Information processing device and information processing method

Abstract

To obtain error information with higher accuracy regarding an error in position information obtained from signal strength measurement.SOLUTION: An information processing device includes: a first acquisition section that acquires first position data indicating a first position estimated from a result of signal strength measurement in a target space; a second acquisition section that acquires second position data indicating a second position actually measured at the same position as the position of the signal strength measurement in the target space by a method that does not rely on the signal strength measurement; and an output section that outputs information relating to an error of the first position in accordance with comparison between the first position data and the second position data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information processing device and an information processing method. [Background technology]

[0002] There are known techniques for calculating errors in estimated positions due to radio wave strength. For example, Patent Document 1 discloses an invention for estimating errors in indoor positioning caused by physical characteristics such as reflected radio waves. The invention described in Patent Document 1 reflects error information related to the position estimation of a mobile object due to radio wave strength in a bias amount distribution map for each base station. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 5278365 Summary of the Invention [Problem to be solved by the invention]

[0004] The technology described in Patent Document 1 estimates the position and error of a mobile station based on a signal from a base station, and there is a limit to the position information that can be obtained from the signal from the base station.

[0005] In contrast to this, the present invention provides a technique for obtaining more accurate error information regarding errors in location information obtained from radio wave intensity measurements. [Means for solving the problem]

[0006] One aspect of the present disclosure provides an information processing device having a first acquisition unit that acquires first position data indicating a first position estimated based on the results of radio wave intensity measurement in a target space, a second acquisition unit that acquires second position data indicating a second position actually measured at the same position in the target space as the radio wave intensity measurement using a method other than the radio wave intensity measurement, and an output unit that outputs information regarding an error in the first position based on a comparison between the first position data and the second position data.

[0007] Another aspect of the present disclosure provides an information processing method including the steps of acquiring first position data indicating a first position estimated based on the results of radio wave intensity measurement in a target space, acquiring second position data indicating a second position actually measured by a method other than the radio wave intensity measurement at the same position in the target space as the radio wave intensity measurement, and outputting information regarding an error in the first position based on a comparison between the first position data and the second position data. [Effects of the Invention]

[0008] According to the present invention, it is possible to obtain more accurate error information regarding errors in position information obtained from radio wave intensity measurements. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an example of the system configuration of an information processing system 1. [Figure 2] FIG. 1 is a diagram illustrating an example of the functional configuration of an information processing system 1. [Figure 3] FIG. 1 is a diagram illustrating an example of a hardware configuration of an information processing device 10. [Figure 4] 4 is a sequence chart illustrating a method for measuring radio wave intensity in the information processing system 1. [Figure 5] FIG. 10 is a diagram illustrating a measurement database 1001. [Figure 6] FIG. 10 is a diagram illustrating self-position estimation using SLAM processing. [Figure 7] 3 is a flowchart illustrating a position error estimation method and a route optimization method in the information processing system 1. [Figure 8] FIG. 10 is a diagram illustrating a map showing a second location. [Figure 9] FIG. 4 is a diagram illustrating an example of an outline of first position data. [Figure 10] FIG. 10 is a diagram illustrating a map showing a first location. [Figure 11] FIG. 10 is a diagram illustrating a first position error estimation method. [Figure 12] FIG. 10 is a diagram illustrating a new route for measuring radio wave intensity. DETAILED DESCRIPTION OF THE INVENTION

[0010] 1. Configuration FIG. 1 is a diagram illustrating the system configuration of an information processing system 1. In this example, the information processing system 1 (or simply referred to as the "system") is a system for measuring the strength of radio waves output from an access point (an example of wireless communication transmission equipment) that performs wireless communication in a target space (hereinafter referred to as the "target space"), such as an indoor facility. Radio wave strength measurement refers to the implementation of a test, experiment, or survey to measure the radio wave strength of radio waves from the wireless communication transmission equipment, i.e., the so-called RSSI (Received Signal Strength Indicator) value. The wireless communication transmission equipment is wireless equipment such as a Wi-Fi access point that is pre-installed in the target space. Radio wave strength measurement is an essential measurement method for collecting radio wave strength samples in indoor position estimation (so-called "indoor positioning") where satellite positioning using GPS (Global Positioning System) or the like does not function adequately. In a typical example, a geographical map (hereinafter referred to as the "radio wave strength map") reflecting the radio wave strength in the target space is created based on the results of the radio wave strength measurement. In indoor positioning, location estimation is performed using radio wave strength, so the accuracy of the radio wave strength map is directly linked to the accuracy of location estimation. Therefore, there is a demand for high measurement accuracy (quality) of the collected samples themselves and for more efficient radio wave strength measurements.

[0011] In recent years, due to the manpower and time required for radio wave intensity measurement, techniques for collecting radio wave information using mobile objects (e.g., robots) moving through the target space have become increasingly popular, replacing fixed-point measurement methods using sensors installed in a grid pattern (lattice or square) in the target space. However, with conventional related technologies, the results of radio wave information collection depend on the robot's movement path, resulting in many locations that cannot be covered and measurement results with inconsistent accuracy. Depending on the results of radio wave intensity measurement, re-measurement may be considered, but improved measurement results cannot be obtained unless the robot's movement path is evaluated or revised. Based on these issues, the information processing system 1 obtains more accurate error information regarding the error in the location information obtained from radio wave intensity measurement. Furthermore, the information processing system 1 optimizes robot control through learning, prioritizing the re-collection of radio wave information from areas with low position estimation accuracy based on the error information.

[0012] The information processing system 1 includes an information processing device 10 and a robot 20. The information processing device 10 is an information processing device or a server device in the information processing system 1. In this example, the information processing device 10 acquires a result of radio wave intensity measurement in a target space from the robot 20. The result of the radio wave intensity measurement includes, for example, numerical data of radio wave intensity for each measurement point (an example of RSSI data). A specific method for performing the radio wave intensity measurement will be described later. The information processing device 10 performs actual position measurement at the same position (measurement point) in the target space S1 as the radio wave intensity measurement using a method other than radio wave intensity measurement. The method other than radio wave intensity measurement is, for example, a method of self-location estimation and environmental map generation using SLAM (Simultaneous Localization and Mapping). In this example, the information processing device 10 acquires image data representing an image captured by the robot 20 at the same position as the radio wave intensity measurement. The image data is an image of the target space S1 captured by a camera (an example of a capturing means) or the like. The image data includes images of the target space S1 captured from various viewpoints. The information processing device 10 performs SLAM processing on the image data to simultaneously estimate the position of the robot 20 and generate an environmental map showing the target space S1. The environmental map of the target space S1 (or simply referred to as "map information") is a 3D environmental map (or a 2D environmental map) generated using image data of the target space S1. The 3D environmental map is obtained, for example, by analyzing and integrating image data captured from multiple viewpoints to create a three-dimensional 3D model. Typical map creation methods include Gaussian Splatting (GS), photogrammetry, and Neural Radiance Fields (NeRF). Based on these techniques, the information processing system 1 obtains highly accurate error information regarding errors in position information obtained from radio wave intensity measurements.

[0013] In this system, data indicating the position of the robot 20 (an example of a first position) estimated based on the results of radio wave intensity measurement in the target space S1 is defined as first position data. The first position is estimated based on a radio wave intensity map for each access point generated from the results of radio wave intensity measurement. The first position includes, for example, position information or coordinate information of the robot 20 in the target space S1. Alternatively, the first position includes relative position information or distance information of the robot 20 with respect to each access point. On the other hand, data indicating the position of the robot 20 estimated by image data of the target space S1 and SLAM processing (an example of a second position) is defined as second position data. The second position is an example of a position actually measured in the target space S1 at the same position as the radio wave intensity measurement but using a method other than radio wave intensity measurement. The second position includes, for example, position information or coordinate information of the robot 20 in the target space S1 (or an environmental map).

[0014] The information processing device 10 acquires information regarding the error of the first position (an example of error information) in response to a comparison between the first position data and the second position data. In this example, the error (also referred to as "error") is an index indicating the degree to which the first position of the robot 20 estimated based on the radio wave intensity measurement deviates from the second position. If the error is large, it is deemed that the collection of radio wave intensity samples through the radio wave intensity measurement is insufficient, and the information processing device 10 must review the movement route traveled by the robot 20. The information processing device 10 repeatedly performs radio wave intensity measurement and evaluates the error (reviews the movement route) until the error of the first position converges to a certain criterion. Ultimately, the information processing device 10 can acquire an optimal route in which the error of the estimated position relatively satisfies the predetermined criterion.

[0015] The robot 20 is a machine or device in the information processing system 1 that measures radio wave intensity in a target space S1. The target space S1 represents a space where radio wave intensity measurement is to be performed. At the time of measurement, a plurality of access points (also simply abbreviated as "AP") 800 are installed in the target space S1 as equipment for wireless communication. The access points 800 (an example of wireless communication transmission equipment 80) are equipment for wireless communication. For example, the access points 800 include wireless access points, wireless routers (modems), wireless LAN (Local Area Network) devices, repeaters, or various wireless terminals. The radio wave intensity measurement is an investigation to measure radio wave intensity at each measurement point along the trajectory traveled by the robot 20 in the target space S1 where these access points 800 are installed.

[0016] In this example, the robot 20 moves (draws a trajectory) along a predetermined or random path in the target space S1 and measures the radio wave intensity at each measurement point. At the same time, the robot 20 captures images of the target space S1 using a camera mounted on the robot. The captured images are used to estimate the robot 20's own position and generate an environmental map showing the target space S1 (details will be described later). The robot 20 transmits various data to the information processing device 10 via the network 9. The robot 20 is composed of various functional elements, and in particular has a moving means, a measuring means, an imaging means, and a communication means for performing the above radio wave intensity measurement. The imaging means includes, for example, a monocular camera (wide-angle camera, fisheye camera, omnidirectional camera), a compound eye camera (stereo camera, multi-camera), or an RGB-D camera (depth camera, ToF camera). The robot 20 may be equipped with at least one of various sensors, particularly a LiDAR (Light Detection and Ranging) or laser device, an autonomous control function using AI or the like, a microphone, and a speaker (audio device).

[0017] 2 is a diagram illustrating an example of the functional configuration of the information processing system 1. In this embodiment, the information processing device 10 has functional blocks (components) including a first acquisition unit 11, a second acquisition unit 12, an output unit 13, an error estimation unit 14, a route determination unit 15, an environmental map generation unit 16, a map generation unit 17, a position estimation unit 18, a storage unit 191, and a control unit 192. In this example, the storage unit 191 stores various data and programs including a database, for example. In this example, the control unit 192 performs various controls.

[0018] The first acquisition unit 11 acquires first position data indicating a first position estimated from the results of radio wave intensity measurement in the target space. The first acquisition unit 11 acquires radio wave intensity for each measurement point from the robot 20. The first acquisition unit 11 instructs the map generation unit 17 to generate a radio wave intensity map in the target space. The map generation unit 17 instructs the position estimation unit 18 to estimate the first position using the radio wave intensity map. The position estimation unit 18 estimates the first position using the radio wave intensity map. The first acquisition unit 11 acquires first position data including the first position from the position estimation unit 18.

[0019] The second acquisition unit 12 acquires second position data indicating a second position actually measured by a method not relying on radio wave intensity measurement at the same position in the target space as the radio wave intensity measurement. In this example, SLAM is used as the method not relying on radio wave intensity. The second position data is position data indicating a position measured by SLAM. The method not relying on radio wave intensity is preferably a method that has higher accuracy in position measurement (or position estimation) than a method relying on radio wave intensity measurement. For example, SLAM processing is processing that simultaneously performs self-position estimation and environmental map generation. The second acquisition unit 12 performs SLAM processing on image data captured by the robot 20. The second acquisition unit 12 acquires the self-position of the robot 20 estimated by the SLAM processing. Furthermore, the second acquisition unit 12 instructs the environmental map generation unit 16 to generate an environmental map indicating the target space. The environmental map generation unit 16 generates the environmental map from the image data. Note that the environmental map (an example of map data) is data created using position data obtained by SLAM.

[0020] The output unit 13 outputs information about the error in the first position in response to a comparison between the first position data and the second position data. The information about the error is, for example, information indicating the magnitude of the error, such as the numerical value of the error itself. The output unit 13 acquires the information about the error in the first position from the error estimation unit 14. The error estimation unit 14 acquires the first position data from the first acquisition unit 11 and the second position data from the second acquisition unit 12.

[0021] The error estimation unit 14 estimates an error in the first position based on a comparison between the first position data and the second position data. The error estimation unit 14 estimates an error in the first position obtained as a result of the radio wave intensity measurement, based on the second position data obtained by performing SLAM processing on the image data. The error estimation unit 14 estimates an error for each measurement point (an example of a first position) included in the first position data.

[0022] The route determination unit 15 determines a new route for measuring radio wave strength in accordance with the error. The new route for measuring radio wave strength is a route for the robot 20 to perform remeasurement. The route determination unit 15 repeatedly changes the route using the results of the new radio wave strength measurement until the error obtained is equal to or less than a predetermined threshold, and determines the optimal route. The threshold is a reference value set for the error of the first position data when the second position data is used as a reference. The larger this error, the less accurate the radio wave strength measurement itself is deemed to be.

[0023] The route determination unit 15 uses machine learning to change the route so as to reduce the error. The machine learning is performed using a machine learning model that has been trained in advance using a data set indicating past measurement results as training data. The machine learning model learns the data set related to route changes and obtains a policy for route changes that efficiently converges the error. The machine learning model outputs a route determined in accordance with this policy. By repeatedly using the machine learning model, the route determination unit 15 can ultimately determine the optimal route that minimizes the error.

[0024] The environmental map generating unit 16 generates an environmental map showing the target space based on the second position data. The map information is a 2D or 3D environmental map generated using image data showing an image of the target space. Alternatively, it may be a 3D virtual space (metaverse) reproduced on a computer in imitation of the target space.

[0025] The environmental map generation unit 16 generates a 3D environmental map using image data representing captured images of the target space. Specifically, the environmental map generation unit 16 estimates measurement points (the position or movement trajectory of the robot 20) using SLAM (Simultaneous Localization and Mapping) processing, for example, based on the image data captured by the robot 20, and constructs a three-dimensional space using GS (Gaussian Splatting) processing. Based on these technologies, the environmental map generation unit 16 can reproduce the target space on a computer based on image data captured from multiple viewpoints.

[0026] Image data is acquired at the same measurement points as the radio wave intensity measurement. The robot 20 stops at the measurement points on the set route and performs radio wave intensity measurement and SLAM processing while stopped. In this example, the robot 20 takes images at each measurement point using, for example, an imaging means and transmits the image data to the information processing device 10. A 3D environmental map is generated by the environmental map generation unit 16 based on the acquired image data.

[0027] The route determination unit 15 determines a route using an environmental map. The route determination unit 15 acquires the environmental map from the environmental map generation unit 16. The route determination unit 15 outputs route data indicating a new route to the robot 20. The route data is, for example, coordinate data in which the coordinates of measurement points are listed in order or map data in which a route is drawn on a map. The robot 20 measures radio wave intensity along the route indicated by the route data.

[0028] The map generation unit 17 generates a radio wave intensity map of the target space obtained from the results of the radio wave intensity measurement. The radio wave intensity map is generated based on the results of the radio wave intensity measurement, i.e., the radio wave intensity measured by the robot 20. The radio wave intensity map includes an environmental map of the target space S1. The first acquisition unit 11 acquires RSSI data from the robot 20 via a network as a result of the radio wave intensity measurement. The RSSI data is numerical data indicating the radio wave intensity of the radio waves. The map generation unit 17 acquires the RSSI data for each measurement point from the first acquisition unit 11.

[0029] The radio wave intensity map may be generated based on the results of radio wave intensity measurements performed along the optimal route. Since the radio wave intensity samples collected along the optimal route have a small error in the estimated location, the information processing device 10 can obtain a radio wave intensity map with higher accuracy.

[0030] The position estimation unit 18 estimates the position from the result of the radio wave intensity measurement. More specifically, the position estimation unit 18 estimates the position of the robot 20 or the wireless communication transmission equipment 80 from the result of the radio wave intensity measurement. As an example, the position estimation unit 18 uses machine learning to estimate the position of the robot 20 or the wireless communication transmission equipment 80. In this example, the position estimation unit 18 performs machine learning using a machine learning model trained using training data including a radio wave intensity map.

[0031] The location may be estimated using a radio wave intensity map generated along the optimal route. Since radio wave intensity samples collected along the optimal route have a small error in the estimated location, the information processing device 10 can perform more accurate location estimation. This location estimation includes estimating the first location of the robot 20.

[0032] FIG. 3 is a diagram illustrating an example of the hardware configuration of an information processing device 10. The information processing device 10 is physically configured as a computer including a processor 101, a memory 102, a storage 103, a communication device 104, an input device (optional), a display device (optional), and a bus connecting these. Each of these devices operates using power supplied from a battery (not shown). In the following description, the term "device" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the information processing device 10 may be configured to include one or more of the devices shown in FIG. 3, or may be configured without including some of the devices. Furthermore, the information processing device 10 may be configured by communicating with multiple devices each having a different housing.

[0033] Each function of the information processing device 10 is realized by loading predetermined software (programs) onto hardware such as the processor 101, memory 102, etc., so that the processor 101 performs calculations, controls communication via the communication device 104, and controls at least one of reading and writing of data in the memory 102 and storage 103.

[0034] The processor 101 controls the entire computer by running, for example, an operating system. The processor 101 may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. Furthermore, for example, a baseband signal processing unit, a call processing unit, etc. may be realized by the processor 101.

[0035] The processor 101 reads programs (program codes), software modules, data, etc. from at least one of the storage 103 and the communication device 104 into the memory 102, and executes various processes in accordance with these. The programs used are those that cause a computer to execute at least some of the operations described below. The functional blocks of the information processing device 10 may be implemented by a control program stored in the memory 102 and running on the processor 101. Various processes may be executed by one processor 101, or may be executed simultaneously or sequentially by two or more processors 101. The processor 101 may be implemented by one or more chips. The programs may be transmitted to the information processing device 10 via a telecommunications line.

[0036] The memory 102 is a computer-readable recording medium and may be configured by, for example, at least one of a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 102 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 102 can store executable programs (program codes), software modules, etc. for implementing the method according to this embodiment.

[0037] Storage 103 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray® disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy disk, a magnetic strip, etc. Storage 103 may also be referred to as an auxiliary storage device.

[0038] The communication device 104 is hardware (transmission / reception device) for performing communication between computers via at least one of a wired network and a wireless network, and is also called, for example, a network device, a network controller, a network card, or a communication module.

[0039] Each device, such as the processor 101 and the memory 102, is connected by a bus for communicating information. The bus may be configured using a single bus, or different buses may be used between each device.

[0040] The information processing device 10 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 101 may be implemented using at least one of these pieces of hardware.

[0041] In this example, the programs stored in the storage 103 include a program for causing a computer to function as a server of the information processing system 1 (hereinafter referred to as a "server program").

[0042] When the processor 101 is executing a server program, the processor 101, memory 102, storage 103, and communication device 104 are examples of functional blocks for operating the information processing device 10. The processor 101 is an example of a first acquisition unit 11, a second acquisition unit 12, an error estimation unit 14, a route determination unit 15, an environmental map generation unit 16, a map generation unit 17, a position estimation unit 18, and a control unit 192. At least one of the memory 102 and the storage 103 is an example of a storage unit 191. The communication device 104 is an example of the first acquisition unit 11, the second acquisition unit 12, and the output unit 13. The configuration of the information processing system 1 has been described above. Next, the operation of the information processing system 1 will be described.

[0043] 2.Operation 2-1.Radio wave intensity measurement Fig. 4 is a sequence chart illustrating a method for measuring radio wave intensity in the information processing system 1. The process in Fig. 4 is started when, for example, a user instructs the robot 20 to start measuring radio wave intensity.

[0044] In step S101, the robot 20 starts moving from an arbitrary position in the target space S1. The robot 20 is autonomously controllable and can move freely within the target space S1. For example, the robot 20 randomly wanders around the target space S1 while avoiding obstacles using various sensors mounted thereon.

[0045] In step S102, the robot 20 receives radio waves from each access point 800 at the measurement point and measures the radio wave intensity. For example, the robot 20 performs the measurement at any frequency (periodically) while moving in the target space S1. The location of the robot 20 at the time of measurement is the measurement point. In this application, the location where the measurement is performed is defined as the "measurement point."

[0046] Simultaneously with the measurement of radio wave intensity, the robot 20 photographs the target space S1 from various viewpoints using a photographing means such as a camera at the same position (measurement point) as the measurement of radio wave intensity. The photographed images are recorded as image data in a form corresponding to the measurement results of radio wave intensity. In this application, the location where the photographs are taken is defined as the "photography point." Hereinafter, the photography point will be distinguished from the measurement point as necessary.

[0047] In step S103, the information processing device 10 acquires various data from the robot 20. The various data include at least RSSI data and image data. In this example, the information processing device 10 acquires the data from the robot 20 via a network or the like. Data communication between the robot 20 and the information processing device 10 may be performed via an access point 800 or the like within the target space S1. Note that the robot 20 may transmit data to the information processing device 10 immediately after measurement or photographing.

[0048] In step S104, the information processing device 10 records various data in a database. Here, the database for managing various data will be described.

[0049] FIG. 5 is a diagram illustrating the measurement database 1001. In this example, the measurement database 1001 includes multiple records. Each record corresponds to a record of each radio wave intensity measurement. Each record includes a measurement ID, a location ID, a timestamp, an AP (access point) ID, radio wave intensity, image data, and a traveled distance (cumulative). The measurement ID and location ID are unique identification information for each radio wave intensity measurement performed by the robot 20 and for each measurement location (and image capture location) in the target space S1. Although the locations (measurement location and image capture location) where radio wave intensity measurement and image capture are performed are basically the same, for convenience of the processing described below, a corresponding location ID is assigned to each location. The timestamp is time information indicating the time when the measurement was performed. The AP (access point) ID is unique identification information for each access point 800 that is the source of the radio waves measured in each measurement. The APID includes, for example, an SSID (Service Set Identifier), particularly a BSSID (Basic Service Set Identifier). The robot 20 uniquely identifies radio waves emitted from the access points 800 installed in the target space S1. This allows the robot 20 to measure the radio wave strength of each access point 800. The radio wave strength is the RSSI value (in dBm units) of each access point 800. The image data is an image taken simultaneously with the measurement. The travel distance (an example of travel information) is the numerical value of the distance accumulated since the robot 20 started moving. Note that the measurement database 1001 may also record information related to the specifications of each access point 800 (for example, power information).

[0050] Returning to FIG. 4, in step S105, the information processing device 10 performs SLAM processing using image data. In this example, SLAM is, for example, Visual SLAM. According to Visual SLAM, self-location estimation of the robot 20 and creation of an environmental map of the target space S1 are simultaneously performed based on image data captured by a camera. This allows the information processing device 10 to acquire trajectory data that depicts the movement history of the robot 20 in the target space S1, that is, the actually measured second position, on a map. The trajectory data includes at least information on the position or coordinates of the measurement point (an example of the second position). Note that the information processing device 10 may only perform self-location estimation of the robot 20 in the SLAM processing. Here, self-location estimation by SLAM processing will be described.

[0051] FIG. 6 is a diagram illustrating self-position estimation using SLAM processing. Map data 2001 is data of an environmental map including the position of the robot 20 during measurement and a second position as a result of movement. FIG. 6 shows a viewpoint viewed perpendicularly from the ceiling to the floor in the target space S1. The robot 20 is an icon of the robot body during movement (measurement). A trajectory OB2 represents the trajectory of movement from when the robot 20 starts moving until a certain time. A point X21 is a measurement point where the robot 20 performed a measurement. Note that the point X21 is drawn as a plot (rectangle) in the figure. Note that the information processing device 10 may generate the map data 2001 based on movement information such as the movement speed, movement distance, or movement direction of the robot 20.

[0052] Returning to FIG. 4, in step S106, the information processing device 10 transmits the second position data to the robot 20. This allows the robot 20 to know its own position. Note that the estimation of its own position (SLAM processing) in step S105 may be performed by the robot 20 itself. Furthermore, the information processing device 10 may output data on the position of the robot 20 and the environmental map to an external device as necessary. This allows a user using the system to know the movement state of the robot 20 in real time.

[0053] The robot 20 changes its movement path in accordance with the acquired second position data. The robot 20, which had been moving randomly, moves so as to acquire a map of the entire target space S1. This allows the information processing device 10 to grasp the entire range of the target space S1. This eliminates local bias in the map data, and reduces errors in the position information obtained by SLAM.

[0054] Finally, the robot 20 utilizes the second position data to return to the position where it started moving (start point). The robot 20 ends the measurement when it returns to the initial position and notifies the information processing device 10 of this.

[0055] As described above, the information processing system 1 can collect RSSI data and image data by using the robot 20. The RSSI data obtained as a result of the radio wave intensity measurement is used to estimate a first position of the robot 20. Furthermore, image data acquired (actually measured) at the same position as the radio wave intensity measurement is used to estimate a second position of the robot 20. The second position data is also used, for example, for the movement of the robot 20. Therefore, it is preferable that the processes of steps S103 to S106 are performed constantly. From the viewpoint of such a processing procedure, it is reasonable for the information processing device 10 to estimate the position of the robot 20 while measuring the radio wave intensity. Next, a position error estimation method and a route optimization method by the information processing device 10 will be described.

[0056] 2-2. Location error estimation method and route optimization method FIG. 7 is a flowchart illustrating a location error estimation method and a route optimization method in the information processing system 1. In step S1, the robot 20 measures radio wave intensity. This corresponds to, for example, the sequence processing in section 2-1. The information processing device 10 starts the following processing when triggered by the completion of the radio wave intensity measurement by the robot 20 described in section 2-1. Note that the following flow represents processing executed mainly by the information processing device 10.

[0057] In step S2, the information processing device 10 acquires the second position from SLAM. This corresponds to, for example, part of the sequence processing in section 2-1. For example, the information processing device 10 acquires the second position based on the processing described in section 2-1. For the sake of repetition, a simplified explanation will be given. In section 2-1, the robot 20 captures an image of the target space S1 using an imaging means at the same position (measurement point) as the radio wave intensity measurement, simultaneously with the radio wave intensity measurement (step S102). The information processing device 10 performs SLAM processing based on the image data acquired from the robot 20, and acquires the second position (step S105). The information processing device 10 acquires the second position upon completion of the radio wave intensity measurement of the robot 20. Here, the second position will be described.

[0058] FIG. 8 is a diagram illustrating a map showing the second position. In this example, map M2 is an example of a map showing an environmental map. In this example, trajectory OB2 represents the trajectory traveled by the robot 20. Point X21 is an object (a rectangular plot) representing one of the measurement points on the trajectory. The configuration of map M2 is basically the same as that of map data 2001 in FIG. 6. For ease of viewing, an icon for the robot 20 is not displayed in the figure. Map M2 is an example of an environmental map representing the target space S1 generated by Visual SLAM or the like. In the present invention, map M2 is drawn from a perspective looking down from the ceiling to the floor of the target space S1 to visualize the trajectory of the robot 20 and the arrangement of objects in the target space S1. Note that the environmental map may be two-dimensional or three-dimensional. For example, the information processing device 10 constructs a three-dimensional space model by GS processing using image data. The GS processing is performed based on the image data and position coordinate data. The position coordinate data may be the same data as the position information estimated by SLAM processing.

[0059] Returning to Fig. 7, in step S3, the information processing device 10 estimates the first position of the robot 20 based on the result of the radio wave intensity measurement by the robot 20. More specifically, the information processing device 10 executes two-stage processing: (a) creating a radio wave intensity map for each access point based on the result of the radio wave intensity measurement, and (b) estimating the first position of the robot 20 using the radio wave intensity map and the actual measured value of the radio wave intensity for each measurement point. Details will be explained below.

[0060] FIG. 9 is a diagram illustrating an example of the outline of the first position data. In this example, FIG. 9 is a schematic diagram illustrating the above-described processes (A) and (B) performed by the information processing device 10. In the first step (A), the information processing device 10 generates a radio wave intensity map of the target space S1 based on the results of radio wave intensity measurement by the robot 20. In this example, the information processing device 10 generates a radio wave intensity map for each access point 800 using RSSI data for each access point 800. The radio wave intensity map includes an environmental map obtained by SLAM processing. The information processing device 10 generates a heat map (an example of a radio wave intensity map) that represents the radio wave intensity for each measurement point using color shading corresponding to the numerical value. The radio wave intensity map includes the estimated position of the corresponding access point 800. For example, the information processing device 10 performs position estimation using a machine learning model (hereinafter referred to as "machine learning model ML1") that learns the correspondence between radio wave intensity and distance from past training data. For example, the machine learning model ML1 includes a machine learning model such as K-nearest neighbors, neural networks (NNs), support vector machines (SVMs), or random forests. Alternatively, the machine learning model ML1 may be configured by a relatively simple algorithm based on triangulation, for example.

[0061] In the second step (a), the information processing device 10 estimates a first position of the robot 20 using a radio wave intensity map and the actual measurement value of the radio wave intensity at each measurement point. In this example, the information processing device 10 can estimate the distance from the access point 800 to the robot 20, which is estimated from multiple radio wave intensity maps. When multiple access points 800 (access point 801, access point 802, access point 803, etc.) are installed in the target space S1, once the distance between each of the multiple access points 800 is determined, the measurement point of the robot 20 can be estimated. By estimating the position of the robot 20 at each measurement point, the information processing device 10 can ultimately obtain trajectory data indicating the first position to which the robot 20 has moved. Here, the first position will be described.

[0062] FIG. 10 is a diagram illustrating a map showing a first position. In this example, map M1 is an example of a map showing an environmental map. Map M1 includes an environmental map obtained by SLAM processing. In this example, trajectory OB1 represents the trajectory traveled by the robot 20. Point X11 is an object (drawn as a "dot") representing one of the measurement points on the trajectory. Here, map M1 includes the positions of multiple access points 800 (e.g., access point 801 and access point 802). In this example, the position of access point 800 on the map is displayed as a distinguishable object (a "star-shaped plot" in the figure). As an example, the information processing device 10 can estimate the distance from the access point 800 to a measurement point (e.g., point X1) according to a procedure such as that shown in FIG. 9. Therefore, by connecting the positions of each measurement point (point X), trajectory OB1 can be obtained as a rough shape as shown in the figure. When considering actual radio wave intensity measurement by the robot 20, the measurement itself is performed at physically discontinuous (discrete) positions. Therefore, the information processing device 10 may acquire the trajectory OB1 by correcting the position of the robot 20 moved between the measurement points. Note that the map M1 is drawn here from a viewpoint looking down from the ceiling to the floor of the target space S1.

[0063] Returning to FIG. 7, in step S4, the information processing device 10 compares the first position data with the second position data and estimates the error of the first position. The first position is merely an estimate of the position based on the random trajectory of the robot 20. Therefore, the error of the first position tends to be larger when compared to the second position, which has higher accuracy. Possible causes of the error include a small number of measurement samples, low measurement density, or reduced accuracy due to the physical characteristics of radio waves. In contrast, the second position is the result of position estimation based on SLAM and environmental map creation. Therefore, the second position data is data that reflects the actual environment and position information of the target space S1 with relatively high accuracy. The information processing device 10 estimates the error in the first position data when the information of the second position data is used as the reference (true) data.

[0064] The basic processing is performed as follows: The information processing device 10 identifies a target measurement point from among multiple measurement points in the second position data. The information processing device 10 references the measurement database 1001 and reads out the first position data for that measurement point. The information processing device 10 calculates the geographical distance between the first position and the second position from these data. This distance is "information related to the error." The information processing device 10 repeatedly performs this calculation for all measurement points included in the measurement database 1001. Here, a model that visualizes the error estimation will be described.

[0065] FIG. 11 is a diagram illustrating a method for estimating a first position error. In this example, map M3 is a map that visualizes a comparison between first position data and second position data. For example, map M3 is based on the environmental map of map M2. Here, for ease of viewing, map M3 overlays the starting point of the second position (point X21) on map M2 with the starting point of the first position (point X11). In practice, map M3 does not need to be generated; it is sufficient to compare the first position and the second position (i.e., calculate the distance) on the data of the information processing device 10. In this example, the starting points of each piece of data are overlaid on the map, and areas with large errors in the first position are illustrated. Areas T1 and T2 are areas that visually extract areas where there is a large error in the first position relative to the second position. In the figure, area T is hatched. The information processing device 10 acquires information about the error in the first position based on the comparison between the first position data and the second position data. In this example, the information about the error is the difference in distance or coordinate between the first position and the second position for each measurement point (point X).

[0066] As a result, the information processing device 10 can obtain improved (i.e., highly accurate and reliable) error information regarding the error of the location information obtained from the radio wave intensity measurement based on the comparison between the first location data and the second location data. This allows the information processing system 1 to monitor (evaluate) the location estimation accuracy for each radio wave intensity measurement.

[0067] Returning to FIG. 7, in step S5, the information processing device 10 determines whether the error of the first position obtained from the map M3 satisfies a convergence condition. The convergence condition is, for example, a condition that the distance (an example of an error) of the first position relative to the second position is equal to or less than a threshold value for all measurement points. If the convergence condition is satisfied (step S5: YES), the information processing device 10 proceeds to step S6.

[0068] In step S6, the information processing device 10 determines the trajectory (i.e., the first position data) obtained by the movement of the robot 20 as the optimal route. The optimal route is the route with the most accurate position information obtained by measuring radio wave intensity alone. This means that radio wave intensity information has been collected so as to sufficiently cover areas in the target space S1 where positioning accuracy is low. Therefore, the radio wave intensity map obtained from the results of the radio wave intensity measurement by the robot 20 is a highly accurate map. The information processing device 10 does not need to collect any more radio wave intensity information by the robot 20. The information processing device 10 associates the first data representing the optimal route, the radio wave intensity information for each measurement point, the obtained radio wave intensity map, etc., and records them in a database (and then ends the process).

[0069] On the other hand, if the convergence condition is not satisfied (step S5: NO), that is, if there is even one measurement point where the error in the first position exceeds the threshold, the information processing device 10 advances the process to step S7.

[0070] In step S7, the information processing device 10 determines a new route for measuring radio wave intensity. Specifically, the information processing device 10 resets a route for the robot 20 to move preferentially through the area surrounding the measurement point where the error in the first position is large. The "surrounding area" refers to an area that satisfies a predetermined condition and is determined based on a second position corresponding to the first position determined to have a large error. The predetermined condition is, for example, that the area is within a predetermined distance from the second position. Alternatively, the predetermined condition is, for example, that the area is within an ellipse that includes all of the consecutive second positions with large errors. "Moving preferentially" means that the density of measurement points within the area is higher than outside the area.

[0071] One of the effects of resetting the route is expected to be improved accuracy of the measurement samples. By re-measuring the area (such as area T) around a measurement point with a large error in a series of measurements, the density of measurement points increases, thereby improving the accuracy of the measurement samples in that area. Basically, the more frequent the measurements, the easier it is to improve the sample accuracy in that area. However, since there is not enough time to measure the entire area, re-measurements are focused on the area around the measurement point where the accuracy in the initial measurement is thought to be low (i.e., the error is large). As a result, the measurement density in that area increases, and it is expected that the measurement accuracy will be improved compared to the previous measurement. Note that simply re-measuring the same measurement point (one point) is not sufficient; it is preferable to set multiple new measurement points in an area of ​​a certain size around that point (an area that was not a measurement point the previous time). Based on this perspective, the information processing device 10 resets the route.

[0072] 11 again, in map M3, the areas where the error in the first position is large are areas T1 and T2. Therefore, the information processing device 10 resets a new route for measuring radio wave intensity that densely covers at least areas T1 and T2. Here, the new route for measuring radio wave intensity will be described.

[0073] FIG. 12 is a diagram illustrating a new route for measuring radio wave strength. In this example, map M4 is an example of an environmental map showing a new route for measuring radio wave strength by the robot 20. The map M4 is based on the environmental map obtained by SLAM. Route R1 is a new, reset route for measuring radio wave strength. Route R1 is set as a route that preferentially includes the peripheries of areas T1 and T2, where the error in the first position was large last time. As an example, changing the movement method of the robot 20 can be considered to measure a specific area densely. In the figure, the robot 20 performs measurements while moving in a zigzag pattern within area T1 and while moving in a circular pattern within area T2. This increases the movement distance within the area, i.e., increases the density of measurement points. The route change includes such a change in the movement method. The information processing device 10 performs the route change using a machine learning model or the like. Specifically, the information processing device 10 performs the route change using a machine learning model (hereinafter referred to as the "machine learning model ML2") that learns routes that reduce errors from past training data. As the training data, for example, training data is used in which the shape and size of the surrounding area set for a measurement point determined to have a large error, as well as the placement and number of new measurement points within the surrounding area, are used as explanatory variables, and the error is used as the target variable.

[0074] Returning to FIG. 7, the information processing device 10 returns the process to step S1. In step S1, the information processing device 10 instructs the robot 20 to measure radio wave intensity along a new route. When issuing the instruction, the information processing device 10 outputs route information (map M4) to the robot 20. The robot 20 refers to the map M4. The robot 20 identifies its own position on the map M4 and then measures radio wave intensity again. In this case, it is preferable that the robot 20 measures radio wave intensity from the same starting point as the previous time. The information processing system 1 repeats the processes from step S1 to step S5 until the error becomes equal to or less than the threshold. In this example, the information processing device 10 measures radio wave intensity while repeatedly changing the route until the error becomes equal to or less than the threshold. Through the above flow, the machine learning model ML2 learns, by reinforcement learning, a route setting policy that converges the error more efficiently.

[0075] In step S7, the information processing device 10 may reset a route that preferentially includes areas of the target space S1 that have not yet been covered by the collection of actual measurement data through radio wave intensity measurements. In this case, the information processing device 10 may bias, for example, by setting a reward for locations where radio wave intensity measurements have not yet been performed (or where there is little radio wave intensity measurement). In this example, the information processing device 10 sets a reward term (an example of a coefficient) for setting a route to an unmeasured area in the target space S1. The information processing device 10 resets the route depending on the magnitude of the coefficient. This allows the information processing device 10 to identify areas with large coefficients and perform a search in the unmeasured area.

[0076] As a result, the information processing device 10 can determine an optimal route that reduces position estimation errors in the target space S1. Furthermore, the information processing device 10 can improve the performance of a machine learning model (for example, machine learning model ML2) used for route changes. When measuring radio wave intensity in various spaces, the information processing device 10 can use the machine learning model ML2, whose performance has been improved, to determine an optimal route. The information processing system 1 can collect radio wave information more efficiently.

[0077] 3. Variations The present invention is not limited to the above-described embodiment, and various modifications are possible. Some modifications will be described below. Two or more of the following features may be combined and applied.

[0078] (1) Information Processing System 1 The hardware configuration and network configuration of the information processing system 1 are not limited to those exemplified in the embodiment. The information processing system 1 may have any hardware configuration and network configuration as long as the required functions can be realized. For example, multiple devices may physically cooperate to function as the information processing system 1. For example, the information processing system 1 may include a terminal of a user (hereinafter referred to as a "user terminal") using the target space S1 or a receiver installed in the target space S1. The user terminal (e.g., a smartphone) and the receiver measure the radio wave intensity (RSSI) of the radio waves emitted by the wireless communication transmission equipment 80. The information processing device 10 acquires RSSI data from the user terminal and the receiver. The information processing device 10 may acquire first position data based on the acquired data. The user terminal acquires image data of the target space S1 and transmits it to the information processing device 10. The information processing device 10 may acquire second position data based on this image data.

[0079] (2) Information processing device 10 The correspondence between the functional elements of the information processing device 10 and the hardware is not limited to that exemplified in the embodiments. For example, in the embodiments, at least some of the functions described as being implemented in the information processing device 10 may be implemented in another device or system, and conversely, at least some of the functions described as being implemented in another device or system may be implemented in the information processing device 10. For example, the robot 20 may perform processing performed by the information processing device 10. The robot 20 may perform SLAM processing using image data. The robot 20 may acquire first position data and second position data using map data obtained from SLAM processing and the results of radio wave intensity measurement.

[0080] (3) Robot 20 The robot 20 is not limited to the example shown in the embodiment. The robot 20 may have any hardware configuration as long as it can realize the required functions and operations. The robot 20 may have any measurement means. For example, the robot 20 may measure the radio wave intensity of a smart device (e.g., a smart home appliance or a smart speaker) in addition to the access point 800. In this case, the robot 20 may perform measurements according to wireless communication standards other than Wi-Fi, such as Bluetooth, Zigbee, or Matter. Any communication standard may be used for the measurement. Note that the smart device to be measured is preferably a device fixed to the target space (e.g., a smart light bulb or a smart lock). The robot 20 may have any imaging means. The imaging means may be, for example, an analog camera, a stereo camera, a depth camera (sensor), a thermography camera, a motion camera (sensor), a network (IP) camera, a cloud camera, or an infrared camera. Furthermore, the data used for estimating the position of the robot 20 and creating an environmental map does not have to be image data, and may be, for example, point cloud data obtained from a LiDAR.

[0081] (4) Wireless communication transmission equipment 80 (access point 800) The wireless communication transmission equipment 80 is not limited to the example shown in the embodiment. The wireless communication transmission equipment 80 may have any hardware configuration as long as it can realize the required functions and operations. The wireless communication transmission equipment 80 may be a wireless communication base station or the like. The wireless communication transmission equipment 80 may be a small cell, microcell, picocell (nanocell), femtocell, or the like installed indoors. The wireless communication transmission equipment 80 may have a function to connect with the information processing device 10 and the robot 20 via wireless communication.

[0082] (5) Radio wave intensity measurement The sequence chart shown in FIG. 4 merely illustrates one example of the operations, and the radio wave intensity measurement method in the information processing system 1 is not limited to this. Some of the illustrated operations may be changed or omitted, the order may be changed, or new operations may be added. In step S102, the robot 20 may acquire any data. In addition to image data, the robot 20 may acquire point cloud data from LiDAR or distance data from a depth camera. In step S102, the robot 20 basically performs measurement and photography at the same height relative to the floor of the target space S1, but the height of the measurement means and photography means may be changed to increase the amount of data. In step S105, the information processing device 10 may perform Visual SLAM, LiDAR SLAM, Depth SLAM, or the like.

[0083] (6) Location error estimation method and route optimization method The flowchart shown in FIG. 7 merely illustrates an example of the operation, and the position error estimation method and route optimization method in the information processing system 1 are not limited thereto. Some of the illustrated operations may be changed or omitted, the order may be changed, or new operations may be added. In step S3, the information processing device 10 may generate a radio wave intensity map including position information of the target space S1 or the robot 20. The information processing device 10 may generate a radio wave intensity map integrated for multiple access points 800, rather than for each access point 800. The information processing device 10 may acquire first position data using these radio wave intensity maps. Regarding the acquisition of the first position data, the machine learning model ML1 may have a function to accept input of the radio wave intensity for each measurement point and the radio wave intensity map as explanatory variables. Furthermore, the machine learning model ML1 may have a function to output first position data reflecting the position of the robot 20 as a target variable. In other words, the two-stage processing (a) and (b) described in the embodiment may be integrated by the machine learning model ML1.

[0084] In step S4, the information processing device 10 may estimate the error in any manner. As another example, the information processing device 10 may acquire the map M3 by superimposing trajectories using a machine learning model or the like. Specifically, the information processing device 10 superimposes trajectories using a machine learning model (hereinafter referred to as "machine learning model ML3") that learns the matching rate of feature amounts of trajectory data (first position data and second position data) from past training data. The machine learning model ML3 attempts to superimpose trajectories with reference to the general shapes of the trajectories, etc. The machine learning model ML3 may identify the superimposition position at which the distance between points X is smallest among multiple measurement points included in the trajectories. The information processing device 10 may perform such trajectory superimposition processing to estimate the error.

[0085] (7) Database The databases or data of the information processing system 1 shown in Figures 5, 6, 8, and 10 to 12 are not limited to those exemplified in the embodiments. In this example, any data may be recorded in the database. For example, the measurement database 1001 may include movement information of the robot 20. The map data 2001 may include coordinate information and time information of measurement points. The first position data and the second position data may be a 3D environmental map or a 2D environmental map.

[0086] (8) Methods that do not rely on radio wave intensity measurements The method not relying on radio wave intensity measurement is not limited to the one exemplified in the embodiment. The method not relying on radio wave intensity measurement may be a method of actually measuring the second position (obtaining second position data) using various sensors. The second position data preferably has position information with higher accuracy than radio wave intensity measurement, and may be any data that can be used as a comparison standard to estimate the error in determining the first position.

[0087] (9) Other The various programs executed by processor 101 may be provided by downloading via a network such as the Internet, or may be provided in a state recorded on a computer-readable non-transitory recording medium such as a DVD-ROM. Each processor may be, for example, a CPU, an MPU (Micro Processing Unit), or a GPU (Graphics Processing Unit).

[0088] The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wires, wirelessly, etc.) and these multiple devices. The functional block may also be realized by combining the single device or multiple devices with software.

[0089] Functions include, but are not limited to, judgment, determination, assessment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, election, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0090] For example, the information processing device 10 according to an embodiment of the present disclosure may function as a computer that performs the processing of the present disclosure.

[0091] Each aspect / embodiment described in the present disclosure may be applied to at least one of systems using LTE (Long Term Evolution), LTE-Advanced (LTE-A), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), FRA (Future Radio Access), NR (New Radio), W-CDMA (registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark), IEEE 802.20, UWB (Ultra-Wideband), Bluetooth (registered trademark), or other appropriate systems, and next-generation systems extended based on these. Furthermore, a combination of multiple systems (e.g., a combination of at least one of LTE and LTE-A with 5G) may also be applied.

[0092] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0093] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be sent to another device.

[0094] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0095] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0096] Software, whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise, shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc. Additionally, software, instructions, information, etc. may be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then such wired and / or wireless technologies are included within the definition of a transmission medium.

[0097] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof. Note that terms described in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings.

[0098] Furthermore, the information, parameters, etc. described in this disclosure may be expressed using absolute values, may be expressed using relative values ​​from a predetermined value, or may be expressed using other corresponding information.

[0099] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0100] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must in some way precede the second element.

[0101] The "unit" in the configuration of each of the above devices may be replaced with "means," "circuit," "device," or the like.

[0102] When used in this disclosure, the terms "include," "including," and variations thereof are intended to be inclusive, similar to the term "comprising." Furthermore, when used in this disclosure, the term "or" is not intended to be an exclusive or.

[0103] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0104] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different." [Explanation of symbols]

[0105] 1...information processing system, 10...information processing device, 20...robot, 11...first acquisition unit, 12...second acquisition unit, 13...output unit, 14...error estimation unit, 15...route determination unit, 16...environmental map generation unit, 17...map generation unit, 18...position estimation unit, 191...storage unit, 192...control unit, 101...processor, 102...memory, 103...storage, 104...communication device, 1001...measurement database, 2001...map data, 80...wireless communication transmission equipment, 800, 801, 802, 803...access points, 9...network

Claims

1. a first acquisition unit that acquires first position data indicating a first position estimated based on a result of measuring radio wave intensity in a target space; a second acquisition unit that acquires second position data indicating a second position actually measured by a method other than the radio wave intensity measurement at the same position in the target space as the radio wave intensity measurement; an output unit that outputs information about an error in the first position in response to a comparison between the first position data and the second position data; An information processing device having the above.

2. a route determination unit that determines a new route for measuring radio wave intensity in accordance with the error; The information processing device according to claim 1 ,

3. The route determination unit repeats route changes until the error obtained using the new radio wave intensity measurement result becomes equal to or less than a predetermined threshold, and determines an optimal route. The information processing device according to claim 2 .

4. The route determination unit changes the route so as to reduce the error using machine learning. The information processing device according to claim 3 .

5. an environmental map generation unit that generates an environmental map showing the target space based on the second position data; The route determination unit determines the route using the environmental map. The information processing device according to claim 2 .

6. a map generation unit that generates a radio wave intensity map in the target space obtained from the results of the radio wave intensity measurement; The information processing device according to claim 1 ,

7. a position estimation unit that estimates a position from the result of the radio wave intensity measurement; The information processing device according to claim 6 , further comprising:

8. a map generation unit that generates a radio wave intensity map in the target space obtained from the result of the radio wave intensity measurement; The radio wave strength map is generated based on the results of radio wave strength measurements performed on the optimal route. The information processing device according to claim 3 .

9. a position estimation unit that estimates a position from the result of the radio wave intensity measurement; The location is estimated using the radio wave intensity map generated along the optimal route. The information processing device according to claim 8 .

10. acquiring first position data indicating a first position estimated based on a result of measuring radio wave intensity in a target space; acquiring second position data indicating a second position actually measured by a method other than the radio wave intensity measurement at the same position in the target space as the radio wave intensity measurement; outputting information relating to an error in the first position in response to a comparison between the first position data and the second position data; An information processing method comprising:

Images