Position estimation device, position estimation method, and position estimation program

Abstract

This position estimation device 1 comprises: a wireless communication control unit 1-0 that determines a transmission command related to initiating transmission or the transmission frequency or transmission schedule of a wireless signal used for position estimation and that transmits the transmission command of the wireless signal to a wireless communication unit of a fixed terminal installed in the same environment as the position estimation device or to a wireless communication unit of a position estimation target; wireless communication units 1-1 to 1-R that receive the wireless signal transmitted from the wireless communication unit of the fixed terminal or the wireless communication unit of the position estimation target on the basis of the transmission command, and that acquire, from the wireless signal, channel information related to radio wave propagation; an input feature amount generation unit 1-2 that converts the channel information into an input feature amount that can be input to a position estimation model; and a position estimation model usage unit 1-3 that estimates and calculates the position of the position estimation target by inputting the input feature amount to the position estimation model that models, by machine learning, the relationship between the channel information related to the radio wave propagation and position information of the position estimation target.

Description

[Technical field]

[0001] The present invention relates to a position estimation device, a position estimation method, and a position estimation program. [Background technology]

[0002] The realization of the Internet of Things (IOT), in which various devices are connected to the Internet, is progressing. Various devices, such as automobiles, drones, and construction machinery vehicles, are becoming wirelessly connected. Regarding wireless communication standards, the wireless LAN (Local Area Network) defined by the standard IEEE 802.11, Bluetooth (registered trademark), cellular communication using LTE and 5G, LPWA (Low Power Wide Area) communication for IOT, ETC (Electronic Toll Collection System) used for vehicle communication, VICS (Vehicle Information and Communication System), ARIB-STD-T109, etc., are also developing and are expected to become more widespread in the future.

[0003] In order to ensure high throughput and reliability, wireless communication devices have introduced MIMO (Multiple input multiple output) communication technology using multiple antennas. MIMO communication technology can improve throughput and reliability by utilizing channel information that indicates how radio waves are propagating between the transmitting side and the receiving side. For example, a transmitting wireless communication device supports a transmission function of a feedback signal that conveys channel information to a receiving wireless communication device (see Non-Patent Document 1).

[0004] There is also known a technique that uses channel information related to radio wave propagation to estimate the position of a wireless communication device (see Non-Patent Documents 2 and 3). For example, the position of a wireless communication device is identified based on the arrival time and level of a wireless signal wirelessly communicated with multiple base stations. [Prior art documents] [Non-patent literature]

[0005] [Non-Patent Document 1] “Part 11: Wireless LAN Medium Access Control (MAC) and Physical Layer (PHY) Specifications”, IEEE Computer Society, IEEE Std 802.11, 2016, p.2396-p.2400 [Non-Patent Document 2] Y. Tao, et al., “A Novel System for WiFi Radio Map Automatic Adaptation and Indoor Positioning”, in IEEE Transactions on Vehicular Technology, vol. 67, no. 11, November 2018, p.10683-p.10692 [Non-Patent Document 3] H. CAO, and 5 others, “Indoor Positioning Method Using WiFi RTT Based on LOS Identification and Range Calibration”, in Proc., ISPRS International Journal of Geo-Information, September 2020 Summary of the Invention [Problem to be solved by the invention]

[0006] However, conventional position estimation technologies have the drawback of requiring wireless communication devices to simultaneously communicate with multiple base stations and have high time resolution capabilities, resulting in high costs for estimating the position of an object.

[0007] The present invention has been made in consideration of the above circumstances, and an object of the present invention is to provide a technique capable of estimating the position of an object at low cost. [Means for solving the problem]

[0008] A position estimation device of one embodiment of the present invention includes a wireless communication control unit that determines a transmission command regarding the start of transmission, transmission frequency, or transmission schedule of a wireless signal used for position estimation, and transmits the transmission command for the wireless signal to a wireless communication unit of a fixed terminal installed in the same environment as the device itself or to a wireless communication unit of a target for position estimation; a wireless communication unit that receives a wireless signal transmitted from the wireless communication unit of the fixed terminal or the wireless communication unit of the target for position estimation based on the transmission command, and acquires channel information regarding radio wave propagation from the wireless signal; an input feature generation unit that converts the channel information into input features that can be input to a position estimation model; and a position estimation model utilization unit that estimates and calculates the position of the target for position estimation by inputting the input features into a position estimation model that models the relationship between the channel information regarding radio wave propagation and the position information of the target for position estimation using machine learning.

[0009] A position estimation method of one embodiment of the present invention is a position estimation method performed by a position estimation device, and includes the steps of determining a transmission command regarding the start of transmission, transmission frequency, or transmission schedule of a wireless signal used for position estimation, and transmitting the transmission command for the wireless signal to a wireless communication unit of a fixed terminal installed in the same environment as the device itself or to a wireless communication unit of a target for position estimation, receiving a wireless signal transmitted from the wireless communication unit of the fixed terminal or the wireless communication unit of the target for position estimation based on the transmission command, and acquiring channel information regarding radio wave propagation from the wireless signal, converting the channel information into input features that can be input into a position estimation model, and inputting the input features into a position estimation model that models the relationship between the channel information regarding radio wave propagation and the position information of the target for position estimation using machine learning, thereby estimating and calculating the position of the target for position estimation.

[0010] A position estimation program according to one embodiment of the present invention causes a computer to function as the position estimation device. Effect of the Invention

[0011] According to the present invention, it is possible to provide a technique capable of estimating the position of an object at low cost. [Brief description of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram showing the overall configuration of a wireless communication system according to this embodiment. [Diagram 2] FIG. 2 is a diagram showing basic operations (prerequisite operations) of a wireless communication system. [Diagram 3] FIG. 3 is a diagram illustrating an operation (first example) of the wireless communication system. [Figure 4] FIG. 4 is a diagram illustrating an operation (second example) of the wireless communication system. [Diagram 5] FIG. 5 is a diagram illustrating an operation (third example) of the wireless communication system. [Figure 6] FIG. 6 is a diagram illustrating an operation (fourth example) of the wireless communication system. [Figure 7] FIG. 7 is a diagram illustrating an operation (fifth example) of the wireless communication system. [Figure 8] FIG. 8 is a diagram showing the experimental environment area. [Figure 9] FIG. 9 is a diagram showing an example of division of the experiment environment area. [Figure 10] FIG. 10 is a diagram showing the measurement results of the position estimation error. [Figure 11] FIG. 11 is a diagram showing the best combination of terminals for each area. [Figure 12] FIG. 12 is a diagram illustrating a hardware configuration of the position estimation device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In the description of the drawings, the same parts are given the same reference numerals and the description will be omitted.

[0014] [Summary of the invention] The present invention estimates the position of a specific object by using commonly used general-purpose wireless communication information, that is, by using channel information between a fixed terminal installed at a fixed location and a position estimation device, or by using channel information between a specific object located in the same environment as the fixed terminal and a position estimation device. Specifically, a transmission command regarding the start of transmission of a wireless signal used for position estimation, etc. is transmitted to a wireless communication unit of the fixed terminal or a wireless communication unit of the specific object, and an input feature amount of the channel information included in the wireless signal transmitted based on the transmission command is input to a position estimation model, thereby estimating the position of the specific object in the real world.

[0015] In this way, the present invention estimates the position of a specific object using channel information, making it possible to estimate the position of a specific object using general-purpose wireless communication, and providing a technology that can estimate the position of a specific object at low cost.

[0016] In addition, since the present invention transmits a transmission command regarding the start of transmission of a radio signal used for position estimation, etc., it becomes possible to transmit a radio signal according to the communication quality, etc. of the wireless communication system, thereby improving the reliability of estimating the position estimation target and improving the estimation accuracy of the position estimation target, and making it possible to reduce the operating costs required for estimating the position of a specific object.

[0017] The channel information is information indicating how radio waves are propagating between a transmitting wireless communication terminal and a receiving wireless communication terminal. In MIMO communication technology, the channel information is information indicating the state of radio wave propagation between multiple antennas provided in the transmitting wireless communication terminal and multiple antennas provided in the receiving wireless communication terminal. For example, the channel information is information obtained from propagation loss, or information obtained from propagation loss and phase rotation information of radio waves.

[0018] The input feature amount is a feature amount of channel information that has been converted so that the channel information can be input to the position estimation model. For example, the input feature amount is the unconverted channel information itself, or a numerical value obtained by performing various calculations on the channel information.

[0019] A specific object is a movable object whose position is estimated and is located in the same environment as the wireless communication terminal. The position of a specific object is, for example, a position on a path along which the specific object is moving, a position in a two-dimensional space (such as a map), or a position in a three-dimensional space. In addition to this position information, more detailed physical states such as orientation and speed may be estimated.

[0020] [Overall configuration of wireless communication system] FIG. 1 is a diagram showing the overall configuration of a wireless communication system according to this embodiment.

[0021] The wireless communication system includes a position estimation device 1, and fixed terminals 3-1 to 3-M, or position estimation targets 2-1 to 2-Q, or both the fixed terminals 3-1 to 3-M and the position estimation targets 2-1 to 2-Q.

[0022] The position estimation device 1 estimates the position of a specific object located in the same environment as the fixed terminals 3-1 to 3-M, that is, the position of at least one of the position estimation targets 2-1 to 2-Q (M is an integer equal to or greater than 1), by collecting channel information of a wireless signal transmitted from at least one of the fixed terminals 3-1 to 3-M. The position estimation device 1 also estimates the position of at least one of the position estimation targets 2-1 to 2-Q (Q is an integer equal to or greater than 1), by collecting channel information of a wireless signal transmitted from at least one of the position estimation targets 2-1 to 2-Q. The position estimation device 1 can estimate the position of the position estimation target using the channel information of the fixed terminal, can estimate the position of the position estimation target using the channel information of the position estimation target, and can estimate the position of the position estimation target using the channel information of the fixed terminal and the channel information of the position estimation target.

[0023] The fixed terminals 3-1 to 3-M include wireless communication units 3-1-1 to 3-M-1. One fixed terminal may include one or more wireless communication units. The position estimation targets 2-1 to 2-Q may include wireless communication units 2-1-1 to 2-Q-1. One position estimation target may include one or more wireless communication units. The wireless communication units 3-1-1 to 3-M-1, or the wireless communication units 2-1-1 to 2-Q-1, or both of them transmit a pilot signal that is known in transmission and reception, or a wireless signal including channel information between an arbitrary wireless communication unit. The arbitrary wireless communication unit is the wireless communication units 1-1 to 1-R included in the position estimation device 1, or another wireless communication unit.

[0024] The position estimation device 1 receives a wireless signal from a fixed terminal 3-i (1≦i≦M) via the wireless communication units 1-1 to 1-R, or receives a wireless signal from a position estimation target 2-j (1≦j≦Q) via the wireless communication units 1-1 to 1-R.

[0025] Then, the position estimation device 1 acquires, from the received wireless signals, channel information between any wireless communication unit 3-i-1 of the multiple fixed terminals 3-1 to 3-M and any of its own wireless communication units 1-1 to 1-R, or acquires, from the received wireless signals, channel information between any wireless communication unit 2-j-1 of the multiple position estimation targets 2-1 to 2-Q and any of its own wireless communication units 1-1 to 1-R.

[0026] Then, the position estimation device 1 inputs the acquired channel information to the input feature generation unit 1-2. The input feature generation unit 1-2 converts the channel information into input features suitable for input to a position estimation model, and inputs the converted input features to the position estimation model utilization unit 1-3.

[0027] Thereafter, the location estimation model utilization unit 1-3 estimates the location of the location estimation target 2-j by inputting the input features of the channel information collected from at least one fixed terminal 3-i among the fixed terminals 3-1 to 3-M into a location estimation model that models the relationship between the location information of the location estimation target and the input features of the channel information using machine learning.

[0028] Alternatively, the position estimation model utilization unit 1-3 estimates the position of the position estimation target 2-j by inputting input features of channel information collected from at least one of the position estimation targets 2-1 to 2-Q, into the position estimation model.

[0029] Alternatively, the location estimation model utilization unit 1-3 estimates the location of the location estimation target 2-j by inputting input features of channel information collected from multiple terminals (fixed terminals, location estimation targets) among the fixed terminals 3-1 to 3-M and the location estimation targets 2-1 to 2-Q into the location estimation model.

[0030] [Fixed terminal configuration] The fixed terminal 3-i is a wireless communication terminal equipped with a wireless communication unit 3-i-1 and installed in a predetermined environment. The fixed terminal 3-i is preferably fixed to, for example, a wall, a floor, a ceiling, or the like so as not to move. The fixed terminal 3-i may be realized using a special dedicated device, or may be realized using any terminal having a built-in wireless communication unit, such as a smartphone or a PC. One fixed terminal 3-i may be equipped with multiple wireless communication units 3-i-1. There may be multiple fixed terminals 3-i.

[0031] [Configuration of location estimation target equipped with wireless communication unit] The position estimation target 2-j is a mobile wireless communication terminal equipped with a wireless communication unit 2-j-1, and is a position estimation target. For example, the position estimation target 2-j is an autonomous mobile robot. The position estimation device 1 estimates the position of the position estimation target 2-j using only channel information of the fixed terminal 3-j, and may not be equipped with the wireless communication unit 2-j-1. One position estimation target 2-j may be equipped with multiple wireless communication units 2-j-1. There may be multiple position estimation targets 2-j.

[0032] [Configuration of location estimation device] The position estimation device 1 is, for example, a base station of a wireless communication system installed at a major location. The position estimation device 1 may have any configuration including a wireless communication unit capable of communicating with a fixed terminal 3-i and a position estimation target 2-j. It is preferable that the antenna units of the wireless communication units 1-1 to 1-R of the position estimation device 1 are fixed in order to improve the accuracy of position estimation.

[0033] As shown in FIG. 1, the position estimation device 1 includes, for example, a wireless communication control unit 1-0, wireless communication units 1-1 to 1-R, an input feature generation unit 1-2, a position estimation model utilization unit 1-3, a position estimation model training unit 1-4, and a position estimation target information generation unit 1-5.

[0034] The wireless communication control unit 1-0 has a function of determining a transmission command regarding the transmission of a wireless signal to be used for position estimation, and transmitting the determined wireless signal transmission command via the wireless communication units 1-1 to 1-R to the wireless communication unit 3-j-1 of a fixed terminal 3-i installed in the same environment as the wireless communication unit 1-0 itself and the wireless communication unit 2-j-1 of a position estimation target 2-j.

[0035] The wireless communication units 1-1 to 1-R are communication units that perform wireless communication or transmit and receive wireless signals. At least one of the wireless communication units 1-1 to 1-R can cause the wireless communication unit 3-j-1 of the fixed terminal 3-i or the wireless communication unit 2-j-1 of the location estimation target 2-j to transmit a wireless signal for acquiring channel information. The wireless communication units 1-1 to 1-R may be compatible with multiple frequencies, multiple frequency bands, or multiple wireless communication systems.

[0036] The wireless communication units 1-1 to 1-R each have a function of transmitting a wireless signal including the transmission command to the wireless communication unit 3-j-1 of the fixed terminal 3-i or the wireless communication unit 2-j-1 of the position estimation target 2-j, receiving a wireless signal transmitted from the wireless communication unit 3-j-1 of the fixed terminal 3-i or the wireless communication unit 2-j-1 of the position estimation target 2-j based on the transmission command, and acquiring channel information related to radio wave propagation from the received wireless signal. When the wireless communication units 1-1 to 1-R acquire channel information corresponding to the fixed terminal 3-i or the position estimation target 2-j, they input the acquired channel information to the input feature generator 1-2.

[0037] The input feature generator 1-2 has a function of converting input channel information into input feature values ​​that can be input to a position estimation model. The input feature generator 1-2 inputs the converted input feature value of the channel information to the position estimation model utilization unit 1-3.

[0038] The position estimation model utilization unit 1-3 has a function of estimating and calculating the position of at least one position estimation target 2-j among the moving or stopped position estimation targets 2-1 to 2-Q by inputting the input feature amount to the position estimation model, and outputting the estimated and calculated position information. The position estimation model utilization unit 1-3 may use a position estimation model generated in advance, or may use a position estimation model generated and updated by the position estimation model training unit 1-4.

[0039] The location estimation model is a real-world communication model generated by training the relationship between separately measured location information of the location estimation target 2-j and channel information (≒ input feature amount) related to radio wave propagation acquired from the fixed terminal 3-i and the location estimation target 2-j by machine learning. Alternatively, the location estimation model may be generated by generating a space equivalent to the real space in a simulation space by digital twin technology or the like, and using the relationship between the virtually generated location estimation target and the channel information calculated by simulation. The location estimation model may be generated from the relationship between the channel information measured by another location estimation unit and the location estimation target.

[0040] The location estimation model training unit 1-4 has a function of separately acquiring data on location information of the location estimation target 2-j, and training an estimated location estimation model capable of estimating the location of the location estimation target 2-j based on the relationship between the acquired location information and channel information, thereby generating a location estimation model. The location estimation model training unit 1-4 also has a function of updating the generated location estimation model. As an updating method, for example, fine tuning or transfer learning known in deep learning can be used.

[0041] The location information of the location estimation target 2-j may be acquired by periodically collecting location measurement data by a location measurement function mounted on the location estimation target 2-j by some means. In addition, by using a predetermined machine learning model, it is possible to estimate and learn the relationship between the location information of the location estimation target 2-j and channel information obtained from the fixed terminal 3-i. The some means may be a sensor, a camera, radio positioning, SLAM (Simultaneous Localization And Mapping), GPS (Global Positioning System), etc. mounted on the location estimation target 2-j. The location estimation device 1 stores the location and time information of the location estimation target 2-j obtained by radio positioning of the location estimation target 2-j in a storage unit, and periodically inputs the location and time information collectively to the location estimation model training unit 1-4, thereby making it possible to use the information as teacher data for training the location estimation model.

[0042] The position estimation model training unit 1-4 can train the position estimation model by learning the relationship between the input position and time information of the position estimation target 2-j and the channel information and time information also stored in the storage unit by comparing them on the same time axis. Alternatively, the position estimation model training unit 1-4 may acquire the position information of the position estimation target 2-j from information of a camera, a sensor, etc. mounted on the position estimation device 1, and train the position estimation model by learning the relationship with the channel information at the same time and the same time zone.

[0043] The location estimation target information generating unit 1-5 acquires, for example, a location estimation target ID, a wireless communication ID, etc., in wireless communication of the location estimation target 2-j. In addition, the location estimation target information generating unit 1-5 may generate, as unique information for improving the detection performance of the location estimation target 2-j, for example, owner information, the form of a person, a car, a drone, etc., and a category ID classified by communication unit information such as the antenna configuration, antenna height, number of antennas, antenna shape, terminal type, communication mode, power consumption mode, and application used of the wireless communication unit 2-j-1. The information acquired / generated by the location estimation target information generating unit 1-5 is input to the location estimation model of the location estimation model utilizing unit 1-3, or input to the location estimation model training unit 1-4.

[0044] [Basic operation of wireless communication system (prerequisite operation)] FIG. 2 is a diagram showing basic operations (prerequisite operations) of a wireless communication system.

[0045] First, the wireless communication unit 3-i-1 of the fixed terminal 3-i, the wireless communication unit 2-j-1 of the location estimation target 2-j, or both of them perform wireless communication with a predetermined wireless communication device (assumed to be the wireless communication unit 1-1 of the location estimation device 1) and start transmitting a wireless signal including a pilot signal or channel information (step S1-1).

[0046] Next, the wireless communication unit 1-k of the position estimation device 1 receives wireless signals transmitted from the wireless communication unit 3-i-1 of the fixed terminal 3-i and the wireless communication unit 2-j-1 of the position estimation target 2-j, and acquires channel information related to radio wave propagation from the received wireless signals (step S1-2).

[0047] Next, the input feature generator 1-2 converts the acquired channel information on radio wave propagation into input feature suitable for input to the position estimation model (step S1-3). The input feature is, for example, at least a part of the channel information that is not converted, or a numerical value obtained by performing various calculations on the channel information. For example, the method generates values ​​of the phase, amplitude, real component, and imaginary component of one or more feature quantities related to the received power of a wireless signal, the signal power, power ratio information obtained from the moving average of the received power and the signal power, a channel matrix consisting of radio wave propagation coefficients between multiple antennas, a correlation matrix of the channel matrix, an operational matrix obtained by signal processing the channel matrix, an operational matrix obtained by signal processing the correlation matrix, an operational matrix obtained by signal processing a channel matrix or a correlation matrix corresponding to multiple frequencies, a unitary matrix obtained by linearly operating the channel matrix, a unitary matrix obtained by linearly operating the correlation matrix, a unitary matrix obtained by linearly operating the operational matrix, a diagonal matrix obtained by linearly operating the channel matrix, a diagonal matrix obtained by linearly operating the correlation matrix, a diagonal matrix obtained by linearly operating the operational matrix, a triangular matrix obtained by linearly operating the channel matrix, a triangular matrix obtained by linearly operating the correlation matrix, and a triangular matrix obtained by linearly operating the operational matrix, and generates values ​​obtained by standardizing the range of the coefficients of the one or more values. The input feature generating unit 1-2 may store the input feature as time-series data and output the input feature for a plurality of times from the past to the present to the position estimation model. At least one of the time-series information may be used. A specific method for calculating the input feature will be described later.

[0048] Furthermore, the position estimation device 1 may generate auxiliary information other than the channel information to be input to the position estimation model, and add the generated auxiliary information to the input feature (step S1-4). The auxiliary information is, for example, the position estimation target 2-j or specific information for identifying the position estimation target 2-j, temperature and position information of a camera, a sensor, etc., status information such as the position, speed, and settings of the estimation target device and its surrounding reflective structures, time, temperature, humidity, congestion status, and setting information of the wireless communication system.

[0049] Finally, the location estimation model utilization unit 1-3 inputs the input feature amount of the converted channel information to the location estimation model, thereby estimating and calculating the location information of the location estimation target 2-j and outputting it (step S1-5).

[0050] [How to collect channel information and how to calculate input features] An example of a method for collecting channel information and a method for calculating input feature quantities will be described below.

[0051] [How to collect channel information and how to calculate input features (first example)] In the first method, the fixed terminal 3-i or the location estimation target 2-j transmits a pilot signal that is known in transmission and reception. By transmitting a known pattern in advance, the wireless communication unit 1-r (1≦r≦R) of the location estimation device 1 can obtain a channel matrix between the antenna (number of receiving antennas: Mr) of its own wireless communication unit 1-r and the antenna (number of transmitting antennas: Ni) of the wireless communication unit 3-i-1 or wireless communication unit 2-j-1 that transmitted the pilot signal. If OFDM (orthogonal frequency division multiplexing) is used in various wireless communication systems, it is possible to obtain a channel matrix of subcarriers corresponding to multiple frequencies.

[0052] From the channel matrix H of the "number of transmitting antennas Ni × number of receiving antennas Mr" obtained in this way, an input feature to be input to the position estimation model utilization unit 1-3 is generated. For example, when obtaining a channel matrix for multiple subcarriers by OFDM, the channel matrix of the η-th subcarrier is H η The method of converting the input feature is as follows: First, the channel matrix H η The normalized channel matrix G η and the amplitude information γ η Or power information γ η 2 and, it is separated into.

[0053]

number

[0054] G η For example, ||G η || F = 1. F represents the Frobenium norm. γ η Generally, γ has a large fluctuation range and can change by 10 to the power of 5 or more. η or γ η 2 It is also possible to convert the value into dB, define the maximum and minimum values, and convert the value to be expressed as a normalized value within the range of 0 to 1. The value γ all may also be used.

[0055] In addition, as shown in equation (2), the amplitude information γ η Separate for each antenna, and normalize the norm value to a certain value to obtain each column vector g 1,η ~g Mr,η and its amplitude value γ 1,η ~γ Mr,η and may be obtained.

[0056]

number

[0057] g a,η For example, ||g a,η || F = 1. a,η or γ a,η 2 It is also possible to convert the value into dB, define the maximum and minimum values, and convert the value into a normalized value within the range of 0 to 1. The value γ corresponding to the a-th column vector obtained by selecting or averaging multiple values ​​for η is a,all may also be used.

[0058] In addition, as shown in equation (3), the amplitude information γ η Separate for each antenna, and normalize the norm value to a certain value to obtain each row vector g'1,η ~g' Ni,η and its amplitude value γ' 1,η ~γ' Ni,η and may be obtained.

[0059]

number

[0060] g' b,η For example, ||g' b,η || F = 1. b,η and γ' b,η 2 It is also possible to convert the value into dB, define the maximum and minimum values, and convert the value to be expressed as a normalized value within the range of 0 to 1. The value γ' corresponding to the b-th column vector obtained by selecting or averaging multiple values ​​for η is b,all may also be used.

[0061] Channel matrix H η , the normalized channel matrix G η , normalized vector g a,η , normalized vector g' b,η The real and imaginary parts of each element can be used as input features, or the imaginary numbers can be used as input information as is, or the imaginary numbers can be converted into another format such as angle information, or quantized.

[0062] Also, the channel matrix H η The correlation matrix H is generated using η H η H , H η H H η The normalized channel matrix G η The correlation matrix G is generated using η G η H , G η H G η The channel matrix H η , the normalized channel matrix G η, and their correlation matrix H η H η H , H η H H η , G η G η H , G η H G η The matrix ΣH is the sum or average of multiple frequencies. η , ΣG η , ΣH η H η H , ΣH η H H η , ΣG η G η H , ΣG η H G η Eigenvalues, diagonal matrices, and unitary matrices obtained by performing QR decomposition, SVD (Singular value decomposition), eigenvector decomposition, etc. of these matrices can be used.

[0063] In addition, the above matrix ΣH η , ΣG η , ΣH η H η H , ΣH η H H η , ΣG η G η H , ΣG η H G η Using the above, the power characteristics for the direction of arrival for the communication device, obtained by the direction of arrival estimation technology, may be used as the input feature. For example, a value obtained by multiplying each of the vector components by (1,exp(jdθ),exp(j2dθ),...,exp(jNdθ)) can be calculated for θ. It is also possible to generate θ at any angle interval from 0 to 2π, and use the output for multiple θ as the input feature. d is a predetermined constant. N is the number of elements of the vector.

[0064] In other words, the input feature generation unit 1-2 generates, as input features, values ​​of the phase, amplitude, real component, imaginary component of one or more of the features related to the received power of a wireless signal, signal power, power ratio information obtained from a moving average of the received power and signal power, a channel matrix consisting of radio wave propagation coefficients between multiple antennas, a correlation matrix of the channel matrix, an operational matrix obtained by signal processing the channel matrix, an operational matrix obtained by signal processing the correlation matrix, an operational matrix obtained by signal processing a channel matrix or a correlation matrix corresponding to multiple frequencies, a unitary matrix obtained by linearly operating the channel matrix, a unitary matrix obtained by linearly operating the correlation matrix, a unitary matrix obtained by linearly operating the operational matrix, a diagonal matrix obtained by linearly operating the channel matrix, a diagonal matrix obtained by linearly operating the correlation matrix, a diagonal matrix obtained by linearly operating the operational matrix, a triangular matrix obtained by linearly operating the channel matrix, a triangular matrix obtained by linearly operating the correlation matrix, and a triangular matrix obtained by linearly operating the operational matrix, and generates values ​​obtained by standardizing the range of the coefficients of the one or more values. The input feature generation unit 1-2 may store the input feature as time-series data and output the input feature for multiple times from the past to the present (the one or more values ​​above, values ​​obtained by normalizing the range of the coefficients of the one or more values) to the position estimation model.

[0065] In a wireless communication system using equalization technology, it is possible to estimate the arrival time, power, and phase condition of the path of the arriving electrical signal. Even channel information obtained in this way in a time series can be used as input features for a position estimation model by normalizing the power, converting it to frequency components, and using features and angle information extracted by existing direction-of-arrival technology.

[0066] [How to collect channel information and how to calculate input features (second example)] In the second method, the fixed terminal 3-i or the location estimation target 2-j communicates with a specific wireless base station, estimates channel information from a pilot signal transmitted from and received by the specific wireless base station, generates feedback information by quantizing the signal in some way, and transmits a wireless signal including the generated feedback information. The wireless communication unit 1-r of the location estimation device 1 receives the wireless signal and obtains channel information between the specific wireless base station and the fixed terminal 3-i or the location estimation target 2-j, which is included in the received wireless signal.

[0067] First, a pilot signal that is known in transmission and reception is transmitted from a specific known wireless base station. By transmitting a known pattern in advance, the wireless communication unit 3-i-1 of the fixed terminal 3-i or the wireless communication unit 2-j-1 of the location estimation target 2-j can obtain a channel matrix between its own receiving antenna (number of receiving antennas: Ni) and the antenna (number of transmitting antennas: Mt) of the specific wireless base station that transmitted the pilot signal. In the case of OFDM, which is used in various wireless communication systems, it is possible to obtain a channel matrix of subcarriers corresponding to multiple frequencies.

[0068] The channel matrix H for the number of transmitting antennas Mt × the number of receiving antennas Ni obtained in this way is α For example, when a channel matrix is ​​obtained for a plurality of subcarriers by OFDM, the channel matrix of the η-th subcarrier is expressed as H α,η Here, when the specific wireless base station is the wireless communication unit 1-r of the position estimation device 1, the number of transmitting antennas Mt is equal to the number of receiving antennas Mr defined for the wireless communication unit 1-r in the first method. In this case, the channel matrix H α,η is the channel matrix H η corresponds to the transpose of

[0069] Therefore, as a method for converting the input features, the channel matrix H α,η The normalized channel matrix G α,η and the amplitude information γα,η Or power information γ η 2 and, it is separated into.

[0070]

number

[0071] G α,η For example, ||G α,η || F = 1. F represents the Frobenium norm. γ α,η or γ α,η 2 It is also possible to convert the value into dB, define the maximum and minimum values, and convert the range to be expressed as a normalized value within the range of 0 to 1. A value γ α,all may be used. α,all When averaging, the true values ​​may be averaged, or the true values ​​may be converted to dB and then averaged, or the true values ​​may be averaged and then converted to dB units.

[0072] In addition, as shown in equation (5), the amplitude information γ α,η Separate for each antenna, and normalize the norm value to a certain value to obtain each column vector g α,1,η ~g α,Ni,η and its amplitude value γ α,1,η ~γ α,Ni,η and may be obtained.

[0073]

number

[0074] g α,a,η For example, ||g α,a,η || F = 1. α,a,η or γ α,a,η 2It is also possible to convert the value into dB, define the maximum and minimum values, and convert the value into a normalized value within the range of 0 to 1. The value γ corresponding to the a-th column vector obtained by selecting or averaging multiple values ​​for η is α,a,all may also be used.

[0075] In addition, as shown in equation (6), the amplitude information γ α,η Separate for each antenna, and normalize the norm value to a certain value to obtain each row vector g' α,1,η ~g' α,Mt,η and its amplitude value γ' α,1,η ~γ' α,Mt,η and may be obtained.

[0076]

number

[0077] g' α,b,η For example, ||g' α,b,η || F = 1. α,b,η and γ' α,b,η 2 It is also possible to convert the value into dB, define the maximum and minimum values, and convert the value to be expressed as a normalized value within the range of 0 to 1. The value γ' corresponding to the b-th column vector obtained by selecting or averaging multiple values ​​for η is α,b,all may also be used.

[0078] Channel matrix H α,η , the normalized channel matrix G α,η , normalized vector g α,a,η , normalized vector g' α,b,η The real and imaginary parts of each element can be used as input features, or the imaginary numbers can be used as input information as is, or the imaginary numbers can be converted into another format such as angle information, or quantized.

[0079] Also, the channel matrix H α,η The correlation matrix H is generated using α,η H α,η H , Hα,η H H α,η The normalized channel matrix G α,η The correlation matrix G is generated using α,η G α,η H , G α,η H G α,η The channel matrix H α,η , the normalized channel matrix G α,η , and their correlation matrix H α,η H α,η H , H α,η H H α,η , G α,η G α,η H , G α,η H G α,η The matrix ΣH is the sum or average of multiple frequencies. α,η , ΣG α,η , ΣH α,η H α,η H , ΣH α,η H H α,η , ΣG α,η G α,η H , ΣG α,η H G α,η Eigenvalues, diagonal matrices, and unitary matrices obtained by performing QR decomposition, SVD, eigenvector decomposition, etc. of these matrices can be used.

[0080] As an example, we will show a case where the channel information feedback used in the wireless LAN standard IEEE 802.11n / ac / ax is used. This is the case where the channel matrix H α,ηThe right singular matrix obtained by SVD in is compressed into angle information, quantized, and generated corresponding to multiple frequencies, and fed back. The unitary matrix is ​​converted into angles φ and ψ as a compressed beamforming feedback matrix, and is fed back together with SNR information. Details are described in non-patent literature, but by performing matrix calculations using angle information as in equation (7), a V matrix corresponding to the right singular matrix of the channel matrix can be obtained.

[0081]

number

[0082] Ni is the number of receiving antennas. Mt is the number of transmitting antennas. This expression is written with a focus on a certain frequency, and the V matrix in equation (7) exists for the specified number of subcarriers, and angle information is generated for each subcarrier. Furthermore, from the information corresponding to the eigenvalues ​​of the channel matrix, together with the SNR information of the smaller number of antennas, Ni or Mt, it is quantized with a specified number of quantization bits, stored in a wireless signal, and transmitted. The wireless communication unit 1-r of the position estimation device 1 can obtain this angle information and SNR information, and can also obtain RSSI information of the wireless signal.

[0083] The angle information may be used as the input feature as it is. The sine and cosine components calculated from the angle information may be used as the input feature. A matrix obtained by converting the angle information back into a right singular matrix using equation (7) may be used. After converting the angle information back into a right singular matrix, an averaging matrix obtained by averaging the right singular matrix or its correlation matrix in the frequency direction may be used. A matrix obtained by further performing signal processing such as QR decomposition on the averaging matrix may be used.

[0084] In the above format, the imaginary part of the last element of each column vector of the right singular matrix compressed as angle information is always 0, so if the right singular matrix is ​​obtained as an M×Ni matrix, the value 2×Mt×Ni-Ni becomes meaningful information from the numerical values ​​of the real and imaginary parts of each element. For example, if the right singular matrix is ​​a 4×1 matrix, a total of seven elements with a real part of 4 and an imaginary part of 3 become meaningful information, and if a 4×2 matrix is ​​obtained, a total of 14 elements with a real part of 8 and an imaginary part of 6 become meaningful information. Since the imaginary part of the last element of each column is 0, the last element of each column does not need to be used.

[0085] [Operation of wireless communication system] The higher the frequency of collecting channel information, the more frequently and accurately the position of the location estimation target 2-j can be estimated. However, it is necessary to use more wireless communication resources, which affects wireless communication. Therefore, in this embodiment, the collection process of channel information by the above-mentioned first method or second method is controlled. That is, the transmission start time and transmission frequency of the wireless signal transmitted from the fixed terminal 3-i or the location estimation target 2-j are adjusted. For example, a plurality of input feature quantities that are continuous in time are generated in a predetermined long or short period. In addition, the collection period of channel information is set independently for the fixed terminal 3-i or the location estimation target 2-j, respectively, or the collection frequency is reduced when it is desired to emphasize the quality of the wireless communication system in consideration of the influence on the wireless communication system. The location estimation is performed only once, or for a predetermined time period. This makes it possible to realize the operation cost required for the location estimation of the location estimation target at a lower cost. A specific example will be described below.

[0086] [Operation of wireless communication system (first example)] In the first example, a case where the transmission frequency of a wireless signal used for position estimation is adjusted will be described. In addition to the transmission frequency, for example, the transmission start time or the transmission schedule can also be adjusted in the same manner.

[0087] 3 is a diagram showing an operation (first example) of the wireless communication system, which shows a processing flow for starting position estimation or for designating the transmission frequency of a wireless signal including a pilot signal or channel information for position estimation.

[0088] First, when the wireless communication control unit 1-0 decides to perform location estimation or to specify the frequency at which location estimation is performed, it notifies the fixed terminal 3-i or the location estimation target 2-j of a command to transmit a signal or to specify the frequency at which the signal is transmitted (step S2-1).

[0089] In the case of the first method (transmission of pilot signal), the wireless communication control unit 1-0 notifies the fixed terminal 3-i or the location estimation target 2-j, which is the sender of the wireless signal, of the above command using one of the wireless communication units 1-1 to 1-R (step S2-1). Upon receiving the command, the fixed terminal 3-i or the location estimation target 2-j starts transmitting a pilot signal or starts transmitting a pilot signal at a specified transmission frequency according to the instructions included in the command (step S2-2).

[0090] The start of transmission of a wireless signal for acquiring channel information for position estimation can be determined based on the traffic of the wireless communication system, a request for position estimation by an application, or the accuracy of position estimation, as described below. Furthermore, the trigger may be detection by another method that an object that can be a target for position estimation has entered the environment of the position estimation system, or the trigger may be the state of another system, such as performing position estimation when a specific time or condition is satisfied, or a failure of a position estimation device other than the position estimation device of the present invention.

[0091] In the case of the second method (transmission of channel information) described above, the wireless communication control unit 1-0 issues a command to one of the wireless communication units 1-1 to 1-R electrically connected to the fixed terminal 3-i or the location estimation target 2-j to start generating a wireless signal requesting feedback of channel information or to instruct the frequency of generating the wireless signal (step S2-1). This wireless signal transmits a pilot signal known for transmission and reception to the communication partner, and quantizes channel information obtained from the pilot signal received by the fixed terminal 3-i or the location estimation target 2-j on the receiving side in some way, and causes the fixed terminal 3-i or the location estimation target 2-j to transmit a wireless signal including the channel information (step S2-2).

[0092] That is, in the second method, the wireless communication control unit 1-0 causes the fixed terminal 3-i or the location estimation target 2-j to transmit a wireless signal including channel information via any one of the wireless communication units 1-1 to 1-R. When causing the wireless signal including channel information to be transmitted at a certain transmission frequency, the transmission frequency can be realized by the transmission frequency of the wireless signal for estimating the channel information transmitted by the wireless communication units 1-1 to 1-R. This is because, in order for the fixed terminal 3-i or the location estimation target 2-j to acquire channel information, it is necessary for the transmission of a pilot signal from the communication partner and the reception of the pilot signal.

[0093] [Operation of wireless communication system (Example 2)] In the second example, a case will be described in which the transmission frequency of a wireless signal is determined based on the degree of congestion of wireless communication at a frequency of wireless communication being used.

[0094] 4 is a diagram showing an operation (second example) of the wireless communication system, which illustrates a processing flow in which the status of the wireless communication system is used when controlling the frequency of position estimation.

[0095] In this control, any one of the wireless communication units 1-1 to 1-R has a function of monitoring the resource tightness of the frequency band used for position estimation. Specifically, the wireless communication unit evaluates to what extent the transmission of wireless signals for position estimation is permitted in the frequency band by measuring the time ratio during which a certain signal is received with a receiving power higher than a predetermined level in the frequency band, counting the number of terminals communicating, measuring the number and frequency of use of high-priority applications, and measuring the number of wireless signals in a certain period of time (step S3-1).

[0096] Thereafter, the wireless communication control unit 1-0 refers to the evaluation result of the location estimation frequency allowed for the congestion level in the above frequency band, and determines the location estimation frequency (step S3-2).

[0097] For example, the transmission frequency of the wireless signal for position estimation is predetermined to be 1 second intervals when the temporal reception ratio of wireless signals (wireless signals with a level higher than a predetermined reception power) over a 10 second period is 80% or more, 0.5 second intervals when it is 50-70%, 0.2 second intervals when it is 20-50%, and 0.1 second intervals when it is 0-20%, and the transmission frequency of the wireless signal for position estimation is determined based on the measured temporal occupancy rate.

[0098] Alternatively, the number of fixed terminals 3-i or location estimation targets 2-j that transmit wireless communication may be determined instead of the transmission frequency. When wireless signals are transmitted from many wireless communication units, even if the transmission frequency of each wireless communication unit is low, the impact on the wireless communication system is large. Therefore, by limiting the number of terminals and using channel information corresponding to as few wireless communication units as possible, the impact on the wireless communication system can be minimized.

[0099] [Operation of wireless communication system (third example)] In the third example, a case will be described in which the transmission frequency of a wireless signal is determined according to the position estimation accuracy of a position estimation target required by a predetermined application program.

[0100] 5 is a diagram showing an operation (third example) of the wireless communication system, illustrating a processing flow in which an application program using estimated location information determines the frequency of transmitting a wireless signal for location estimation.

[0101] First, an application program that uses location information generates information related to the accuracy or frequency of location estimation (step S4-1). After that, the wireless communication control unit 1-0 changes the frequency of wireless signal transmission according to the accuracy or frequency of location estimation included in the information (step S4-2).

[0102] [Operation of wireless communication system (Example 4)] In the fourth example, a case is described in which the transmission of a wireless signal used for estimating the position of a position estimation target is stopped or the frequency of transmission of the wireless signal is reduced depending on the contribution or degree of contribution of the wireless signal to the position estimation of the position estimation target.

[0103] Fig. 6 is a diagram showing an operation (fourth example) of the wireless communication system. This is a processing flow for minimizing the influence on the wireless communication system and detecting unnecessary fixed terminals by stopping or reducing the transmission frequency of wireless signals that are not contributing to the location estimation of the location estimation target.

[0104] First, the wireless communication control unit 1-0 evaluates the accuracy of location estimation and evaluates the contribution and contribution rate of wireless signals to location estimation (step S5-1). After that, the wireless communication control unit 1-0 instructs the fixed terminal 3-i or the location estimation target 2-j to stop transmitting or reduce the frequency of transmitting wireless signals of wireless communication terminals (wireless communication units of fixed terminals, wireless communication units of targets for location estimation) that are not contributing to location estimation (step S5-2). In addition to stopping transmission or reducing the frequency of transmitting, it is also possible to reduce operation costs by removing the fixed terminal in question from the group of used fixed terminals.

[0105] The evaluation of the position estimation accuracy is, for example, to generate a position estimation model by combining multiple fixed terminals 3-i and position estimation targets 2-j, output position estimation results corresponding to multiple combinations of terminals corresponding to the acquired channel information, extract the output results that are deviating, and stop the transmission of wireless signals and the acquisition of channel information from the fixed terminals 3-i or position estimation targets 2-j related to the position estimation model, or reduce the transmission frequency. The deviation of the output results can be detected using an algorithm for detecting anomalies in machine learning. Alternatively, the contribution degree to position estimation and contribution degree are evaluated in advance in accordance with the position of the position estimation target, and it is possible to determine whether to stop the transmission of wireless signals with low contribution degree and contribution degree, stop the acquisition of channel information, and reduce the transmission frequency according to the current position and movement of the position estimation target.

[0106] [Operation of wireless communication system (5th example)] In the fifth example, a case is described in which transmission of a wireless signal used for estimating the position of a position estimation target is started or the frequency of transmission of the wireless signal is increased depending on the contribution or degree of contribution of the wireless signal to the position estimation of the position estimation target.

[0107] 7 is a diagram showing an operation (fifth example) of the wireless communication system. This is a processing flow for increasing the accuracy of location estimation while minimizing the influence on the wireless communication system and detecting fixed terminals not required for location estimation by starting transmission or increasing the transmission frequency of wireless signals that contribute to location estimation and stopping transmission or decreasing the transmission frequency of wireless signals that do not contribute to location estimation based on the accuracy of location estimation of the target of location estimation.

[0108] First, the wireless communication control unit 1-0 evaluates the accuracy of location estimation for the location conditions of the location estimation target, and evaluates the contribution and contribution rate of wireless signals to the location estimation (step S6-1).Then, the wireless communication control unit 1-0 determines the start of transmission or increase in transmission frequency of wireless signals for location estimation of wireless communication terminals that have a high contribution to location estimation or will have a high contribution rate in the near future for the current location of the location estimation target in the current configuration estimated by the location estimation model utilization unit 1-3, and conversely, instructs the stop of transmission or decrease in transmission frequency of wireless signals of wireless communication terminals that have not contributed to the location estimation or will not contribute in the future (step S6-2).

[0109] The accuracy of location estimation is evaluated, for example, by generating a location estimation model by combining fixed terminals 3-i and location estimation targets 2-j in multiple combinations, outputting location estimation results corresponding to multiple combinations of terminals corresponding to the acquired channel information, extracting those output results for which deviations have occurred, and stopping the transmission of wireless signals or the acquisition of channel information from the fixed terminals 3-i or location estimation targets 2-j related to that location estimation model, or reducing the transmission frequency.

[0110] Alternatively, a location estimation model is generated by combining multiple fixed terminals 3-i and location estimation targets 2-j, and a control is executed at a low occurrence frequency to transmit a radio signal for acquiring channel information from the wireless communication unit of the fixed terminal 3-i and location estimation target 2-j that is not currently in use, or to transmit a radio signal for channel estimation to estimate channel information, and to delay a feedback signal. Then, when it is found that a location estimation model including the fixed terminal 3-i or location estimation target 2-j that is not currently in use but acquired at a low frequency is effective, it is determined to start transmitting a radio signal for acquiring channel information of the fixed terminal 3-i or location estimation target 2-j, or to increase the transmission frequency. Alternatively, it is possible to evaluate the contribution degree / degree of contribution to location estimation in advance in accordance with the position of the location estimation target, and to decide to stop transmitting a radio signal with a low contribution degree / degree of contribution, stop or start acquiring channel information, and decrease or increase the transmission frequency according to the current position and movement of the location estimation target.

[0111] Another advantage of the control method based on the contribution to the location estimation accuracy according to the fourth and fifth examples is that it is possible to extract fixed terminals 3-i or location estimation targets 2-j with low contributions. In other words, by evaluating the predicted location information in real time or offline using a location estimation model based on multiple combinations of fixed terminals 3-i or location estimation targets 2-j, it is possible to obtain fixed terminals 3-i or location estimation targets 2-j that contribute little or do not contribute at all. In this way, it is also possible to remove fixed terminals 3-i or location estimation targets 2-j that do not contribute to location estimation, or to make it possible to re-operate them by changing the conditions such as their location.

[0112] [Experimental Results] The position estimation method and its effects according to this embodiment will be described with reference to specific examples and indoor experimental results.

[0113] Four fixed terminals 3-1 to 3-4, one location estimation target 2-1, and a location estimation device 1 connected to two wireless communication units 1-1 and 1-2 were placed in an indoor experimental environment area shown in Fig. 8. The location estimation target 2-1 is traveling in a figure-8 pattern in the center of the experimental environment area. The fixed terminals 3-1 to 3-4 are performing wireless communication with a base station AP, which is an access point.

[0114] The fixed terminals 3-1 to 3-4 and the location estimation target 2-1 are requested by the base station AP to report channel information every 100 ms, and transmit angle information of the channel information as feedback using the channel information feedback method defined in the wireless LAN standard IEEE 802.11ac. The base station AP has four antennas. The fixed terminals 3-1 to 3-4, the location estimation target 2-1, and the wireless communication units 1-1 and 1-2 each have two antennas. Communication was performed using a 20 MHz bandwidth and a carrier frequency of 5.66 GHz.

[0115] The two wireless communication units 1-1 and 1-2 can obtain angle information generated from a right singular matrix of a channel matrix between the fixed terminals 3-1 to 3-4 and the base station AP, SNR, and RSSI values ​​in the wireless communication units 1-1 and 1-2 of wireless signals from the fixed terminals 3-1 to 3-4. One RSSI is obtained from each of the wireless communication units 1-1 and 1-2.

[0116] The input feature generator 1-2 calculates a unitary matrix from the angle information according to the above-mentioned formula, and averages the calculated unitary matrix by frequency. This results in a total of 14 components, consisting of 8 real parts and 6 imaginary parts. In addition, 14+2+2=18 input features, including the dB values ​​of the two pieces of SNR information normalized to be distributed in the range of 0 to 1 and the dB values ​​of the RSSI at the receiving antennas of the wireless communication units 1-1 and 1-2 normalized to be distributed in the range of 0 to 1, are acquired for each fixed terminal at a cycle of 100 ms.

[0117] Here, a method for generating a location estimation model will be described.

[0118] In order to generate a position estimation model according to this embodiment, an autonomous robot, which is a position estimation target 2-1, is driven for 8 hours in an indoor experimental environment area. At this time, the position estimation model training unit 1-4 generates training data in which highly accurate position information of the autonomous robot obtained from a LIDAR (light detection and ranging) and tire control information provided in the position estimation target, and the above-mentioned input feature amount related to propagation are arranged in the same time series at 200 ms intervals. As described above, the generation period of the input feature amount is 100 ms, but the latest information obtained in a time width divided by 200 ms intervals is selected and used to generate training data.

[0119] The generated training data was then used to train a location estimation model using a deep neural network that uses a GRU (Gated Recurent Unit) and direct connections. The learning rate was 0.0002, and the optimization algorithm used was ADAM. The GRU had one hidden layer and a dimension of 35, and the weights and biases were updated by backpropagation to output X and Y coordinate information within the experimental environment area using two direct connection layers with input 35 and output 35, and one direct connection layer with input 35 and output 2. The updated location estimation model was used.

[0120] Figure 10 shows the results of arranging the error from the actual value of the location estimation output in units of m. From the left, 18 input features were generated for each terminal from the channel information from the terminals (fixed terminals, location estimation devices) 2-1, 3-1, 3-2, 3-3, 3-4, {2-1,3-1}, {2-1,3-2}, {2-1,3-3}, {2-1,3-4}, {2-1,3-1,3-2,3-3,3-4}, {2-1,3-1,3-3}, {2-1,3-3,3-4}, and input into the location estimation model to predict location information. The results are organized by the estimation error for each area divided in Figure 9.

[0121] In the operation of the wireless communication system (Example 5), when generating input features from channel information from the wireless communication unit of the fixed terminal or the target of location estimation in advance, a location estimation model is generated for all the combinations in FIG. 10, and the contribution to the location estimation accuracy for the separately measured location information of the autonomous robot is obtained from FIG. 10. FIG. 11 shows the combinations that can output the highest location estimation accuracy in Areas A to F. In this way, if the contribution of the input features to the location of the target of location estimation can be evaluated in advance, it is possible to determine whether to transmit or stop the wireless signal according to the location of the target of location estimation. For example, when a robot enters or approaches Area A, channel information from all fixed terminals and the target of location estimation is collected, and the wireless signal of the fixed terminal 3-2 is stopped in Areas B to F, and the transmission of the wireless signal of the fixed terminal 3-4 is further stopped in Areas B, D, E, and F, it can be seen that there is no effect on the location estimation accuracy. Furthermore, it can be seen from the result of FIG. 10 that the best or second best effect is obtained overall by using the combination of {2-1, 3-1, 3-3}. For this reason, it may be possible to consider eliminating or changing the locations of fixed terminals 3-2 and 3-4. Furthermore, in Area A, whether to select channel information of all terminals may be determined based on the degree of congestion of the wireless communication system from the operation of the wireless communication system (second example). If there are no constraints, such as the wireless communication system not being used much for data communication, channel information may be acquired from all terminals, and if there are constraints, it may be determined to use a location estimation model using channel information from {2-1, 3-1, 3-3} as the second best combination.

[0122] [Effects of this embodiment] According to this embodiment, the position estimation device 1 includes a wireless communication control unit 1-0 that determines a transmission command related to the start of transmission, transmission frequency, or transmission schedule of a wireless signal used for position estimation, and transmits the transmission command for the wireless signal to a wireless communication unit of a fixed terminal installed in the same environment as the device itself or to a wireless communication unit of a target for position estimation; wireless communication units 1-1 to 1-R that receive wireless signals transmitted from the wireless communication unit of the fixed terminal or the wireless communication unit of the target for position estimation based on the transmission command, and acquire channel information related to radio wave propagation from the wireless signals; an input feature generation unit 1-2 that converts the channel information into input features that can be input to a position estimation model; and a position estimation model utilization unit 1-3 that estimates and calculates the position of the target for position estimation by inputting the input features into a position estimation model that models the relationship between the channel information related to radio wave propagation and the position information of the target for position estimation by machine learning.

[0123] In other words, the position of the position estimation target is estimated using channel information regarding radio wave propagation contained in the wireless signal of the wireless communication terminal and a position estimation model, so that the position estimation of the position estimation target can be performed using general-purpose wireless communication, providing a technology that can estimate the position of the position estimation target at low cost.

[0124] In addition, since the position estimation device 1 transmits a transmission command regarding the start of transmission, transmission frequency, or transmission schedule of the wireless signal used for position estimation, it becomes possible to transmit the wireless signal according to the communication quality, etc., of the wireless communication system, thereby improving the reliability of estimating the position estimation target, improving the estimation accuracy of the position estimation target, and enabling the operating costs required for estimating the position of a specific object to be achieved at a lower cost.

[0125] [others] The present invention is not limited to the above-described embodiment, and various modifications are possible within the scope of the present invention.

[0126] The position estimation device 1 of the present embodiment described above can be realized, for example, by using a general-purpose computer system including a CPU 901, a memory 902, a storage 903, a communication device 904, an input device 905, and an output device 906, as shown in Fig. 12. The memory 902 and the storage 903 are storage devices. In the computer system, the CPU 901 executes a predetermined program loaded on the memory 902, thereby realizing each function of the position estimation device 1.

[0127] The position estimation device 1 may be implemented by one computer. The position estimation device 1 may be implemented by multiple computers. The position estimation device 1 may be a virtual machine implemented in a computer. The program for the position estimation device 1 may be stored in a computer-readable recording medium such as an HDD, an SSD, a USB memory, a CD, or a DVD. The program for the position estimation device 1 may also be distributed via a communication network. [Explanation of symbols]

[0128] 1:Position estimation device 1-0: Wireless communication control unit 1-1~1-R: Wireless communication section 1-2: Input feature generation unit 1-3: Location estimation model utilization section 1-4: Location estimation model training section 1-5: Location estimation target information generation unit 2-1~2-Q: Location estimation target 2-1-1~2-Q-1: Wireless communication section 3-1~3-M: Fixed terminal 3-1-1~3-M-1: Wireless communication department 901:CPU 902: Memory 903: Storage 904: Communication equipment 905: Input device 906: Output device

Claims

1. a wireless communication control unit that determines a transmission command related to a transmission start, transmission frequency, or transmission schedule of a wireless signal used for position estimation, and transmits the transmission command of the wireless signal to a wireless communication unit of a fixed terminal installed in the same environment as the device itself or a wireless communication unit of a target for position estimation; a wireless communication unit that receives a wireless signal transmitted from a wireless communication unit of the fixed terminal or a wireless communication unit of the target for location estimation based on the transmission command, and acquires channel information related to radio wave propagation from the wireless signal; an input feature generator that converts the channel information into an input feature that can be input to a position estimation model; a location estimation model utilization unit that estimates and calculates a location of the location estimation target by inputting the input feature amount to a location estimation model that models a relationship between channel information on the radio wave propagation and location information of the location estimation target by machine learning, The wireless communication control unit A position estimation device that calculates the contribution of a wireless signal transmitted from the wireless communication unit of the fixed terminal or the wireless communication unit of the position estimation target to position estimation based on the position estimation accuracy of the position estimation target, and decides to stop or start transmission of the wireless signal transmitted from the wireless communication unit of the fixed terminal or the wireless communication unit of the position estimation target, or decides the transmission frequency of the wireless signal, depending on the contribution.

2. The wireless communication unit includes: Detects the degree of congestion of wireless communication in the frequency band being used, The wireless communication control unit The position estimation device according to claim 1 , further comprising: a transmission frequency of a wireless signal or a number of wireless communication units that transmit a wireless signal, based on the degree of congestion.

3. The wireless communication control unit 3. The position estimation device according to claim 1, wherein the frequency of transmitting the radio signal is determined in accordance with a position estimation accuracy required by a predetermined application program.

4. The input feature generation unit As the input feature amount, the received power of the wireless signal, the signal power, power ratio information obtained from a moving average of the received power or the signal power, a channel matrix of the channel information, a correlation matrix of the channel matrix, an operational matrix obtained by signal processing the channel matrix, an operational matrix obtained by signal processing the correlation matrix, an operational matrix obtained by signal processing the channel matrix or the correlation matrix corresponding to a plurality of frequencies, a unitary matrix obtained by linearly operating the channel matrix, a unitary matrix obtained by linearly operating the correlation matrix, a unitary matrix obtained by linearly operating the operational matrix, 4. The position estimation device according to claim 1, further comprising: a diagonal matrix obtained by linearly operating a channel matrix; a diagonal matrix obtained by linearly operating the correlation matrix; a diagonal matrix obtained by linearly operating the operation matrix; a triangular matrix obtained by linearly operating the channel matrix; a triangular matrix obtained by linearly operating the correlation matrix; and a triangular matrix obtained by linearly operating the operation matrix; the device generates values ​​of phase, amplitude, real component, and imaginary component of one or more feature quantities, a standardized value of a coefficient range of the one or more values, and the one or more values ​​or the standardized values ​​for a plurality of times.

5. A position estimation method performed by a position estimation device, determining a transmission command for starting transmission, transmission frequency, or transmission schedule of a wireless signal used for location estimation, and transmitting the transmission command for the wireless signal to a wireless communication unit of a fixed terminal installed in the same environment as the own device or to a wireless communication unit of a target for location estimation; receiving a wireless signal transmitted from a wireless communication unit of the fixed terminal or a wireless communication unit of the target of location estimation based on the transmission command, and acquiring channel information related to radio wave propagation from the wireless signal; converting the channel information into input features that can be input into a location estimation model; a step of inputting the input feature amount into a position estimation model that models a relationship between channel information regarding the radio wave propagation and position information of the position estimation target by machine learning, thereby estimating and calculating a position of the position estimation target; a step of calculating a contribution degree to the position estimation of a wireless signal transmitted from a wireless communication unit of the fixed terminal or a wireless communication unit of the target for position estimation based on the position estimation accuracy of the target for position estimation, and determining whether to stop or start transmission of the wireless signal transmitted from the wireless communication unit of the fixed terminal or the wireless communication unit of the target for position estimation, or determining a transmission frequency of the wireless signal, depending on the contribution degree; A location estimation method that performs the above.

6. A position estimation program that causes a computer to function as the position estimation device according to any one of claims 1 to 4.

Images