, a subroutine, an object, an executable, a thread of execution, a process, a function or any combination thereof.

[0035] Therefore, in one or more example aspects, specific implementations and / or use cases, the described functions may be implemented with hardware, software, or any combination thereof. If implemented with software, the functions may be stored or encoded as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media. Storage media may be any available medium that can be accessed by a computer. By way of example, such computer-readable media may include random access memory (RAM), read-only memory (ROM), electrically erasable programmable ROM (EEPROM), optical disk storage, magnetic disk storage, other magnetic storage devices, combinations of these types of computer-readable media, or any other medium that can be used to store computer-executable code in the form of instructions or data structures that can be accessed by a computer.

[0036] Although various aspects, specific implementations and / or use cases are described in this application by the illustration of some examples, additional or different aspects, specific implementations and use cases may be generated in many different arrangements and scenarios. The various aspects, specific implementations and / or use cases described herein can be implemented across many different platform types, devices, systems, shapes, sizes and packaging arrangements. For example, aspects, specific implementations and / or use cases can be generated via integrated chip specific implementations and other devices based on non-module components (e.g., end-user equipment, vehicles, communication equipment, computing equipment, industrial equipment, retail / purchase equipment, medical equipment, artificial intelligence (AI) enabled devices, etc.). Although some examples may be specifically for use cases or applications, or may not be specifically for use cases or applications, the described examples may have a wide range of applicability. Aspects, specific implementations and / or use cases may be in the range from chip-level or modular components to non-modular, non-chip-level specific implementations, and further to the range of aggregated, distributed or original equipment manufacturer (OEM) devices or systems in conjunction with one or more technologies herein. In some practical environments, the equipment in conjunction with the various aspects and features described may also include additional components and features for implementing and practicing the various aspects claimed and described. For example, the transmission and reception of wireless signals necessarily include multiple components for analog and digital purposes (e.g., hardware components including antennas, RF chains, power amplifiers, modulators, buffers, processors, interleavers, adders / accumulators, etc.) The techniques described herein can be practiced in a wide variety of devices of various sizes, shapes, and configurations, chip-level components, systems, distributed arrangements, aggregated or disaggregated components, end-user devices, etc.

[0037] The deployment of a communication system (such as a 5G NR system) may be arranged with various components or constituent parts in a variety of ways. In a 5G NR system or network, a network node, a network entity, a mobility element of a network, a radio access network (RAN) node, a core network node, a network element or a network equipment (such as a base station (BS), or one or more units (or one or more components) that perform base station functionality may be implemented in an aggregated architecture or a decomposed architecture. For example, a BS (such as a Node B (NB), an evolved NB (eNB), an NR BS, a 5G NB, an access point (AP), a transmit receive point (TRP) or a cell, etc.) may be implemented as an aggregated base station (also referred to as an independent BS or a monolithic BS) or a decomposed base station.

[0038] A converged base station may be configured to utilize a radio protocol stack physically or logically integrated within a single RAN node. A decomposed base station may be configured to utilize a protocol stack physically or logically distributed between two or more units, such as one or more central or centralized units (CUs), one or more distributed units (DUs), or one or more radio units (RUs). In some aspects, a CU may be implemented within a RAN node, and one or more DUs may be co-located with the CU, or alternatively, may be geographically or virtually distributed in one or more other RAN nodes. A DU may be implemented to communicate with one or more RUs. Each of a CU, a DU, and a RU may be implemented as a virtual unit, i.e., a virtual central unit (VCU), a virtual distributed unit (VDU), or a virtual radio unit.

[0039] Base station operation or network design may take into account the aggregated nature of base station functionality. For example, a disaggregated base station may be used in an integrated access backhaul (IAB) network, an open radio access network (O-RAN (network configuration such as that initiated by the O-RAN Alliance)), or a virtualized radio access network (vRAN, also known as a cloud radio access network (C-RAN)). Decomposition may include distributing functionality across two or more units at various physical locations, as well as virtually distributing functionality of at least one unit, which may enable flexibility in network design. Various units of a disaggregated base station or disaggregated RAN architecture may be configured for wired or wireless communication with at least one other unit.

[0040] Figure 1 1 is a diagram 100 illustrating an example of a wireless communication system and an access network. The illustrated wireless communication system includes a disaggregated base station architecture. The disaggregated base station architecture may include one or more CUs 110 that may communicate directly with a core network 120 via a backhaul link, or indirectly with the core network 120 through one or more disaggregated base station units, such as a near real-time (near RT) RAN intelligent controller (RIC) 125 via an E2 link, or a non-real-time (non-RT) RIC 115 associated with a service management and orchestration (SMO) framework 105, or both. The CU 110 may communicate with one or more DUs 130 via corresponding midhaul links, such as an F1 interface. The DU 130 may communicate with one or more RUs 140 via corresponding fronthaul links. The RU 140 may communicate with corresponding UEs 104 via one or more radio frequency (RF) access links. In some implementations, a UE 104 may be served simultaneously by multiple RUs 140.

[0041] Each of the units (i.e., CU 110, DU 130, RU 140, and near-RT RIC 125, non-RT RIC 115, and SMO framework 105) may include or be coupled to one or more interfaces configured to receive or send signals, data, or information (collectively, signals) via a wired or wireless transmission medium. Each of the units or an associated processor or controller that provides instructions to the communication interface of the unit may be configured to communicate with one or more of the other units via a transmission medium. For example, the units may include a wired interface configured to receive or send signals to one or more of the other units on a wired transmission medium. Additionally, the units may include a wireless interface that may include a receiver, a transmitter, or a transceiver (such as an RF transceiver) configured to receive or send signals, or both, to one or more of the other units on a wireless transmission medium.

[0042] In some aspects, CU 110 may host one or more higher layer control functions. Such control functions may include radio resource control (RRC), packet data convergence protocol (PDCP), service data adaptation protocol (SDAP), etc. Each control function may be implemented using an interface that is configured to communicate signals with other control functions hosted by CU 110. CU 110 may be configured to handle user plane functionality (i.e., central unit-user plane (CU-UP)), control plane functionality (i.e., central unit-control plane (CU-CP)), or a combination thereof. In some specific implementations, CU 110 may be logically split into one or more CU-UP units and one or more CU-CP units. When implemented in an O-RAN configuration, the CU-UP unit may communicate bidirectionally with the CU-CP unit via an interface (such as an E1 interface). As needed, CU 110 may be implemented to communicate with DU 130 for network control and signaling.

[0043] DU 130 may correspond to a logical unit that includes one or more base station functions for controlling the operation of one or more RUs 140. In some aspects, DU 130 may host one or more of a radio link control (RLC) layer, a medium access control (MAC) layer, and one or more high physical (PHY) layers (such as modules for forward error correction (FEC) encoding and decoding, scrambling, modulation and demodulation, etc.) depending at least in part on a functional split such as that defined by 3GPP. In some aspects, DU 130 may also host one or more low PHY layers. Each layer (or module) may be implemented using an interface that is configured to communicate signals with other layers (and modules) hosted by DU 130 or with control functions hosted by CU 110.

[0044] The lower layer functionality may be implemented by one or more RUs 140. In some deployments, the RU 140 controlled by the DU 130 may correspond to a logical node that hosts RF processing functions or low PHY layer functions (such as performing fast Fourier transform (FFT), inverse FFT (iFFT), digital beamforming, physical random access channel (PRACH) extraction and filtering, etc.), or both, based at least in part on functional splitting (such as lower layer functional splitting). In such an architecture, the RU 140 may be implemented to handle over-the-air (OTA) communications with one or more UEs 104. In some specific implementations, real-time and non-real-time aspects of control plane and user plane communications with the RU 140 may be controlled by the corresponding DU 130. In some scenarios, this configuration may enable the implementation of the DU 130 and the CU 110 in a cloud-based RAN architecture (such as a vRAN architecture).

[0045] The SMO framework 105 may be configured to support RAN deployment and provisioning of non-virtualized network elements and virtualized network elements. For non-virtualized network elements, the SMO framework 105 may be configured to support the deployment of dedicated physical resources for RAN coverage requirements, which may be managed via an operation and maintenance interface (such as an O1 interface). For virtualized network elements, the SMO framework 105 may be configured to interact with a cloud computing platform (such as an open cloud (O-Cloud) 190) to perform network element lifecycle management (such as instantiating virtualized network elements) via a cloud computing platform interface (such as an O2 interface). Such virtualized network elements may include, but are not limited to, CU 110, DU 130, RU 140, and near-RT RIC 125. In some specific implementations, the SMO framework 105 may communicate with hardware aspects of the 4G RAN (such as an open eNB (O-eNB) 111) via the O1 interface. Additionally, in some specific implementations, the SMO framework 105 may communicate directly with one or more RUs 140 via the O1 interface. The SMO framework 105 may also include a non-RT RIC 115 configured to support the functionality of the SMO framework 105 .

[0046] The non-RT RIC 115 may be configured to include logic functions that enable non-real-time control and optimization of RAN elements and resources, artificial intelligence (AI) / machine learning (ML) (AI / ML) workflows including model training and updating, or policy-based guidance of applications / features in the near-RT RIC 125. The non-RT RIC 115 may be coupled to or communicate with the near-RT RIC 125 (such as via an A1 interface). The near-RT RIC 125 may be configured to include logic functions that enable near-real-time control and optimization of RAN elements and resources via data collection and actions through an interface (such as via an E2 interface) that connects one or more CUs 110, one or more DUs 130, or both, and the O-eNB with the near-RT RIC 125.

[0047] In some implementations, in order to generate an AI / ML model to be deployed in the near-RT RIC 125, the non-RT RIC 115 may receive parameters or external enrichment information from an external server. Such information may be utilized by the near-RT RIC 125 and may be received from a non-network data source or from a network function at the SMO framework 105 or the non-RT RIC 115. In some examples, the non-RT RIC 115 or the near-RT RIC 125 may be configured to tune RAN behavior or performance. For example, the non-RT RIC 115 may monitor long-term trends and patterns of performance and employ AI / ML models to perform corrective actions through the SMO framework 105 (such as via reconfiguration of O1) or via the creation of RAN management policies (such as A1 policies).

[0048] At least one of the CU 110, the DU 130, and the RU 140 may be referred to as a base station 102. Therefore, the base station 102 may include one or more of the CU 110, the DU 130, and the RU 140 (each component is indicated by a dotted line to indicate that each component may be included in the base station 102, or may not be included in the base station). The base station 102 provides an access point to the core network 120 for the UE 104. The base station 102 may include a macro cell (a high-power cellular base station) and / or a small cell (a low-power cellular base station). Small cells include femto cells, pico cells, and micro cells. A network including both small cells and macro cells may be referred to as a heterogeneous network. A heterogeneous network may also include a home evolved Node B (eNB) (HeNB), which may provide services to a restricted group referred to as a closed subscriber group (CSG). The communication link between RU 140 and UE 104 may include uplink (UL) (also known as reverse link) transmission from UE 104 to RU 140 and / or downlink (DL) (also known as forward link) transmission from RU 140 to UE 104. The communication link may use multiple-input multiple-output (MIMO) antenna technology, including spatial multiplexing, beamforming and / or transmission diversity. The communication link may be through one or more carriers. For each carrier allocated in a carrier aggregation of up to Yx MHz (x component carriers) for transmission in each direction, the base station 102 / UE 104 may use a spectrum of up to Y MHz (e.g., 5MHz, 10MHz, 15MHz, 20MHz, 100MHz, 400MHz, etc.) bandwidth. The carriers may or may not be adjacent to each other. The allocation of carriers may be asymmetric with respect to DL and UL (e.g., more or fewer carriers may be allocated for DL ​​compared to UL). The component carrier may include a primary component carrier and one or more secondary component carriers. The primary component carrier may be referred to as a primary cell (PCell) and the secondary component carrier may be referred to as a secondary cell (SCell).

[0049] Some UEs 104 may communicate with each other using a device-to-device (D2D) communication link 158. The D2D communication link 158 may use DL / UL wireless wide area network (WWAN) spectrum. The D2D communication link 158 may use one or more sidelink channels, such as a physical sidelink broadcast channel (PSBCH), a physical sidelink discovery channel (PSDCH), a physical sidelink shared channel (PSSCH), and a physical sidelink control channel (PSCCH). The D2D communication may be through a variety of wireless D2D communication systems, such as, for example, Bluetooth, Wi-Fi based on the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standard, LTE, or NR.

[0050] The wireless communication system may also include a Wi-Fi AP 150 that communicates with a UE 104 (also referred to as a Wi-Fi station (STA)) via a communication link 154, for example, in a 5 GHz unlicensed spectrum, etc. When communicating in an unlicensed spectrum, the UE 104 / AP 150 may perform a clear channel assessment (CCA) to determine whether a channel is available prior to communication.

[0051] The electromagnetic spectrum is typically subdivided into various categories, bands, channels, etc. based on frequency / wavelength. In 5G NR, two initial operating bands have been identified as frequency range designations FR1 (410 MHz-7.125 GHz) and FR2 (24.25 GHz-52.6 GHz). Although a portion of FR1 is greater than 6 GHz, FR1 is often (interchangeably) referred to as the “sub-6 GHz” band in various documents and articles. A similar naming issue sometimes occurs with respect to FR2, which is often (interchangeably) referred to as the “millimeter wave” band in documents and articles, although it is different from the extremely high frequency (EHF) band (30 GHz–300 GHz) that is identified as the “millimeter wave” band by the International Telecommunication Union (ITU).

[0052] Frequencies between FR1 and FR2 are generally referred to as mid-band frequencies. Recent 5G NR research has identified the operating bands for these mid-band frequencies as frequency range designation FR3 (7.125 GHz–24.25 GHz). The bands falling within FR3 can inherit FR1 characteristics and / or FR2 characteristics, and therefore can effectively extend the features of FR1 and / or FR2 to mid-band frequencies. In addition, higher frequency bands are currently being explored to extend 5G NR operations to more than 52.6 GHz. For example, three higher operating bands have been identified as frequency range designations FR2-2 (52.6 GHz–71 GHz), FR4 (71 GHz–114.25 GHz), and FR5 (114.25 GHz–300 GHz). Each of these higher frequency bands falls within the EHF band.

[0053] In view of the above, unless otherwise specified, if the term "6 GHz or less" is used in this document, it can broadly refer to frequencies that may be less than 6 GHz, may be within FR1, or may include mid-band frequencies. In addition, unless otherwise specified, if the term "millimeter wave" is used in this document, it can broadly refer to frequencies that may include mid-band frequencies, may be within FR2, FR4, FR2-2 and / or FR5, or may be within the EHF band.

[0054] The base station 102 and the UE 104 may each include multiple antennas (such as antenna elements, antenna panels, and / or antenna arrays) to facilitate beamforming. The base station 102 may send a beamformed signal 182 to the UE 104 in one or more transmit directions. The UE 104 may receive the beamformed signal from the base station 102 in one or more receive directions. The UE 104 may also send a beamformed signal 184 to the base station 102 in one or more transmit directions. The base station 102 may receive the beamformed signal from the UE 104 in one or more receive directions. The base station 102 / UE 104 may perform beam training to determine the best receive direction and transmit direction for each of the base station 102 / UE 104. The transmit direction and receive direction of the base station 102 may be the same or different. The transmit direction and receive direction of the UE 104 may be the same or different.

[0055] The base station 102 may include and / or be referred to as a gNB, a Node B, an eNB, an access point, a base transceiver station, a radio base station, a radio transceiver, a transceiver function, a basic service set (BSS), an extended service set (ESS), a transmit receive point (TRP), a network node, a network entity, a network equipment, or some other suitable term. The base station 102 may be implemented as an integrated access backhaul (IAB) node, a relay node, a sidelink node, an aggregated (monolithic) base station with a baseband unit (BBU) (including a CU and a DU) and a RU, or as a disaggregated base station including one or more of a CU, a DU, and / or a RU. A set of base stations that may include disaggregated base stations and / or aggregated base stations may be referred to as a next generation (NG) RAN (NG-RAN).

[0056] The core network 120 may include an access and mobility management function (AMF) 161, a session management function (SMF) 162, a user plane function (UPF) 163, a unified data management (UDM) 164, one or more location servers 168, and other functional entities. AMF 161 is a control node that handles signaling between UE 104 and core network 120. AMF 161 supports registration management, connection management, mobility management, and other functions. SMF 162 supports session management and other functions. UPF 163 supports packet routing, packet forwarding, and other functions. UDM 164 supports the generation of authentication and key agreement (AKA) credentials, user identity handling, access authorization, and subscription management. One or more location servers 168 are illustrated as including a gateway mobile location center (GMLC) 165 and a location management function (LMF) 166. However, in general, the one or more location servers 168 may include one or more location / positioning servers, which may include one or more of the GMLC 165, the LMF 166, the positioning determination entity (PDE), the serving mobile location center (SMLC), the mobile positioning center (MPC), etc. The GMLC 165 and the LMF 166 support UE location services. The GMLC 165 provides an interface for clients / applications (e.g., emergency services) to access UE positioning information. The LMF 166 receives measurement results and assistance information from the NG-RAN and the UE 104 via the AMF 161 to calculate the positioning of the UE 104. The NG-RAN may determine the positioning of the UE 104 using one or more positioning methods. Positioning the UE 104 may involve signal measurements, positioning estimates, and optional speed calculations based on these measurements. Signal measurements may be performed by the UE 104 and / or the serving base station 102. The measured signals may be based on a satellite positioning system (SPS) 170 (e.g., one or more of a global navigation satellite system (GNSS), a global positioning system (GPS), a non-terrestrial network (NTN), or other satellite positioning / location systems), LTE signals, wireless local area network (WLAN) signals, Bluetooth signals, a terrestrial beacon system (TBS), sensor-based information (e.g., an atmospheric pressure sensor, a motion sensor), an NR enhanced cell ID (NR E-CID) method, NR signals (e.g., multi-round trip time (multi-RTT), DL angle of departure (DL-AoD), DL time difference of arrival (DL-TDOA), UL time difference of arrival (UL-TDOA), and UL angle of arrival (UL-AoA) positioning), and / or one or more of other systems / signals / sensors.

[0057] Examples of UE 104 include cellular phones, smart phones, session initiation protocol (SIP) phones, laptops, personal digital assistants (PDAs), satellite radios, global positioning systems, multimedia devices, video devices, digital audio players (e.g., MP3 players), cameras, game consoles, tablet computers, smart devices, wearable devices, vehicles, electric meters, gas pumps, large or small kitchen appliances, healthcare equipment, implants, sensors / actuators, displays, or any other similarly functional devices. Some of the UEs 104 may be referred to as IoT devices (e.g., parking meters, gas pumps, toasters, vehicles, heart monitors, etc.). UE 104 may also be referred to as stations, mobile stations, subscriber stations, mobile units, subscriber units, wireless units, remote units, mobile devices, wireless devices, wireless communication devices, remote devices, mobile subscriber stations, access terminals, mobile terminals, wireless terminals, remote terminals, mobile phones, user agents, mobile clients, clients, or some other suitable terminology. In some scenarios, the term UE may also be applied to one or more supporting devices, such as in a device constellation arrangement. One or more of these devices may access the network collectively and / or individually.

[0058] Reference again Figure 1 In certain aspects, a device, which may be a UE 104, a base station 102 / 180, a component of a base station 102 / 180, or a location server (e.g., a GMLC 165, a LMF 166), may include a positioning ML component 198 / 199 configured to perform PR measurement error detection and classification based on SV geometry. In one configuration, the positioning ML component 198 / 199 may be configured to determine at least one geometric orientation relative to the UE for each SV in a set of SVs. In such a configuration, the positioning ML component 198 / 199 may determine a relative PR weight for each SV in the set of SVs based on an ML classifier and the geometric orientation relative to the UE determined for each SV in at least a subset of the set of SVs. In such a configuration, the positioning ML component 198 / 199 may estimate the positioning of the UE based on the PR measurements of each SV in the set of SVs and the relative PR weights of each SV in the set of SVs.

[0059] Figure 2A FIG200 is a diagram illustrating an example of a first subframe within a 5G NR frame structure. Figure 2B FIG230 is a diagram illustrating an example of DL channels within a 5G NR subframe. Figure 2C FIG250 is a diagram illustrating an example of a second subframe within a 5G NR frame structure. Figure 2DFIG280 is a diagram illustrating an example of UL channels within a 5G NR subframe. The 5G NR frame structure may be frequency division duplex (FDD), where for a particular set of subcarriers (carrier system bandwidth), subframes within that subcarrier set are dedicated to either DL or UL, or may be time division duplex (TDD), where for a particular set of subcarriers (carrier system bandwidth), subframes within that subcarrier set are dedicated to both DL and UL. Figure 2A , Figure 2C In the example provided, the 5G NR frame structure is assumed to be TDD, where subframe 4 is configured with slot format 28 (most of which are DL), where D is DL, U is UL, and F is flexible between DL / UL, and subframe 3 is configured with slot format 1 (all of which are UL). Although subframes 3 and 4 are shown as having slot formats 1 and 28, respectively, any particular subframe may be configured with any of the various available slot formats 0 to 61. Slot formats 0 and 1 are both DL and both UL, respectively. Other slot formats 2-61 include a mix of DL, UL, and flexible symbols. The slot format is configured for the UE via a received slot format indicator (SFI) (dynamically configured via DL control information (DCI) or semi-statically / statically configured via radio resource control (RRC) signaling). Note that the following description also applies to the 5G NR frame structure as TDD.

[0060] FIG. 2A to FIG. 2D The frame structure is illustrated, and various aspects of the present disclosure may be applicable to other wireless communication technologies that may have different frame structures and / or different channels. A frame (10ms) may be divided into 10 subframes of the same size (1ms). Each subframe may include one or more time slots. A subframe may also include a microslot, which may include 7, 4 or 2 symbols. Each time slot may include 14 or 12 symbols, depending on whether the cyclic prefix (CP) is conventional or extended. For a conventional CP, each time slot may include 14 symbols, and for an extended CP, each time slot may include 12 symbols. The symbol on the DL may be a CP orthogonal frequency division multiplexing (OFDM) (CP-OFDM) symbol. The symbol on the UL may be a CP-OFDM symbol (for high throughput scenarios) or a discrete Fourier transform (DFT) spread OFDM (DFT-s-OFDM) symbol (also known as a single carrier frequency division multiple access (SC-FDMA) symbol) (for power-limited scenarios; limited to single-stream transmission). The number of time slots within a subframe is based on the CP and parameter set. The parameter set defines the subcarrier spacing (SCS) and effectively defines the symbol length / duration, which is equal to 1 / SCS.

[0061]

[0062] For normal CP (14 symbols / slot), different parameter sets μ0 to 4 allow 1, 2, 4, 8, and 16 slots per subframe, respectively. For extended CP, parameter set 2 allows 4 slots per subframe. Accordingly, for normal CP and parameter set μ, there are 14 symbols / slot and 2 μ timeslots / subframe. The subcarrier spacing can be equal to 2 μ *15kHz, where μ is parameter set 0 to 4. Therefore, the subcarrier spacing for parameter set μ=0 is 15kHz, and the subcarrier spacing for parameter set μ=4 is 240kHz. The symbol length / duration is inversely related to the subcarrier spacing. FIG. 2A to FIG. 2D An example of a parameter set μ=2 with a normal CP of 14 symbols per slot and 4 slots per subframe is provided. The slot duration is 0.25 ms, the subcarrier spacing is 60 kHz, and the symbol duration is about 16.67 μs. Within a frame set, there may be one or more different bandwidth parts (BWPs) that are frequency-division multiplexed (see Figure 2B ). Each BWP may have a specific parameter set and CP (normal or extended).

[0063] A resource grid may be used to represent a frame structure. Each slot includes a resource block (RB) (also referred to as a physical RB (PRB)) extending over 12 consecutive subcarriers. The resource grid is divided into a plurality of resource elements (REs). The number of bits carried by each RE depends on the modulation scheme.

[0064] like Figure 2A As illustrated, some of the REs carry reference (pilot) signals (RS) for the UE. The RS may include a demodulation RS (DM-RS) (indicated as R for a particular configuration, but other DM-RS configurations are possible) and a channel state information reference signal (CSI-RS) for channel estimation at the UE. The RS may also include a beam measurement RS (BRS), a beam refinement RS (BRRS), and a phase tracking RS (PT-RS).

[0065] Figure 2BExamples of various DL channels within a subframe of a frame are illustrated. A physical downlink control channel (PDCCH) carries DCI within one or more control channel elements (CCEs) (e.g., 1, 2, 4, 8, or 16 CCEs), each CCE including six RE groups (REGs), each REG including 12 consecutive REs in an OFDM symbol of an RB. A PDCCH within a BWP may be referred to as a control resource set (CORESET). The UE is configured to monitor PDCCH candidates in a PDCCH search space (e.g., a common search space, a UE-specific search space) during a PDCCH monitoring opportunity on a CORESET, wherein the PDCCH candidates have different DCI formats and different aggregation levels. Additional BWPs may be located at higher and / or lower frequencies on the channel bandwidth. A primary synchronization signal (PSS) may be within symbol 2 of a particular subframe of a frame. The PSS is used by UE 104 to determine subframe / symbol timing and physical layer identification. A secondary synchronization signal (SSS) may be within symbol 4 of a particular subframe of a frame. The SSS is used by the UE to determine the physical layer cell identity group number and the radio frame timing. Based on the physical layer identity and the physical layer cell identity group number, the UE can determine the physical cell identifier (PCI). Based on the PCI, the UE can determine the location of the DM-RS. The physical broadcast channel (PBCH) carrying the master information block (MIB) can be logically grouped with the PSS and SSS to form a synchronization signal (SS) / PBCH block (also referred to as an SS block (SSB)). The MIB provides the system frame number (SFN) and the number of RBs in the system bandwidth. The physical downlink shared channel (PDSCH) carries user data, broadcast system information such as system information blocks (SIBs) that are not sent via the PBCH, and paging messages.

[0066] like Figure 2C As illustrated, some of the REs carry DM-RS (indicated as R for a particular configuration, but other DM-RS configurations are possible) for channel estimation at the base station. The UE may send a DM-RS for a physical uplink control channel (PUCCH) and a DM-RS for a physical uplink shared channel (PUSCH). The PUSCH DM-RS may be sent in the first or first two symbols of the PUSCH. Depending on whether a short PUCCH or a long PUCCH is sent and depending on the specific PUCCH format used, the PUCCH DM-RS may be sent in different configurations. The UE may send a sounding reference signal (SRS). The SRS may be sent in the last symbol of a subframe. The SRS may have a comb structure, and the UE may send the SRS on one of the teeth of the comb. The SRS may be used by the base station for channel quality estimation to achieve frequency-dependent scheduling of the UL.

[0067] Figure 2DExamples of various UL channels within a subframe of a frame are illustrated. The PUCCH may be located at a position as indicated in one configuration. The PUCCH carries uplink control information (UCI), such as scheduling requests, channel quality indicators (CQI), precoding matrix indicators (PMI), rank indicators (RI), and hybrid automatic repeat request (HARQ) acknowledgement (ACK) (HARQ-ACK) feedback (i.e., one or more HARQ ACK bits indicating one or more ACKs and / or negative ACKs (NACKs)). The PUSCH carries data and may additionally be used to carry a buffer status report (BSR), a power headroom report (PHR), and / or UCI.

[0068] Figure 3 370 is a block diagram of a base station 310 communicating with a UE 350 in an access network. In the DL, Internet Protocol (IP) packets may be provided to a controller / processor 375. The controller / processor 375 implements layer 3 and layer 2 functionality. Layer 3 includes a radio resource control (RRC) layer, and layer 2 includes a service data adaptation protocol (SDAP) layer, a packet data convergence protocol (PDCP) layer, a radio link control (RLC) layer, and a medium access control (MAC) layer. The controller / processor 375 provides RRC layer functionality associated with broadcasting of system information (e.g., MIB, SIB), RRC connection control (e.g., RRC connection paging, RRC connection establishment, RRC connection modification, and RRC connection release), inter-radio access technology (RAT) mobility, and measurement configuration for UE measurement reporting; PDCP layer functionality associated with header compression / decompression, security (encryption, decryption, integrity protection, integrity verification), and handover support functions; RLC layer functionality associated with delivery of upper layer packet data units (PDUs), error correction through ARQ, concatenation, segmentation and reassembly of RLC service data units (SDUs), re-segmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functionality associated with mapping between logical channels and transport channels, multiplexing of MAC SDUs onto transport blocks (TBs), demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction through HARQ, priority handling, and logical channel prioritization.

[0069] The transmit (TX) processor 316 and receive (RX) processor 370 implement layer 1 functionality associated with various signal processing functions. Layer 1 (which includes the physical (PHY) layer) may include error detection on the transport channel, forward error correction (FEC) coding / decoding of the transport channel, interleaving, rate matching, mapping to the physical channel, modulation / demodulation of the physical channel, and MIMO antenna processing. The TX processor 316 handles the mapping to the signal constellation based on various modulation schemes (e.g., binary phase shift keying (BPSK), quadrature phase shift keying (QPSK), M-order phase shift keying (M-PSK), M-order quadrature amplitude modulation (M-QAM)). The decoded and modulated symbols can then be divided into parallel streams. Subsequently, each stream can be mapped to an OFDM subcarrier, multiplexed with a reference signal (e.g., a pilot) in the time domain and / or frequency domain, and then combined using an inverse fast Fourier transform (IFFT) to produce a physical channel carrying a time domain OFDM symbol stream. The OFDM stream is spatially pre-coded to generate multiple spatial streams. Channel estimates from a channel estimator 374 may be used to determine the coding and modulation schemes, as well as for spatial processing. Channel estimates may be derived from reference signals and / or channel state feedback sent by the UE 350. Each spatial stream may then be provided to a different antenna 320 via a separate transmitter 318Tx. Each transmitter 318Tx may modulate a radio frequency (RF) carrier for transmission using a corresponding spatial stream.

[0070] At the UE 350, each receiver 354Rx receives a signal through its corresponding antenna 352. Each receiver 354Rx recovers the information modulated onto the RF carrier and provides the information to a receive (RX) processor 356. The TX processor 368 and the RX processor 356 implement layer 1 functionality associated with various signal processing functions. The RX processor 356 can perform spatial processing on the information to recover any spatial stream destined for the UE 350. If multiple spatial streams are destined for the UE 350, they can be merged into a single OFDM symbol stream by the RX processor 356. The RX processor 356 then converts the OFDM symbol stream from the time domain to the frequency domain using a fast Fourier transform (FFT). The frequency domain signal includes a separate OFDM symbol stream for each subcarrier of the OFDM signal. The symbols on each subcarrier and the reference signal are recovered and demodulated by determining the most likely signal constellation point sent by the base station 310. These soft decisions can be based on channel estimates calculated by the channel estimator 358. The soft decisions are then decoded and deinterleaved to recover the data and control signals originally sent on the physical channel by the base station 310. The data and control signals are then provided to the controller / processor 359, which implements layer 3 and layer 2 functionality.

[0071] The controller / processor 359 may be associated with a memory 360 that stores program codes and data. The memory 360 may be referred to as a computer readable medium. In the UL, the controller / processor 359 provides demultiplexing between transport channels and logical channels, packet reassembly, decryption, header decompression, and control signal processing to recover IP packets. The controller / processor 359 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operations.

[0072] Similar to the functions described in conjunction with DL transmissions performed by the base station 310, the controller / processor 359 provides RRC layer functionality associated with system information (e.g., MIB, SIB) acquisition, RRC connection, and measurement reporting; PDCP layer functionality associated with header compression / decompression and security (encryption, decryption, integrity protection, integrity verification); RLC layer functionality associated with delivery of upper layer PDUs, error correction through ARQ, concatenation, segmentation and reassembly of RLC SDUs, resegmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functionality associated with mapping between logical channels and transport channels, multiplexing of MAC SDUs onto TBs, demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction through HARQ, priority handling, and logical channel prioritization.

[0073] The TX processor 368 may use channel estimates derived by the channel estimator 358 from a reference signal or feedback sent by the base station 310 to select appropriate coding and modulation schemes and to facilitate spatial processing. The spatial streams generated by the TX processor 368 may be provided to different antennas 352 via corresponding transmitters 354Tx. Each transmitter 354Tx may modulate an RF carrier with a corresponding spatial stream for transmission.

[0074] UL transmissions are processed at the base station 310 in a manner similar to that described in conjunction with the receiver functionality at the UE 350. Each receiver 318Rx receives a signal through its respective antenna 320. Each receiver 318Rx recovers information modulated onto an RF carrier and provides the information to the RX processor 370.

[0075] The controller / processor 375 may be associated with a memory 376 that stores program codes and data. The memory 376 may be referred to as a computer readable medium. In the UL, the controller / processor 375 provides demultiplexing between transport channels and logical channels, packet reassembly, decryption, header decompression, control signal processing to recover IP packets. The controller / processor 375 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operations.

[0076] At least one of the TX processor 368, the RX processor 356, and the controller / processor 359 may be configured to perform operations related to Figure 1 The positioning ML component 198 combines various aspects.

[0077] At least one of the TX processor 316, the RX processor 370, and the controller / processor 375 may be configured to perform operations related to Figure 1 The positioning ML component 199 combines various aspects.

[0078] Figure 4 4 is a diagram illustrating an example of UE positioning based on reference signal measurements (which may also be referred to as “network-based positioning”) according to various aspects of the present disclosure. UE 404 may be at time T SRS_TX UL-SRS 412 is sent and at time T PRS_RX A DL positioning reference signal (PRS) (DL-PRS) 410 is received. TRP 406 may be at time T SRS_RX Receive UL-SRS 412 and at time T PRS_TX 410. UE 404 may receive DL-PRS 410 before transmitting UL-SRS 412, or may transmit UL-SRS 412 before receiving DL-PRS 410. In both cases, a positioning server (e.g., location server 168) or UE 404 may determine the UL-SRS 412 based on ||T SRS_RX –T PRS_TX |–|T SRS_TX –T PRS_RX || determines RTT 414. Thus, multi-RTT positioning may utilize UE Rx-Tx time difference measurements (ie, |T SRS_TX –T PRS_RX |) and DL-PRS reference signal received power (RSRP) (DL-PRS-RSRP), and the measured TRP Rx-Tx time difference measurement (ie, |T SRS_RX –T PRS_TX|) and UL-SRS-RSRP. The UE 404 measures the UE Rx-Tx time difference measurement (and optionally the DL-PRS-RSRP of the received signal) using the assistance data received from the positioning server, and the TRP 402, 406 measures the gNB Rx-Tx time difference measurement (and optionally the UL-SRS-RSRP of the received signal) using the assistance data received from the positioning server. These measurements may be used at the positioning server or the UE 404 to determine the RTT, which is used to estimate the position of the UE 404. Other methods for determining the RTT are possible, such as, for example, using DL-TDOA and / or UL-TDOA measurements.

[0079] DL-AoD positioning may utilize the measured DL-PRS-RSRP of downlink signals received from multiple TRPs 402, 406 at the UE 404. The UE 404 measures the DL-PRS-RSRP of the received signals using assistance data received from a positioning server, and the resulting measurements, along with the departure azimuth angle (A-AoD), departure zenith angle (Z-AoD), and other configuration information, are used to position the UE 404 relative to neighboring TRPs 402, 406.

[0080] DL-TDOA positioning may utilize DL Reference Signal Time Difference (RSTD) (and optionally DL-PRS-RSRP) of downlink signals received from multiple TRPs 402, 406 at the UE 404. The UE 404 measures the DL RSTD (and optionally DL-PRS-RSRP) of the received signals using assistance data received from a positioning server, and the resulting measurements are used along with other configuration information to position the UE 404 relative to neighboring TRPs 402, 406.

[0081] UL-TDOA positioning may utilize the UL relative time of arrival (RTOA) (and optionally UL-SRS-RSRP) of uplink signals sent from the UE 404 at multiple TRPs 402, 406. The TRPs 402, 406 measure the UL-RTOA (and optionally UL-SRS-RSRP) of the received signals using assistance data received from a positioning server, and the resulting measurements are used along with other configuration information to estimate the position of the UE 404.

[0082] UL-AoA positioning may utilize the measured azimuth angle of arrival (A-AoA) and zenith angle of arrival (Z-AoA) of uplink signals sent from the UE 404 at multiple TRPs 402, 406. The TRPs 402, 406 measure the A-AoA and Z-AoA of the received signals using assistance data received from a positioning server, and the resulting measurements are used along with other configuration information to estimate the position of the UE 404.

[0083] Additional positioning methods may be used to estimate the position of the UE 404, such as, for example, UE-side UL-AoD and / or DL-AoA. Note that data / measurements from various techniques may be combined in various ways to increase accuracy, determine and / or enhance certainty, supplement / complete measurements, and / or replace / provide missing information.

[0084] A device equipped with a Global Navigation Satellite System (GNSS) receiver may determine its position based on GNSS positioning. GNSS is a network of satellites that broadcasts timing and orbit information used for navigation and positioning measurements. GNSS may include groups of satellites, called clusters, that broadcast signals (which may be referred to as GNSS signals) to control stations and users of the GNSS. Based on the broadcast signals, a user may be able to determine its position (e.g., via trilateration). For the purposes of this disclosure, a device (e.g., UE) equipped with a GNSS receiver or capable of receiving GNSS signals may be referred to as a GNSS device, and a device (such as a satellite) capable of sending GNSS signals may be referred to as a space vehicle (SV).

[0085] Figure 5 5 is a diagram illustrating an example of GNSS positioning according to various aspects of the present disclosure. A GNSS device 506 may estimate its position and time based at least in part on data (e.g., GNSS signals 504) received from a plurality of space vehicles (SVs) 502, wherein each SV 502 may carry a record of its position and time and may send the data (e.g., the record) to the GNSS device 506. Each SV 502 may also include a clock that is synchronized with other clocks of the SV and with a ground clock. If the SV 502 detects a deviation from the time kept on the ground, the SV 502 may correct for it. The GNSS device 506 may also include a clock, but the clock of the GNSS device 506 may be less stable and accurate than the clock of the SV 502.

[0086] Because the speed of radio waves may be constant and independent of satellite speed, the time delay between the time when SV 502 transmits GNSS signal 504 and the time when GNSS device 506 receives GNSS signal 504 may be proportional to the distance from SV 502 to GNSS device 506. In some examples, GNSS device 506 may use a minimum of four SVs to calculate / estimate one or more unknown quantities associated with positioning (e.g., three positioning coordinates and a clock bias from satellite time, etc.).

[0087] Each SV 502 may continuously broadcast a GNSS signal 504 (e.g., with a modulated carrier wave) that may include a pseudo-random code (e.g., a sequence of ones and zeros) known to the GNSS device 506, and may also include a message including the time of transmission and the SV position at that time. In other words, each GNSS signal 504 may carry two types of information: time and carrier wave (e.g., with a modulated waveform of an input signal to be transmitted electromagnetically). Based on the GNSS signal 504 received from the SV 502, the GNSS device 506 may measure the time of arrival (TOA) of the GNSS signal 504 and estimate the time of flight (TOF) of the GNSS signal 504. Then, based on the TOF, the GNSS device 506 may calculate its three-dimensional position and clock bias, and the GNSS device 506 may determine its position on the earth. For example, the position of the GNSS device 506 may be converted into latitude, longitude, and altitude relative to an ellipsoidal earth model. These coordinates may be displayed on a display such as a moving map, or recorded or used by some other system (such as a vehicle guidance system).

[0088] Although the distance between the GNSS device and the SV can be estimated based on the time it takes for the GNSS signal to reach the GNSS device, the signal sequence of the SV may be delayed relative to the sequence of the GNSS device. Therefore, in some examples, a delay may be applied to the sequence of the GNSS device so that the two sequences are aligned. For example, in order to estimate the delay, the GNSS device may align the pseudo-random binary sequence included in the SV signal with an internally generated pseudo-random binary sequence. Since the GNSS signal of the SV takes time to reach the GNSS device, the sequence of the SV may be delayed relative to the sequence of the GNSS device. By gradually delaying the sequence of the GNSS device, the two sequences can eventually be aligned. The accuracy of GNSS positioning may depend on various factors, such as SV geometry, GNSS signal blockage, atmospheric conditions and / or GNSS receiver design features / quality. For example, the accuracy of the GNSS receiver used by a smart phone or smart watch may be lower than that of the GNSS receiver used by vehicles and exploration equipment.

[0089] In some scenarios, non-line-of-sight (NLOS) GNSS measurements (e.g., measurements of GNSS signals made by a GNSS device) may reduce outdoor positioning fix accuracy, such as in urban areas. For example, if there are obstacles between the SV and the GNSS device, such as physical structures (e.g., buildings, tunnels) and terrain (e.g., mountains), the GNSS signals received by the GNSS device may be weakened and / or include offsets / delays.

[0090] Figure 6 600 is a diagram illustrating an example of NLOS GNSS measurements in an urban area according to various aspects of the present disclosure. A GNSS device 606 may receive a GNSS signal (which may be referred to as an LOS signal) from an SV 602 based on a line-of-sight (LOS) condition. However, due to obstruction and environmental conditions, the GNSS device 606 may receive a GNSS signal (which may be referred to as an NLOS signal) from another SV 604 based on an NLOS condition, wherein the GNSS signal from the SV 604 may penetrate and / or bounce off one or more objects (e.g., buildings, trees, etc.) before reaching the GNSS device 606. Since an NLOS signal may generally take longer to reach the GNSS device than an LOS signal, the NLOS signal may include excessive delay. Therefore, when multiple GNSS measurements are based on NLOS conditions, the positioning accuracy and speed of the GNSS device may be reduced. This in turn may reduce the efficiency and accuracy of certain location-based service (LBS) applications (such as navigation applications and ride-sharing applications). Furthermore, the degradation in accuracy may be more significant during a warm start of a GNSS device where the initial time and positioning uncertainty is large (eg, approximately one kilometer).In some examples, continuous fix accuracy may also be reduced.

[0091] Various aspects presented herein can improve the performance and accuracy of GNSS-based positioning. Various aspects presented herein provide a machine learning (ML) model that utilizes SV geometry and raw GNSS observables to classify GNSS pseudorange (PR) measurements in terms of relative NLOS errors (e.g., excess delay). Based on the ML classification, a GNSS device (e.g., UE or location server) can determine appropriate weights for PR measurements in a GNSS positioning estimator (e.g., weighted least squares (WLS), Kalman filter (KF), etc.).

[0092] For purposes of this disclosure, "inference" or "ML inference" may refer to the process of running data points into an ML model (e.g., via an inference host) to estimate an output such as a single numeric score (e.g., to make predictions using a trained ML algorithm). "Inference host" or "ML inference host" may refer to a network function that hosts an ML model during inference mode (in conjunction with Figure 7 Detailed description). Alternatively, in another aspect of the present disclosure, a GNSS device (e.g., a UE) may be configured to employ computing resources and an ML model to process PR measurements from different SVs and feed the training data to an ML training host, where the ML training host may be co-located / associated with a server (e.g., a positioning server) for offline and / or online training of the ML model to classify (e.g., predict / estimate) GNSS PR measurements. Similarly, for purposes of the present disclosure, "training" or "ML training" may refer to the process of running data points to train or teach an ML model (e.g., via a training host). A "training host" or "ML training host" may refer to a network function (in conjunction with a server) that hosts an ML model during a training mode. Figure 7 Detailed description). In addition, the term "pseudorange" (or pseudorange) may refer to the pseudorange between a SV (e.g., a satellite) and a navigation satellite receiver (such as a GNSS receiver). For example, in order for a navigation satellite receiver to determine its position, a satellite navigation receiver may determine the distances to multiple satellites and their positions at the time of transmission. These positions may be estimated for any point in time, given the knowledge of the orbital parameters of the satellites. The pseudorange for each satellite may be obtained by multiplying the speed of light by the time it takes for a signal to travel from the satellite to the receiver.

[0093] Figure 7 700 is a diagram illustrating an example architecture of a functional framework associated with an ML model (also referred to as an ML classifier) ​​according to various aspects of the present disclosure. In some scenarios, the functional framework of the ML model can be further enhanced by data collection through use cases and / or examples. In one example, as shown in diagram 700, the functional architecture of the ML model may include multiple logical entities, such as a model training host 702, a model inference host 704, a data source 706, and / or a participant 708. In some examples, multiple logical entities may be co-located on the same device (e.g., UE, positioning device, etc.) or network node (e.g., base station, component of a base station, server, etc.). In other examples, different logical entities may be located at different devices or network nodes.

[0094] The model inference host 704 can be configured to run an ML model based on the inference data provided by the data source 706, and the model inference host 704 can generate output (e.g., prediction) using the inference data input to the participants 708. The participants 708 can be devices or entities. For example, the participants 708 can be a GNSS device or a location server associated with the GNSS device, etc. In addition, the participants 708 can also depend on the type of tasks performed by the model inference host 704, the type of inference data provided to the model inference host 704, and / or the type of output generated by the model inference host 704, etc.

[0095] After the participant 708 receives the output from the model inference host 704, the participant 708 may determine whether or how to take action based on the output. For example, if the participant 708 is a location server and the output from the model inference host 704 is associated with a PR measurement classification, the participant 708 may determine how to classify one or more PR measurements performed based on the output. The participant 708 may then indicate the classification to at least one action subject 710. In some examples, the participant 708 and at least one action subject 710 may be the same entity (e.g., a GNSS device). For example, if the participant 708 (e.g., a location server) provides classification and / or weighting for certain PR measurements performed by the action subject 710 (e.g., a GNSS device), the participant 708 may send a PR classification / weighting configuration to the action subject 710. In response, the action subject 710 may apply the classification / weighting configuration to its PR measurement.

[0096] The data source 706 may also be configured to collect data that is used as training data for training an ML model or as inference data for feeding an ML model inference operation. For example, the data source 706 may collect data from one or more GNSS devices or location servers (which may include an action subject 710), and provide the collected data to the model training host 702 for use in ML model training. For example, after the action subject 710 (e.g., a GNSS device) receives a PR measurement classification / weighting configuration from a participant 708 (e.g., a location server), the action subject 710 may provide performance feedback associated with the PR measurement classification / weighting configuration to the data source 706, wherein the performance feedback may be used by the model training host 702 to monitor or evaluate ML model performance, for example, whether the output (e.g., prediction) provided by the participant 708 is accurate. In some examples, if the output provided by the participant 708 is inaccurate (or the accuracy is below an accuracy threshold), the model training host 702 may determine to modify or retrain the ML model used by the model inference host, such as via ML model deployment / update.

[0097] In one aspect of the present disclosure, an ML model is provided to classify GNSS PR measurements in terms of relative NLOS errors based on SV geometry. Thus, the classification provided by the ML model may enable a positioning device (e.g., a GNSS device) or a positioning server to determine a more appropriate weight for each PR measurement in a GNSS positioning estimator, which may include positioning estimates based on weighted least squares (WLS) (e.g., a generalization of ordinary least squares and linear regression, where knowledge of the observation variance is incorporated into the regression) and / or based on a Kalman filter (KF) (e.g., using a series of measurements observed over time (including statistical noise and other inaccuracies), and producing an estimate of the unknown variable that is more accurate than based on a single measurement alone by estimating a joint probability distribution over the variable for each time frame). In one example, the training of the ML model may be based on PR error estimates (e.g., data source 706) provided by a higher performance positioning device (such as atomic clock accurate hardware). An atomic clock may refer to a clock that measures time by monitoring the radiation frequency of atoms based on atoms with different energy levels.

[0098] Fig. 8A800A is a diagram illustrating an example ML training of an ML model capable of classifying GNSS PR measurements (e.g., in terms of relative NLOS errors) according to various aspects of the present disclosure. In one example, the training of the ML model may be performed offline at an ML workstation / server. For example, a model training host (e.g., model training host 702) may receive features from a data source (e.g., data source 706) (such as a higher performance positioning device with atomic clock accurate hardware or an end-user device (e.g., participant 708 and / or action subject 710)) for training an ML model to classify GNSS PR measurements in terms of relative NLOS errors (hereinafter may be referred to as an "ML classifier" or "weight-based ML classifier"), because signals received by a GNSS device via an NLOS path may include more errors and / or higher delays than signals received via an LOS path. In one example, features used to train a weight-based ML classifier may include raw GNSS SV observables (e.g., raw GNSS measurements), such as carrier-to-noise ratio (C / No), elevation / azimuth, autocorrelation function (ACF), code-carrier phase consistency, measurement status and error flags from hardware and measurement engines, consistency checks between different band measurements from the same SV (e.g., between L1 band and L5 band measurements), weighted least squares a posteriori residuals, and / or signal (energy) integration information (e.g., duration, mode, etc.) for each SV measurement, etc. Then, based on the features collected from the plurality of SVs, the model training host may be configured to derive a relationship between the plurality of SVs for the weight-based ML classifier. For example, the relationship may be based on SV geometry, such as a geometric orientation of a set of SVs relative to a GNSS device, wherein the geometric orientation may depend on at least one azimuth (or elevation) and zenith angle between the GNSS device and a corresponding SV in the set of SVs.

[0099] Fig. 9 900 is a diagram illustrating example SV geometries in accordance with various aspects of the present disclosure. In one example, the training of a weight-based ML classifier may be based on the geometry of the SVs, such as based on the spherical distances between the SVs relative to a ground point (e.g., observed / measured by a GNSS device). For example, the diagram shown at 902 is an example sky map of multiple SVs observed by a GNSS device at a ground point (e.g., SV positions relative to the GNSS device). The sky map may provide an example of SV tracks and / or spherical distances between SVs at a given ground point. As shown at 904, the spherical distance between two SVs (e.g., SV(j) and SV(i)) may refer to the distance along the great circle of the two SVs.

[0100] In one aspect of the present disclosure, if the spherical distance between two SVs is below a distance threshold (e.g., the distance between the two SVs is small), there may be a correlation between the two SVs (in terms of measurements), at least from the perspective of the GNSS device. For example, as shown at 902, since SV3 and SV4 are closer to each other than other SVs (e.g., SV 1, 2, 5, 7, and 9, etc.), the signals measured from SV3 and SV4 may have some common conditions (e.g., LOS conditions, NLOS conditions, etc.) and / or errors (e.g., ionospheric / tropospheric errors). Therefore, measurements of SV3 (e.g., feature / raw measurements) may be used to assist measurements of SV4, and vice versa. For example, if the GNSS device measures a signal from SV3 and derives a set of errors associated with SV3, the GNSS device may be configured to assume that the same set of errors also applies to signals from SV4. In another example, if the GNSS device receives a signal from SV4 via an NLOS path, the GNSS device may also assume that the signal received from SV3 is based on the NLOS path. Therefore, returning to reference Fig. 8A , based at least in part on the geometry between the SVs and features obtained from the SVs (e.g., raw GNSS SV observables), a weight-based ML classifier may be trained to provide relative weights for PR measurements from an SV based on measurements from one or more other SVs, and the weight-based ML classifier may perform the same operation on all PR measurements from multiple SVs to provide relative weights for these PR measurements (which may also be referred to as relative PR weights). For example, since SVs that are closer to each other may have similar errors, the relative PR weights may be configured as a function associated with these errors (which may be referred to as PR errors). Therefore, the weight-based ML classifier may be trained to classify the likelihood of LOS and / or NLOS conditions, where PR measurements based on NLOS conditions may be set with lower weights than PR measurements based on LOS conditions. In other words, the relative PR weight of one SV in a set of SVs may be based on the spherical distance between the one SV and each SV in at least a subset of the set of SVs, and the spherical distance between the one SV and another SV may be based on the geometric orientation of the one SV compared to the geometric orientation of the other SV. In addition, the relative PR weight of an SV in the SV set may also be based on one or more of the following: carrier-to-noise ratio, autocorrelation function, code-carrier phase consistency, measurement status or error flag, consistency between different frequency band measurements of the one SV, weighted least squares posterior residual or signal integration information, etc.

[0101] In one example, a weight-based ML classifier can be trained based on a graph convolutional network (GCN). GCN is a type of convolutional neural network (CNN) that can work directly on graphs and exploit their structural information. GCN can be used to classify nodes in a graph where labels are available for a small subset of nodes. For example, Fig. 9 As shown in the diagram at 902 of , each SV in the sky graph can be represented by a node in the GCN, and if the spherical distance between two nodes (e.g., two SVs) is below a distance threshold, the two nodes can be connected to each other. For example, SV 3 can be connected to SV 4 and SV 7, SV 7 can be connected to SV 3, SV 4, SV 5, and SV 9, and SV 1 can be connected to SV 5, and so on. Therefore, it can be assumed that each node can have some relationship with other nodes in the graph, which are represented by edge connections and edge weights (spherical distances between SVs). Each connected node can provide additional information to each other by sharing their corresponding node features through a neighbor node aggregation method (which can be referred to as "message passing"). There may also be other variations and alternatives to message passing.

[0102] Fig.10 1000 is a diagram illustrating an example ML training based on GCN according to various aspects of the present disclosure. A target node can be predicted via a neural network using aggregated neighboring node features, which can be a task like node classification or structure / context determination. For example, during ML training, a target node (e.g., a target SV) can first sample neighboring nodes (e.g., other SVs) of a candidate node (e.g., an SV with a spherical distance below a threshold). The target node can then aggregate feature information (e.g., raw GNSS SV observables) from these candidate nodes, and the target node can predict graph context and labels based on the aggregated feature information. In other words, a graph can be constructed to represent SV measurements based on the geometric structure of the SV (e.g., a sky map), and then a graph neural network (GNN) (e.g., GCN) and GNN-like ML methods (e.g., non-seasonal variation (NSV), multi-layer perceptron (MLP)) can be used to effectively use neighboring SV measurements to assist in primary SV classification.

[0103] Figure 8B is a diagram 800B illustrating an example ML inference for an ML model capable of classifying GNSS PR measurements in accordance with various aspects of the present disclosure. Fig. 8AFollowing the weight-based ML classifier discussed above, a GNSS device or a location server may use the weight-based ML classifier to classify PR measurements from different SVs. For example, a GNSS device may measure PRs of multiple SVs, and the weight-based ML classifier may provide a relative PR weight for each PR measured. For example, referring to Fig. 9 , the GNSS device may measure the PR of SV 1, SV 2, SV 3, SV 4, SV 5, SV 7, and SV 9, and the weight-based ML classifier may provide a PR weight for the PR measurements in the PR measurements from each SV based on the measurements from the other SVs. Subsequently, the GNSS device may perform a positioning estimate based on the weighted PR measurements, which may provide a higher positioning accuracy compared to non-weighted PR measurements. Therefore, by using accurate PR error labels (e.g., obtained from a third-party real positioning device and an atomic clock reference) to construct label data for ML training, the ML model may construct classification label data based on the PR error labels, such as based on a combination of absolute PR errors and relative differences within a given lock period (Figure). An period may refer to a moment used as a reference point for some time-varying astronomical quantity.

[0104] In another aspect of the present invention, in order to enable the deployment of the various aspects presented herein on GNSS devices with lower computing resources, a weight-based ML classifier may be trained and provide inferences based on non-seasonal variations (NSV) and / or multi-layer perceptrons (MLPs), which may reduce the complexity of ML training and / or ML inference, but the performance / accuracy of positioning may be slightly reduced. MLP may refer to a neural network in which the mapping between input and output may be nonlinear. For example, MLP may be a class of feedforward artificial neural networks (ANNs), which may refer to a network composed of multi-layer perceptrons (with threshold activation). MLP may include at least three layers of nodes: an input layer, one or more hidden layers, and an output layer. In addition to the input nodes, each node may be a neuron using a nonlinear activation function. The input may be combined with the initial weights into a weighted sum and subject to an activation function. Then, each layer (starting from the input layer) may feed its calculation results and / or internal representations of the data to the next layer, which may reach the output layer. In some examples, MLP may be trained using a supervised learning technique known as backpropagation. Backpropagation may refer to a learning mechanism that allows an MLP to iteratively adjust weights in a network with the goal of minimizing a cost function. Outputs may be generated from multiple inputs based on an MLP.

[0105] Fig.111100 is a diagram illustrating an example architecture of an MLP-based near-GCN classifier according to various aspects of the present disclosure. For an MLP-based weight-based ML classifier, features from multiple SVs may be provided to the front end of the MLP (e.g., the input layer of the MLP). The features may then be aggregated based on their weights through one or more hidden layers of the MLP to generate a relative PR weight for each SV (relative to other SVs). For example, to determine the relative PR weight of SV(i), features (e.g., measurements) from SV(i) and other SVs (e.g., SV(j), SV(k), SV(l), etc.) may be provided to the MLP. Then, based on ML training, the relative PR weight of SV(i) may be obtained. Although an MLP-based ML classifier may have lower performance and accuracy than a GCN-based ML classifier, the performance tradeoff may be acceptable in some scenarios because memory and CPU usage may be significantly reduced.

[0106] Fig.12 1200 is an example of a horizontal error cumulative distribution function (CDF) for an MLP-based ML classifier and a GCN-based ML classifier according to various aspects of the present disclosure. The accuracy of a GNSS device may be measured based on the accuracy of a horizontal component (e.g., easting and northing), which may be expressed by a circular error probability (CEP). The CEP may indicate that there is a 50% probability that the true horizontal position is within a circle whose radius is equal to the value of the CEP. As shown in the diagram 1200, both the GCN-based ML classifier and the MLP-based ML classifier may provide better positioning performance compared to a baseline performance (e.g., no ML classifier / classification). Although the GCN-based ML classifier may provide better performance in terms of horizontal error compared to the MLP-based ML classifier (e.g., the GCN-based ML classifier is closer to the true-based performance than the MLP-based ML classifier), the MLP-based ML classifier consumes relatively less memory (e.g., approximately 33KB) compared to the GCN-based ML classifier (e.g., approximately 11.2MB). Therefore, in some scenarios, for GNSS devices with less memory availability or for GNSS devices with lower capabilities, MLP-based ML classifiers may be a more appropriate choice.

[0107] Fig.131300 is a diagram illustrating an example of receiver operating characteristics of an MLP-based ML classifier and a GCN-based ML classifier according to various aspects of the present disclosure. Diagram 1300 illustrates the performance of an MLP-based ML classifier and a GCN-based ML classifier in terms of receiver operating characteristics based on the area under the curve (AUC). AUC is a measure of the ability of a classifier to distinguish between classes. Generally, the higher the AUC, the better the model performs in distinguishing between positive and negative classes. As illustrated in diagram 1300, a GCN-based ML classifier may provide better performance in terms of receiver operating characteristics compared to an MLP-based ML classifier. Therefore, in some scenarios, a GCN-based ML classifier may be a more appropriate choice for GNSS devices with sufficient memory availability or for GNSS devices that specify higher positioning accuracy and / or speed.

[0108] In another aspect of the present invention, a positioning grid-based ML classifier is provided to a GNSS device to improve the accuracy of identifying a hot start position of the GNSS device. A hot start of a GNSS device may refer to a scenario in which the GNSS device remembers its last estimated position or is able to estimate its initial position (e.g., based on the location of a serving base station or access point), the almanac used, and UTC time, but does not know which SVs are in view. The GNSS device may then perform a reset and attempt to acquire SV GNSS signals and estimate a new position. The GNSS device may have a rough idea of ​​which SVs to look for based on the last known position, and the almanac data may help the GNSS device identify which satellites are visible in the sky. This process may take some time.

[0109] In one aspect, a GNSS device may be configured to estimate its initial position and establish a positioning grid with a fixed resolution (e.g., with multiple grid points) based on the estimated initial position, which covers a positioning uncertainty region. The GNSS device may then calculate the PR measurement residuals for each SV at each grid point of the positioning grid. A positioning grid-based ML classifier may be trained to process the GNSS observables for each SV and the PR measurement residuals obtained by the GNSS device to infer / predict the probability of whether a grid point is near the actual position of the GNSS device. For example, a positioning grid-based ML classifier may be trained based on PR error estimates derived from known distances between an atomic clock accurate and / or GNSS device position and a grid point position, and the positioning grid-based ML classifier may use the distribution of grid point probabilities on the positioning grid to estimate the GNSS device position.

[0110] Fig.141400 is a diagram illustrating an example of known and unknown parameters of a GNSS device during a warm start according to various aspects of the present disclosure. During a warm start of a GNSS device 1402, the GNSS device 1402 may be able to identify: (1) GNSS PR measurements: raw range measurements obtained from a GNSS measurement engine (e.g., based on local GNSS arrival time minus GNSS transmit time); (2) SV position: the position of the SV 1404 derived from ephemeris or XTRA; and (3) initial estimated GNSS device position: the initial position of the GNSS device 1402 used for fixed position calculation. On the other hand, the GNSS device 1402 may not be able to identify one or more of the following: (a) actual GNSS device position: the actual position of the GNSS device 1402; (b) SV range: the distance from the position of SV 1404 to the position of the GNSS device 1402, which distance may be unique for each individual SV; (c) SV range error: the SV range error calculated based on the initial estimated GNSS device position and the SV position, which error may be unique for each individual SV (e.g., a typical error is -1km to +1km); (d) measurement error: measurement error due to noise and / or excess delay (e.g., a typical noise error = + / -10m, and a typical excess delay error = +20m to +300m); and / or (e) clock error: the GNSS time error determined from the local receiver clock, which error may apply to all PR measurements in the same period (e.g., a typical clock error is -10km to +10km). Therefore, to determine the SV range, the GNSS device 1402 may be directed to account for or determine three sources of error (eg, clock error, noise error, and excess delay error).

[0111] For example, to determine the SV range error, the GNSS device 1402 may be configured to distinguish whether the measurement error includes both a noise error and an excess delay error (hereinafter referred to as "Case A"), or whether the measurement error includes a noise error but does not include an excess delay error (hereinafter referred to as "Case B"). Case A measurements are more likely to be associated with NLOS measurements (e.g., based on NLOS conditions or multipath reception of GNSS signals) because they include excess delay errors, while Case B measurements are more likely to be associated with LOS measurements (e.g., based on LOS conditions or multipath reception of GNSS signals) because they do not include excess delay errors (thereby providing better range estimates). In some examples, knowledge of the clock error may be skipped because the clock error may be common to all PR measurements. In some scenarios, for a set of N PR measurements (e.g., typically N=15 to 50), the initially estimated GNSS device position (and therefore the SV range error) may continually change to make the Case A measurement look like a Case B measurement, and vice versa. Therefore, in one aspect of the present invention, an ML classifier (hereinafter referred to as a "positioning grid-based ML classifier") may be trained to classify whether a PR measurement is associated with case A or case B, because among the N PR measurements, there may generally be a subset of case A measurements, and the measurement errors may be specified to be accurately modeled. For example, the positioning grid-based ML classifier may be trained to initially distinguish between case A and case B for the GNSS device 1402, and then the GNSS device 1402 may be able to estimate a more accurate clock error and receiver position. In other words, if the positioning grid-based ML classifier works properly, the measurement error calculated after using the estimated clock error and the actual receiver position may be a noise error or an excess delay error plus a noise error (e.g., no measurement error may indicate an early arrival).

[0112] Fig.15 1500 is a diagram illustrating an example of identifying a position of a GNSS device (e.g., GNSS device 1402) based on a positioning grid approach in accordance with various aspects of the present disclosure. In one example, during a warm start, GNSS device 1402 may be configured to define a two-dimensional (2D) rectangular positioning grid approximately centered around an initial estimated GNSS device position, with grid points spaced apart at defined distances (e.g., X meters apart). GNSS device 1402 may be specified to consider only grid points that fall within a positioning uncertainty region (e.g., a circular region) defined by the initial positioning uncertainty (e.g., within a radius of Y meters from the initial estimated GNSS device position).

[0113] Then, for each grid point (G) within the positioning grid, the GNSS device 1402 may calculate the PR measurement residual for the PR measurement set available at the current time period, where the PR measurement residual may be equal to the difference between the PR measurement minus the predicted PR (e.g., PR measurement residual = PR measurement - predicted PR, where predicted PR = the range of G to SV 1404, and certain correction factors may be excluded for simplicity). The PR measurement residual measured at the grid point may provide what the PR measurement residual would look like at the grid point when the GNSS device 1402 is located at the grid point. For example, assuming there are a total of ten (10) PR measurements (e.g., measured from ten SVs), including five (5) case A measurements (e.g., PR measurements including excess delay error and noise error) and five (5) case B measurements (e.g., PR measurements including only noise error), which may be distinguished by the GNSS device 1402 based on the trained positioning grid-based ML classifier. As shown at 1406, when the grid point used to calculate the PR measurement residual (e.g., grid point G(j)) is further away from the actual GNSS device position (e.g., nine grid spacings away), the case A measurements and the case B measurements may tend to be randomly distributed at early and late points of the distribution. On the other hand, as shown at 1408, when the grid point used to calculate the PR measurement residual (e.g., grid point G(i)) is closer to the actual GNSS device position (e.g., one grid spacing away), the case B measurements may be distributed / aggregated in the earliest range of the distribution, while the case A measurements may be evenly distributed at later points of the distribution. In other words, based on the distribution of the case A and case B measurements, the GNSS device 1402 may estimate its actual position more quickly and accurately. In other words, the GNSS device 1402 is more likely to be located near (e.g., close to) the grid points having the case A and case B measurements distributed as shown at 1408, and less likely to be located near the grid points having the case A and case B measurements distributed as shown at 1406.

[0114] When the measured grid point (e.g., G(i)) is closer to the true position of the GNSS device 1402, good PR measurement residuals (e.g., measurements without excessive delay) may be distributed / clustered on the early side of the distribution because the nature of GNSS reflections is delay, which may be random (e.g., it depends on how the SV signal reflects off buildings and other obstacles). Therefore, if the grid point is close (near) to the true position of the GNSS device 1402, there is a characteristic graph in which good measurements (e.g., case B measurements) are distributed / clustered in the early part of the distribution, and bad measurements (e.g., case A measurements) are distributed / clustered in the later part of the distribution due to delay. Such clustering associated with G(i) is due to the estimated PR (depending on G(i)) being closer to the measured PR (e.g., the true position of the GNSS device 1402). However, if the measured grid point is not close to the true position of the GNSS device, the case A measurement and the case B measurement may be confused because the error between the measured grid point and the true position of the GNSS may also be random. Since there are essentially two sources of error, one due to reflections (e.g., NLOS conditions) and the other being the error in the GNSS device's position, both may be projected into the prediction of the distance to the satellite. Thus, the two sources of error may interfere with each other constructively or destructively, resulting in a distribution / clustering pattern as shown at 1406. Such clustering associated with G(j) is due to the estimated PR (depending on G(j)) being further away from the measured PR (e.g., the true position of the GNSS device 1402).

[0115] Similarly, in another aspect of the present disclosure, an ML classifier (e.g., an additional ML classifier or a positioning grid-based ML classifier) ​​may be trained to identify whether a grid point is close to the actual position of the GNSS device 1402, thereby estimating the actual position of the GNSS device 1402. For example, the positioning grid-based ML classifier may be trained to first identify whether a PR measurement of a plurality of SVs from a period is a case A measurement or a case B measurement, and then the positioning grid-based ML classifier may determine the probability of whether a grid point is close to the actual position of the GNSS device 1402 based on the aggregation / distribution pattern of the case A and case B measurements. Based on the probability of identifying whether each of the grid points within the positioning uncertainty region is close to the GNSS device 1402, the GNSS device 1402 may create a 2D heat map showing the probability (e.g., expressed as a percentage, such as 50% or 75%) or the likelihood (e.g., expressed as a relative comparison, such as low, medium, and high) of whether these grid points are close to the actual position of the GNSS device 1402.

[0116] Fig.16is a diagram 1600 illustrating an example ML classifier based on a positioning grid for inferring whether a grid point is close to an actual position of a GNSS device in accordance with various aspects of the present disclosure. The ML classifier based on the positioning grid can use all available information for training and inference. For example, the ML classifier based on the positioning grid can use the measurement errors of all PR measurements and / or the actual GNSS device position as labels, and use the GNSS measurement observables of each SV (e.g., C / No, code / carrier consistency, carrier phase availability, weighted least squares posterior residuals, etc.), the geometric relationships between SVs (e.g., combined with Fig. 9 spherical distance described) and / or the distribution of PR measurement residuals calculated at grid points as features for ML training and inference. For example, a positioning grid-based ML classifier can be trained based on a multi-class GCN to estimate the weighted probabilities of all SVs. Then, another per-grid-point ML classifier can be further trained to receive the weighted probability of each SV and / or the PR measurement residuals of each SV as features, and generate labels for grid points based on the grid spacing between the grid points and the actual GNSS device positioning (e.g., if the grid point is <= 1 grid spacing away from the actual GNSS device positioning, it is TRUE, and if the grid point is > 1 grid spacing away from the actual GNSS device positioning, it is FALSE, and so on). Therefore, during ML inference, the positioning grid-based ML classifier can calculate the probability that each grid point is within 1 grid spacing from the actual GNSS device positioning, and the positioning grid-based ML classifier can declare the position of the actual GNSS device positioning based on a 2D heat map of grid point probabilities.

[0117] In another aspect of the present invention, the likelihood / probability of whether the grid point is close to the actual position of the GNSS receiver and / or the PR set of each grid point (e.g., for case A measurement and case B measurement) may be further provided as a combination of Fig. 8A , Figure 8B , Fig. 9 , Fig.10 and Fig.11 The features of the weight-based ML classifier described above enable the weight-based ML classifier to further determine the weights of the PR measurements from different SVs based on these possibilities / probabilities and / or the PR set of each grid point. The GNSS device or location server can then determine or estimate the location of the GNSS device based on the weighted PR measurements, which can further enhance the accuracy of the GNSS device positioning.

[0118] In another aspect of the present invention, a first ML classifier (ie, a weight-based ML classifier) ​​may determine the position of the GNSS device based on the weighted PR measurements (eg, as combined with Fig. 8A , Figure 8B , Fig. 9 , Fig.10 and Fig.11 ), and a second ML classifier (i.e., a positioning grid-based ML classifier) ​​may determine the position of the GNSS device based on the grid points (e.g., as combined with Figures 14 to 16 The third ML classifier may then receive the determined positions of the GNSS device from both the first ML classifier and the second ML classifier, and the third ML classifier may weight the positions from the first and second ML classifiers and provide an estimated GNSS device position based on the weighted positions.

[0119] Fig.17 1700 is a flowchart of a positioning estimation method. The method may be performed by a positioning device or a positioning entity (e.g., UE 104; base station 102, GNSS device 506, 606, 1402; apparatus 1804; network entity 1802). The method may enable a device to perform PR measurement error detection and classification based on SV geometry via ML, and the device (e.g., device) may be associated with a UE, a location server, or a combination thereof.

[0120] At 1702, the positioning device or the positioning entity may determine at least one geometric orientation relative to the UE for each SV in the SV set, such as in combination with Fig. 9 For example, the GNSS device may determine at least one geometric orientation relative to the GNSS device for each SV in the SV set based on a sky map. The determination of the geometric orientation may be performed by, for example Fig.18 The positioning ML component 198 of the device 1804 and / or the positioning ML component 199 of the network entity 1802 are executed.

[0121] In one example, the geometric orientation may depend on at least one azimuth angle (or elevation angle) and a zenith angle between the UE and a corresponding SV in the set of SVs.

[0122] At 1704, the positioning device or the positioning entity may determine a relative PR weight for each SV in the set of SVs based on the geometric orientation relative to the UE determined for each SV in at least a subset of the set of SVs (and in some examples also based on the ML classifier), such as in combination with Figure 8B and Fig. 9 For example, the GNSS device may determine a relative PR weight for each SV in the SV set based on the ML classifier and a geometric orientation of each SV in at least a subset of the SV set relative to the UE. The relative PR weight may be determined by Fig.18 The positioning ML component 198 of the device 1804 and / or the positioning ML component 199 of the network entity 1802 are executed.

[0123] In one example, the relative PR weight of one SV in the set of SVs may be based on a spherical distance between the one SV and each SV in at least a subset of the set of SVs, wherein the spherical distance between the one SV and another SV may be based on a geometric orientation of the one SV compared to a geometric orientation of the other SV. In such examples, the relative PR weight of the one SV in the set of SVs may be further based on one or more of: a carrier-to-noise ratio, an autocorrelation function, code-carrier phase consistency, a measurement status or error flag, consistency between different frequency band measurements of the one SV, a weighted least squares a posteriori residual, or signal integration information.

[0124] In such examples, the relative PR weight may be based on the relative PR error predicted by the ML classifier.

[0125] At 1706, the positioning device or the positioning entity may estimate the positioning of the UE based on the PR measurement of each SV in the SV set and the relative PR weight of each SV in the SV set, such as in combination with Figure 8B For example, the GNSS device may estimate the position of the GNSS device based on the PR measurement of each SV in the SV set and the relative PR weight of each SV in the SV set. The estimation of the position of the UE may be performed by, for example Fig.18 The SPS module 1816 / positioning ML component 198 of the device 1804 and / or the positioning ML component 199 of the network entity 1802 are executed.

[0126] In an example, the positioning device or the positioning entity may receive a signal from the SV set, and perform the PR measurement on the SV set based on the signal.

[0127] Fig.181800 is an example of a hardware implementation of an example device 1804. The device 1804 may be a UE, a component of a UE, or may implement UE functionality. In some aspects, the device 1804 may include a cellular baseband processor 1824 (also referred to as a modem) coupled to one or more transceivers 1822 (e.g., a cellular RF transceiver). The cellular baseband processor 1824 may include on-chip memory 1824'. In some aspects, the device 1804 may also include one or more subscriber identity module (SIM) cards 1820 and an application processor 1806 coupled to a secure digital (SD) card 1808 and a screen 1810. The application processor 1806 may include on-chip memory 1806'. In some aspects, the device 1804 may also include a Bluetooth module 1812, a WLAN module 1814, an SPS module 1816 (e.g., a GNSS module), one or more sensor modules 1818 (e.g., an atmospheric pressure sensor / altimeter; a motion sensor such as an inertial management unit (IMU), a gyroscope, and / or an accelerometer; light detection and ranging (LIDAR), radio-aided detection and ranging (RADAR), sound navigation and ranging (SONAR), a magnetometer, audio, and / or other technologies for positioning), an additional memory module 1826, a power source 1830, and / or a camera 1832. The Bluetooth module 1812, the WLAN module 1814, and the SPS module 1816 may include an on-chip transceiver (TRX) (or in some cases, only a receiver (RX)). The Bluetooth module 1812, the WLAN module 1814, and the SPS module 1816 may include their own dedicated antennas and / or communicate using an antenna 1880. The cellular baseband processor 1824 communicates with the UE 104 and / or with the RU associated with the network entity 1802 through the transceiver 1822 via one or more antennas 1880. The cellular baseband processor 1824 and the application processor 1806 may each include a computer-readable medium / memory 1824', 1806', respectively. The additional memory module 1826 may also be considered as a computer-readable medium / memory. Each computer-readable medium / memory 1824', 1806', additional memory module 1826 may be non-transitory. The cellular baseband processor 1824 and the application processor 1806 are each responsible for general processing, including executing software stored on a computer-readable medium / memory. The software enables the cellular baseband processor 1824 / application processor 1806 to perform the various functions described above when executed by the cellular baseband processor 1824 / application processor 1806. The computer-readable medium / memory can also be used to store data manipulated by the cellular baseband processor 1824 / application processor 1806 when executing the software.The cellular baseband processor 1824 / application processor 1806 may be a component of the UE 350 and may include the memory 360 and / or at least one of the TX processor 368, the RX processor 356, and the controller / processor 359. In one configuration, the device 1804 may be a processor chip (modem and / or application) and include only the cellular baseband processor 1824 and / or the application processor 1806, while in another configuration, the device 1804 may be the entire UE (e.g., see. Figure 3 350) and includes additional modules of device 1804.

[0128] As discussed above, the positioning ML component 198 / 199 is configured to: determine at least one geometric orientation relative to the UE for each SV in the SV set; determine a relative PR weight for each SV in the SV set based on the ML classifier and the geometric orientation relative to the UE determined for each SV in at least a subset of the SV set; and estimate the positioning of the UE based on the PR measurement of each SV in the SV set and the relative PR weight of each SV in the SV set. The positioning ML component 198 may be within the cellular baseband processor 1824, the application processor 1806, or both the cellular baseband processor 1824 and the application processor 1806. The positioning ML component 198 / 199 may be one or more hardware components that are specifically configured to perform the stated process / algorithm, implemented by one or more processors configured to perform the stated process / algorithm, stored in a computer-readable medium for implementation by one or more processors, or some combination of the above. As shown, the device 1804 may include a variety of components configured for various functions. In one configuration, the device 1804 (and in particular the cellular baseband processor 1824 and / or the application processor 1806) includes: a component for determining at least one geometric orientation relative to the UE for each SV in the SV set; a component for determining a relative PR weight for each SV in the SV set based on an ML classifier and the geometric orientation relative to the UE determined for each SV in at least a subset of the SV set; a component for estimating the positioning of the UE based on the PR measurement of each SV in the SV set and the relative PR weight of each SV in the SV set; a component for receiving a signal from the SV set; and a component for performing the PR measurement on the SV set based on the signal. In some examples, the component may be the positioning ML component 198 of the device 1804, or be configured to perform the functions recorded by the component. As described above, the device 1804 may include a TX processor 368, an RX processor 356, and a controller / processor 359. Thus, in one configuration, the means may be the TX processor 368, the RX processor 356, and / or the controller / processor 359 configured to perform the functions recited by the means. In other examples, the means may be the positioning ML component 199 of the network entity 1802, which is configured to perform the functions recited by the means. As described above, the network entity 1802 may include the TX processor 316, the RX processor 370, and the controller / processor 375. Thus, in one configuration, the means may be the TX processor 316, the RX processor 370, and / or the controller / processor 375 configured to perform the functions recited by the means.

[0129] It should be understood that the specific order or hierarchy of the blocks in the disclosed process / flowchart is only an illustration of the exemplary method. It should be understood that the specific order or hierarchy of the blocks in the process / flowchart can be rearranged based on design preferences. In addition, some blocks can be combined or omitted. The attached method claims provide the elements of each block in a sample order, but are not limited to the specific order or hierarchy provided.

[0130] The foregoing description is provided to enable any person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects. Therefore, the claims are not limited to the various aspects described herein, but should be given the full scope consistent with the language claims. Unless otherwise specified, reference to an element in the singular form does not mean "one and only one", but "one or more". Terms such as "if", "when ..." and "at ..." do not mean a direct temporal relationship or reaction. That is, these phrases, such as "when ...", do not mean an instant action in response to the occurrence of an action or during the occurrence of an action, but only mean that if the condition is met, the action will occur without a specific or instantaneous time constraint to make the action occur. The word "exemplary" is used herein to mean "used as an example, instance, or illustration". Any aspect described as "exemplary" herein is not necessarily interpreted as being preferred or having an advantage over other aspects. Unless otherwise specified, the term "some" refers to one or more. Combinations such as "at least one of A, B, or C," "one or more of A, B, or C," "at least one of A, B and C," "one or more of A, B, and C," and "A, B, C, or any combination thereof" include any combination of A, B, and / or C, and may include multiple A, multiple B, or multiple C. Specifically, combinations such as "at least one of A, B, or C," "one or more of A, B, or C," "at least one of A, B, and C," "one or more of A, B, and C," and "A, B, C, or any combination thereof" may be only A, only B, only C, A and B, A and C, B and C, or A and B and C, where any such combination may contain one or more members of A, B, or C. A set should be interpreted as a set of elements, where the number of elements is one or more. Thus, for a set of X, X will include one or more elements. If the first device receives data from the second device or sends data to the second device, the data may be received / sent directly between the first device and the second device, or indirectly between the first device and the second device through a collection of devices. All structural and functional equivalents of the elements throughout the various aspects described in this disclosure that are known or will later be known to a person of ordinary skill in the art are expressly incorporated herein by reference and are covered by the claims. In addition, nothing disclosed herein is intended to be dedicated to the public, regardless of whether such disclosure is explicitly stated in the claims. Words such as "module", "mechanism", "element", "device", etc. cannot replace the word "component". Therefore, no claim element will be understood as a component plus function unless the element is explicitly stated using the phrase "component for..."

[0131] As used herein, the phrase "based on" should not be interpreted as referring to a closed set of information, one or more conditions, one or more factors, etc. In other words, the phrase "based on A" (where "A" can be information, a condition, a factor, etc.) should be interpreted as "based at least on A" unless specifically stated differently.

[0132] The following aspects are merely illustrative and may be combined with other aspects or teachings described herein without limitation.

[0133] Aspect 1 is a positioning estimation method, the method comprising: determining at least one geometric orientation relative to the UE for each SV in a SV set; determining a relative PR weight of each SV in the SV set based on an ML classifier and the geometric orientation relative to the UE determined for each SV in at least one subset of the SV set; and estimating the positioning of the UE based on the PR measurement of each SV in the SV set and the relative PR weight of each SV in the SV set.

[0134] Aspect 2 is a method according to aspect 1, wherein the geometric orientation depends on at least one azimuth angle and zenith angle between the UE and a corresponding SV in the set of SVs.

[0135] Aspect 3 is a method according to any one of Aspects 1 and 2, wherein the relative PR weight of one SV in the SV set is based on the spherical distance between the one SV and each SV in the at least one subset of the SV set, and the spherical distance between the one SV and another SV is based on the geometric orientation of the one SV compared to the geometric orientation of the other SV.

[0136] Aspect 4 is a method according to any one of Aspects 1 to 3, wherein the relative PR weight of the one SV in the SV set is further based on one or more of the following: carrier-to-noise ratio, autocorrelation function, code-carrier phase consistency, measurement status or error flag, consistency between different frequency band measurements of the one SV, weighted least squares posterior residual or signal integration information.

[0137] Aspect 5 is a method according to any one of aspects 1 to 4, wherein the relative PR weight is based on a relative PR error predicted by the ML classifier.

[0138] Aspect 6 is a method according to any one of aspects 1 to 5, wherein the method is performed by the UE, a location server, or a combination thereof.

[0139] Aspect 7 is a method according to any one of aspects 1 to 6, the method further comprising: receiving a signal from the SV set; and performing the PR measurement on the SV set based on the signal.

[0140] Aspect 8 is a device for positioning estimation, and the device is used to implement any one of aspects 1 to 7.

[0141] Aspect 9 is a device for positioning estimation, comprising means for implementing any one of aspects 1 to 7.

[0142] Aspect 10 is a computer-readable medium storing computer-executable code, wherein the code, when executed by a processor, causes the processor to implement any one of aspects 1 to 7.

[0143] Aspect 11 is a positioning estimation method, the method comprising: determining at least one geometric orientation relative to the UE for each SV in a SV set; determining a relative PR weight of each SV in the SV set based on the geometric orientation relative to the UE determined for each SV in at least one subset of the SV set; and estimating the positioning of the UE based on the PR measurement of each SV in the SV set and the relative PR weight of each SV in the SV set.

[0144] Aspect 12 is a method according to aspect 11, wherein the geometric orientation depends on at least one azimuth angle and zenith angle between the UE and a corresponding SV in the set of SVs.

[0145] Aspect 13 is a method according to any one of Aspects 11 and 12, wherein the relative PR weight of one SV in the SV set is based on the spherical distance between the one SV and each SV in the at least one subset of the SV set, and the spherical distance between the one SV and another SV is based on the geometric orientation of the one SV compared to the geometric orientation of the other SV.

[0146] Aspect 14 is a method according to any one of Aspects 11 to 13, wherein the relative PR weight of the one SV in the SV set is further based on one or more of the following: carrier-to-noise ratio, autocorrelation function, code-carrier phase consistency, measurement status or error flag, consistency between different frequency band measurements of the one SV, weighted least squares posterior residual, or signal integration information.

[0147] Aspect 15 is a method according to any one of aspects 11 to 14, wherein the relative PR weight is based on a relative PR error predicted by an ML classifier.

[0148] Aspect 16 is a method according to any one of aspects 1 to 15, wherein the method is performed by the UE, a location server, or a combination thereof.

[0149] Aspect 17 is a method according to any one of aspects 11 to 16, the method further comprising: receiving a signal from the set of SVs; and performing the PR measurement on the set of SVs based on the signal.

[0150] Aspect 18 is a device for positioning estimation, wherein the device is used to implement any one of aspects 11 to 17.

[0151] Aspect 19 is a device for positioning estimation, comprising means for implementing any one of aspects 11 to 17.

[0152] Aspect 20 is a computer-readable medium storing computer-executable code, wherein the code, when executed by a processor, causes the processor to implement any one of aspects 11 to 17.

Claims

1. A device for positioning estimation, the device comprising: Memory; and at least one processor coupled to the memory and based at least in part on the information stored in the memory, the at least one processor configured to: determining, for each space vehicle (SV) in a set of space vehicles (SVs), at least one geometric orientation relative to a user equipment (UE); determining a relative pseudorange (PR) weight for each SV in the set of SVs based on a machine learning (ML) classifier and a geometric orientation relative to the UE determined for each SV in at least a subset of the set of SVs; as well as The positioning of the UE is estimated based on the PR measurement of each SV in the set of SVs and the relative PR weight of each SV in the set of SVs. 2 . The apparatus of claim 1 , wherein the geometric orientation depends on at least one azimuth angle and a zenith angle between the UE and a corresponding SV in the set of SVs.

3. An apparatus according to claim 1, wherein the relative PR weight of one SV in the SV set is based on the spherical distance between the one SV and each SV in the at least one subset of the SV set, and the spherical distance between the one SV and another SV is based on the geometric orientation of the one SV compared to the geometric orientation of the other SV.

4. An apparatus according to claim 3, wherein the relative PR weight of the one SV in the SV set is further based on one or more of the following: carrier-to-noise ratio, autocorrelation function, code-carrier phase consistency, measurement status or error flag, consistency between different frequency band measurements of the one SV, weighted least squares posterior residual or signal integration information.

5. The apparatus of claim 1, wherein the relative PR weight is based on a relative PR error predicted by the ML classifier. The apparatus of claim 1 , wherein the apparatus is associated with the UE, a location server, or a combination thereof.

7. The device according to claim 1, further comprising: receiving a signal from the set of SVs; as well as The PR measurement is performed on the set of SVs based on the signal.

8. The apparatus of claim 7, further comprising a global navigation satellite system (GNSS) receiver coupled to the at least one processor and configured to receive the signal from the set of SVs.

9. A positioning estimation method, the method comprising: determining, for each space vehicle (SV) in a set of space vehicles (SVs), at least one geometric orientation relative to a user equipment (UE); determining a relative pseudorange (PR) weight for each SV in the set of SVs based on a machine learning (ML) classifier and a geometric orientation relative to the UE determined for each SV in at least a subset of the set of SVs; as well as The positioning of the UE is estimated based on the PR measurement of each SV in the set of SVs and the relative PR weight of each SV in the set of SVs.

10. The method of claim 9, wherein the geometric orientation depends on at least one azimuth angle and a zenith angle between the UE and a corresponding SV in the set of SVs.

11. A method according to claim 9, wherein the relative PR weight of one SV in the SV set is based on the spherical distance between the one SV and each SV in the at least one subset of the SV set, and the spherical distance between the one SV and another SV is based on the geometric orientation of the one SV compared to the geometric orientation of the other SV.

12. The method of claim 11, wherein the relative PR weight of the one SV in the SV set is further based on one or more of the following: carrier-to-noise ratio, autocorrelation function, code-carrier phase consistency, measurement status or error flag, consistency between different frequency band measurements of the one SV, weighted least squares a posteriori residual, or signal integration information.

13. The method of claim 9, wherein the relative PR weight is based on a relative PR error predicted by the ML classifier.

14. The method of claim 9, wherein the method is performed by the UE, a location server, or a combination thereof.

15. The method according to claim 9, further comprising: receiving a signal from the set of SVs; as well as The PR measurement is performed on the set of SVs based on the signal.

16. A device for positioning estimation, the device comprising: means for determining, for each SV in a set of space vehicles (SVs), at least one geometric orientation relative to a user equipment (UE); means for determining a relative pseudorange (PR) weight for each SV in the set of SVs based on a machine learning (ML) classifier and a geometric orientation relative to the UE determined for each SV in at least a subset of the set of SVs; and Means for estimating a position of the UE based on a PR measurement of each SV in the set of SVs and the relative PR weight of each SV in the set of SVs.

17. The apparatus of claim 16, wherein the geometric orientation depends on at least one azimuth angle and a zenith angle between the UE and a corresponding SV in the set of SVs.

18. An apparatus according to claim 16, wherein the relative PR weight of one SV in the SV set is based on the spherical distance between the one SV and each SV in the at least one subset of the SV set, and the spherical distance between the one SV and another SV is based on the geometric orientation of the one SV compared to the geometric orientation of the other SV.

19. An apparatus according to claim 18, wherein the relative PR weight of the one SV in the SV set is further based on one or more of the following: carrier-to-noise ratio, autocorrelation function, code-carrier phase consistency, measurement status or error flag, consistency between different frequency band measurements of the one SV, weighted least squares posterior residual or signal integration information.

20. The apparatus of claim 16, wherein the relative PR weight is based on a relative PR error predicted by the ML classifier.

21. The apparatus of claim 16, wherein the apparatus is associated with the UE, a location server, or a combination thereof.

22. The apparatus according to claim 16, further comprising: means for receiving a signal from said set of SVs; and Means for performing the PR measurement on the set of SVs based on the signal.

23. The apparatus of claim 22, further comprising a global navigation satellite system (GNSS) receiver configured to receive the signals from the set of SVs.

24. A computer readable medium storing computer executable code which, when executed by a processor, causes the processor to: determining, for each space vehicle (SV) in a set of space vehicles (SVs), at least one geometric orientation relative to a user equipment (UE); determining a relative pseudorange (PR) weight for each SV in the set of SVs based on a machine learning (ML) classifier and a geometric orientation relative to the UE determined for each SV in at least a subset of the set of SVs; as well as The positioning of the UE is estimated based on the PR measurement of each SV in the set of SVs and the relative PR weight of each SV in the set of SVs.

25. A positioning estimation method, the method comprising: determining, for each space vehicle (SV) in a set of space vehicles (SVs), at least one geometric orientation relative to a user equipment (UE); determining a relative pseudorange (PR) weight for each SV in the set of SVs based on a geometric orientation relative to the UE determined for each SV in at least a subset of the set of SVs; as well as The positioning of the UE is estimated based on the PR measurement of each SV in the set of SVs and the relative PR weight of each SV in the set of SVs.

26. The method of claim 25, wherein the geometric orientation depends on at least one azimuth and zenith angle between the UE and a corresponding SV in the set of SVs.

27. A method according to claim 25, wherein the relative PR weight of one SV in the SV set is based on the spherical distance between the one SV and each SV in the at least one subset of the SV set, and the spherical distance between the one SV and another SV is based on the geometric orientation of the one SV compared to the geometric orientation of the other SV.

28. The method of claim 27, wherein the relative PR weight of the one SV in the SV set is further based on one or more of: carrier-to-noise ratio, autocorrelation function, code-carrier phase consistency, measurement status or error flag, consistency between different frequency band measurements of the one SV, weighted least squares a posteriori residual, or signal integration information.

29. The method of claim 25, wherein the method is performed by the UE, a location server, or a combination thereof.

30. The method of claim 25, further comprising: receiving a signal from the set of SVs; as well as The PR measurement is performed on the set of SVs based on the signal.

Images