Method and apparatus for classifying gestures by using ultra-wideband communication signals

Abstract

The present disclosure provides a method by which an electronic device classifies gestures by using UWB signals. A method of the present disclosure may comprise the steps of: using a trained first CNN model in order to acquire first prediction data for classifying whether a signal corresponding to UWB CIR is an LOS signal or an NLOS signal based on UWB CIR data; if the signal is classified as a LOS signal, using a trained second CNN model to obtain second prediction data for classifying the gesture based on sensor data corresponding to the UWB CIR data; if the signal is classified as an NLOS signal, using a trained third CNN model to obtain third prediction data for classifying the gesture based on sensor data corresponding to the UWB CIR data; using a first filtering method to filter at least two of the first prediction data, the second prediction data, and the third prediction data; and classifying the gesture based on the filtered data.

Description

Technical Field

[0001] The present disclosure relates to a method and apparatus for classifying gestures using UWB signals.

[0002] Furthermore, the present disclosure relates to a method and apparatus for estimating a position of an electronic device using UWB signals. Background Art

[0003] The Internet, a human-centered connected network in which humans generate and consume information, is now evolving into the Internet of Things (IoT), in which distributed entities (such as things) exchange and process information. The Internet of Everything (IoE), which combines IoT technology and big data processing technology through connection with cloud servers, etc., has emerged. As technical elements, such as "sensing technology", "wired / wireless communication and network infrastructure", "service interface technology", and "security technology" have been required for IoT implementation. Recently, sensor networks, machine-to-machine (M2M) communication, machine type communication (MTC), etc. have been studied.

[0004] Such an IoT environment can provide intelligent Internet technology (IT) services that create new value for human life by collecting and analyzing data generated between connected things. Through the integration and combination between existing information technology (IT) and various industrial applications, IoT can be applied to various fields including smart homes, smart buildings, smart cities, smart cars or connected cars, smart grids, healthcare, smart appliances, and advanced medical services. Summary of the invention

[0005] Technical issues

[0006] The present disclosure provides a method for classifying a signal into a Line Of Sight (LOS) / Non-LOS (NLOS) signal by using UWB Channel Impulse Response (CIR) data.

[0007] Furthermore, the present disclosure provides a method of classifying a gesture by using a signal classification result and sensor data.

[0008] Furthermore, the present disclosure provides a method of classifying a UWB signal into a line-of-sight (LOS) / non-LOS (NLOS) signal and estimating a position of an electronic device based on the classification result.

[0009] Technical Solutions

[0010] According to various embodiments of the present disclosure, a method of an electronic device may include an operation of obtaining first prediction data for classifying whether a signal corresponding to a UWB channel impulse response (UWB CIR) is a line-of-sight (LOS) signal or a non-LOS (NLOS) signal based on UWB CIR data by using a trained first convolutional neural network (CNN) model, an operation of obtaining second prediction data for classifying a gesture based on sensor data corresponding to the UWB CIR data by using a trained second CNN model, an operation of obtaining third prediction data for classifying a gesture based on the sensor data corresponding to the UWB CIR data by using a trained third CNN model, an operation of performing filtering on at least two of the first prediction data, the second prediction data, and the third prediction data by using a first filtering scheme, and an operation of classifying a gesture based on the filtered data, wherein the second CNN model may be trained using sensor data associated with the LOS signal, and the third CNN model may be trained using sensor data associated with the NLOS signal.

[0011] According to various embodiments of the present disclosure, an electronic device may include a transceiver and a controller connected to the transceiver, wherein the controller may be configured to: obtain first prediction data for classifying whether a signal corresponding to a UWB channel impulse response (CIR) is a line-of-sight (LOS) signal or a non-LOS (NLOS) signal based on UWB CIR data by using a trained first convolutional neural network (CNN) model, obtain second prediction data for classifying a gesture based on sensor data corresponding to the UWB CIR data by using the trained first convolutional neural network (CNN) model, obtain third prediction data for classifying a gesture based on the sensor data corresponding to the UWB CIR data by using the trained second CNN model when the signal is classified as a LOS signal, classify the gesture by using the trained third CNN model, perform filtering of at least two of the first prediction data, the second prediction data, and the third prediction data by using a first filtering scheme, and classify the gesture based on the filtered data, wherein the second CNN model may be trained using the sensor data associated with the LOS signal, and the third CNN model may be trained using the sensor data associated with the NLOS signal.

[0012] According to an embodiment of the present disclosure, a method of an electronic device may include an operation of identifying an average value of line-of-sight (LOS) probabilities of multiple received UWB signals. The method of the electronic device may include an operation of comparing the average value of the LOS probabilities of multiple received UWB signals with a first threshold, and determining whether a DL-TDoA environment is a LOS environment based on the comparison result. The method of the electronic device may include an operation of adaptively adjusting a ranging frequency used by the electronic device for ranging when it is determined that the DL-TDoA environment is a LOS environment. Each of the multiple received UWB signals may include a UWB message for DL-TDoA positioning.

[0013] According to various embodiments of the present disclosure, an electronic device may include a transceiver and a controller connected to the transceiver. The controller may identify an average value of line-of-sight (LOS) probabilities of multiple received UWB signals. The controller may compare the average value of the LOS probabilities of multiple received UWB signals with a first threshold, and may determine whether a DL-TDoA environment is a LOS environment based on the comparison result. When it is determined that the DL-TDoA environment is a LOS environment, the controller may adaptively adjust the ranging frequency used by the electronic device for ranging. Each of the multiple received UWB signals may include a UWB message for DL-TDoA positioning.

[0014] Beneficial Effects

[0015] According to the method of the present disclosure, the accuracy of LOS / NLOS signal classification can be increased.

[0016] In addition, according to the method of the present disclosure, the accuracy of posture classification can be increased.

[0017] Furthermore, according to the method of the present disclosure, the accuracy of the position estimation associated with the electronic device by using the UWB signal can be increased.

[0018] Furthermore, according to the method of the present disclosure, power consumed when estimating the position of an electronic device using a UWB signal can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a block diagram schematically illustrating an electronic device;

[0020] Figure 2a is a diagram showing the architecture of a UWB device according to an embodiment of the present disclosure;

[0021] Figure 2b is a diagram showing a configuration of a framework of a UWB device according to an embodiment of the present disclosure;

[0022] Figure 3ais a diagram showing an example of UWB CIR data according to an embodiment of the present disclosure;

[0023] Figure 3b is a diagram showing an example of valid UWB CIR data according to an embodiment of the present disclosure;

[0024] Figure 3c is a diagram showing an example of LOS signals and NLOS signals classified using UWB CIR data according to an embodiment of the present disclosure;

[0025] Figure 4 is a diagram illustrating a DS-TWR according to an embodiment of the present disclosure;

[0026] Figure 5 is a diagram illustrating DL-TDoA according to an embodiment of the present disclosure;

[0027] Figure 6 is a diagram illustrating a training process and a deployment process for LOS / NLOS signal classification using UWB channel impulse response data according to an embodiment of the present disclosure;

[0028] Figure 7 is a diagram showing a configuration of a user equipment for LOS / NLOS classification according to an embodiment of the present disclosure;

[0029] Figure 8 is a diagram illustrating a training process for gesture classification based on LOS / NLOS signal classification using UWB channel impulse response data according to an embodiment of the present disclosure;

[0030] Fig. 9 is a diagram illustrating a deployment process for gesture classification based on LOS / NLOS signal classification using UWB channel impulse response data according to an embodiment of the present disclosure;

[0031] Fig.10 is a diagram showing a configuration of a user device for gesture classification using LOS / NLOS classification according to an embodiment of the present disclosure;

[0032] Fig.11 is a diagram illustrating a gesture classification method of an electronic device according to an embodiment of the present disclosure;

[0033] Fig.12 is a diagram showing a structure of an electronic device according to an embodiment of the present disclosure;

[0034] Fig.13a is a diagram showing the structure of a UWB MAC frame according to an embodiment of the present disclosure;

[0035] Fig.13bis a diagram showing the structure of a UWB PHY packet according to an embodiment of the present disclosure;

[0036] Fig.14 is a diagram showing an example of a cluster configured with a plurality of UWB anchor points according to an embodiment of the present disclosure;

[0037] Fig.15a is a diagram illustrating a method for performing UWB ranging based on a DL-TDoA scheme by a UWB device according to an embodiment of the present disclosure;

[0038] Fig.15b is a diagram showing an example of a ranging block structure for a downlink TDoA scheme according to an embodiment of the present disclosure;

[0039] Fig.16a is a diagram illustrating an example of a LOS environment in the case of DL-TDoA positioning according to an embodiment of the present disclosure;

[0040] Fig.16b It is shown in Fig.16a FIG. 1 is a diagram showing an example of LOS probability data of a UWB signal obtained in a DL-TDoA positioning environment;

[0041] Fig.17a is a diagram illustrating an example of a LOS environment in the case of DL-TDoA positioning according to an embodiment of the present disclosure;

[0042] Fig.17b is shown with the user device based on Fig.17a A diagram showing an example of a graph associated with acceleration values ​​of a mobile in a DL-TDoA positioning environment;

[0043] Fig.18a is a diagram showing an example of a NLOS environment in the case of DL-TDoA positioning according to an embodiment of the present disclosure;

[0044] Fig.18b It is shown in Fig.18a FIG. 1 is a diagram showing an example of LOS probability data of a UWB signal obtained in a DL-TDoA positioning environment;

[0045] Fig.19 is a diagram showing a configuration of a user equipment capable of reducing power consumption based on LOS / NLOS classification according to an embodiment of the present disclosure; and

[0046] Fig. 20 is a diagram illustrating a structure of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0047] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

[0048] When describing the embodiments, descriptions related to technical contents that are well known in the relevant field and not directly related to the present disclosure will be omitted. Such unnecessary omission of descriptions is intended to prevent the main idea of ​​the present disclosure from being obscured and to convey the main idea more clearly.

[0049] For the same reason, in the drawings, some elements may be exaggerated, omitted or schematically shown. In addition, the size of each element does not fully reflect the actual size. In each of the drawings, the same reference numerals are used to mark the same or equivalent elements.

[0050] By referring to the embodiments described in detail below in conjunction with the accompanying drawings, the advantages and features of the present disclosure and the ways to achieve them will be apparent. However, the present disclosure is not limited to the embodiments set forth below, but can be implemented in various different forms. The following embodiments are provided only to fully disclose the present disclosure and inform those skilled in the art of the scope of the present disclosure, and the present disclosure is limited only by the scope of the attached claims. Throughout the specification, the same or similar reference numerals represent the same or similar elements.

[0051] In this article, it will be understood that each box of the flowchart diagram and the combination of boxes in the flowchart diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device create a device for implementing the function specified in one or more flowchart boxes. These computer program instructions can also be stored in a computer-usable or computer-readable memory, which can instruct the computer or other programmable data processing device to act in a particular way, so that the instructions stored in the computer-usable or computer-readable memory produce an article of instruction means including the function specified in the flowchart box or multiple boxes. The instructions executed on a computer or other programmable data processing device so that a series of operating steps are performed on the computer or other programmable data processing device to generate a computer-implemented process can provide steps for implementing the functions specified in the flowchart block.

[0052] In addition, each box in the flow chart may represent a module, a fragment or a portion of a code, which includes one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may not occur in order. For example, two boxes shown in succession may actually be executed substantially simultaneously, or the boxes may sometimes be executed in reverse order, depending on the functions involved.

[0053] As used in the embodiments of the present disclosure, the term "unit" refers to a software element or a hardware element, such as a field programmable gate array (FPGA) or an application specific integrated circuit (ASIC), and the "unit" can perform certain functions. However, a "unit" does not always have a meaning limited to software or hardware. A "unit" can be constructed to be stored in an addressable storage medium or to execute one or more processors. Therefore, a "unit" includes, for example, software elements, object-oriented software elements, class elements or task elements, processes, functions, attributes, procedures, subroutines, program code segments, drivers, firmware, microcodes, circuits, data, databases, data structures, tables, arrays, and parameters. The elements and functions provided by a "unit" can be combined into a smaller number of elements or "units", or divided into a larger number of elements or "units". In addition, elements and "units" can be implemented as one or more CPUs in a reproduction device or a secure multimedia card. In addition, a "unit" in various embodiments of the present disclosure can include one or more processors.

[0054] As used herein, the term "terminal" or "device" may also be referred to as a mobile station (MS), a user equipment (UE), a user terminal (UT), a wireless terminal, an access terminal (AT), a terminal, a subscriber unit, a subscriber station (SS), a wireless device, a wireless communication device, a wireless transmission / reception unit (WTRU), a mobile node, a mobile device or other terms. Various examples of terminals may include a cellular phone, a smart phone with a wireless communication function, a personal digital assistant (PDA) with a wireless communication function, a wireless modem, a portable computer with a wireless communication function, a photographing device such as a digital camera with a wireless communication function, a gaming device with a wireless communication function, a music storage and playback home appliance with a wireless communication function, an Internet port appliance capable of wireless Internet access and browsing, and a portable unit or terminal with an integrated combination of these functions. In addition, the terminal may include a machine-to-machine (M2M) terminal and a machine type communication (MTC) terminal / device, but is not limited thereto. In the specification, a terminal may also be referred to as an electronic device or simply a device.

[0055] Hereinafter, the operating principle of the present disclosure will be described in detail in conjunction with the accompanying drawings. In the following description of the present disclosure, when it is determined that the description may make the subject matter of the present disclosure unnecessarily unclear, the detailed description of the known functions or configurations incorporated herein will be omitted. The terms to be described below are defined in consideration of the functions in the present disclosure, and may differ depending on the user, the user's intention or habit. Therefore, the definition of the terms should be based on the content in the entire specification.

[0056] Hereinafter, embodiments of the present disclosure will be described in detail in conjunction with the accompanying drawings. In the following description of the embodiments of the present disclosure, a communication system using UWB will be described by way of example, but the embodiments of the present disclosure may be applied to other communication systems with similar technical backgrounds or characteristics. Examples thereof may include communication systems using Bluetooth or Zigbee. Therefore, based on the determination of those skilled in the art, the embodiments of the present disclosure may be applied to other communication systems with some modifications without significantly departing from the scope of the present disclosure.

[0057] In addition, when describing the present disclosure, when it is determined that the description may make the subject matter of the present disclosure unnecessarily unclear, a detailed description of known functions or configurations incorporated herein will be omitted. The terms to be described below are terms defined in consideration of the functions in the present disclosure, and may differ depending on the user, the user's intention, or custom. Therefore, the definition of the terms should be based on the content in the entire specification.

[0058] Generally speaking, wireless sensor network technology can be divided into wireless local area network (WLAN) technology and wireless personal area network (WPAN) technology according to the recognition distance. In this case, WLAN is a technology based on IEEE 802.11 and enables access to a backbone network within a radius of about 100m. WPAN is a technology based on IEEE 802.15 and includes Bluetooth, ZigBee, Ultra Wideband (UWB), etc. A wireless network embodying those wireless network technologies may include multiple electronic devices.

[0059] According to the definition of the Federal Communications Commission (FCC), UWB is a wireless communication technology that uses a bandwidth of 500MHz or greater, or at least 20% of the bandwidth corresponds to the center frequency. UWB can be the bandwidth itself to which UWB communication is applied. UWB allows secure and accurate ranging between devices. Through the above, UWB can achieve relative position estimation based on the distance between two devices, or can achieve accurate position estimation of a device based on the distance from a stationary device (whose position is known).

[0060] Predetermined terms used in the description provided below are provided to help understanding of the present disclosure, and the terms may be changed to other terms without departing from the scope of the technical concept of the present disclosure.

[0061] An "Application Specific File (ADF)" is a data structure within an application data structure that is capable of hosting application or application specific data.

[0062] "Application Protocol Data Unit (APDU)" is a command and response used in UWB devices to communicate with application data structures.

[0063] The “application specific data” may be, for example, a file structure having a root level and an application level, and includes UWB control information and UWB session data required for a UWB session.

[0064] A "controller" may be a ranging device that defines and controls ranging control messages (RCMs) (or control messages). A controller may define and control ranging characteristics by sending control messages.

[0065] A "controller" may be a ranging device that uses ranging parameters in an RCM (or control message) received from a controller. A controller may use the same ranging features as those configured by the controller via a control message.

[0066] Unlike "static STS", "dynamic scrambled timestamp sequence (STS) mode" may be an operation mode in which STS is not repeated during a ranging session. In this mode, STS is managed by the ranging device, and the ranging session key for generating STS may be managed by the security component.

[0067] For example, an "applet" may be an applet executed in a secure component that includes UWB parameters and service data. The applet may be a FiRa applet.

[0068] A “ranging device” may be a device capable of performing UWB ranging. In the present disclosure, a ranging device may be an enhanced ranging device (ERDEV) defined by IEEE802.15.4z or a FiRa device. A ranging device may be referred to as a UWB device.

[0069] A "UWB-enabled application" may be an application for UWB services. For example, a UWB-enabled application may be an application of UWB services that uses a framework API to configure an OOB connector, security services, and / or UWB sessions. A "UWB-enabled application" may be referred to simply as an application or a UWB application. A UWB-enabled application may be a FiRa-enabled application.

[0070] A "framework" may be a component that enables access to a profile and provides individual UWB configuration and / or notifications. For example, a framework may be a collection of logical software components including a profile manager, an OOB connector, security services, and / or UWB services. The framework may be a FiRa framework.

[0071] An "OOB connector" may be a software component for configuring an out-of-band (OOB) connection (eg, a BLE connection) between ranging devices. The OOB connector may be a FiRa OOB connector.

[0072] A "profile" may be a predefined set of UWB and OOB configuration parameters. A profile may be a FiRa profile.

[0073] A "profile manager" may be a software component that embodies the profiles available in the ranging device. The profile manager may be a FiRa profile manager.

[0074] A "service" may be an implementation of a use case that provides a service to an end user.

[0075] A "smart ranging device" may be a ranging device that can embody the optional framework API. A smart ranging device may be a FiRa smart device.

[0076] A "Global Dedicated File (GDF)" can be application-specific data at the root level, including data required to configure a USB session.

[0077] A "framework API" may be an API used by UWB-enabled applications to communicate with the framework.

[0078] An "initiator" may be a ranging device that initiates a ranging exchange. The initiator may initiate a ranging exchange by sending a first RFRAME (ranging exchange message).

[0079] An "object identifier (OID)" may be an identifier of an ADF in an application data structure.

[0080] "Out-of-band (OOB)" may be data communications that are the basis of wireless technology and do not use UWB.

[0081] A "Ranging Data Set (RDS)" may be data required to configure a UWB session (eg, UWB session key, session ID, etc.), where confidentiality, authenticity, and integrity need to be protected.

[0082] A "responder" may be a ranging device that responds to an initiator in a ranging exchange. A responder may respond to a ranging exchange message received from an initiator.

[0083] "STS" can be an encrypted sequence to increase the integrity and accuracy of the ranging measurement timestamp. STS can be generated from the ranging session key.

[0084] A "secure channel" may be a data channel that is protected from eavesdropping and tampering.

[0085] For example, where a dynamic STS is used, a “secure component” may be an entity (eg, a secure element (SE) or a trusted execution environment (TEE)) that has a defined security level and interfaces with the UWBS in order to provide the UWBS with an RDS.

[0086] “SE” may be a tamper-resistant secure hardware component that may be used as a secure component in a ranging device.

[0087] "Secure ranging" may be ranging based on an STS generated via a strong cryptographic operation.

[0088] A “security service” may be a software component used to interface with a secure component, such as a secure element or TEE.

[0089] A "service applet" may be an applet within a security component that manages service specific transactions.

[0090] The "service data" may be data defined by a service provider and needs to be transferred between two ranging devices to implement a service.

[0091] A "Service Provider" may be an entity that defines and provides the hardware and software necessary to deliver a predetermined service to an end user.

[0092] "Static STS mode" may be a mode of operation in which the STS is repeated during a session and may not need to be managed by a security component.

[0093] The "Secure UWB Service (SUS) applet" may be an applet in the SE that communicates with the applet in order to search for data required to enable a secure UWB session with another ranging device. In addition, the SUS applet may pass corresponding data (information) to the UWBS.

[0094] A "UWB Service" may be a software component that provides access to a UWB S.

[0095] A "UWB session" may be a period of time from the start to the end of communication between a controller and a controlled object via UWB. A UWB session may include ranging, data transfer, or both ranging and data transfer.

[0096] The “UWB session ID” may be an ID (eg, a 32-bit integer) that identifies a UWB session and is shared between a controller and a controlled entity.

[0097] The "UWB session key" may be a key used to protect a UWB session. The UWB session key may be used to generate an STS. The UWB session key may be a UWB ranging session key (URSK) and may be simply referred to as a session key.

[0098] A "UWB subsystem (UWBS)" may be a hardware component that embodies the UWB PHY and MAC layers (spec). The UWBS may have an interface to the framework and an interface to a security component for searching for RDS.

[0099] A "UWB message" may be a message including a payload IE sent by a UWB device (e.g., ERDEV). A UWB message may be, for example, a message such as a ranging initiation message (RIM), a ranging response message (RRM), a ranging final message (RFM), a control message (CM), a measurement report message (MRM), a ranging result report message (RRRM), a control update message (CUM), or a one-way ranging (OWR). Multiple messages may be combined into a single message when necessary.

[0100] "OWR" may be a ranging scheme that uses messages transmitted in one direction between a ranging device and one or more other ranging devices. OWR may be used to measure time difference of arrival (TDoA). In addition, OWR may be used to measure AoA by the receiving side instead of measuring TDoA. In this case, a pair of advertisers and observers may be used.

[0101] "TWR" may be a ranging scheme that measures the time of flight (ToF) and estimates the relative distance between the two devices by exchanging ranging messages between the two devices. The TWR scheme may be one of bilateral two-way ranging (DS-TWR) and unilateral two-way ranging (SS-TWR). SS-TWR may be a process of performing ranging by performing one round-trip time measurement. For example, SS-TWR may include a RIM transmission operation from an initiator to a responder and an RRM transmission operation from a responder to an initiator. DS-TWR may be a process of performing ranging by performing two round-trip time measurements. For example, DS-TWR may include a RIM transmission operation from an initiator to a responder, an RRM transmission operation from a responder to an initiator, and an RFM transmission operation from an initiator to a responder. Via ranging exchange (ranging message exchange), the time of flight (ToF) may be calculated, and the distance between the two devices may be estimated. In the TWR process, the measured AoA information (e.g., AoA azimuth result, AoA elevation result) may be delivered to another ranging device via RRRM or another message. In the present disclosure, the TWR may be referred to as a UWB TWR.

[0102] "DL-TDoA" may be referred to as downlink time difference of arrival (DL-TDoA) or reverse TDoA. When multiple anchor devices broadcast messages or exchange messages, the user device (tag device) may overhear the message of the anchor device, which is a basic operation. DL-TDoA may be classified as a type of one-way ranging, similar to uplink TDoA. A user device performing a DL-TDoA operation may overhear messages sent from two anchor devices, and may calculate a time difference of arrival (TDoA) proportional to the distance difference between the user device and the anchor device. The user device may calculate the relative distance to the anchor device by using the TDoA of multiple pairs of anchor devices, and may use it for positioning. The operation of the anchor device for DL-TDoA may perform an operation similar to the bilateral two-way ranging (DS-TWR) defined in IEEE 802.15.4z, and may also include another useful time information, enabling the user device to calculate the TDoA. In the present disclosure, DL-TDoA may be referred to as DL-TDoA positioning.

[0103] An "anchor device" may be referred to as an anchor, a UWB anchor, or a UWB anchor device, and may be a UWB device that is set in a predetermined location to provide a positioning service. For example, an anchor device may be a UWB device that a service provider installs in a wall, ceiling, structure, etc. in a room to provide an indoor positioning service. An anchor device may be classified as an initiator anchor or a responder anchor based on the order and role of message transmission.

[0104] An "initiator anchor" may be referred to as an initiator UWB anchor, an initiator anchor device, etc., and may indicate the initiation of a predetermined ranging round. The initiator anchor may schedule a ranging slot, in which a responder anchor operating in the ranging slot responds. The initiation message of the initiator anchor may be referred to as an initiator downlink TDoA message (initiator DTM) or a polling message. The initiation message of the initiator anchor may include a transmission timestamp. The initiator anchor may additionally deliver a termination message after receiving a response from the responder anchor. The termination message of the initiator anchor may be referred to as a final DTM or a final message. The termination message may include a reply time regarding a message sent by the responder anchor. The termination message may include a transmission timestamp.

[0105] A "responder anchor" may be referred to as a responder UWB anchor, a responder UWB anchor device, a responder anchor device, etc. A responder anchor may be a UWB anchor that responds to an initiation message of an initiator anchor. The message transmitted by the responder anchor as a response may include a reply time of the initiation message. The message transmitted by the responder anchor as a response may be referred to as a responder DTM or a response message. The response message of the responder anchor may include a transmission timestamp.

[0106] A "cluster" may be a collection of UWB anchors covering a predetermined area. A cluster may be configured with an initiator UWB anchor and a responder UWB anchor that responds thereto. 2D positioning typically requires a single initiator UWB anchor and at least three responder UWB anchors, and 3D positioning requires a single initiator UWB anchor and at least four responder UWB anchors. If the initiator UWB anchor and the responder UWB anchor can be accurately time synchronized (time synchronization) via a separate wired / wireless connection, 2D positioning requires a single initiator UWB anchor and two responder UWB anchors, and 3D positioning requires a single initiator UWB anchor and three responder UWB anchors. Unless otherwise mentioned, it is assumed that there is no separate wired / wireless device for time synchronization between UWB anchors. A cluster area may be a space for UWB anchors that constitute a cluster. Positioning services may be provided to user devices by configuring multiple clusters to support positioning services for a wide area. A cluster may be referred to as a cell. Cluster operations can be understood as operations on anchor points belonging to a cluster.

[0107] Figure 1 is a block diagram schematically illustrating an electronic device.

[0108] refer to Figure 1 , the electronic device 101 in the network environment 100 may communicate with the electronic device 102 via the first network 198 (e.g., a short-range wireless communication network), or communicate with the electronic device 104 or the server 108 via the second network 199 (e.g., a long-range wireless communication network). According to an embodiment, the electronic device 101 may communicate with the electronic device 104 via the server 108. According to an embodiment, the electronic device 101 may include a processor 120, a memory 130, an input module 150, a sound output module 155, a display module 160, an audio module 170, a sensor module 176, an interface 177, a connection terminal 178, a haptic module 179, a camera module 180, a power management module 188, a battery 189, a communication module 190, a user identification module 196, or an antenna module 197. In some embodiments, at least one component (e.g., the connection terminal 178) may be omitted from the electronic device 101, or one or more other components may be added to the electronic device 101. In some embodiments, some components (eg, sensor module 176 , camera module 180 , or antenna module 197 ) may be integrated into a single component (eg, display module 160 ).

[0109] The processor 120 may execute, for example, software (e.g., program 140) to control at least one other component (e.g., hardware or software component) of the electronic device 101 coupled to the processor 120, and may perform various data processing or calculations. According to one embodiment, as at least part of the data processing or calculation, the processor 120 may store a command or data received from another component (e.g., sensor module 176 or communication module 190) in the volatile memory 132, process the command or data stored in the volatile memory 132, and store the resulting data in the non-volatile memory 134. According to an embodiment, the processor 120 may include a main processor 121 (e.g., a central processing unit (CPU) or an application processor (AP)) or an auxiliary processor 123 (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor) that may operate independently of the main processor 121 or in conjunction with the main processor 121. For example, when the electronic device 101 includes a main processor 121 and an auxiliary processor 123, the auxiliary processor 123 may be adapted to consume less power than the main processor 121 or be specific to a specified function. The auxiliary processor 123 may be implemented separately from the main processor 121 or as a part of the main processor 121.

[0110] The auxiliary processor 123 may replace the main processor 121 when the main processor 121 is in an inactive (e.g., sleep) state or control at least some of the functions or states related to, for example, at least one of the components of the electronic device 101 (e.g., display module 160, sensor module 176, or communication module 190) together with the main processor 121 when the main processor 121 is in an active (e.g., executing an application) state. According to an embodiment, the auxiliary processor 123 (e.g., an image signal processor or a communication processor) may be implemented as a part of another component (e.g., camera module 180 or communication module 190) related to the auxiliary processor 123 function. According to an embodiment, the auxiliary processor 123 (e.g., a neural processing unit) may include a hardware structure specified for artificial intelligence model processing. The artificial model may be generated by machine learning. Such learning may be performed, for example, by the electronic device 101 in which the artificial intelligence model is executed or via a separate server (e.g., server 108). The learning algorithm may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the above examples. The artificial intelligence model may include a plurality of artificial neural network layers. The artificial neural network may be one of a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep neural network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q network, and a combination of two or more thereof, but is not limited to the above examples. Additionally or alternatively, in addition to the hardware structure, the artificial intelligence model may also include a software structure.

[0111] The memory 130 may store various data used by at least one component of the electronic device 101 (e.g., the processor 120 or the sensor module 176). The various data may include, for example, input data or output data of software (e.g., the program 140) and commands related thereto. The memory 130 may include a volatile memory 132 or a nonvolatile memory 134.

[0112] The program 140 may be stored as software in the memory 130 , and may include, for example, an operating system (OS) 142 , middleware 144 , or applications 146 .

[0113] The input module 150 may receive a command or data to be used by another component (e.g., the processor 120) of the electronic device 101 from outside (e.g., a user) of the electronic device 101. The input module 150 may include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0114] The sound output module 155 can output sound signals to the outside of the electronic device 101. The sound output module 155 may include, for example, a speaker or a receiver. The speaker may be used for general purposes, such as playing back multimedia or recording. The receiver may be used to receive an incoming call. Depending on the embodiment, the receiver may be implemented as a part of the speaker or as a separate part from the speaker.

[0115] The display module 160 can visually provide information to the outside of the electronic device 101 (e.g., a user). The display module 160 may include, for example, a display, a hologram device, or a projector, and a control circuit for controlling a corresponding one of the display, the hologram device, and the projector. According to an embodiment, the display module 160 may include a touch sensor adapted to detect a touch, or a pressure sensor adapted to measure the strength of a force caused by a touch.

[0116] The audio module 170 may convert sound into an electrical signal, and vice versa. According to an embodiment, the audio module 170 may obtain sound via the input module 150, or output sound via the sound output module 155 or an external electronic device (e.g., electronic device 102 (e.g., speaker or earphone)) directly or wirelessly coupled to the electronic device 101.

[0117] The sensor module 176 may detect an operating state (e.g., power or temperature) of the electronic device 101 or an environmental state (e.g., a user's state) outside the electronic device 101, and then generate an electrical signal or data value corresponding to the detected state. According to an embodiment, the sensor module 176 may include, for example, a gesture sensor, a gyro sensor, an atmospheric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an infrared (IR) sensor, a biosensor, a temperature sensor, a humidity sensor, or an illumination sensor.

[0118] The interface 177 may support one or more designated protocols to be used for direct or wireless coupling of the electronic device 101 with an external electronic device (e.g., the electronic device 102). According to an embodiment, the interface 177 may include, for example, a high-definition multimedia interface (HDMI), a universal serial bus (USB) interface, a secure digital (SD) card interface, or an audio interface.

[0119] The connection terminal 178 may include a connector via which the electronic device 101 may be physically connected to an external electronic device (eg, the electronic device 102). According to an embodiment, the connection terminal 178 may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (eg, a headphone connector).

[0120] The haptic module 179 may convert the electrical signal into mechanical stimulation (eg, vibration or movement) or electrical stimulation, which may be recognized by the user via his tactile sense or kinesthetic sense. According to an embodiment, the haptic module 179 may include, for example, a motor, a piezoelectric element, or an electrical stimulator.

[0121] The camera module 180 may capture still images or moving images. According to an embodiment, the camera module 180 may include one or more lenses, image sensors, image signal processors, or flashes.

[0122] The power management module 188 may manage power supplied to the electronic device 101. According to one embodiment, the power management module 188 may be implemented as, for example, at least a portion of a power management integrated circuit (PMIC).

[0123] The battery 189 may supply power to at least one component of the electronic device 101. According to an embodiment, the battery 189 may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0124] The communication module 190 may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device 101 and an external electronic device (e.g., electronic device 102, electronic device 104, or server 108), and perform communication via the established communication channel. The communication module 190 may include one or more communication processors that can operate independently of the processor 120 (e.g., an application processor) and support direct (e.g., wired) communication or wireless communication. According to an embodiment, the communication module 190 may include a wireless communication module 192 (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module 194 (e.g., a local area network (LAN) communication module or a power line communication (PLC) module). A corresponding one of these communication modules may communicate with the external electronic device 104 via the first network 198 (e.g., via the first network 198 and the second network 198). g. A second network 199 (e.g., Bluetooth™, wireless fidelity (Wi-Fi) direct, or infrared data association (IrDA)) or a second network 199 (e.g., a communication network). For example, a remote communication network, such as a traditional cellular network, a 5G network, a next generation communication network, the Internet, or a computer network (e.g., a LAN or a wide area network (WAN)). These various types of communication modules may be incorporated into a single component (e.g., a single chip), or may be implemented as multiple components (e.g., multiple chips) separated from each other. The wireless communication module 192 may use user information (e.g., an International Mobile Subscriber Identity (IMSI)) stored in the user identification module 196 to identify or authenticate the electronic device 101 in a communication network (e.g., a first network 198 or a second network 199).

[0125] The wireless communication module 192 can support 5G networks and next-generation communication technologies after the 4G network, such as new radio (NR) access technology. NR access technology can support high-speed transmission of high-capacity data (enhanced mobile broadband (eMBB)), terminal power minimization and multi-terminal access (massive machine type communication (mMTC)) or ultra-reliable and low-latency communication (URLLC). The wireless communication module 192 can support high-frequency bands (e.g., mmWave bands) to achieve, for example, high data transmission rates. The wireless communication module 192 can support various technologies for ensuring performance on high-frequency bands, such as, for example, beamforming, massive multiple input and multiple output (massive MIMO), full-dimensional MIMO (FD-MIMO), array antennas, analog beamforming, or massive antennas. The wireless communication module 192 can support various requirements specified in the electronic device 101, an external electronic device (e.g., an electronic device 104), or a network system (e.g., a second network 199). According to an embodiment, the wireless communication module 192 may support a peak data rate for implementing eMBB (e.g., 20 Gbps or greater), loss coverage for implementing mMTC (e.g., 164 dB or less), or U-plane delay for implementing URLLC (e.g., 0.5 ms or less for each of the downlink (DL) and uplink (UL), or 1 ms or less for a round trip).

[0126] The antenna module 197 may transmit or receive a signal or power to or from the outside of the electronic device 101 (e.g., an external electronic device). According to an embodiment, the antenna module 197 may include an antenna including a radiation element formed of a conductive material or a conductive pattern formed in or on a substrate (e.g., a printed circuit board (PCB)). According to an embodiment, the antenna module 197 may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication scheme used in a communication network such as the first network 198 or the second network 199 may be selected from the plurality of antennas by the communication module 190, for example. Then, a signal or power may be transmitted or received between the communication module 190 and the external electronic device via the selected at least one antenna. According to an embodiment, another component other than the radiation element (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module 197.

[0127] According to various embodiments, the antenna module 197 may form a millimeter wave antenna module. According to an embodiment, the millimeter wave antenna module may include a printed circuit board, an RFIC disposed at or adjacent to a first surface (e.g., a lower surface) of the printed circuit board and capable of supporting a specified high frequency band (e.g., a millimeter wave frequency band), and a plurality of antennas (e.g., array antennas) disposed at or adjacent to a second surface (e.g., an upper surface or a side surface) of the printed circuit board and capable of transmitting or receiving signals in the specified high frequency band.

[0128] At least some of the above components may be coupled to each other and communicate signals (e.g., commands or data) therebetween via an inter-peripheral communication scheme (e.g., a bus, general purpose input and output (GPIO), a serial peripheral interface (SPI), or a mobile industry processor interface (MIPI)).

[0129] According to an embodiment, a command or data may be sent or received between the electronic device 101 and the external electronic device 104 via a server 108 coupled to the second network 199. Each of the external electronic devices 102 or 104 may be a device of the same type or a different type as the electronic device 101. According to an embodiment, all or some operations to be performed at the electronic device 101 may be performed at one or more of the external electronic devices 102, 104, or 108. For example, if the electronic device 101 should automatically perform a function or service, or in response to a request from a user or another device, the electronic device 101 may request one or more external electronic devices to perform at least a portion of the function or service instead of or in addition to performing the function or service. The one or more external electronic devices receiving the request may perform at least a portion of the requested function or service, or an additional function or additional service related to the request, and pass the result of the execution to the electronic device 101. The electronic device 101 may provide the result as at least a part of the reply to the request with or without further processing the result. To this end, for example, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used. The electronic device 101 may provide ultra-low latency services using, for example, distributed computing or mobile edge computing. In another embodiment, the external electronic device 104 may include an Internet of Things (IoT) device. The server 108 may be an intelligent server using machine learning and / or neural networks. Depending on the embodiment, the external electronic device 104 or the server 108 may be included in the second network 199. The electronic device 101 may be applied to intelligent services (e.g., smart homes, smart cities, smart cars, or healthcare) based on 5G communication technology or IoT-related technologies.

[0130] The electronic device according to the various embodiments set forth herein may be one of various types of electronic devices. The electronic device may include, for example, a portable communication device (e.g., a smart phone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a household appliance. The electronic device according to the embodiments of the present disclosure is not limited to those described above.

[0131] It should be understood that the various embodiments of the present disclosure and the terms used therein are not intended to limit the technical features set forth herein to specific embodiments, and the present disclosure includes various changes, equivalents or alternatives of the corresponding embodiments. With respect to the description of the accompanying drawings, similar reference numerals may be used to specify similar or related elements. The singular form of the noun corresponding to the project may include one or more of the project, unless otherwise clearly indicated by the relevant context. As used herein, each of the phrases such as "A or B", "at least one of A and B", "at least one of A or B", "A, B or C", "at least one of A, B and C" and "at least one of A, B or C" may include any one or all possible combinations of the projects listed together in the corresponding phrases in the phrase. Terms such as "first", "second", "the first" and "the second" may be used to simply distinguish the corresponding element from another element, and do not limit the element in other aspects (e.g., importance or order). If an element (e.g., a first element) is referred to as being “coupled with / to another element (e.g., a second element)” or “connected with / to another element (e.g., a second element)” with or without the term “operably” or “communicatively”, it means that the element may be coupled with / connected to / to another element directly (e.g., by wire), wirelessly, or via a third element.

[0132] As used in various embodiments of the present disclosure, the term "module" may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with other terms (e.g., "logic," "logic block," "component," or "circuit"). A "module" may be a single integrated component suitable for performing one or more functions or its smallest unit or part. For example, according to an embodiment, a "module" may be implemented in the form of an application specific integrated circuit (ASIC).

[0133] Various embodiments as set forth herein may be implemented as software (e.g., program 140) including one or more instructions stored in a storage medium (e.g., internal memory 136 or external memory 138) readable by a machine (e.g., electronic device 101). For example, a processor (e.g., processor 120) of a machine (e.g., electronic device 101) may call at least one of the one or more instructions stored in the storage medium and execute it. This allows the machine to be operated to perform at least one function according to at least one instruction called. One or more instructions may each include a code generated by a compiler or a code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. In this article, the term "non-transitory" simply means that the storage medium is a tangible device and does not include signals (e.g., electromagnetic waves), but the term does not distinguish between where data is semi-permanently stored in the storage medium and where data is temporarily stored in the storage medium.

[0134] According to an embodiment, the method according to various embodiments of the present disclosure may be included and provided in a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., a compact disc read-only memory (CD-ROM)), or distributed online (e.g., downloaded or uploaded) via an application store (e.g., PlayStore TM), or distributed directly between two user devices (e.g., smart phones). If distributed online, at least a portion of the computer program product may be temporarily generated or at least temporarily stored in a machine-readable storage medium, such as a memory of a manufacturer's server, an application store's server, or a relay server.

[0135] According to various embodiments, each of the above-mentioned elements (e.g., a module or a program) may include a single entity or multiple entities, and some of the multiple entities may also be separately arranged in another element. According to various embodiments, one or more of the above-mentioned elements or operations may be omitted, or one or more other elements or operations may be added. Alternatively or additionally, multiple elements (e.g., a module or a program) may be integrated into a single element. In this case, according to various embodiments, the integrated element may still perform one or more functions of each of the multiple elements in the same or similar manner as performed by a corresponding one of the multiple elements before integration. According to various embodiments, the operations performed by a module, a program or another element may be performed sequentially, in parallel, repeatedly or heuristically, or one or more of the operations may be performed or omitted in a different order, or one or more other operations may be added.

[0136] Figure 2a is a diagram illustrating the architecture of a UWB device according to an embodiment of the present disclosure.

[0137] In the present disclosure, the UWB device 200 may be an electronic device that supports UWB communication. For example, the UWB device 200 may be Figure 1 An example of an electronic device 101.

[0138] The UWB device 200 may be, for example, a ranging device supporting UWB ranging. According to an embodiment, the ranging device may be an enhanced ranging device (ERDEV) or a FiRa device.

[0139] exist Figure 2a In the embodiment of the present invention, the UWB device 200 may interact with another UWB device via a UWB session.

[0140] In addition, the UWB device 200 may include a first interface (Interface #1), which is an interface between the UWB-enabled application 210 and the UWB framework 220, and the first interface may enable the UWB-enabled application 110 in the UWB device 200 to use the UWB capability of the UWB device 200 in a predetermined manner. According to an embodiment, the first interface may be a framework API or a proprietary interface, but is not limited thereto.

[0141] Furthermore, the UWB device 200 may include a second interface (Interface #2) which is an interface between the UWB framework 210 and the UWB subsystem (UWBS) 230. According to an embodiment, the second interface may be a UWB command interface (UCI) or a proprietary interface, but is not limited thereto.

[0142] refer to Figure 2a , the UWB device 200 may include a UWB-enabled application 210, a framework (UWB framework) 220, and / or a UWBS 230 including a UWB MAC layer and a UWB physical layer. In some embodiments, some entities may not be included in the UWB device, or additional entities (eg, a security layer) may be further included.

[0143] The UWB-enabled application 210 can trigger the configuration of the UWB session by the UWBS 230 by using the first interface. In addition, the UWB-enabled application 210 can use one of the predefined configuration files. For example, the UWB-enabled application 210 can use one of the configuration files defined in FiRa, or can use a custom configuration file. The UWB-enabled application 210 can manage related events such as service discovery, ranging notification, and / or error conditions by using the first interface.

[0144] The framework 220 may enable access to configuration files and provide individual UWB configurations and / or notifications. In addition, the framework 220 may support at least one of a function of performing UWB ranging and transactions, a function of providing an interface to the UWBS 230 and applications, or a function of estimating the location of the device 200. The framework 220 may be a set of software components. As described above, the UWB-enabled application 210 may interface with the framework 220 via a first interface, and the framework 220 may interface with the UWBS 230 via a second interface.

[0145] In the present disclosure, the UWB-enabled application 210 and / or the framework 220 may be embodied by an application processor (AP) (or a processor). Therefore, in the present disclosure, it is understood that the operation of the UWB-enabled application 210 and / or the framework 220 is performed by the AP (or a processor). In the present disclosure, the framework may be referred to as an AP or a processor.

[0146] UWBS 230 may be a hardware component including a UWB MAC layer and a UWB physical layer. UWBS 230 may perform UWB session management and may communicate with a UWBS of another UWB device. UWBS 230 may interface with framework 120 via a second interface and may obtain security data from a security component. In an embodiment, framework 220 (or an application processor) may send a command to UWBS 230 via UCI, and UWBS 230 may pass a response to the command to framework 220. UWBS 230 may pass a notification to framework 120 via UCI.

[0147] Figure 2b is a diagram illustrating a configuration of a framework of a UWB device according to an embodiment of the present disclosure.

[0148] Figure 2b A UWB device can be Figure 2a Examples of UWB devices.

[0149] refer to Figure 2b , the framework 220 may include, for example, software components such as a profile manager 221 , an OOB connector 222 , a security service 223 , and / or a UWB service 224 .

[0150] The profile manager 221 may perform a role for managing profiles available in UWB devices. Here, a profile may be a set of parameters required to configure communications between UWB devices. For example, a profile may include parameters indicating the OOB secure channel used, UWB / OOB configuration parameters, parameters indicating whether the use of a predetermined security component is mandatory, and / or parameters related to the file structure of an ADF. The UWB-enabled application 210 may communicate with the profile manager 221 via a first interface (e.g., a framework API).

[0151] The OOB connector 222 may perform a role for configuring an OOB connection with another device. The OOB connector 222 may manage OOB operations including a discovery operation and / or a connection operation. The OOB component (eg, a BLE component) 250 may be connected to the OOB connector 222 .

[0152] The security service 223 may perform the role of interfacing with the security component 240 (such as SE or TEE).

[0153] The UWB service 224 may perform a role of managing the UWBS 230. The UWB service 224 may embody a second interface, and may provide access from the profile manager 321 to the UWBS 230.

[0154] The present disclosure provides a method and apparatus for performing gesture detection by using a UWB signal. The UWB signal may be a UWB signal for DL-TDoA ranging (OWR), or may be a UWB signal for DS-TWR ranging. In the present disclosure, a gesture may be related to, for example, the content of a user carrying a user device (e.g., hand-held) or the position where the user holds the user device (e.g., back pocket / front pocket).

[0155] The present disclosure provides a method for receiving a UWB signal, obtaining UWB channel impulse response (CIR) data, and classifying whether the UWB signal is a line-of-sight (LOS) signal or a non-LOS (NLOS) signal based on the UWB CIR data. For LOS signal or NLOS signal classification, a convolutional neural network (CNN) algorithm can be used. As described above, by using a CNN model to classify data with time series characteristics, high classification accuracy can be provided. As input data of the CNN model for classifying LOS signals or NLOS signals, valid CIR data with noise removed from UWB CIR data can be used. Through the above, the accuracy of LOS / NLOS signal classification and the accuracy of posture classification can be increased.

[0156] The present disclosure may provide a scheme for classifying postures by using LOS signal or NLOS signal classification results (signal classification results) and sensing data. As sensing data, data of an inertial measurement unit (IMU) sensor may be used. In order to perform posture classification using the signal classification results and the sensing data, two CNN models (e.g., 2 CNN models in a parallel structure) may be used, which are different from the CNN models used for LOS / NLOS signal classification. One of the two CNN models may be trained using IMU data (first training data) associated with the LOS signal, and the other CNN model may be trained using IMU data (second training data) associated with the NLOS signal. By using separate CNN models to classify data with different characteristics, the classification accuracy may be improved.

[0157] The present disclosure provides a method for filtering the predicted data output from each CNN model before performing the final LOS / NLOS signal classification and the final posture classification. For filtering, a moving average filter can be used. Through the above, the accuracy of LOS / NLOS signal classification and the accuracy of posture classification can be increased.

[0158] The present disclosure provides a method for using classified LOS / NLOS signals and / or classified gestures by various applications of a user device. For example, an application for a tagless door, a digital car key application, or a point of service (POS) application can use the classification method of the present disclosure. The application can appropriately provide a predetermined service or a function / parameter associated with the predetermined service by using an accurately classified LOS / NLOS signal and / or a classified gesture.

[0159] According to an embodiment, by using accurately classified LOS / NLOS signals, an application can adjust an adaptive ranging frequency for power saving. For example, an application can configure a maximum sleep duration by adjusting an adaptive ranging frequency using classified LOS / NLOS signals.

[0160] According to an embodiment, an application may selectively use only LOS signals via accurate LOS / NLOS signal classification, thereby improving the accuracy of position estimation.

[0161] According to an embodiment, the application can configure adaptive access boundaries via accurate LOS / NLOS signal and gesture classification. For example, when the situation of NLOS signal / back pocket gesture is identified, the application can delay the start of service.

[0162] Figure 3a is a diagram illustrating an example of UWB CIR data according to an embodiment of the present disclosure.

[0163] The UWB channel impulse response (CIR) may be obtained by receiving a UWB signal. For example, when an electronic device receives a UWB signal for DL-TDoA or a UWB signal for DS-TWR, the electronic device may obtain UWB CIR data based on the received signal. In the present disclosure, the UWB CIR may be referred to as CIR for short.

[0164] According to an embodiment, the electronic device may obtain UWB CIR data by using a correlation value between an impulse function and a received UWB signal.

[0165] An example of UWB CIR data obtained based on a UWB signal can be as follows Figure 3a As shown. Figure 3a As shown in , for example, 1016 CIR values ​​may be output. For example, each CIR value may be a value measured or obtained based on each UWB signal including a final message (RIM) of the DS-TWR process received by the responder from the initiator. Alternatively, for example, each CIR value may be a value measured or obtained based on each UWB signal including a final message received by the user equipment (tag device) from the initiator anchor point in the DL-TDoA process.

[0166] See also Figure 3a , a peak in amplitude may occur after a predetermined CIR index (eg, CIR index 750).

[0167] Figure 3b is a diagram illustrating an example of valid UWB CIR data according to an embodiment of the present disclosure.

[0168] In the present disclosure, the effective UWB CIR may be a CIR having a significant value among CIRs. That is, in contrast to noise, the effective UWB CIR may be a CIR measured or obtained by an actual signal. In the present disclosure, the effective UWB CIR may be referred to as an effective CIR (eCIR).

[0169] According to an embodiment, the electronic device may process the CIR value before the peak value occurs as noise, and may process n CIR values ​​from the peak value as eCIR.

[0170] According to an embodiment, the electronic device may determine n CIRs as eCIRs based on a CIR index obtained by subtracting a margin value from a CIR index where a peak occurs. For example, in a case where a peak occurs at CIR index 750 and a margin value is 5 (margin=5) and the n value is configured as 200 (n=200), the electronic device may identify CIRs from CIR index 745 to CIR index 945 as ECRIs. As described above, CIRs may be classified into signals and noises, and examples of classification may be as follows. Figure 3b shown.

[0171] In the case where CIRs classified as eCIRs among the obtained CIRs are used only as input data of the CNN model for LOS / NLOS signal classification, inaccurate noise can be removed and the accuracy of classification can be increased.

[0172] Furthermore, in the case of using a CIR classified as an eCIR among the obtained CIRs, a delay for CIR data exchange can be optimized.

[0173] Furthermore, in the case of using a CIR classified as an eCIR among the obtained CIRs, an input matrix may be optimized and processing efficiency of a terminal may be improved.

[0174] Figure 3c is a diagram illustrating an example of LOS signals and NLOS signals classified using UWB CIR data according to an embodiment of the present disclosure.

[0175] As described above, the CIR value used for LOS signal / NLOS signal classification may be an eCIR value. Figure 3c As shown in , n (eg, 200) eCIR values ​​can be used for LOS / NLOS signal classification.

[0176] The CIR values ​​(eCIR values) of the LOS signal and the NLOS signal may have different characteristics.

[0177] For example, the LOS signal may have at least one of the following characteristics.

[0178] -The peak value of CIR is higher than the peak value of NLOS signal.

[0179] - The CIR values ​​after the peak drop significantly to the noise level.

[0180] - A small number of peaks occur, for example, one or two peaks.

[0181] For example, the NLOS signal may have at least one of the following characteristics.

[0182] -The peak value of CIR is lower than the peak value of LOS signal.

[0183] - It takes a long time before the CIR value after the peak drops to the noise level.

[0184] -Multiple peaks appear due to multipath signals.

[0185] Due to the difference in characteristics of the CIR value between the LOS signal and the NLOS signal, whether the corresponding signal is a LOS signal or a NLOS signal may be classified based on the measured CIR data.

[0186] According to an embodiment, the electronic device may use a deep learning algorithm to classify whether the corresponding signal is a LOS signal or a NLOS signal by using the CIR data (eCIR data) of the corresponding signal. For example, the electronic device may classify the LOS / NLOS signal by using a CNN model (CNN algorithm). Figures 4 to 11 Describe the LOS / NLOS signal classification method using a CNN model.

[0187] Hereinafter, for convenience of description, it is assumed that four cases for generating data for LOS / NLOS signal classification and / or posture classification are classified as follows.

[0188] (1) Hand LOS situation (Hand-held (LOS) posture): A situation where the user holds the electronic device in his hand (hand-held) and does not cover the UWB antenna of the electronic device.

[0189] (2) Hand-NLOS situation (Hand-held (NLOS) posture): The user holds the electronic device in his hand (hand-held) and covers the UWB antenna of the electronic device.

[0190] (3) Front pocket (LOS) situation (Front pocket (LOS) posture): The electronic device is in the user's front pocket and the LOS signal is protected.

[0191] (4) Back pocket (NLOS) situation (back pocket (NLOS) posture): The electronic device is in the user's back pocket and the signal is blocked by the human body effect.

[0192] In a predetermined environment (e.g., an environment where the user's electronic device is close to (approaching) an initiator of UWB ranging (e.g., an initiator of DS-TWR or an initiator anchor point of DL-TDoA (OWR)), data for the above four situations (e.g., UWB CIR data and / or IMU sensor data) may be collected. The collected data may be used to train and test each CNN model. In this case, the embodiment is not limited thereto, and data for another environment and / or another situation may be collected and used to train / test the CNN model according to the embodiment.

[0193] refer to Figure 4 and Figure 5 , an example of an environment in which LOS / NLOS classification may be applied will be described, e.g., Figure 4 DS-TWR and Figure 5 DL-TDoA.

[0194] Figure 4 is a diagram illustrating a DS-TWR according to an embodiment of the present disclosure.

[0195] refer to Figure 4, DS-TWR may be performed between the first electronic device 410 and the second electronic device 420.

[0196] exist Figure 4 In the embodiment of the present invention, for the convenience of description, it is assumed that the first electronic device 410 performs the role of the initiator of DS-TWR, and the second electronic device 420 as the electronic device of the user performs the role of the responder of DS-TWR. In this case, it is assumed that the second electronic device 420 is close to the first electronic device 410 as the initiator. In this case, the embodiment is not limited thereto, and for example, the opposite case may also be applied.

[0197] According to an embodiment, the first electronic device 410 may be, for example, a UWB-based door (UWB smart door), and the second electronic device 420 may be an electronic device of a user (eg, a smart phone of the user).

[0198] refer to Figure 4 In one ranging cycle (one ranging measurement cycle), the first electronic device 410 as an initiator may initiate a DS-TWR ranging process by sending a ranging initiation message (RIM), and the second electronic device 420 as a responder may send a ranging response message (RRM) as a response message to the RIM to the first electronic device 410, and the first electronic device 410 may send a ranging final message (RFM) as a response message to the RRM to the second electronic device 420. One ranging measurement cycle of DS-TWR may be repeatedly (e.g., periodically) performed.

[0199] According to an embodiment, the second electronic device 420 may obtain a CIR value of each UWB signal including the received RFM. The CIR data obtained in this way may be used for LOS / NLOS signal classification.

[0200] According to an embodiment, the second electronic device 420 may obtain sensing data of the IMU sensor and CIR data. According to an embodiment, the period for obtaining the IMU sensor data may be different from (e.g., shorter than) the period for obtaining the CIR data. In this case, in order to input the IMU sensor data corresponding to the CIR data as the input of the CNN model, a sequencing operation needs to be performed.

[0201] Figure 5 is a diagram illustrating DL-TDoA according to an embodiment of the present disclosure.

[0202] according to Figure 5In the embodiment, for ease of description, it is assumed that a single initiator anchor point (initiator UWB anchor point) 510 and three responder anchor points (responder UWB anchor points) 520-1, 520-2, and 520-3 are used for DL-TDoA. In this case, it is assumed that the electronic device 530 is close to the initiator anchor point 510 as the initiator. In this case, the embodiment is not limited thereto, and for example, a different number of anchor point devices may also be applied.

[0203] refer to Figure 5 , in one ranging cycle (one ranging measurement cycle), the initiator anchor point 510 as an initiator may initiate the DL-TDoA ranging process by sending an initiation message, and each of the responder anchor points 520-1, 520-2, and 520-3 as responders may send a response message to the initiation message to the initiation anchor point 510, and the initiator anchor point 510 may send a final message as a response message to the response message to each of the responder anchor points 520-1, 520-2, and 520-3. The user equipment 530 may receive the initiation message, the response message, and the final message, and may estimate its position according to the previously defined method.

[0204] According to an embodiment, the user equipment 530 may obtain a CIR value of each UWB signal including the received final message. The CIR data obtained in this manner may be used for LOS / NLOS signal classification.

[0205] According to an embodiment, the user device 530 may obtain sensing data of the IMU sensor and CIR data. According to an embodiment, the period for obtaining the IMU sensor data may be different from (e.g., shorter than) the period for obtaining the CIR data. In this case, in order to input the IMU sensor data corresponding to the CIR data as the input of the CNN model, a sequencing operation needs to be performed.

[0206] Figure 6 is a diagram illustrating a training process and a deployment process for LOS / NLOS signal classification using UWB channel impulse response data according to an embodiment of the present disclosure.

[0207] exist Figure 6 In the embodiment of , for ease of description, it is assumed that the training process 610 is performed in the remote server and the deployment process 620 is performed in the user device. In this case, the embodiment is not limited thereto. For example, if the user device is a device with high computing power, the training process may also be performed in the user device.

[0208] refer to Figure 6 , the training process 610 will be described.

[0209] In the training process 610, the server may collect input data in operation 611. For example, the server may collect CIR data (eg, eCIR data including n eCIR values) as input data for training.

[0210] In operation 612, the server may perform CIR normalization processing on the collected input data. For example, the server may normalize the collected input data to a range of 0 to 1. In this example, the CIR normalization of operation 612 is an optional operation and may be omitted.

[0211] The server may input CIR normalized data or CIR non-normalized data as input data of the CNN model, and may perform processing of LOS / NLOS classification using the CNN model in operation 613 .

[0212] Tables 1 and 2 given below show examples of hyperparameters and features of the CNN model for LOS / NLOS classification.

[0213] [Table 1]

[0214] layer Number of filters Filter size Activation Function Conv1D 64 5 - Instance Normalization - - ReLU MaxPool1D - 2 - Conv1D 128 11 - Instance Normalization - - ReLU MaxPool1D - 2 - Conv1D 256 17 - Instance Normalization - - ReLU MaxPool1D - 2 - Conv1D 512 5 - Instance Normalization - - ReLU MaxPool1D - 2 - Flatten - - - Intensive - - sigmoid

[0215] [Table 2]

[0216]

[0217] In operation 614, the server may obtain the prediction value output from the CNN model. According to an embodiment, the prediction value may include a prediction probability value corresponding to a label (eg, label 1) of the LOS signal and a prediction probability value corresponding to a label (eg, label 2) of the NLOS signal.

[0218] In operation 615, the server may obtain a ground truth value of the corresponding signal. According to an embodiment, the ground truth value may include a ground truth probability value of a label (eg, label 1) corresponding to the LOS signal and / or a ground truth probability value of a label (eg, label 2) corresponding to the NLOS signal.

[0219] In operation 616, the server may calculate the loss between the predicted value of operation 614 and the ground truth value of operation 615 and the gradient value by using a loss function. For example, the total loss may be calculated based on the loss between the predicted value and the ground truth value associated with the LOS signal and the loss between the predicted value and the ground truth value associated with the NLOS signal.

[0220] The server can update the parameters of the CNN model by using the values ​​obtained in operation 616. For example, by using a back-propagation scheme, the server can update the parameters of the CNN model to reduce the loss. The parameters updated as described above can be used in the CNN model to process subsequent input data (e.g., subsequent n eCIR values).

[0221] By performing the above training process 610 on all collected input data sets (e.g., each input data set includes n eCIR values), the server can continuously update the parameters of the CNN model (CNN parameters) to reduce the loss. The user device can obtain or download the CNN parameters trained in this manner. In addition, the user device can download information associated with whether normalization is used. In addition, the user device can download the standard deviation related to the CNN model.

[0222] In the following, reference Figure 6 , the deployment process 620 will be described.

[0223] In the deployment process 620, the user device may collect real-time input data in operation 621. For example, the user device may collect a plurality of CIR values ​​(e.g., eCIR values) as input data, and may divide and process them based on a predetermined number of lengths (sizes) (e.g., n lengths). According to an embodiment, the length (n) may be the same as the length (n) used for training.

[0224] In operation 622, the user equipment may perform CIR normalization on the collected input data. For example, the user equipment may normalize the collected input data to a range of 0 to 1. In this example, the CIR normalization of operation 622 is an optional operation and may be omitted.

[0225] The user device may input CIR normalized data or CIR non-normalized data as input data of the CNN model, and may perform processing for LOS / NLOS classification using the CNN model in operation 623. The CNN model of the user device may use CNN parameters obtained by the training process 610 in order to process the input data.

[0226] In operation 624, the user device may obtain the prediction data (real-time prediction data) output from the CNN model. According to an embodiment, the prediction data output from the CNN model may include a prediction value (first prediction value) of the first eCIR data (the first n eCIR data in the real-time input data), a prediction value (second prediction value) of the second eCIR data (the second n eCIR data in the real-time input data), ..., and a prediction value (nth prediction value) of the nth eCIR data (nnth eCIR data in the real-time input data). According to an embodiment, each prediction value may include a prediction probability value of a label (e.g., label 1) corresponding to a LOS signal and / or a prediction probability value of a label (e.g., label 2) corresponding to a NLOS signal associated with the corresponding eCIR data.

[0227] In operation 625, the user equipment may perform filtering of the prediction value (prediction data) by using a filter (e.g., a low pass filter (LPF) or a moving average filter). According to an embodiment, the moving average filter may have a window length parameter indicating the length of a window for calculating an average value of the data as a hyperparameter, and the user equipment may perform filtering of the prediction data by using the moving average filter with the window length parameter. For example, the user equipment may replace each prediction value with an average value by using the moving average filter, the average value being associated with the corresponding prediction value and being obtained based on the window length parameter.

[0228] In operation 626, the user device may obtain an output label of the real-time input data by using the filtered data. By using the filtered data, the user device may finally determine whether the output label of the signal corresponding to the real-time input data is a label corresponding to the LOS signal (e.g., label 1) or a label corresponding to the NLOS signal (e.g., label 2). Through the above, the user device may finally classify whether the corresponding signal is a LOS signal or a NLOS signal. As described above, before the final LOS / NLOS signal classification, by providing filtering using a moving average filter on the predicted data output from the CNN model, the accuracy of the LOS / NLOS signal classification may be increased.

[0229] Table 3 given below shows a comparison of the accuracy of LOS / NLOS classification between a case with an LPF filter (eg, a moving average filter) and a case without an LPF filter.

[0230] [Table 3]

[0231] Hand (LOS) Front pocket (LOS) Hand (LOS) Back pocket (NLOS) w / o LPF 87.4% 78.8% 99.8% 75.4% w / LPF 99.4% 92.0% 100% 90.6%

[0232] Figure 7 is a diagram illustrating a configuration of a user equipment for LOS / NLOS classification according to an embodiment of the present disclosure.

[0233] refer to Figure 7 , the user equipment 700 may include a UWB antenna 710, a CIR collector 720, a machine learning unit 30, a classification processor 740, a central controller 750 and / or a storage device 750. The classification processor 740 may include an effect CIR generator 741, a normalizer 742 and / or a moving average filter 743.

[0234] According to an embodiment, some of the above components may be omitted, or additional components may be further included. According to an embodiment, two or more of the above components may be combined into a single component. According to an embodiment, all or part of the above components may be embodied by at least one processor (or controller). For example, components other than the UWB antenna 710 and the storage device 750 may be embodied by at least one processor (or controller).

[0235] The UWB antenna 710 may receive at least one UWB signal from another electronic device. For example, the UWB antenna 710 may receive at least one UWB signal for DS-TWR or at least one UWB signal for DL-TDoA.

[0236] The CIR collector 720 may collect CIR data from at least one UWB signal received via the UWB antenna 710. The CIR collector 720 may transfer the collected CIR data to the effective CIR generator 741. The collected CIR data may include a plurality of CIR values.

[0237] The effective CIR generator 741 may generate effective CIR data from the collected CIR data. The effective CIR generator 741 may pass the generated effective CIR data to the normalizer 742, or may pass it directly to the machine learning unit 730. The effective CIR data may include a plurality of effective CIR values, and may be processed by the machine learning unit 730 in units of a predetermined number of values ​​(e.g., in units of n values).

[0238] The normalizer 742 may normalize the value of the effective CIR (eCIR) data. For example, the normalizer 742 may normalize the value of the effective CIR data to a value within a range of 0 to 1. The normalizer 742 may be an optional configuration. For example, the normalizer 742 may not be included in the user equipment 700, or the processing of the normalizer 742 may be omitted, although the normalizer 742 is included in the user equipment 700.

[0239] The machine learning unit 730 can generate prediction data using the input valid CIR data. According to an embodiment, the machine learning unit 730 can generate prediction data using a CNN model. According to an embodiment, the CNN parameters of the CNN model can be downloaded from a server that pre-performs a training process. Therefore, the machine learning unit 730 can use an optimized CNN model.

[0240] According to an embodiment, the machine learning unit 730 may perform processing in units of a predetermined number of eCIRs (e.g., n eCIRs) (eCIR sets), and may output a prediction value for each corresponding eCIR set. For example, the prediction data may include a prediction value (first prediction value) for the first n eCIRs (first eCIR set), a prediction value (second prediction value) for the subsequent n eCIRs (second eCIR set), ..., and a prediction value (nth prediction value) for the nnth eCIR (nth eCIR set). Each prediction value may include a prediction probability value corresponding to LOS and a prediction probability value corresponding to NLOS with respect to the corresponding eCIR set.

[0241] The machine learning unit 730 may pass the prediction data to the central controller 750 and / or the moving average filter 743 .

[0242] The central controller 750 may transfer the received prediction data to the storage device 730. The storage device 730 may store the received prediction data, and may transfer the stored prediction data to the moving average filter 743.

[0243] By using the prediction data (e.g., current prediction data) received from the machine learning unit 730 and the prediction data (e.g., previous prediction data) received from the storage device 760, the moving average filter 743 can calculate an average value based on a predetermined window length parameter, and can perform filtering of the prediction data using the average value. The filtered prediction data can be used for final LOS signal or NLOS signal classification. The filtered prediction data can be used by various applications.

[0244] Figure 8 is a diagram illustrating a training procedure for gesture classification based on LOS / NLOS signal classification using UWB channel impulse response data according to an embodiment of the present disclosure.

[0245] exist Figure 8 In the embodiment, for ease of description, it is assumed that the training process 810 is executed in a remote server.

[0246] refer to Figure 8 , the training process 800 will be described.

[0247] In the training process 800, the server may collect input data in operation 801. For example, the server may collect CIR data (eg, eCIR data including n eCIR values) as input data for training.

[0248] In operation 802, the server may perform CIR normalization processing on the collected input data. For example, the server may normalize the collected input data to a range of 0 to 1. In this example, the CIR normalization of operation 802 is an optional operation and may be omitted.

[0249] The server may input CIR normalized data or CIR non-normalized data as input data of the first CNN model, and may perform processing for LOS / NLOS classification using the first CNN model in operation 803. In the present disclosure, the first CNN model is referred to as a CNN model for LOS / NLOS classification.

[0250] The server may obtain a prediction value (a first prediction value or first prediction information) output from the first CNN model in operation 804. According to an embodiment, the first prediction value may include a prediction probability value of a label (e.g., label A) corresponding to the LOS signal and a prediction probability value of a label (e.g., label b) corresponding to the NLOS signal.

[0251] In operation 805, the server may obtain a ground truth value (a first ground truth value or first ground truth information) of the corresponding signal. According to an embodiment, the first ground truth value may include a ground truth probability value of a label (e.g., label 1) corresponding to the LOS signal and a ground truth probability value of a label (e.g., label 2) corresponding to the NLOS signal.

[0252] In operation 806, the server may calculate the loss between the predicted value of operation 804 and the ground truth value of operation 805 and the gradient value by using a loss function. For example, the total loss may be calculated based on the loss between the predicted value and the ground truth value associated with the LOS signal and the loss between the predicted value and the ground truth value associated with the NLOS signal.

[0253] The server may update the parameters of the first CNN model by using the values ​​obtained in operation 806. For example, by using a back-propagation scheme, the server may update the parameters of the first CNN model to reduce the loss. The parameters updated as described above may be used in the first CNN model to process subsequent input data (e.g., subsequent n eCIR values).

[0254] By performing the above training process 800 on all collected eCIR sets (e.g., each eCIR set includes n eCIR values), the server can continuously update the parameters of the first CNN model (CNN parameters) to reduce the loss. The user device can obtain or download the trained CNN parameters of the first CNN model. In addition, the user device can download information associated with whether normalization is used. In addition, the user device can download the standard deviation related to the first CNN model.

[0255] Based on the prediction value of the corresponding eCIR set, the server may determine that the signal corresponding to the corresponding eCIR set is classified as a LOS signal or a NLOS signal. For example, in the prediction value of the corresponding eCIR set, if the prediction probability value corresponding to the LOS signal is greater than the prediction probability value corresponding to the NLOS signal, the server may determine that the signal corresponding to the corresponding eCIR set is classified as a LOS signal. As another example, in the prediction value of the corresponding eCIR set, if the prediction probability value corresponding to the NLOS signal is greater than the prediction probability value corresponding to the LOS signal, the server may determine that the signal corresponding to the corresponding eCIR set is classified as a NLOS signal.

[0256] In the case where the signal corresponding to the corresponding eCIR set is classified as a LOS signal, a classification procedure associated with posture detection based on the second CNN model can be executed. Alternatively, in the case where the signal corresponding to the corresponding eCIR set is classified as a NLOS signal, a classification procedure associated with posture detection based on the third CNN model can be executed. In the present disclosure, the second CNN model is referred to as a CNN model for posture classification, which is trained using IMU sensor data associated with the LOS signal. In the present disclosure, the third CNN model is referred to as a CNN model for posture classification, which is trained using IMU sensor data associated with the NLOS signal.

[0257] Tables 4 and 5 given below show examples of hyperparameters and features of CNN models (second CNN model / third CNN model) for posture classification.

[0258] [Table 4]

[0259] layer Number of filters Filter size Activation Function Conv1D 64 2 - Instance Normalization - - ReLU MaxPool1D - 2 - Conv1D 128 2 - Instance Normalization - - ReLU MaxPool1D - 2 - Conv1D 256 2 - Instance Normalization - - ReLU MaxPool1D - 2 - Flatten - - - Intensive - - S-type

[0260] [Table 5]

[0261] Weight Initializer random Solver Adam Maximum number of training epochs 100 Batch size 10 Shuffle Each period quit 0.2 Loss Function Binary Cross Entropy

[0262] In operation 807, the server may collect sensor input data. The sensor input data may be sensor input data associated with the LOS signal (first sensor input data) or sensor input data associated with the NLOS signal (second sensor input data). For example, sensor data collected in the above environment in a state where the UWB antenna is not covered or carried in a front pocket may be sensor input data associated with the LOS signal (first sensor input data), and sensor data collected in the above environment in a state where the UWB antenna is covered or carried in a back pocket may be sensor input data associated with the NLOS (second sensor input data).

[0263] According to an embodiment, the sensor input data may include IMU values ​​associated with m time steps (m time series IMU values).

[0264] In operation 808, the server may perform a sequencing process to input sensor input data corresponding to the input data of the first CNN model to the second CNN model or the third CNN model. For example, the server may perform a sequencing process to input sensor input data collected during the same period as the period for collecting input data including n eCIR values ​​to the second CNN model or the third CNN model.

[0265] When the signal is classified as a LOS signal, the server may input the sequenced processed first sensor input data as input data for training the second CNN model, and may perform processing for posture classification using the second CNN model in operation 809. For example, by using the input data, the second CNN model may perform an operation of predicting whether the posture associated with the corresponding sensor input data is a first posture (e.g., hand-held) or a second posture (e.g., front pocket). In operation 810, the server may obtain a predicted value (a second predicted value or second prediction information) output from the second CNN model. According to an embodiment, the predicted value may include a predicted probability value of a label (e.g., label 1) corresponding to a first posture (e.g., hand-held (LOS)) associated with the first sensor input data associated with LOS and a predicted probability value of a label (e.g., label 2) corresponding to a second posture (e.g., front pocket (LOS)).

[0266] When the signal is classified as an NLOS signal, the server may input the sequenced processed second sensor input data as input data for training the third CNN model, and may perform processing for posture classification using the third CNN model in operation 811. For example, by using the input data, the third CNN model may perform an operation of predicting whether the posture associated with the corresponding sensor input data is a third posture (e.g., hand-held (NLOS)) or a fourth posture (e.g., back pocket (NLOS)). In operation 812, the server may obtain a predicted value (a second predicted value or second prediction information) output from the third CNN model. According to an embodiment, the predicted value associated with the second sensor input data associated with LOS may include a predicted probability value of a label (e.g., label 3) corresponding to the third posture (e.g., hand-held (NLOS)) and a predicted probability value of a label (e.g., label 4) corresponding to the fourth posture (e.g., back pocket (NLOS)).

[0267] In operation 813, the server may obtain a ground truth value (a second ground truth value or second ground truth information) associated with the corresponding posture. According to an embodiment, the second ground truth value may include a ground truth probability value corresponding to a label (e.g., label 1) of the first posture, a ground truth probability value corresponding to a label (e.g., label 2) of the second posture, a ground truth probability value corresponding to a label (e.g., label 3) of the third posture, and / or a ground truth probability value corresponding to a label (e.g., label 4) of the fourth posture.

[0268] In operation 814, by using a loss function, the server can calculate the loss between the second predicted value of operation 810 and the second ground truth value and the gradient value of operation 813, and / or can calculate the loss between the third predicted value of operation 812 and the second ground truth value and the gradient value of operation 813.

[0269] The server may update the parameters of the corresponding CNN model (the second CNN model or the third CNN model) by using the values ​​obtained in operation 814. For example, the server may update the parameters of the second CNN model using the loss and / or gradient obtained based on the second predicted value of operation 810 and the second gradient true value of operation 813. Alternatively, the server may update the parameters of the third CNN model using the loss and / or gradient obtained based on the third predicted value of operation 812 and the second gradient true value of operation 813. According to an embodiment, the server may update the parameters of the corresponding CNN model to reduce the loss by using a back-propagation scheme.

[0270] The parameters updated as described above can be used in the corresponding CNN model to process subsequent input data (e.g., subsequent m IMU sensing values).

[0271] By performing the above training process 800 on all collected IMU sensor data sets (e.g., each IMU sensor data set includes m IMU sensing values), the server can continuously update the parameters (CNN parameters) of the second CNN model and the third CNN model to reduce the loss. The user device can obtain or download the trained CNN parameters of the second CNN model and the third CNN model.

[0272] Fig. 9 is a diagram illustrating a deployment process for classifying gestures based on LOS / NLOS signal classification performed using UWB channel impulse response data according to an embodiment of the present disclosure.

[0273] exist Fig. 9 In the embodiment, for ease of description, it is assumed that the deployment process 900 is executed in a user device.

[0274] refer to Fig. 9 , the deployment process 900 will be described.

[0275] In the deployment process 900, the user equipment may collect input data in operation 901. For example, the user equipment may collect a plurality of CIR values ​​(e.g., eCIR values) as input data, and may divide and process them based on a predetermined number of lengths (sizes) (e.g., n lengths). According to an embodiment, the length (n) may be the same as the length (n) used for training.

[0276] In operation 902, the user equipment may perform CIR normalization on the collected input data. For example, the user equipment may normalize the collected input data to a range of 0 to 1. In this example, the CIR normalization of operation 902 is an optional operation and may be omitted.

[0277] The user equipment may input CIR normalized data or CIR non-normalized data as input data of the first CNN model, and may perform processing for LOS / NLOS classification using the first CNN model in operation 903. In the present disclosure, the first CNN model is referred to as a CNN model for LOS / NLOS classification.

[0278] In operation 904, the user equipment may obtain a prediction value (a first prediction value or first prediction information) output from the first CNN model. According to an embodiment, the first prediction value may include a prediction probability value of a label (e.g., label A) corresponding to the LOS signal and a prediction probability value of a label (e.g., label B) corresponding to the NLOS signal.

[0279] The user device may perform the above-described LOS / NLOS classification process on each of all collected eCIR sets (e.g., each eCIR set includes n eCIR values). In operation 905, the user device may perform filtering of the prediction data (first prediction data) including each prediction value obtained from the first CNN model by using a moving average filter.

[0280] Based on the prediction value of the corresponding eCIR set, the user equipment may determine that the signal corresponding to the corresponding eCIR set is classified as a LOS signal or a NLOS signal. For example, in the prediction value of the corresponding eCIR set, if the prediction probability value corresponding to the LOS signal is greater than the prediction probability value corresponding to the NLOS signal, the user equipment may determine that the signal corresponding to the corresponding eCIR set is classified as a LOS signal. As another example, in the prediction value of the corresponding eCIR set, if the prediction probability value corresponding to the NLOS signal is greater than the prediction probability value corresponding to the LOS signal, the user equipment may determine that the signal corresponding to the corresponding eCIR set is classified as a NLOS signal.

[0281] In the case where the signal corresponding to the corresponding eCIR set is classified as a LOS signal, a classification procedure associated with posture detection based on the second CNN model can be executed. Alternatively, in the case where the signal corresponding to the corresponding eCIR set is classified as a NLOS signal, a classification procedure associated with posture detection based on the third CNN model can be executed. In the present disclosure, the second CNN model is referred to as a CNN model for posture classification, which is trained using IMU sensor data associated with the LOS signal. In the present disclosure, the third CNN model is referred to as a CNN model for posture classification, which is trained using IMU sensor data associated with the NLOS signal.

[0282] In operation 906, the user device may collect sensor input data. The sensor input data may be sensor input data associated with the LOS signal (first sensor input data) or sensor input data associated with the NLOS signal (second sensor input data). According to an embodiment, the sensor input data may include IMU values ​​associated with m time steps.

[0283] In operation 907, the user device may perform a sequencing process to input sensor input data corresponding to the input data of the first CNN model to the second CNN model or the third CNN model. For example, the user device may perform a sequencing process to input sensor input data collected during the same time period as the time period for collecting input data including n eCIR values ​​to the second CNN model or the third CNN model.

[0284] When the signal is classified as a LOS signal, the user device may input sensor input data (first sensor input data) as input data of the second CNN model, and may perform processing for posture classification using the second CNN model in operation 908. For example, by using the input data, the second CNN model may perform an operation of predicting whether the posture associated with the corresponding sensor input data is a first posture (e.g., hand-held (LOS)) or a second posture (e.g., front pocket (LOS)). The user device may obtain a predicted value (a second predicted value or second prediction information) output from the second CNN model in operation 909. According to an embodiment, the predicted value may include a predicted probability value of a label (e.g., label 1) corresponding to the first posture (e.g., hand-held (LOS)) associated with the first sensor input data associated with LOS and a predicted probability value of a label (e.g., label 2) corresponding to the second posture (e.g., front pocket (LOS)).

[0285] When the signal is classified as an NLOS signal, the server may input the sequenced processed sensor input data (second sensor input data) as input data for training the third CNN model, and may perform processing for posture classification using the third CNN model in operation 910. For example, by using the input data, the third CNN model may perform an operation of predicting whether the posture associated with the corresponding sensor input data is a third posture (e.g., hand-held (NLOS)) or a fourth posture (e.g., back pocket (NLOS)). In operation 911, the user device may obtain a predicted value (a second predicted value or second prediction information) output from the third CNN model. According to an embodiment, the predicted value may include a predicted probability value of a label (e.g., label 1) corresponding to the third posture (e.g., hand-held (NLOS)) associated with the second sensor input data associated with NLOS and a predicted probability value of a label (e.g., label 4) corresponding to the fourth posture (e.g., front pocket (NLOS)).

[0286] The user device may perform the above-described posture classification process on each of all IMU sensor data sets (e.g., each IMU sensor data set includes m IMU sensing values). In operation 912, the user device may perform filtering of the prediction data (second prediction data) including each prediction value obtained from the second CNN model, or may perform filtering of the prediction data (third prediction data) including each prediction value obtained from the third CNN model, by using a moving average filter. As described above, by providing filtering of the prediction data output from each CNN model using a moving average filter before the final LOS / NLOS signal classification and the final posture classification, the accuracy of the LOS / NLOS signal and posture classification may be increased.

[0287] The user device may determine a posture by using the filtered first prediction data and the filtered second prediction data. For example, by using the filtered first prediction data and the filtered second prediction data, it may be determined whether the corresponding posture is a first posture (e.g., a hand (LOS) posture) or a second posture (e.g., a front (LOS)).

[0288] Optionally, the user device may determine the posture by using the filtered first prediction data and the filtered third prediction data. For example, by using the filtered first prediction data and the filtered third prediction data, it may be determined whether the corresponding posture is the third posture (e.g., hand (NLOS) posture) or the fourth posture (e.g., back (NLOS)).

[0289] Fig.10 is a diagram illustrating a configuration of a user device for gesture classification using LOS / NLOS classification according to an embodiment of the present disclosure.

[0290] refer to Fig.10 , the user equipment 1000 may include an IMU sensor 1010, a sensor data collector 1020, a UWB antenna 1030, a CIR collector 1040, a machine learning unit 1050, a classification processor 1060, a central controller 1070 and / or a storage device 1080. The classification processor 1060 may include an effect CIR generator 1061, a normalizer 1062, a moving average filter 1063 and / or a sequence generator 1064.

[0291] According to an embodiment, some of the above components may be omitted, or additional components may be further included. According to an embodiment, two or more of the above components may be combined into a single component. According to an embodiment, all or part of the above components may be embodied by at least one processor. For example, components other than the IMU sensor 1010, the UWB antenna 1030, and the storage device 1080 may be embodied by at least one processor (or controller).

[0292] The IMU sensor 1010 may sense its surrounding environment. According to an embodiment, the IMU sensor 1010 may be a sensor capable of measuring a predetermined force, an angular velocity, and / or an orientation of a body by using a combination of an accelerometer, a gyroscope, and / or a magnetometer. The IMU sensor 1010 may transmit the sensing data to the sensor data collector 1020.

[0293] The sensor data collector 1020 may pass the collected sensor data to the sequence generator 1064 .

[0294] The sequence generator 1064 may perform a sequencing process to input sensor input data corresponding to the input data of the first CNN model to the second CNN model or the third CNN model. For example, the sequence generator 1064 may perform a sequencing process to input sensor input data collected during the same period as the period for collecting input data including n eCIR values ​​to the second CNN model or the third CNN model.

[0295] The UWB antenna 1030 may receive at least one UWB signal from another electronic device. For example, the UWB antenna 1030 may receive at least one UWB signal for DS-TWR or at least one UWB signal for DL-TDoA.

[0296] The CIR collector 1040 may collect CIR data from at least one UWB signal received via the UWB antenna 1030. The CIR collector 1040 may transfer the collected CIR data to the effective CIR generator 1061. The collected CIR data may include a plurality of CIR values.

[0297] The effective CIR generator 1061 may generate effective CIR data from the collected CIR data. The effective CIR generator 1061 may pass the generated effective CIR data to the normalizer 1062, or may pass it directly to the machine learning unit 1050. The effective CIR data may include a plurality of effective CIR values, and may be processed by the machine learning unit 1050 in units of a predetermined number of values ​​(e.g., in units of n values).

[0298] The normalizer 1062 may normalize the value of the effective CIR (eCIR) data. For example, the normalizer 1062 may normalize the value of the effective CIR data to a value within a range of 0 to 1. The normalizer 1062 may be an optional configuration. For example, the normalizer 1062 may not be included in the user equipment 1000, or the processing of the normalizer 1062 may be omitted, although the normalizer 742 is included in the user equipment 1000.

[0299] The machine learning unit 1050 may generate prediction data using input data. According to an embodiment, the machine learning unit 730 may generate at least one prediction data using at least one CNN model, and may download CNN parameters of each CNN model from a server that pre-performs a training process.

[0300] According to an embodiment, by using the first CNN model, the machine learning unit 1050 can generate first prediction data for LOS / NLOS classification from the input valid CIR data. According to an implementation, the first CNN model can perform processing in units of a predetermined number of eCIRs (e.g., n eCIRs) (eCIR sets), and can output a prediction value for each corresponding eCIR set. For example, the first prediction data may include a prediction value (first prediction value) of the first n eCIRs (first eCIR set), a prediction value (second prediction value) of the subsequent n eCIRs (second eCIR set), ..., and a prediction value (nth prediction value) of the nnth eCIR (nth eCIR set). Each prediction value may include a prediction probability value corresponding to LOS and a prediction probability value corresponding to NLOS associated with the corresponding eCIR set.

[0301] According to an embodiment, by using a second CNN model, the machine learning unit 1050 may generate second prediction data for classifying a posture associated with LOS from the input sensor data. According to an embodiment, the second CNN model may perform processing in units of a predetermined number of sensing values ​​(e.g., m sensing values) (sensor data set), and may output a prediction value for each corresponding eCIR set. For example, the second prediction data may include a prediction value (first prediction value) of the first m sensing values ​​(first sensing data set), a prediction value (second prediction value) of the subsequent m sensing values ​​(second sensing data set), ..., and a prediction value (nth prediction value) of the nmth sensing value (nth sensing data set). Each prediction value may include a prediction probability value associated with the corresponding sensing data set, associated with LOS, corresponding to the first posture, and a prediction probability value corresponding to the second posture.

[0302] According to an embodiment, by using a third CNN model, the machine learning unit 1050 may generate third prediction data for classifying a posture associated with NLOS from the input sensor data. According to an embodiment, the third CNN model may perform processing in units of a predetermined number of sensing values ​​(e.g., m sensing values) (sensor data set), and may output a prediction value for each corresponding sensing data set. For example, the third prediction data may include a prediction value (first prediction value) of the first m sensing values ​​(first sensing data set), a prediction value (second prediction value) of the subsequent m sensing values ​​(second sensing data set), ..., and a prediction value (nth prediction value) of the nmth sensing value (nth sensing data set). Each prediction value may include a prediction probability value associated with the corresponding sensing data set, associated with NLOS, corresponding to the first posture, and a prediction probability value corresponding to the second posture.

[0303] The machine learning unit 1050 may pass the prediction data (eg, the first prediction data, the second prediction data, and / or the third prediction data) to the central controller 1070 and / or the moving average filter 1064 .

[0304] The central controller 1070 may transfer the received prediction data to the storage device 1080. The storage device 1080 may store the received prediction data, and may transfer the stored prediction data to the moving average filter 1064.

[0305] The moving average filter 1064 may filter each prediction data. The filtered prediction data may be used for final posture classification. The filtered prediction data may be used by various applications. According to an embodiment, the application may provide different services or service-related parameters (e.g., thresholds) according to the posture classified based on the filtered prediction data.

[0306] Fig.11 is a diagram illustrating a gesture classification method of an electronic device according to an embodiment of the present disclosure.

[0307] exist Fig.11 In the embodiment of the present invention, the electronic device may be an electronic device of a user (user device). Fig.11 The description of each operation can be found in the reference above. Figures 4 to 10 Descriptions of the operations / steps described, unless they contradict each other.

[0308] refer to Fig.11 In operation 1110, the electronic device may obtain first prediction data for classifying whether a signal corresponding to the UWB CIR is a LOS signal or a NLOS signal based on the UWB CIR data by using the trained first CNN model.

[0309] In operation 1120, the electronic device may identify whether the signal is classified as a LOS signal.

[0310] When the signal is classified as the LOS signal, in operation 1130, the electronic device may obtain second prediction data for classifying a gesture based on the sensor data corresponding to the UWB CIR data by using the trained second CNN model.

[0311] When the signal is classified as the LOS signal, in operation 1140, the electronic device may obtain third prediction data for classifying a gesture based on the sensor data corresponding to the UWB CIR data by using the trained third CNN model.

[0312] In operation 1150, the electronic device may perform filtering of at least two of the first prediction data, the second prediction data, and the third prediction data by using a first filtering scheme.

[0313] In operation 1160 , the electronic device may classify the gesture based on the filtered data.

[0314] According to an embodiment, the second CNN model may be trained using sensor data associated with the LOS signal, and the third CNN model may be trained using sensor data associated with the NLOS signal.

[0315] According to an embodiment, when the signal is classified as the LOS signal, the electronic device may classify one of at least one gesture associated with the LOS signal as a gesture based on the filtered first prediction data and the filtered second prediction data.

[0316] According to an embodiment, when the signal is classified as the NLOS signal, the electronic device may classify one of the at least one gesture associated with the NLOS signal as a gesture based on the filtered first prediction data and the filtered third prediction data.

[0317] According to an embodiment, the first filtering scheme may be a moving average filtering scheme.

[0318] According to an embodiment, the sensor data may be sensor data obtained from an IMU sensor.

[0319] According to an embodiment, the UWB CIR data may include effective CIR data obtained by removing noise from CIR data obtained based on a UWB signal for DL-TDoA ranging, or may include effective CIR data obtained by removing noise from CIR data obtained based on a UWB signal for DS-TWR ranging.

[0320] Fig.12 is a diagram illustrating a structure of an electronic device according to an embodiment of the present disclosure.

[0321] exist Fig.12 In the embodiment of the present invention, the electronic device may be a user's electronic device (user device) or a server.

[0322] refer to Fig.12 , the electronic device may include a transceiver 1210, a controller 1220, and a storage device 1230. In the present disclosure, the controller may be defined as a circuit, an application specific integrated circuit, or at least one processor.

[0323] The transceiver 1210 may perform signal transmission or reception with another network entity. The transceiver 1210 may perform data transmission or reception for debugging, for example.

[0324] The controller 1220 may control the overall operation of the electronic device according to an embodiment of the present disclosure. For example, the controller 1220 may control the signal flow in units of blocks so that the operation based on the above flowchart is performed. Specifically, the controller 1220 may control the signal flow based on the block. Figures 1 to 11 Describe the operation of an electronic device.

[0325] The storage device 1230 may store at least one of the information transmitted or received via the transceiver 1210 and the information generated by the controller 1220. For example, the storage device 1230 may store information and data required for gesture classification, which has been referred to in detail. Figures 1 to 11 Described.

[0326] Fig.13a is a diagram illustrating the structure of a UWB MAC frame according to an embodiment of the present disclosure.

[0327] In the present disclosure, the UWB MAC frame may be referred to as a MAC frame or simply a frame. According to an embodiment, the UWB MAC frame may be used to transfer UWB related data (eg, UWB messages, ranging messages, control information, service data, application data, etc.).

[0328] refer to Fig.13a , a UWB MAC frame may include a MAC header (MHR), a MAC payload and / or a MAC trailer (MFR).

[0329] (1) MAC header

[0330] The MAC header may include a frame control field, a sequence number field, a destination address field, a source address field, an auxiliary security header field, and / or at least one header IE field. Depending on the embodiment, some of the above fields may not be included in the MAC header, or additional fields may be further included in the MAC header.

[0331] According to an embodiment, the frame control field may include a frame type field, a security enabled field, a frame pending field, an ack request (AR) field, a PAN ID compression field (PAN ID present field), a sequence number suppression field, an IE present field, a destination addressing mode field, a frame version field, and / or a source addressing model field. According to an embodiment, some of the above fields may not be included in the frame control field, or additional fields may be further included in the frame control field.

[0332] A description of each field follows.

[0333] The frame type field may indicate a frame type. According to an embodiment, the frame type may include a data type and / or a multi-purpose type.

[0334] The Security Enabled field may indicate whether there is an Auxiliary Security Header field. The Auxiliary Security Header field may include information required for security processing.

[0335] The frame pending field may indicate whether the device sending the frame has more data for the recipient. In other words, the frame pending field may indicate whether there is a pending frame for the recipient.

[0336] The ack request (AR) field may indicate whether an acknowledgement of receipt of the frame is required from the receiver.

[0337] The PAN ID Compression field (PAN ID Existence field) may indicate whether the PAN ID field exists.

[0338] The Sequence Number Suppression field may indicate whether the Sequence Number field is present. The Sequence Number field may indicate a sequence identifier for the frame.

[0339] The IE presence field may indicate whether a header IE field and a payload IE field are included in a frame.

[0340] The destination addressing mode field may indicate whether the destination address field includes a short address (eg, 16 bits) or an extended address (eg, 64 bits).The destination address field may indicate the address of the receiver of the frame.

[0341] The frame version field may indicate a frame version. For example, the frame version field may be configured to indicate a value of IEEE std802.15.4z-2020.

[0342] The source addressing mode field may indicate whether the source address field is present, and when the source address field is present, may indicate whether the source address field includes a short address (eg, 16 bits) or an extended address (eg, 64 bits). The source address field may indicate the address of the initiator of the frame.

[0343] (2) MAC payload

[0344] The MAC payload may include at least one payload IE field. According to an embodiment, the payload IE field may include a vendor specific nested IE.

[0345] (3) MAC tail

[0346] The MAC trailer may include an FCS field. The FCS field may include a 16-bit CRC or a 32-bit CRC.

[0347] Fig.13b is a diagram illustrating the structure of a UWB PHY packet according to an embodiment of the present disclosure.

[0348] Fig.13bPart A of shows the structure of a UWB PHY packet to which the STS packet configuration is not applied, and Fig.13b Part B of illustrative examples shows a structure of a UWB PHY packet to which the STS packet configuration is applied. The UWB PHY packet may be referred to as a PHY packet, a PHY PDU (PPDU), or a frame.

[0349] refer to Fig.13b In part A of the PPDU, a synchronization header (SHR), a PHY header (PHR), and a PHY payload (PSDU) may be included. The PSDU may include a MAC frame, and as shown in FIG. 2 , the MAC frame may include a MAC header (MHR), a MAC payload, and / or a MAC trailer (MFR). The synchronization header portion may be referred to as a preamble, and the portion including the PHY header and the PHY payload may be referred to as a data portion.

[0350] The synchronization header may be used for synchronization of signal reception, and may include a SYNC field and a start frame delimiter (SFD).

[0351] The SYNC field may be a field including a plurality of preamble symbols used for synchronization between transmitting / receiving devices. The preamble symbol may be configured by one of predefined preambles.

[0352] The SFD field may be a field indicating the end of the SHR and the start of the data field.

[0353] The PHY header may provide information associated with the configuration of the PHY payload. For example, the PHY header may include information associated with the length of the PSDU, information indicating whether the current frame is an R frame (or a data frame), and the like.

[0354] The PHY layer of a UWB device may include an optional mode for providing reduced air time for high density / low power operation. In this case, the UWB PHY packet may include an encryption sequence (i.e., STS) for increasing the integrity and accuracy of the ranging measurement timestamp. The STS may be included in the STS field of the UWB PHY packet and may be used for secure ranging.

[0355] refer to Fig.13bPart B, in the case of STS packet (SP) configuration 0 (SP0), the STS field may not be included in the PPDU (SP0 packet). In the case of STS configuration 1 (SP1), the STS field may be immediately after the frame start delimiter (SFD) field and before the PHR field (SP1 packet). In the case of SP configuration 2 (SP2), the STS field may be after the PHY payload (SP2 packet). In the case of SP configuration 3 (SP3), the STS field may be immediately after the SFD field, and the PPDU may not include the PHR and data fields (PHY payload) (SP3 packet). That is, in the case of SP3, the PPDU may not include the PHR and the PHY payload.

[0356] like Fig.13b As shown in part B of , each UWB PHY packet may include RMARKER to define a reference time, and RMARKER may be used to obtain a transmission time (transmission timestamp), a reception time (reception timestamp) and / or a time interval of a ranging message (frame) in a UWB ranging process. For example, a UWB PHY packet may include RMARKER in a preamble or at the end of a preamble.

[0357] Fig.14 is a diagram illustrating an example of a cluster configured with a plurality of UWB anchor points according to an embodiment of the present disclosure.

[0358] A cluster can be a collection of UWB anchor points (DT-anchor points) that exchange DTMs with each other to provide positioning services to UWB tags. Fig.14 As shown, the cluster may be a set including a single initiator anchor point (initiator DT anchor point) 1410 and three responder anchor points (responder DT anchor points) 1430a, 1430b, and 1430c. In this case, the embodiment is not limited thereto, and the number of UWB anchor points included in the cluster and the number of initiator anchor points and responder anchor points may be configured differently according to the embodiment.

[0359] According to an embodiment, a UWB anchor point may operate in one or more clusters. In this case, a UWB anchor point operating as an initiator anchor point in one cluster may operate as a responder anchor point in another cluster.

[0360] According to an embodiment, the area covered by one cluster may overlap with the area covered by a neighboring cluster.

[0361] refer to Fig.14, the UWB tag 1420 may receive the DTMs exchanged between the UWB anchor points 1410, 1430a, 1430b, and 1430c, and may calculate TDoAs associated with multiple pairs of anchor devices based on the received DTMs. For example, based on the received DTMs, the UWB tag 1420 may calculate TDoA1 as the TDoA between the initiator anchor point 1410 and the responder anchor point 1430a, TDoA2 as the TDoA between the initiator anchor point 1410 and the responder anchor point 1430b, and TDoA3 as the TDoA between the initiator anchor point 1410 and the responder anchor point 1430c. The UWB tag 1420 may estimate (or determine) its position by using the calculated TDoAs.

[0362] Fig.15a is a diagram illustrating a method of performing UWB ranging based on a DL-TDoA scheme by a UWB device according to an embodiment of the present disclosure.

[0363] exist Fig.15a In the embodiment of FIG. 1 , it is assumed that one initiator anchor point (initiator DT-anchor point) 1510 and n responder anchor points (responder DT-anchor points 1530a, ..., 1530n) operate as UWB anchor points (DT-anchor points). For example, Fig.14 As shown, one initiator anchor point and three responder anchor points can operate as UWB anchor points. In this case, the embodiment is not limited thereto, and the number of UWB anchor points included in the cluster and the number of initiator anchor points and responder anchor points can be configured differently according to the embodiment.

[0364] In operation S1502, the initiator anchor point 1510 may send or broadcast a polling DTM received by the responder anchor points in the cluster, and may initiate a DL-TDoA cycle. The polling DTM may include scheduling information (e.g., ranging slot index) associated with each responder anchor point so as to send the response DTM in the allocated ranging slot. The polling DTM may also include transmission time information (transmission timestamp) indicating the time when the polling DTM was sent. The polling DTM may also include a round index of the current ranging round and a block index of the current ranging block in which the polling DTM is sent. The polling DTM may also include location information of the UWB anchor point that sent the polling DTM.

[0365] According to an embodiment, each responder anchor point 1530a, ..., and 1530n may identify whether to transmit a response DTM and / or a time slot (ranging slot index) for transmitting its response DTM by referring to the scheduling information in the polling DTM.

[0366] In operations S1504a, ..., and S1504n, each responder anchor point 1530a, ..., and 1530n receiving the polling DTM can provide a response to the initiator anchor point 1510 by using the response DTM in the ranging time slot allocated by the polling DTM. For example, each responder anchor point 1530a, ..., and 1530n can send or broadcast the response DTM in its ranging time slot allocated by the polling DTM. Each response DTM may include reply time information indicating the time between the time when the polling DTM is received and the time when the corresponding response DTM is sent. Each response DTM may include a transmission time (transmission timestamp) indicating the time when the corresponding response DTM is sent. Each response DTM may also include a round index of the current ranging round and a block index of the current ranging block of the corresponding response DTM. Each response DTM may also include the location information of the UWB anchor point that sends the corresponding response DTM.

[0367] In operation S1506, the initiator anchor point 1510 receiving the response DTM may additionally send a final DTM to the responder anchor points 1530a, ..., and 1530n. For example, the initiator anchor point 1510 may send or broadcast the final DTM after receiving the response DTM from the responder anchor points 1530a, ..., and 1530n. The final DTM may include each reply time indicating the time between the time when each response DTM is received and the time when the final DTM is sent. That is, the final DTM may include a list of reply times, and the list may include a reply time indicating the time between the time when the corresponding response DTM is received and the time when the final DTM is sent. The final DTM may include a transmission time (transmission timestamp) indicating the time when the final DTM is sent. The final DTM may also include a round index of the current ranging round and a block index of the current ranging block where the final DTM is sent.

[0368] In operation S1508, the tag device (DT-tag) 1520 may receive (or listen to) the polling DTM, the response DTM, and the final DTM, may obtain the information included in each DTM message and the reception time information (reception timestamp) indicating the time when each DTM message is received, and may use the obtained information to calculate the TDoA value. The tag device 1520 may obtain (or estimate) its position by using the calculated TDoA value. For example, the tag device 1520 (ie, the user device) may calculate the relative distance to the anchor device by using the TDoA associated with multiple pairs of anchor devices, and may estimate its position. Through the above, the tag device 1520 may estimate its position without exposing its position.

[0369] Each of the above DTMs may be included in a MAC frame (e.g., Fig.13aMAC frame) and can be transmitted via UWB signal (or PHY packet (e.g., Fig.13b PHY packet)) to send.

[0370] Fig.15b is a diagram showing an example of a ranging block structure for a downlink TDoA scheme according to an embodiment of the present disclosure.

[0371] Fig.15b The ranging block structure is used to perform Fig.15a An example of a ranging block structure for a ranging scheme.

[0372] refer to Fig.15b , a ranging block may include multiple ranging rounds.

[0373] According to an embodiment, the ranging block may include a plurality of ranging rounds respectively allocated to a plurality of clusters. For example, in the case where n clusters are arranged, the ranging block may include a first ranging round allocated to a first cluster, a second ranging round allocated to a second cluster, ..., and an nth ranging round allocated to an nth cluster. Figure 7 b, but according to an embodiment, multiple ranging rounds may be allocated to a single cluster, and a single ranging round may be allocated to multiple clusters.

[0374] According to an embodiment, a ranging round may include a plurality of ranging slots. A ranging round may include a plurality of ranging slots allocated to ranging messages sent by an anchor device belonging to a cluster associated with the corresponding ranging round. For example, in a case where a first cluster is configured with one initiator anchor and three responder anchors, a ranging round of the first cluster may be a first ranging slot (e.g., ranging slot index 0) allocated for sending / receiving a polling message of an initiator anchor included in the first cluster, a second ranging slot allocated for sending / receiving a response message of the first responder anchor, a third ranging slot allocated for sending / receiving a response message of the second responder anchor, a fourth ranging slot allocated for sending / receiving a response message of the third responder anchor, and a fifth ranging slot allocated for sending / receiving a final message of the initiator anchor.

[0375] In this way, ranging slots can be allocated to the ranging round of each cluster.

[0376] Through Fig.15b The ranging block structure shown in the figure, the anchor devices of each cluster can exchange a periodic ranging message via their ranging rounds in a ranging block, and the user device (tag device) can receive the ranging message and can calculate its position. This operation can be repeated for each ranging block. Through the above, the position of the user device can be updated based on the ranging block period.

[0377] Fig.16ais a diagram illustrating an example of a LOS environment in case of DL-TDoA positioning according to an embodiment of the present disclosure.

[0378] exist Fig.16a In the present invention, for ease of description, it is assumed that 6 UWB anchor points for DL-TDoA and one user device (terminal) exist in a gate access area where a gate is located. In this case, the embodiment is not limited thereto, and the number of UWB anchor points for DL-TDoA and the number of user devices may be configured differently.

[0379] refer to Fig.16a , the user equipment 1620 may receive a UWB signal of DL-TDoA from each UWB anchor point 1611, 1612, 1613, 1614, 1615, and 1616. For example, the user equipment 1620 may receive a UWB signal including a polling DTM and / or a UWB signal including a final DTM from an initiator anchor point. For example, the user equipment 1620 may receive a UWB signal including a response DTM from each responder anchor point.

[0380] The user equipment 1620 may obtain information (reception timestamps) associated with reception times of UWB signals respectively received from n adjacent UWB anchor points, and may use the obtained n reception timestamps for DL-TDoA. For example, in the case of three-dimensional (3D) DL-TDoA positioning, DL-TDoA positioning requires UWB signals received from at least four UWB anchor points, and thus the user equipment 1620 may select four reception timestamps from the n reception timestamps in order to estimate its position.

[0381] According to an embodiment, the user equipment 1620 may select a combination of four reception timestamps selectable from n reception timestamps, and may estimate its position using each reception timestamp combination. In this case, the user equipment may estimate its position based on each reception timestamp combination, and may determine an accurate position by removing the position with the highest variance and performing recalculation. That is, the user equipment may determine its position by performing calculation C (n, 4) times.

[0382] The timestamp (receive timestamp) of the UWB signal can be measured using the first peak of the preamble of the UWB signal (e.g., the preamble of the UWB PHY packet included in the UWB signal). In the case where the UWB signal is a LOS signal, one peak appears, so the user equipment 1620 can clearly identify the first peak of the preamble of the corresponding UWB signal. On the contrary, in the case where the UWB signal is a NLOS signal, multiple peaks appear due to the multipath characteristics, so the user equipment 1620 may have difficulty in clearly identifying which peak is the first peak of the preamble of the corresponding UWB signal. Therefore, when the UWB signal is a NLOS signal, there is a high probability that there is an error in the receive timestamp. The error in the receive timestamp may cause an error in DL-TDoA positioning.

[0383] Therefore, when the user equipment 1620 is able to use the LOS / NLOS classification method (e.g., reference Figure 7 and Figure 8 When the LOS quality (e.g., p(LOS)) of the corresponding UWB signal is identified by the LOS / NLOS classification method described in the foregoing, the user equipment 1620 can perform DL-TDoA positioning using only the reception timestamps of the UWB signal with high LOS quality. For example, the user equipment 1620 can perform DL-TDoA positioning using only the reception timestamps of the UWB signal with the first four p(LO). Through the above, accurate positioning can be performed.

[0384] Fig.16b It is shown in Fig.16a FIG. 1 is a diagram of an example of LOS probability data of a UWB signal obtained in a DL-TDoA positioning environment.

[0385] By using LOS / NLOS classification methods (e.g., ref. Figure 7 and Figure 8 ), the user equipment 1620 may obtain the LOS probability (LOS quality) of the UWB signal received from each UWB anchor point.

[0386] For example, Fig.16bAs shown, the LOS probability of the UWB signal received from the first UWB anchor point 1611 may be 0.42 (p(LOS)=0.42), the LOS probability of the UWB signal received from the second UWB anchor point 1612 may be 0.91 (p(LOS)=0.91), the LOS probability of the UWB signal received from the third UWB anchor point 1613 may be 0.94 (p(LOS)=0.94), the LOS probability of the UWB signal received from the fourth UWB anchor point 1614 may be 0.65 (p(LOS)=0.65), the LOS probability of the UWB signal received from the fifth UWB anchor point 1615 may be 0.49 (p(LOS)=0.49). And the LOS probability of the UWB signal received from the sixth UWB anchor point 1616 may be 0.22 (p(LOS)=0.22).

[0387] In the case where there are n UWB anchor points in the DL-TDoA environment, the average LOS probability of the n UWB anchor points ( ) can be expressed as shown in Equation 1 below.

[0388] [Equation 1]

[0389]

[0390] Here, n is the number of UWB anchor points in the DL-TDoA environment, and is the LOS probability of the UWB signal received from the i-th UWB anchor point.

[0391] According to an embodiment, when there are n UWB anchor points in the DL-TDoA environment, a threshold value (p th ). According to an embodiment, in p th < In the case of , the DL-TDoA environment can be regarded as a LOS environment. th ≥ In the case of , the DL-TDoA environment can be regarded as a LOS environment. For example, the threshold (p th ) can be configured to distinguish whether a DL-TDoA environment is a LOS environment or a NLOS environment in a tagless door, digital car key, or POS device. For example, the threshold (p th ) can be configured to 0.5.

[0392] refer to Fig.16a and 16b , when the threshold (p th ) is 0.5, =0.605. Therefore, Fig.16aThe DL-TDoA environment shown in the figure can be regarded as a LOS environment (“p th < ”).

[0393] Reference Fig.16a , based on the distance (d) between the user equipment 1620 and the door 1630 and the distance value (d area ) of the door access area, the user equipment 1620 can determine whether to access the door 1630. According to an embodiment, when d area < d, it is regarded that the user equipment 1620 is located outside the door access area, and the user equipment 1620 does not access the door 1630. When d area ≥ d, it is regarded that the user equipment 1620 attempts to access the door 1630.

[0394] According to an embodiment, in the case of a LOS environment, the user equipment 1620 can adaptively skip ranging, thereby achieving a power saving effect.

[0395] The adaptive ranging frequency (f a ) can be expressed as shown in Equation 2 below.

[0396] [Equation 2]

[0397]

[0398] Here, f represents the ranging frequency in the corresponding DL-TDoA environment, d represents the distance between the user equipment 1620 and the door 1630, and d area represents the straight-line distance from the center of the door 1630 to the door access area. According to an embodiment, at the center of the door 1630, a communication module (for example, a UWB module) supporting the communication of the door 1630 can be located. For example, when f = 200 ms, d = 3 m, and d area = 2 m, f a = 400 ms can be determined according to Equation 2.

[0399] According to an embodiment, in the LOS environment, when d area < d, a power saving effect of times can be obtained by adaptively adjusting the ranging frequency. According to an embodiment, in the LOS environment, when d area > d, the existing ranging frequency f can be used as it is.

[0400] Fig.17a is a diagram showing an example of a LOS environment in the case of DL-TDoA positioning according to an embodiment of the present disclosure.

[0401] Reference Fig.17a, the user equipment 1720 may receive a UWB signal of DL-TDoA from each UWB anchor point 1711, 1712, 1713, 1714, 1715, and 1716. For example, the user equipment 1720 may receive a UWB signal including a polling DTM and / or a UWB signal including a final DTM from an initiator anchor point. For example, the user equipment 1720 may receive a UWB signal including a response DTM from each responder anchor point.

[0402] The user equipment 1720 may obtain information (reception timestamps) associated with reception times of UWB signals received from n adjacent UWB anchor points, respectively, and may use the obtained n reception timestamps for DL-TDoA. For example, in the case of three-dimensional (3D) DL-TDoA positioning, DL-TDoA positioning requires UWB signals received from at least four UWB anchor points, so the user equipment 1720 may select four reception timestamps from the n reception timestamps in order to estimate its position.

[0403] According to an embodiment, the user equipment 1720 may select a combination of four reception timestamps selectable from n reception timestamps, and may estimate its position using each reception timestamp combination. In this case, the user equipment may estimate its position based on each reception timestamp combination, and may determine an accurate position by removing the position with the highest variance and performing a recalculation. That is, the user equipment may determine its position by performing the calculation C(n, 4) times.

[0404] Fig.17b is shown with the user device based on Fig.17a FIG. 4 is a diagram of an example of a graph associated with acceleration values ​​of a mobile in a DL-TDoA positioning environment.

[0405] According to an embodiment, when the user equipment 1720 does not move, the ranging frequency may be adjusted to reduce power. According to an embodiment, since DL-TDoA positioning is also used outside the gate access area, when the user equipment 1720 does not move, the ranging frequency may be adjusted.

[0406] According to an embodiment, when the user device 1720 is moving, the user device 1720 is moved by an inertial measurement unit (IMU) sensor (e.g., Figure 1 The magnitude of the acceleration value measured by the sensor module 176 of the IMU sensor may periodically peak. The IMU sensor may be an inertial measurement device and may be configured as at least one of an acceleration sensor, an angular velocity sensor (gyroscope), or a geomagnetic sensor (magnetometer).

[0407] The acceleration value (a) measured by the IMU sensor m ) can be expressed as shown in Equation 3 below.

[0408] [Equation 3]

[0409]

[0410] Here, a x represents the acceleration on the x-axis, a y represents the acceleration on the y-axis, a z Represents the acceleration on the z-axis.

[0411] According to an embodiment, the step function (H(a)) based on the movement of the user equipment 1720 m )) can be defined as shown in Equation 4 below.

[0412] [Equation 4]

[0413]

[0414] Here, a th Represents the acceleration value measured by the IMU sensor (a m ) is defined to identify whether the user equipment 1720 is moving.

[0415] refer to Fig.17b , when the acceleration value (a m ) is greater than the threshold value (a th ), the user equipment 1720 is considered to be moving at the corresponding time point.

[0416] According to an embodiment, the adaptive ranging frequency (f a ) can be expressed as shown in Equation 5 below.

[0417] [Equation 5]

[0418]

[0419] Here, f represents the ranging frequency in the corresponding DL-TDoA environment, d represents the distance between the user equipment 1720 and the gate 1730, and d area Represents the straight-line distance from the center of door 1730 to the door access area.

[0420] According to an embodiment, in an interval in which there is no movement of the user equipment 1720, by minimizing ranging, a power saving effect of the user equipment 1720 may be obtained.

[0421] Fig.18a is a diagram illustrating an example of a NLOS environment in case of DL-TDoA positioning according to an embodiment of the present disclosure.

[0422] exist Fig.18aIn the present invention, for ease of description, it is assumed that 6 UWB anchor points for DL-TDoA and one user device (terminal) exist in the door access area where the door is located. In this case, the embodiment is not limited thereto, and the number of UWB anchor points for DL-TDoA and the number of user devices may be configured differently.

[0423] refer to Fig.18a , the user equipment 1820 may receive a UWB signal of DL-TDoA from each UWB anchor point 1811, 1812, 1813, 1814, 1815, and 1816. For example, the user equipment 1820 may receive a UWB signal including a polling DTM and / or a UWB signal including a final DTM from an initiator anchor point. For example, the user equipment 1820 may receive a UWB signal including a response DTM from each responder anchor point.

[0424] The user equipment 1820 may obtain information (reception timestamps) associated with reception times of UWB signals respectively received from n adjacent UWB anchor points, and may use the obtained n reception timestamps for DL-TDoA. For example, in the case of three-dimensional (3D) DL-TDoA positioning, DL-TDoA positioning requires UWB signals received from at least four UWB anchor points, and thus the user equipment 1820 may select four reception timestamps from the n reception timestamps in order to estimate its position.

[0425] Fig.18b It is shown in Fig.18a FIG. 1 is a diagram of an example of LOS probability data of a UWB signal obtained in a DL-TDoA positioning environment.

[0426] By using LOS / NLOS classification methods (e.g., ref. Figure 7 and Figure 8 ), the user equipment 1820 may obtain the LOS probability (LOS quality) of the UWB signal received from each UWB anchor point.

[0427] For example, Fig.18bAs shown, the LOS probability of the UWB signal received from the first UWB anchor point 1811 may be 0.42 (p(LOS)=0.42), the LOS probability of the UWB signal received from the second UWB anchor point 1812 may be 0.51 (p(LOS)=0.51), the LOS probability of the UWB signal received from the third UWB anchor point 1813 may be 0.64 (p(LOS)=0.64), the LOS probability of the UWB signal received from the fourth UWB anchor point 1814 may be 0.25 (p(LOS)=0.25), the LOS probability of the UWB signal received from the fifth UWB anchor point 1815 may be 0.49 (p(LOS)=0.49). And the LOS probability of the UWB signal received from the sixth UWB anchor point 1816 may be 0.12 (p(LOS)=0.12).

[0428] refer to Fig.18a and 18b , when the threshold (p th ) is 0.5, =0.405. Therefore, Figure 1 The DL-TDoA environment shown in a can be considered as a NLOS environment (“p th > ”).

[0429] In an NLOS environment, it may be necessary to maximize the utilization of UWB signals received from the UWB anchor point in order to ensure the accuracy of the position estimation of the user equipment 1820. When ranging is arbitrarily skipped in an NLOS environment, there is a high probability that the tracking of the position of the user equipment 1820 is not properly performed.

[0430] According to an embodiment, in a NLOS environment, a plurality of UWB signals are received for each ranging interval, and only n UWB signals among the plurality of UWB signals may be used for positioning of the user equipment 1820 .

[0431] refer to Fig.18a and 18b , when performing 3D positioning of the user equipment 1820, only four UWB signals with high p(LOS) among the multiple UWB signals may be used. For example, when performing 3D positioning of the user equipment 1820, the UWB signal received from the first UWB anchor point 1811, the UWB signal received from the second UWB anchor point 1812, the UWB signal received from the third UWB anchor point 1813, and the UWB signal received from the fifth UWB anchor point 1815 may be utilized. Since regarding the UWB signal received from the first UWB anchor point 1811, the UWB signal received from the second UWB anchor point 1812, the UWB signal received from the third UWB anchor point 1813, and the UWB signal received from the fifth UWB anchor point 1815, = 0.515, partially considered as if it is a LOS environment (p th =0.5), and when compared with the method of using all UWB signals, the 3D positioning accuracy of the user equipment 1820 can be improved.

[0432] refer to Fig.18a and 18b , when performing 2D positioning of the user equipment 1820, only three UWB signals with high p(LOS) among the multiple UWB signals may be used. For example, when performing 2D positioning of the user equipment 1820, the UWB signal received from the second UWB anchor point 1812, the UWB signal received from the third UWB anchor point 1813, and the UWB signal received from the fifth UWB anchor point 1815 may be utilized. Since regarding the UWB signal received from the second UWB anchor point 1812, the UWB signal received from the third UWB anchor point 1813, and the UWB signal received from the fifth UWB anchor point 1815, = 0.547, considered as LOS environment (p th =0.5), and when compared with the method of using all UWB signals, the 2D positioning accuracy of the user equipment 1820 can be improved.

[0433] According to an embodiment, regarding the first n signals with high p(LOS) among all UWB signals in a NLOS environment, <p th In this case, the process for locating the user equipment 1820 may be skipped. According to an embodiment, when the process for locating the user equipment 1820 is skipped, the process of calculating the position of the user equipment 1820 is abandoned, and thus the amount of power consumption may be reduced.

[0434] Fig.19 is a diagram illustrating a configuration of a user equipment capable of reducing power consumption based on LOS / NLOS classification according to an embodiment of the present disclosure.

[0435] refer to Fig.19 The user equipment may include at least one of a CIR collector module 1900 (CIRs of n anchor points), a LOS / NLOS classifier module 1910, an adaptive frequency ranging module 1920, an IMU sensor 1930, a ranging on / off module 1940, a UWB sleep module 1950, a message selection module 1960, a message skip module 1970 (skip message) and a positioning module 1980.

[0436] According to an embodiment, some of the above components may be omitted, or additional components may be further included. According to an embodiment, two or more of the above components may be combined into a single component. According to an embodiment, all or part of the above components may be embodied by a single processor (or controller).

[0437] The CIR collector module 1900 can collect information from the receiver via a UWB antenna (e.g., Figure 8 810) collects CIR data for at least one UWB signal received, and can generate effective CIR data from the collected CIR data. The effective CIR data can include an effective CIR value for each UWB signal.

[0438] The LOS / NLOS classifier module 1910 can classify whether the UWB signal is a LOS signal or a NLOS signal by using a LOS / NLOS classification method based on UWB CIR data (e.g., the above-mentioned LOS / NLOS classification method). The LOS / NLOS classification module 1910 can determine whether the DL-TDoA positioning environment is a LOS environment or a NLOS environment by using the UWB signal in the DL-TDoA positioning environment.

[0439] When the determination result of the LOS / NLOS classifier module 1910 shows that the DL-TDoA positioning environment is a LOS environment, the adaptive frequency ranging module 1920 may adjust the ranging frequency via adaptive ranging skipping and may reduce power associated with the user equipment.

[0440] According to an embodiment, the adaptive frequency ranging module 1920 may be based on the distance (d) between the user equipment and the door and the distance value (d) based on the door access area. area ) to change the ranging frequency. According to an embodiment, the adaptive frequency ranging module 1920 may calculate the adaptive ranging frequency using the above equation 2.

[0441] According to an embodiment, the adaptive frequency ranging module 1920 may be based on the distance (d) between the user equipment and the door, the distance value (d area ), the acceleration value measured by the IMU sensor (a m ) and the threshold value associated with acceleration (a th ) to change the ranging frequency. According to an embodiment, the adaptive frequency ranging module 1920 may calculate the adaptive ranging frequency using the above equation 5.

[0442] The IMU sensor 1930 may be an inertial measurement device and may be configured as at least one of an acceleration sensor, an angular velocity sensor (gyroscope), or a geomagnetic sensor (magnetometer). The IMU sensor 1930 may measure an acceleration value (a m) to identify whether the user device is moving.

[0443] The ranging on / off module 1940 may be based on the adaptive ranging frequency received from the adaptive frequency ranging module 1920 and the acceleration value (a) received from the IMU sensor 1930. m ) to turn on or off the ranging process. According to an embodiment, when the ranging on / off module 1940 turns on the ranging process, the positioning module 1980 can perform DL-TDoA positioning.

[0444] The UWB sleep module 1950 may switch the UWB module of the user equipment to a sleep mode in response to an on / off command of the ranging on / off module 1940 .

[0445] When the determination result of the LOS / NLOS classifier module 1910 shows that the DL-TDoA positioning environment is a NLOS environment, the message selection module 1960 may select n UWB signals from among the multiple UWB signals received from the UWB anchor point for positioning of the user equipment, so as to increase the accuracy of positioning of the user equipment. According to an embodiment, when performing 3D positioning of the user equipment, the message selection module 1960 may only utilize 4 UWB signals with high p (LOS) among the multiple UWB signals. According to an embodiment, when performing 2D positioning of the user equipment, the message selection module 1960 may only utilize 3 UWB signals with high p (LOS) among the multiple UWB signals.

[0446] The message selection module 1960 may select n UWB signals to be used for positioning of the user equipment from among the plurality of UWB signals, and may calculate the LOS probability based on an average value ( ) and threshold (p th ) to determine whether the DL-TDoA positioning environment for receiving n UWB signals is a LOS environment or a NLOS environment.

[0447] When the determination result of the message selection module 1960 shows that the DL-TDoA positioning environment in which n UWB signals are received is an NLOS environment, the message skip module 1970 may skip processing of the corresponding UWB signal in order to prevent positioning from being performed based on an inaccurate signal.

[0448] When the determination result of the message selection module 1960 shows that the DL-TDoA positioning environment in which n UWB signals are received is a LOS environment, the positioning module 1980 may perform DL-TDoA positioning.

[0449] Fig. 20 is a diagram illustrating a structure of an electronic device according to an embodiment of the present disclosure.

[0450] exist Fig. 20In the embodiment of the present invention, the electronic device may be a user's electronic device (user device) or a server.

[0451] refer to Fig. 20 , the electronic device may include a transceiver 2010, a controller 2020, and a memory 2030. In the present disclosure, the controller may be defined as a circuit or an application specific integrated circuit, or at least one processor.

[0452] The transceiver 2010 may perform signal transmission or reception with another UWB device. For example, the transceiver 2010 may receive a UWB signal from another UWB device.

[0453] The controller 2020 may control the overall operation of the electronic device according to the embodiment proposed in the present disclosure. For example, the controller 2020 may control the signal flow in blocks so as to perform operations according to the described flowchart. Specifically, for example, the controller 2020 may control the signal flow in blocks so as to perform operations according to the described flowchart. Figures 1 to 19 Describe the operation of an electronic device.

[0454] The controller 2020 may identify an average value of the line-of-sight (LOS) probabilities of multiple received UWB signals. The controller 2020 may compare the average value of the LOS probabilities of multiple received UWB signals with a first threshold, and may determine whether the DL-TDoA environment is a LOS environment based on the comparison result. When it is determined that the DL-TDoA environment is a LOS environment, the controller 2020 may adaptively adjust the ranging frequency used by the electronic device for ranging. Each of the multiple received UWB signals may include a UWB message for DL-TDoA positioning.

[0455] When the average value of the LOS probabilities of the plurality of received UWB signals is greater than the first threshold, the controller 2020 may determine that the DL-TDoA environment is a LOS environment. When the average value of the LOS probabilities of the plurality of received UWB signals is less than the first threshold, the controller 2020 may determine that the DL-TDoA environment is a NLOS (non-LOS) environment.

[0456] When the DL-TDoA environment is determined to be a NLOS environment, the controller 2020 may perform positioning with respect to the electronic device based on n UWB signals having a high LOS probability among the plurality of received UWB signals.

[0457] When the DL-TDoA environment is determined to be a LOS environment, the controller 2020 may adjust the ranging frequency based on a first value corresponding to the distance between the electronic device and the door and a second value based on the door access area. When the first value is greater than the second value, the controller 2020 may adjust the ranging frequency. When the first value is less than the second value, the controller 2020 may not adjust the ranging frequency.

[0458] When the DL-TDoA environment is determined to be a LOS environment, the controller 2020 may adjust the ranging frequency based on the distance between the electronic device and the door, the value based on the door access area, the acceleration value of the electronic device, and the second threshold of the acceleration value. When the acceleration value of the electronic device is greater than the second threshold, the controller 2020 may determine that the electronic device is moving.

[0459] The memory 2030 may store at least one of information transmitted or received via the transceiver 2010 and information generated via the controller 2020. For example, the memory 2030 may store information related to the reference Figures 1 to 19 UWB signal related information and data.

[0460] In the above detailed embodiments of the present disclosure, the elements included in the present disclosure are expressed in the singular or plural, depending on the detailed embodiments presented. However, for ease of description, the singular form or plural form is appropriately selected for the presented situation, and the present disclosure is not limited to the elements expressed in the singular or plural. Therefore, an element expressed in the plural may also include a single element, or an element expressed in the singular may also include multiple elements.

[0461] Although specific embodiments have been described in the detailed description of the present disclosure, it is apparent that various modifications and changes may be made thereto without departing from the scope of the present disclosure. Therefore, the scope of the present disclosure should not be limited to the embodiments set forth herein, but should be limited by the appended claims and their equivalents.

Claims

1. A method of an electronic device, comprising: obtaining first prediction data for classifying whether a signal corresponding to a UWB CIR is a line-of-sight (LOS) signal or a non-LOS (NLOS) signal based on UWB channel impulse response (UWBCIR) data by using a trained first convolutional neural network (CNN) model; In a case where the signal is classified as a LOS signal, obtaining second prediction data for classifying a gesture based on the sensor data corresponding to the UWB CIR data by using the trained second CNN model; In the case where the signal is classified as an NLOS signal, obtaining third prediction data for classifying a gesture based on the sensor data corresponding to the UWB CIR data by using the trained third CNN model; performing filtering of at least two of the first prediction data, the second prediction data, and the third prediction data by using a first filtering scheme; as well as Classify the posture based on the filtered data, Wherein, the second CNN model is trained using sensor data associated with LOS signals, and the third CNN model is trained using sensor data associated with NLOS signals.

2. The method according to claim 1, wherein: Classification of postures includes: In a case where the signal is classified as the LOS signal, one of the at least one gesture associated with the LOS signal is classified as the gesture based on the filtered first prediction data and the filtered second prediction data.

3. The method according to claim 2, wherein: Classification of postures includes: In case the signal is classified as a NLOS signal, one of the at least one gesture associated with the NLOS signal is classified as the gesture based on the filtered first prediction data and the filtered third prediction data.

4. The method according to claim 3, wherein: The first filtering scheme is a moving average filtering scheme.

5. The method according to claim 1, wherein: Sensor data is obtained from Inertial Measurement Unit (IMU) sensors.

6. The method according to claim 1, wherein: The UWB CIR data includes effective CIR data obtained by removing noise from CIR data obtained based on a UWB signal for downlink time difference of arrival (DL-TDoA) ranging, or includes effective CIR data obtained by removing noise from CIR data obtained based on a UWB signal for dual two-way ranging (DS-TWR) ranging.

7. An electronic device comprising: Transceiver; as well as A controller, connected to the transceiver, Wherein, the controller is configured as: obtaining first prediction data for classifying whether a signal corresponding to a UWB channel impulse response (CIR) is a line-of-sight (LOS) signal or a non-LOS (NLOS) signal based on UWB channel impulse response (CIR) data by using a trained first convolutional neural network (CNN) model; In a case where the signal is classified as a LOS signal, obtaining second prediction data for classifying a gesture based on the sensor data corresponding to the UWB CIR data by using the trained second CNN model; In the case where the signal is classified as an NLOS signal, obtaining third prediction data for classifying a gesture based on the sensor data corresponding to the UWB CIR data by using the trained third CNN model; performing filtering of at least two of the first prediction data, the second prediction data, and the third prediction data by using a first filtering scheme; and Classify the posture based on the filtered data, Wherein, the second CNN model is trained using sensor data associated with LOS signals, and the third CNN model is trained using sensor data associated with NLOS signals.

8. The electronic device according to claim 7, wherein: The controller is further configured to classify one of at least one gesture associated with the LOS signal as the gesture based on the filtered first prediction data and the filtered second prediction data if the signal is classified as the LOS signal.

9. The electronic device according to claim 8, wherein: The controller is further configured to classify, if the signal is classified as the NLOS signal, one of the at least one gesture associated with the NLOS signal as the gesture based on the filtered first prediction data and the filtered third prediction data.

10. The electronic device according to claim 9, wherein: The first filtering scheme is a moving average filtering scheme.

11. The electronic device according to claim 7, wherein: The sensor data is sensor data obtained from an inertial measurement unit (IMU) sensor.

12. The electronic device according to claim 7, wherein: The UWB CIR data includes effective CIR data obtained by removing noise from CIR data obtained based on a UWB signal for downlink time difference of arrival (DL-TDoA) ranging, or effective CIR data obtained by removing noise from CIR data obtained based on a UWB signal for dual two-way ranging (DS-TWR) ranging.

Images