JP2024037369A - Position estimation device, position estimation method, program - Google Patents

Abstract

A position estimation device is provided that can easily estimate the position of an object based on the reception strength at the object of a signal transmitted from a transmitter. The device identifies the detection result of the reception strength at the object of the position estimation of the signal transmitted from the transmitter and the previous estimation result of the position of the object of the position estimation. The device estimates a new position of the object of the position estimation using the reception strength and the previous estimation result of the position. [Selected Figure]

Description

The present invention relates to a position estimation device, a position estimation method, and a program.

The position information of the position estimation target can be specified, for example, by a function such as GNSS (Global Navigation Satellite System) provided in the position estimation target. GNSS uses radio waves transmitted by multiple satellites placed in Earth orbit to determine the position of a receiver with high precision. Here, there is a need for a technology that can accurately estimate the position of a position estimation target without using GNSS. Patent Document 1 discloses a technique for estimating the position of a terminal as a positioning target with high accuracy in an indoor environment.

Japanese Patent Application Publication No. 2016-114361

When estimating the position of a target as described above, there is a need for a technique that can easily estimate the position of the target based on the reception strength at the target of a signal transmitted from a transmitter.

Therefore, an object of the present invention is to provide a position estimating device, a position estimating method, and a program that solve the above-mentioned problems.

According to the first aspect of the present invention, the position estimating device is configured to identify a detection result of a reception strength of a signal transmitted by a transmitter at a position estimation target and a previous position estimation result of the position estimation target. and a position estimating means for estimating a new position of the position estimation target using the reception strength and the previous position estimation result.

According to the second aspect of the present invention, the position estimation method specifies the detection result of the reception strength of the signal transmitted by the transmitter at the position estimation target, and the estimation result of the previous position of the position estimation target, A new position of the position estimation target is estimated using the reception strength and the previous position estimation result.

According to the third aspect of the present invention, the program causes the computer of the position estimating device to detect the reception strength of the signal transmitted by the transmitter at the position estimation target and the previous position estimation result of the position estimation target. and a position estimating means for estimating a new position of the position estimation target using the reception strength and the previous position estimation result.

According to the present invention, the position of the target can be easily estimated based on the reception strength of the signal transmitted from the transmitter at the target.

FIG. 1 is a diagram showing a position estimation system according to the present embodiment. FIG. 3 is a diagram showing the relationship between a radio signal according to the present embodiment and an area provided within a range in which a user terminal moves. FIG. 3 is a functional block diagram of each device according to the present embodiment. It is a diagram showing an example of the hardware configuration of the estimation server according to the present embodiment. FIG. 3 is a diagram showing a distance table according to the present embodiment. It is a diagram showing an example of a neural network using the estimation model according to the present embodiment. FIG. 3 is a diagram showing a processing flow of a user terminal according to the present embodiment. It is a figure showing the processing flow of an estimation server by this embodiment. It is a diagram showing the minimum configuration of an estimation server according to this embodiment. It is a figure which shows the processing flow of the estimation server of the minimum configuration by this embodiment.

Hereinafter, a position estimation system according to an embodiment of the present invention will be described with reference to the drawings.
FIG. 1 is a diagram showing a position estimation system according to the same embodiment. The position estimation system 100 includes at least a position estimation device. In this embodiment, the function of the position estimation device is provided in the estimation server 1. Further, the position estimation system 100 of this embodiment may include a user terminal 2 connected to the estimation server 1 through a communication network. The user terminal 2 is an example of a position estimation target. The user terminal 2 receives the signal transmitted from the wireless signal device 3.

In this embodiment, the estimation server 1 uses the detection result of the reception strength of the signal transmitted by the radio signal 3 in the position estimation target and the estimation result of the previous position of the position estimation target to create a new position estimation target. Estimate the location.

FIG. 2 is a diagram showing the relationship between the radio signal according to this embodiment and the area provided within the movement range of the user terminal.
As shown in FIG. 2, the radio signal equipment 3 is installed at a plurality of positions within the range in which the user terminal 2 moves. The range in which the user terminal 2 moves may be in a closed space such as indoors. The range in which the user terminal 2 moves may not be a closed space. A plurality of areas are set in the range in which the user terminal 2 moves. As an example, FIG. 2 shows a rectangular range in which the user terminal 2 moves, and shows a plurality of small rectangular areas measuring 5 by 5 in the rectangular range. The rectangular area at the top left is called area (1, 1). The lower right area is called area (5, 5). FIG. 2 shows that the current location of the user terminal 2 is area (3, 2). The estimation server 1 estimates the new position of the user terminal 2 using the detection result of the reception strength at the user terminal 2 of the signal transmitted by the radio signal device 3 and the previous position estimation result. The position may indicate a range, and in this embodiment, the estimation server 1 estimates in which area the user terminal 2 is located.

FIG. 3 is a functional block diagram of each device according to this embodiment.
As shown in FIG. 3, the estimation server 1 performs the functions of a control section 11, a specifying section 12, a position estimating section 13, and a transmitting/receiving section 14. The control unit 11 controls each function of the estimation server 1. The specifying unit 12 specifies the detection result of the reception strength of the signal transmitted by the radio signal device 3 at the user terminal 2 and the estimation result of the previous position of the user terminal 2. The position estimating unit 13 estimates a new position of the user terminal 2 using the reception strength specified by the specifying unit 12 and the previous position estimation result of the user terminal 2. The transmitting/receiving unit 14 transmits the estimation result of the position of the user terminal 2 to the user terminal 2. The storage unit 15 stores each piece of information used in the processing of the estimation server 1.

Further, as shown in FIG. 3, the user terminal 2 exhibits the functions of a control section 21, a signal receiving section 22, a processing section 23, and a transmitting/receiving section 24. The control unit 21 controls each function of the user terminal 2. The signal receiving unit 22 receives the signal transmitted by the wireless signal device 3 and detects the reception strength. The processing unit 23 performs processing such as displaying the estimation results of the estimation server 1 on a display. The transmitting/receiving unit 24 transmits and receives information to and from the estimation server 1 . The storage unit 25 stores each piece of information used in the processing of the user terminal 2.

The radio signal device 3 has the function of a transmitting section 31. For example, the transmitter 31 periodically transmits a signal at intervals T2 of several seconds to several tens of seconds. The signal may include information such as the ID of the radio signal 3 and the transmission time. The wireless signal device 3 is a device that transmits a signal at regular intervals using, for example, Wi-Fi or the BLE (Bluetooth Low Energy) standard, and the signal includes an ID that is an identifier of the wireless signal device 3. There is.

FIG. 4 is a diagram showing an example of the hardware configuration of the estimation server according to this embodiment.
As shown in this figure, the estimation server 1 is equipped with various hardware such as a CPU (Central Processing Unit) 101, a ROM (Read Only Memory) 102, a RAM (Random Access Memory) 103, an HDD 104, a communication module 105, and a database 106. It's a computer. Note that the user terminal 2 is also a computer having a similar hardware configuration.

FIG. 5 is a diagram showing a distance table according to this embodiment.
More specifically, the position estimation unit 13 further uses the estimation model and the distance table stored in the storage unit 15 to estimate the area where the user terminal 2 is located. As shown in FIG. 5, the distance table is a data table that stores the distance between each area. Letting point A, point B, . . . , point Z be the center positions (representative positions) of each of a plurality of areas, Area 1 to Area Y, the distances between these points are stored. For example, in FIG. 5, AB associated with point A and point B indicates the distance between point A and point B. The distance between each point may be the distance between areas.

FIG. 6 is a diagram showing an example of a neural network using the estimation model according to this embodiment.
The position estimation unit 13 of the estimation server 1 inputs the signal intensities i1 to iX of the signals transmitted by each of the wireless traffic lights 3 1 to X detected by the user terminal 2 to the input layer of the neural network. As a result, the estimation server 1 calculates likelihoods a1 to aY indicating the degree of certainty that the user terminal 2 is located at each representative point in each of the areas 1 to Y as outputs from the output layer.

Parameters other than the input layer and output layer, such as the number of hidden layers of the neural network, the number of nodes in each hidden layer, optimization method, activation function, learning rate, and number of learning times, can be set arbitrarily for each estimation model. shall be. In addition, the estimation model creates training data in advance using a set of the radio field strength of the signal from each wireless signal 3 that can be observed at a representative point in each area and a number indicating the observed position, and performs machine learning. do.

FIG. 7 is a diagram showing the processing flow of the user terminal according to this embodiment.
Next, the processing flow of the user terminal will be explained.
The signal receiving unit 22 of the user terminal 2 receives signals from each wireless signal device 3 (step S101). The signal receiving unit 22 detects the reception strength of each signal (step S102). The signal receiving unit 22 outputs information indicating the relationship between the ID of each wireless signal device 3 that transmitted the signal and the reception strength of the signal transmitted by each wireless signal device 3 to the processing unit 23. The processing unit 23 determines whether a predetermined time has elapsed since the previous position estimation request (step S103). When the estimation server 1 estimates the position of the user terminal 2 and receives the position estimation result, the storage unit 25 stores the position (area identifier) that is the position estimation result. and an estimated time indicating the time when the position estimation result was requested are stored in association with each other. The processing unit 23 has the previous position estimation result recorded in the storage unit 25, and compares the estimated time of the position estimation result with the current time to determine whether a predetermined time has elapsed since the previous position estimation request. Determine whether or not.

If the processing unit 23 determines that a predetermined period of time has not elapsed since the previous position estimation request, the processing unit 23 includes the previous position estimation result and also sends a pair of the ID of the radio signal 3 and the corresponding reception strength to each radio signal. 3 is generated (step S104). The processing unit 23 instructs the transmitting/receiving unit 24 to transmit the first estimation request. The transmitter/receiver 24 transmits the first estimation request to the estimation server 1 (step S105). The processing unit 23 stores the transmission time of the first estimation request in the storage unit 25 as the above-mentioned estimated time.

If the processing unit 23 determines that a predetermined time has elapsed since the previous position estimation request, it waits to receive a signal from each radio signal device 3 a predetermined number of times. The processing unit 23 acquires the detection results of each signal strength for a predetermined number of times in the signal receiving unit 22 of the signals transmitted from each radio signal device 3 (step S106). The processing unit 23 generates a second estimation request including a plurality of pairs of the signal strength for a predetermined number of times and the ID of the wireless signal device 3 that transmitted the signal of the signal strength (step S107). Similarly, the transmitter/receiver 24 transmits a second estimation request to the estimation server 1 (step S108). The processing unit 23 stores the transmission time of the second estimation request in the storage unit 25 as the above-mentioned estimated time.

FIG. 8 is a diagram showing a processing flow of the estimation server according to this embodiment.
The estimation server 1 receives the first estimation request or the second estimation request (step S201). The identification unit 12 of the estimation server 1 determines whether the previous position estimation result can be identified from the estimation request (step S202). When the previous position estimation result can be specified, the identification unit 12 determines the relationship between the previous position estimation result, each signal strength, and the ID of the radio signal device 3 that transmitted the signal of the signal strength, and determines the position. It is output to the estimator 13. When the previous position estimation result cannot be specified, the specifying unit 12 outputs to the position estimating unit 13 a plurality of relationships between each signal strength and the ID of the radio signal device 3 that transmitted the signal of the signal strength.

When the position estimation unit 13 of the estimation server 1 has acquired the previous position estimation result, it performs the first estimation process (step S203). In the first estimation process, the position estimation unit 13 inputs the signal intensities i1 to iX of the signals transmitted from each radio signal device 3 to a neural network constructed using a learning model. Note that if the user terminal 2 cannot receive a signal transmitted from a certain wireless signal device 3, the reception strength of the signal may be set to 0. As a result, the position estimation unit 13 calculates likelihoods a1 to aY indicating the probability that the user terminal 2 is located in each area 1 to Y (step S204).

Based on the previous position estimation result, the position estimating unit 13 identifies a representative point in another area within a predetermined distance from the representative point in the area where the user was located last time, based on the distance table (step S205). For example, when the previous position estimation result of the user terminal 2 indicates point A, other points located within a predetermined distance from point A are identified based on the distance table. This process is an example of a process that specifies a plurality of new positions within a predetermined range based on the position indicated by the previous position estimation result. The position estimation unit 13 identifies the likelihood with the highest value among the likelihoods of the other identified points (step S206). The position estimation unit 13 estimates the area corresponding to the likelihood or a representative point of the area as the current position of the user terminal 2 (step S207).

Alternatively, the position estimating unit 13 identifies one or more of the likelihoods a1 to aY indicating the probability that the user terminal 2 is located in each area 1 to Y, and identifies one or more likelihoods that are equal to or higher than a threshold, and Based on the distance table, the likelihood with the highest value among the likelihoods corresponding to the similarly specified point may be specified. Then, the position estimating unit 13 estimates the area corresponding to the likelihood or a representative point of the area as the current position of the user terminal 2.

If the position estimation unit 13 of the estimation server 1 has not acquired the previous position estimation result, it performs the second estimation process (step S208). In the second estimation process, the position estimation unit 13 inputs the signal intensities i1 to iX of the signals transmitted from each radio signal device 3 to a neural network constructed using a learning model. As a result, the position estimation unit 13 calculates likelihoods a1 to aY indicating the probability that the user terminal 2 is located in each area 1 to Y (step S209). The position estimation unit 13 identifies the highest likelihood among the likelihoods a1 to aY (step S210). Further, the position estimating unit 13 selects the area corresponding to the likelihood or a representative point of the area as a candidate for the current position of the user terminal 2 (step S211). The position estimation unit 13 repeats the same process a predetermined number of times the signal strength is detected in the user terminal 2. During the predetermined number of repetitions, the position estimating unit 13 estimates the current position candidate (area or its representative point) identified most frequently as the current position (step S212).

The position estimating unit 13 outputs a position estimation result indicating information on the estimated position (information on the area and representative points) to the transmitting/receiving unit 14. The transmitter/receiver 14 transmits the position estimation result to the user terminal 2 (step S213). The transmitting/receiving unit 24 of the user terminal 2 receives the position estimation result (step S109). The processing unit 23 displays, on the display of the user terminal 2, map information indicating information on the area and point where the user terminal 2 is located, based on the position estimation result (step S110). Note that the processing unit 23 may record the reception time of the position estimation result in the storage unit 25 as the above-mentioned estimated time.

The process of the position estimating unit 13 described above is to calculate the likelihood indicating the degree of certainty that the user terminal 2 is located at each of a plurality of different positions based on the reception strength, and select one of the plurality of positions indicated by the previous position estimation result. This is an example of a process of estimating a new position of the user terminal 2 based on one of the positions and the likelihood at each of a plurality of positions.

In addition, the process of the position estimating unit 13 described above specifies new multiple positions within a predetermined range based on the position indicated by the previous position estimation result, and selects a position with a high likelihood among the identified multiple positions. , is an example of a process for estimating the new position of the user terminal 2.

Further, the process of the identifying unit 12 described above is one aspect of the process of determining whether or not the previous position estimation result of the user terminal 2 can be specified.
In addition, in the case where the previous position estimation result of the user terminal 2 cannot be specified, the process of the position estimation unit 13 described above is performed using the radio signal 3 multiple times after determining that the previous position estimation result of the user terminal 2 cannot be specified. Based on the detection result of the reception strength at the user terminal 2 of the signal transmitted by This is one aspect of processing for estimating the new position of the user terminal 2.

Furthermore, the process of the position estimating unit 13 described above uses the detection results of the reception strength at the user terminal 2 of each signal transmitted by the radio signal equipment 3 set at a plurality of different positions to determine the probability that the user terminal 2 is located. This is one aspect of processing that calculates a likelihood indicating a degree for each of a plurality of positions.

In addition, the above-described processing of the position estimating unit 13 uses the reception strength at the user terminal 2 of each signal transmitted by the radio signal equipment 3 set at a plurality of different positions and the learning model to confirm the location of the user terminal 2. This is one aspect of processing that calculates likelihood, which indicates the degree of likelihood, for each of a plurality of positions.

According to the above-described processing, the position of the user terminal 2, which is the current position estimation target, can be calculated with high accuracy using the previous position estimation result.

According to the estimation server that performs the above processing, even in an indoor environment, the current position estimation target can be determined by narrowing down the range in which a certain user terminal 2 may have moved, using the previous position estimation results. The position of the user terminal 2 can be calculated with high accuracy.

FIG. 9 is a diagram showing the minimum configuration of the estimation server according to this embodiment.
FIG. 10 is a diagram showing a processing flow of the estimation server with the minimum configuration according to this embodiment.
As shown in FIG. 9, the estimation server includes at least specifying means 91 and position estimating means 92.
The specifying unit 91 specifies the detection result of the reception strength of the signal transmitted by the transmitter in the position estimation target and the estimation result of the previous position of the position estimation target (step S901).
The position estimating means 92 estimates a new position of the position estimation target using the reception strength and the previous position estimation result (step S902).

The estimation server 1 and user terminal 2 described above have a computer system inside. The steps of each of the above-mentioned processes are stored in a computer-readable recording medium in the form of a program, and the above-mentioned processes are performed by reading and executing this program by the computer.

The above program may be for realizing some of the functions described above. Furthermore, it may be a so-called difference file (difference program) that can realize the above-mentioned functions in combination with a program already recorded in the computer system.

Note that a part or all of the above embodiment may be described as in the following supplementary notes, but is not limited to the following.

(Additional note 1)
Identification means for identifying a detection result of the reception strength of the signal transmitted by the transmitter at the position estimation target and a previous position estimation result of the position estimation target;
a position estimation means for estimating a new position of the position estimation target using the reception strength and the previous position estimation result;
A position estimation device comprising:

(Additional note 2)
The position estimating means is
calculating a likelihood indicating the degree of certainty that the position estimation target is located at each of a plurality of different positions based on the reception strength;
A new position of the position estimation target is estimated based on one of the plurality of positions indicated by the previous position estimation result and a likelihood at each of the plurality of positions.The position according to supplementary note 1. Estimation device.

(Additional note 3)
The position estimating means is
A plurality of new positions within a predetermined range are specified based on the position indicated by the previous position estimation result, and a position with a high likelihood among the specified positions is selected as the new position of the position estimation target. The position estimating device according to Appendix 2.

(Additional note 4)
The specifying means determines whether a previous position estimation result of the position estimation target can be specified;
When the previous position estimation result of the position estimation target cannot be determined, the position estimation means transmits a message transmitted by the transmitter a plurality of times after determining that the previous position estimation result of the position estimation target cannot be determined. Based on the detection result of the reception strength of the signal at the position estimation target, a likelihood indicating the degree of certainty that the position estimation target is located at each of the plurality of different positions is calculated for each of the plurality of positions, and based on the likelihood. The position estimation device according to supplementary note 2 or 3, wherein the position estimation device estimates a new position of the position estimation target.

(Appendix 5)
The position estimating means indicates a degree of certainty that the position estimation target is located, using detection results of reception strengths at the position estimation target of each signal transmitted by the transmitter set at a plurality of different positions. The position estimation device according to any one of Supplementary Notes 2 to 4, wherein a likelihood is calculated for each of the plurality of positions.

(Appendix 6)
The position estimating means calculates a degree of probability that the position estimation target is located, using a learning model and reception strength of each signal transmitted by the transmitter set at a plurality of different positions at the position estimation target. The position estimating device according to any one of Supplementary Notes 2 to 5, wherein a likelihood indicating ? is calculated for each of the plurality of positions.

(Appendix 7)
The position estimating device according to any one of appendices 1 to 6, in which the position indicates a range.

1... Estimation server 2... User terminal 3... Radio signal 11, 21... Control section 12... Specification section 13... Position estimation section 14, 24... Transmission/reception section 15, 25 ... Storage section 22 ... Signal reception section 23 ... Processing section 31 ... Transmission section

Claims (9)

Identification means for identifying a detection result of the reception strength of the signal transmitted by the transmitter at the position estimation target and a previous position estimation result of the position estimation target;
a position estimation means for estimating a new position of the position estimation target using the reception strength and the previous position estimation result;
A position estimation device comprising: The position estimating means is
calculating a likelihood indicating the degree of certainty that the position estimation target is located at each of a plurality of different positions based on the reception strength;
The new position of the position estimation target is estimated based on one of the plurality of positions indicated by the previous position estimation result and the likelihood at each of the plurality of positions. Location estimation device. The position estimating means is
A plurality of new positions within a predetermined range are specified based on the position indicated by the previous position estimation result, and a position with a high likelihood among the specified positions is selected as the new position of the position estimation target. The position estimating device according to claim 2. The specifying means determines whether a previous position estimation result of the position estimation target can be specified;
When the previous position estimation result of the position estimation target cannot be determined, the position estimation means transmits a plurality of times the transmitter transmits a plurality of times after determining that the previous position estimation result of the position estimation target cannot be determined. Based on the detection result of the reception strength of the signal at the position estimation target, a likelihood indicating the degree of certainty that the position estimation target is located at each of the plurality of different positions is calculated for each of the plurality of positions, and based on the likelihood. The position estimating device according to claim 1, wherein the new position of the position estimation target is estimated using the method. The position estimating means indicates a degree of certainty that the position estimation target is located, using detection results of reception strengths at the position estimation target of each signal transmitted by the transmitter set at a plurality of different positions. The position estimating device according to any one of claims 2 to 4, wherein a likelihood is calculated for each of the plurality of positions. The position estimating means calculates a degree of probability that the position estimation target is located, using a learning model and reception strength of each signal transmitted by the transmitter set at a plurality of different positions at the position estimation target. The position estimating device according to claim 5, wherein a likelihood indicating the above is calculated for each of the plurality of positions. The position estimating device according to any one of claims 1 to 4, wherein the position indicates a range. identifying a detection result of the reception strength of the signal transmitted by the transmitter at the position estimation target and a previous position estimation result of the position estimation target;
A position estimation method, wherein a new position of the position estimation target is estimated using the reception strength and the previous position estimation result. The computer of the position estimation device,
identification means for identifying the detection result of the reception strength of the signal transmitted by the transmitter at the position estimation target and the previous position estimation result of the position estimation target;
position estimating means for estimating a new position of the position estimation target using the reception strength and the previous position estimation result;
A program that functions as

Images