Information processing device, system, and program

Abstract

To provide an information processing device, a system, and a program that are useful for efficiently controlling a moving object.SOLUTION: An information processing device according to an embodiment includes first acquisition means, second acquisition means, and setting means. The first acquisition means acquires a first reception power on a path of a moving object passing between a signal radiation source and a radio wave shielding object based on radio waves emitted from the signal radiation source in a status where the radio wave shielding object that shields the radio wave is located at a first position. The second acquisition means acquires a second reception power that is a radio wave radiated from the signal radiation source measured on the path in a status where the radio wave shielding object is not located at the first position. The setting means sets an area of a part of the path as a target area to be used for processing related to the control of the moving object based on an index related to the fluctuation between the first and second reception powers.SELECTED DRAWING: Figure 6

Description

Technical Field

[0001] Embodiments of the present invention relate to an information processing apparatus, a system, and a program.

Background Art

[0002] In recent years, for example, it is known to control a moving body (e.g., a mobile robot, etc.) that moves within a predetermined space by executing wireless communication. In this case, the moving body is controlled to move along a path from a start point to a goal point set on a map of the space in which the moving body moves, based on a control signal for controlling the moving body.

[0003] By the way, the above-described control signal is radiated as radio waves from an antenna (signal radiation source). However, when an object that shields the radio waves (hereinafter referred to as a radio wave shielding body) is disposed within the space in which the moving body moves, a dead zone where the received power decreases occurs at a position facing the antenna across the radio wave shielding body (that is, a zone on the back side of the radio wave shielding body as viewed from the antenna). In such a case, a path that avoids the dead zone can be selected, and the moving body can be moved along the path.

[0004] Here, when the above-described radio wave shielding body is removed, the dead zone is eliminated, so the moving body does not need to avoid the zone. However, unless the elimination of the dead zone (that is, the presence or absence of the radio wave shielding body) is grasped, the moving body cannot be efficiently controlled.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] Therefore, an object of the present invention is to provide an information processing apparatus, a system, and a program that are useful for efficiently controlling a moving object.

Means for Solving the Problems

[0007] The information processing apparatus according to the embodiment includes a first acquisition unit, a second acquisition unit, and a setting unit. The first acquisition unit acquires first received power on the path of a moving object passing between the signal radiation source and the radio wave shielding body based on the radio wave radiated from the signal radiation source in a state where a radio wave shielding body that shields radio waves is disposed at a first position. The second acquisition unit acquires second received power, which is the radio wave radiated from the signal radiation source measured on the path, in a state where the radio wave shielding body is not disposed at the first position. The setting unit sets a partial area on the path as a target area to be used for processing related to the control of the moving object based on an index related to the variation between the first received power and the second received power.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Figure 20

Figure 21

Figure 22

Embodiments for Carrying Out the Invention

[0009] Hereinafter, embodiments will be described with reference to the drawings. The information processing apparatus according to the present embodiment is used to control a moving object (mobile robot) that moves within a predetermined space (hereinafter referred to as a target space) such as a factory or a warehouse.

[0010] First, a scenario to which the information processing apparatus according to the present embodiment is applied will be described. When a moving object moves linearly along a passage in a target space, the control for the moving object may be simple. However, for example, when the passage arranged in the target space is curved or when the moving object needs to avoid an object arranged in the target space, more advanced control is required.

[0011] By the way, when such control for a moving object is performed by wire (that is, a control signal for controlling the moving object is transmitted by wire), there are problems such as the range in which the moving object can move being limited, the control of the moving object becoming impossible due to disconnection, and the wiring work being complicated. In particular, when a large number of moving objects move in the target space, these problems become prominent.

[0012] On the other hand, when the control for the moving object is performed wirelessly (that is, the moving object is wirelessly controlled), the above-described problems can be solved. For such wireless control of a moving object, for example, local 5G can be used. Local 5G is, for example, a 5G network that can be individually used by companies and the like, and since it can achieve high speed, low latency, and a large number of simultaneous connections, it is useful in an environment where a large number of moving objects moving in the target space are wirelessly controlled. Note that it is also possible to use a wireless LAN for wireless control of a moving object.

[0013] Here, the above-described mobile bodies can be broadly classified into those that operate autonomously and those that operate based on commands (control signals) from the outside. Autonomous mobile bodies are useful because each of them can determine the situation and operate accordingly, but they are costly and difficult to apply when a large number of mobile bodies are arranged in the target space. On the other hand, for mobile bodies that operate based on commands from the outside as described above, by aggregating the function of controlling a large number of mobile bodies in one device (for example, an information processing device), the total cost of a system including mobile bodies and information processing devices, etc. can be reduced. In addition, since information on a large number of mobile bodies moving within the target space can be managed collectively, the management of these mobile bodies is relatively easy. Note that the ability to grasp information on a large number of mobile bodies collectively also has advantages from the perspective of optimizing the movement of the entire mobile body.

[0014] Hereinafter, as shown in FIG. 1, it is assumed that a local 5G system (cellular system) that controls the terminal side on the base station side is applied to this embodiment.

[0015] In the example shown in FIG. 1, a situation is assumed in which a plurality of mobile bodies 1 move within the target space. Each of the plurality of mobile bodies 1 is equipped with a radio (such as a mobile terminal) and is communicably connected to the base station 2. Further, an information processing device 3 is connected to the base station 2, and a control signal for controlling the mobile body 1 generated by the information processing device 3 is transmitted from the base station 2 (antenna installed therein) to the mobile body 1. That is, it can be said that the mobile body 1 is communicably connected to the information processing device 3 via the base station 2. Thereby, the mobile body 1 can move within the target space based on the control signal generated in the information processing device 3.

[0016] In addition, in FIG. 1, it is assumed that the moving body 1 is an autonomous mobile robot (AMR), and the information processing device 3 is a server device called, for example, mobile edge computing (MEC). The information processing device 3 may be a server device that provides cloud computing services.

[0017] Here, assume a case where the moving body 1 is controlled to move within the target space shown in FIG. 2. Here, for example, in order to carry (transport) a load such as a cardboard box, consider a situation where the moving body 1 moves from the start point 1b to the goal point 1c along the passage (for example, the running path provided in a factory or a warehouse) 1a within the target space. The moving body may perform operations other than carrying the load from the start point 1b to the goal point 1c.

[0018] In this case, as the path for moving from the start point 1b to the goal point 1c, there are a path 1d corresponding to the shortest path, a path 1e corresponding to the longest path, and a path 1f corresponding to an intermediate path with respect to the shortest path and the longest path.

[0019] According to the target space shown in FIG. 2 described above, by selecting the path 1d (that is, the shortest path) from among the paths 1d to 1f, the moving body 1 can be controlled to move efficiently from the start point 1b to the goal point 1c. The control signal for controlling the moving body 1 in this way is radiated from, for example, the antenna 2a (signal radiation source) installed in the base station 2 to the moving body 1. The antenna 2a is arranged, for example, within the target space. Here, although it has been described that the moving body 1 moves from the start point 1b to the goal point 1c to carry the load, such load carrying is not only once. After the moving body 1 has carried the load from the start point 1b to the goal point 1c, it returns to the start point 1b again and repeats the operation of carrying another load from the start point 1b to the goal point 1c. Also, there may be a plurality of moving bodies 1 that carry the load from the start point 1b to the goal point 1c.

[0020] Here, when the target space where the mobile body 1 moves is, for example, a factory or a warehouse, it is assumed that the arrangement of obstacles (such as cardboard boxes carried by the mobile body 1) in the target space changes over time. Here, as described above, for example, in a situation where the mobile body 1 repeatedly transports luggage from the start point 1b shown in FIG. 2 to the goal point 1c (for example, a plurality of mobile bodies 1 sequentially move along a defined route), it is assumed that an obstacle 1g is arranged in the target space as shown on the left side of FIG. 3.

[0021] When a signal (such as a control signal) is radiated by radio waves from the antenna 2a, if this obstacle 1g is a radio wave shielding body (for example, a cardboard box in which an object that shields radio waves such as metal is packed), the radio waves radiated from the antenna 2a are shielded by the obstacle 1g. Therefore, the state regarding radio wave shielding in the zone 1h facing the antenna 2a across the obstacle 1g (hereinafter referred to as the radio wave propagation environment) deteriorates. In this case, the zone 1h corresponds to a dead zone where the received power has decreased.

[0022] In the example shown in FIG. 3, the zone (that is, the dead zone) 1h where the radio wave propagation environment has deteriorated overlaps with the route 1d. Therefore, when the mobile body 1 moves along the route 1d, the mobile body 1 may not be able to receive the control signal normally in the zone 1h. That is, the obstacle 1g arranged in the target space as described above becomes a factor that hinders the efficient movement (control) of the mobile body 1.

[0023] When the zone 1h is a dead zone in this way, as shown on the right side of FIG. 3, for example, by changing the route 1d to the route 1f (intermediate route), the mobile body 1 can be controlled to avoid the dead zone.

[0024] By the way, in a situation where a plurality of moving bodies 1 repeatedly carry luggage along the path 1f changed from the path 1d (that is, a plurality of moving bodies 1 repeatedly circle between the start point 1b and the goal point 1c), when an obstacle 1g arranged in the target space is removed as time passes, the radio wave propagation environment (deterioration) in the zone 1h is improved and the dead zone is eliminated. In this case, it is preferable to grasp the elimination of the dead zone and change the path along which the moving body 1 moves from the path 1f to the path 1d again (that is, select the path 1d again as an appropriate path for the moving body 1).

[0025] Here, a method for grasping the elimination of the dead zone in the comparative example of the present embodiment will be described.

[0026] First, at an arbitrary timing when the moving body 1 repeatedly carries luggage along the path 1f, the moving body 1 is controlled to move along the path 1d, and a synchronization signal is radiated from the antenna 2a (base station 2) when the moving body 1 passes through the zone 1h. The moving body 1 measures the reception power of the synchronization signal by receiving the synchronization signal radiated from the antenna 2a.

[0027] In the comparative example of the present embodiment, as described above, if the reception power measured in the zone 1h is equal to or greater than the threshold value, it can be grasped that the dead zone has been eliminated (that is, the radio wave propagation environment in the zone 1h has been improved). On the other hand, if the reception power measured in the zone 1h is less than the threshold value, it can be grasped that the dead zone has not been eliminated.

[0028] However, if the moving body 1 is moved to the area 1h while the dead zone has not been eliminated (that is, the obstacle 1g has not been removed), the moving body 1 may not be able to appropriately receive the control signal in the area 1h and may not operate normally (for example, the operation may stop). In this case, it will take time until the normal operation of the moving body 1 resumes, and it cannot be said that the elimination of the dead zone can be appropriately grasped and the moving body 1 can be efficiently controlled. Furthermore, moving through the dead zone may be a factor leading to the occurrence of accidents such as being unable to appropriately receive the control signal (that is, instructions such as changing the moving speed and direction).

[0029] Also, for example, by utilizing the reflection of the laser irradiated from the moving body 1, it is conceivable to directly detect the presence or absence of the obstacle 1g without moving the moving body 1 to the above-described area 1h.

[0030] Here, in a situation where the moving body 1 moves within a target space such as a factory or a warehouse as described above, for example, an obstacle 1g such as a plurality of cardboard boxes for packing a radio wave shielding body stacked in the height direction (that is, loaded) may be arranged, and the height of the obstacle 1g changes when the cardboard box is removed or further stacked. It is considered that the radio wave propagation environment in the area facing the antenna 2a with the obstacle 1g in between depends on the height of the obstacle 1g. Specifically, for example, in the case of the obstacle 1g with a large number of cardboard boxes stacked in the height direction as shown on the left side of FIG. 4, a dead zone is generated by the obstacle 1g, but when the number of cardboard boxes of the obstacle 1g is decreased as shown on the right side of FIG. 4, the influence by the obstacle 1g becomes small and there is a possibility that the dead zone has been eliminated.

[0031] However, according to the straightness of the laser beam emitted from the moving body 1 as described above, it is difficult to grasp the height direction of the obstacle 1g, and it is impossible to grasp the elimination of the dead zone considering the height direction of the obstacle 1g. Although it is conceivable to apply a mechanism capable of grasping the height direction to the moving body 1, in the case of controlling a plurality of moving bodies 1, the cost of constructing the system becomes high.

[0032] Furthermore, when the obstacle 1g that is a radio wave shielding body is replaced with an obstacle that is not a radio wave shielding body, the dead zone may be eliminated even if the obstacle is arranged.

[0033] That is, even if the presence or absence of an obstacle is detected by using the reflection of the laser beam emitted from the moving body 1, there may be a case where the elimination of the dead zone cannot be appropriately grasped based on the detection result.

[0034] Therefore, in the present embodiment, a movement control system capable of efficiently controlling the moving body 1 (that is, grasping the elimination of the dead zone and selecting an appropriate route) while avoiding a situation where the moving body 1 cannot operate normally by moving through the dead zone will be described. Specifically, in the present embodiment, in order to realize efficient control of the moving body 1, it is assumed that the radio wave propagation environment in a target area such as a dead zone (that is, the presence or absence of a radio wave shielding body in the space where the moving body 1 moves) is estimated.

[0035] As shown in FIG. 1 described above, the movement control system according to the present embodiment includes a moving body 1 (for example, an AMR), a base station 2 (antenna 2a), and an information processing device 3 (for example, an MEC) that is communicably connected to the moving body 1 via the base station 2.

[0036] First, with reference to FIG. 5, an example of the functional configuration of the moving body 1 will be described. As shown in FIG. 5, the moving body 1 includes a receiving unit 11, a control unit 12, a distance measuring unit 13, a received power measuring unit 14, and a transmitting unit 15.

[0037] The receiving unit 11 receives a control signal for controlling the mobile body 1. The control signal received by the receiving unit 11 is output to the control unit 12. Also, the receiving unit 11 receives a synchronization signal for measuring the received power described later. The synchronization signal received by the receiving unit 11 is output to the received power measurement unit 14. Note that the control signal and the synchronization signal are radiated from the antenna 2a installed in the base station 2 to the mobile body 1.

[0038] The control unit 12 controls the mobile body 1 based on the control signal output from the receiving unit 11. The mobile body 1 is provided with wheels or the like for moving the mobile body 1, and the control unit 12 controls the rotation speed and direction of the wheels (that is, the moving speed and direction of the mobile body 1) according to the control signal to move the mobile body 1. The moving speed and direction of the mobile body 1 controlled by the control unit 12 are output to the distance measurement unit 13.

[0039] The distance measurement unit 13 is realized by, for example, an optical distance sensor (LRF: Laser Range Finder), and measures the distance from the mobile body 1 to a wall or an obstacle existing around the mobile body 1 based on the time (TOF: Time Of Flight) until the laser (light) irradiated from the LRF is reflected. The distance (LRF scan data indicating the distance) measured by the distance measurement unit 13 in this way and the moving speed and direction (data indicating the moving speed and direction) of the mobile body 1 output from the control unit 12 are output to the transmission unit 15 as data for creating map data described later (hereinafter referred to as map creation data).

[0040] The received power measurement unit 14 measures the received power (radio wave intensity) of the synchronization signal based on the synchronization signal output from the receiving unit 11. The received power data indicating the received power measured by the received power measurement unit 14 is transmitted to the transmission unit 15.

[0041] The transmission unit 15 transmits the map creation data output from the distance measurement unit 13 to the information processing device 3. Also, the transmission unit 15 transmits the received power data output from the received power measurement unit 14 to the information processing device 3.

[0042] Next, with reference to FIG. 6, an example of the functional configuration of the information processing apparatus 3 will be described. The information processing apparatus 3 according to the present embodiment is configured to acquire data from the mobile body 1 side via the base station 2 described above and instruct the mobile body 1 of the route (travel route) along which the mobile body 1 moves.

[0043] In the present embodiment, it is assumed that the information processing apparatus 3 is a MEC. However, the information processing apparatus 3 may be realized as a server device or the like disposed remotely from the base station 2 via a network, or may be realized as a local controller or the like directly connected to the base station 2.

[0044] As shown in FIG. 6, the information processing apparatus 3 includes a processing unit 31 and a storage unit 32. Further, the processing unit 31 includes an acquisition unit 31a, a map data creation unit 31b, a received power map creation unit 31c, a setting unit 31d, a calculation unit 31e, an estimation unit 31f, a control unit 31g, and an output unit 31h.

[0045] The map creation data and the received power data transmitted by the transmission unit 15 included in the mobile body 1 described above are acquired from the base station 2 for the map creation data and the received power data received by the base station 2. The map creation data acquired by the acquisition unit 31a is output to the map data creation unit 31b and the received power map creation unit 31c. The received power data acquired by the acquisition unit 31a is output to the received power map creation unit 31c.

[0046] The map data creation unit 31b creates map data indicating a map of the target space based on the map creation data output from the acquisition unit 31a. The map data created by the map data creation unit 31b is stored in the storage unit 32.

[0047] The received power map creation unit 31c creates a received power map of the target space based on the map creation data and the received power data output from the acquisition unit 31a. The received power map created by the received power map creation unit 31c is stored in the storage unit 32. Note that the received power map is data in the form of a heat map in which the received power measured at each position where the moving body 1 has moved is assigned to that position (that is, the position and the received power are associated with each other).

[0048] Here, the information processing apparatus 3 according to the present embodiment calculates a coefficient used to estimate the presence or absence of a radio wave shielding body in the target space (the space in which the moving body 1 moves), and operates to estimate the presence or absence of the radio wave shielding body using the calculated coefficient.

[0049] When calculating the coefficient used to estimate the presence or absence of a radio wave shielding body in the target space as described above, the acquisition unit 31a measures the received power of the synchronization signal on the path passing between the antenna 2a and the radio wave shielding body (hereinafter referred to as the target path) in a state where a radio wave shielding body is arranged in the target space (a state where it is known that a radio wave shielding body is arranged in the target space). Receiving power data indicating the received power (hereinafter referred to as first received power data) is acquired. Further, the acquisition unit 31a acquires receiving power data (hereinafter referred to as second received power data) indicating the received power of the synchronization signal measured on the above-described target path in a state where no radio wave shielding body is arranged in the target space (a state where it is known that no radio wave shielding body is arranged in the target space).

[0050] When a radio wave shielding body is arranged at the position of the obstacle 1g described in FIG. 3, the above-described target path is, for example, the path 1f shown in FIG. 3. In this case, the acquisition unit 31a acquires, as the first received power data, the received power data indicating the received power measured by the moving body 1 moving along the path 1f in a state where a radio wave shielding body is arranged at the position of the obstacle 1g, and acquires, as the second received power data, the received power data indicating the received power measured by the moving body 1 moving along the path 1f in a state where no radio wave shielding body is arranged at the position of the obstacle 1g.

[0051] The setting unit 31d sets a partial area on the target path as an area (hereinafter referred to as the target area) used for processing related to the control of the mobile body 1 based on an index related to the variation between the received power indicated by the first received power data acquired by the acquisition unit 31a and the received power indicated by the second received power data. In this embodiment, the processing related to the control of the mobile body 1 includes processing for calculating a coefficient used to estimate the presence or absence of the above-described radio wave shielding body and processing for estimating the presence or absence of the radio wave shielding body using the calculated coefficient.

[0052] The calculation unit 31e calculates a coefficient for estimating the presence or absence of the above-described radio wave shielding body based on the received power measured in the target area set by the setting unit 31d among the received powers indicated by the first and second received power data acquired by the acquisition unit 31a.

[0053] Here, when estimating the presence or absence of a radio wave shielding body in the target space, the acquisition unit 31a acquires received power data indicating the received power of the synchronization signal measured on the above-described target path in a state where it is unknown whether a radio wave shielding body is arranged in the target space (that is, a state where it is not known whether a radio wave shielding body is arranged in the target space).

[0054] The estimation unit 31f estimates the presence or absence of a radio wave shielding body based on the received power measured in the target area set by the setting unit 31d among the received powers indicated by the received power data acquired by the acquisition unit 31a as described above and the coefficient calculated in advance by the calculation unit 31e as described above.

[0055] As described above, in the present embodiment, the timing at which the received power used for calculating the coefficient is measured is different from the timing at which the received power used for estimating the presence or absence of the radio wave shielding body is measured. Specifically explaining with reference to FIG. 3, the information processing apparatus 3 (calculation unit 31e and estimation unit 31f) according to the present embodiment calculates a coefficient in advance based on the received power measured on, for example, path 1f (target path). When path 1d is changed to path 1f due to the placement of obstacle 1g (radio wave shielding body) during the operation of the mobile control system, it operates to estimate the presence or absence of the obstacle 1g using the received power measured on the path 1f and the coefficient. That is, in the present embodiment, when the radio wave shielding body such as obstacle 1g is placed and path 1d (i.e., the shortest path) is changed to path 1f (i.e., the intermediate path) passing between the base station 2 and the radio wave shielding body, without moving to the area facing the antenna 2a across the radio wave shielding body (i.e., the area located on the back side of the radio wave shielding body as seen from the base station 2), the presence or absence of the radio wave shielding body (i.e., whether the radio wave shielding body has been removed) is estimated.

[0056] The control unit 31g generates a control signal for controlling the mobile body 1 based on the map data and the received power map stored in the storage unit 32 and the estimation result by the estimation unit 31f. The control signal generated by the control unit 31g is output to the output unit 31h.

[0057] The output unit 31h outputs the control signal output from the control unit 31g to the base station 2. The control signal output from the output unit 31h in this way is radiated from the antenna 2a installed in the base station 2 to the mobile body 1.

[0058] FIG. 7 shows an example of the system configuration of the information processing apparatus 3 shown in FIG. 6. The information processing apparatus 3 includes a CPU 301, a non-volatile memory 302, a RAM 303, a communication device 304, and the like.

[0059] The CPU 301 is a processor for controlling the operations of various components within the information processing apparatus 3. The CPU 301 may be a single processor or may be composed of a plurality of processors. The CPU 301 executes various programs loaded from the non-volatile memory 302 to the RAM 303. These programs include an operating system (OS) and various application programs.

[0060] The non-volatile memory 302 is a storage medium used as an auxiliary storage device. The RAM 303 is a storage medium used as a main storage device. In FIG. 7, only the non-volatile memory 302 and the RAM 303 are shown, but the information processing apparatus 3 may be provided with other storage devices such as an HDD (Hard Disk Drive) and an SSD (Solid State Drive).

[0061] The communication device 304 is a device configured to perform wired communication or wireless communication. The information processing apparatus 3 according to the present embodiment assumes a case where it is connected to the above-described base station 2 by wire (cable), but it may be connected so as to perform wireless communication with the base station 2 via a network.

[0062] In the present embodiment, the processing unit 31 shown in FIG. 6 is realized by at least one processor. The processor includes, for example, a control device and an arithmetic device, and is realized by an analog or digital circuit or the like. The processor may be the above-described CPU 301, or may be a general-purpose processor, a microprocessor, a digital signal processor (DSP), an ASIC, an FPGA, or a combination thereof.

[0063] Also, part or all of the processing unit 31 can be realized by causing a CPU 301 (that is, the computer of the information processing apparatus 3) to execute a predetermined program, that is, by software. This program may be stored in a computer-readable storage medium and distributed, or may be downloaded to the information processing apparatus 3 through a network. Note that part or all of the processing unit 31 may be realized by dedicated hardware or the like, or may be realized by a combination of software and hardware.

[0064] Also, in the present embodiment, the storage unit 32 shown in FIG. 6 is realized by, for example, a nonvolatile memory 302 or another storage device.

[0065] Although detailed description is omitted, part or all of each of the units 11 to 15 included in the moving body 1 shown in FIG. 5 described above may be realized by causing a processor such as a CPU provided in the moving body 1 to execute a predetermined program (that is, software), may be realized by hardware, or may be realized by a combination of software and hardware.

[0066] Here, in the present embodiment, it is estimated whether or not the radio wave shielding body has been removed (that is, the presence or absence of the radio wave shielding body) without moving to a zone facing the antenna 2a across the radio wave shielding body. A method (principle) for realizing such an estimation will be described.

[0067] In the following description, for convenience, it is assumed that the moving body 1 moves in the target space shown in FIG. 8. Specifically, the moving body 1 (AMR) moves in a target space in which obstacles 401 to 403 are arranged as shown in FIG. 8, for example. Note that the obstacles 401 and 403 are non-metal obstacles that do not shield radio waves (that is, do not affect the radio wave propagation environment). On the other hand, the obstacle 402 is an obstacle composed of a radio wave shielding body such as metal that shields radio waves (that is, affects the radio wave propagation environment).

[0068] In the target space shown in FIG. 8, consider paths 400A and 400B as the paths along which the moving body 1 moves from the starting point to the goal point. In this case, since path 400B is a path along which the moving body 1 moves through a zone where radio waves are shielded by the obstacle 402 (i.e., a dead zone), path 400A is selected as the path along which the moving body 1 moves. On the other hand, since path 400B is shorter than path 400A, path 400B should be selected when the obstacle 402 is removed.

[0069] In such a scenario, assume that the moving body 1 repeatedly circles along path 400A shown in FIG. 8 (i.e., moves multiple times). Although the obstacle 402 (radio wave shield) is arranged in FIG. 8, assume that the presence or absence of the obstacle 402 changes while the moving body 1 repeatedly circles along path 400A.

[0070] Here, assume that the moving body 1 is moving along the X-th round of path 400A, and the received power P at the i-th position on the path 400A i is modeled as in Equation (1).

Equation

[0071] In Equation (1), i is an index indicating the position on the path, and j is an index indicating the dominant wave. In this case, for example, j = 1 can be defined as the direct wave, j = 2 as a relatively strong reflected wave, j = 3 as the ground reflected wave, j = 4 as other multiple waves, etc. The relatively strong reflected wave of j = 2 assumes, for example, a reflected wave from the above-mentioned radio wave shield.

[0072] Also, p in Equation (1) ij indicates the power of the dominant wave j at the position i. C j indicates whether the dominant wave j (i.e., the j-th wave) exists or not. For example, when the dominant wave j exists, C j = 1. On the other hand, when the dominant wave j does not exist, C j = 0.

[0073] Next, to explain the model of Equation (1), first consider the propagation channel between transmission and reception as two waves: the direct wave and the reflected wave. In this case, as shown in Equation (2) below, the total received electric field strength E at the receiving side T is represented as the sum of the received electric field strength E1 of the direct wave and the received electric field strength E2 of the reflected wave.

Equation

[0074] Also, the total received power P at the receiving side T is expressed as shown in Equation (3) below using the total received electric field strength E T in the above Equation (2).

Equation

[0075] Note that the above received electric field strengths E1 and E2 are complex numbers, and the "*" in Equation (3) indicates the complex conjugate.

[0076] Furthermore, when the complex received electric field strength E1 is represented by the amplitude A1 and the phase θ1, it becomes as shown in Equation (4).

Equation

[0077] Similarly, when the complex received electric field strength E2 is represented by the amplitude A2 and the phase θ2, it becomes as shown in Equation (5).

Equation

[0078] According to Equation (4) above, E1 * and E2 in Equation (3) are transformed as shown in Equation (6) below.

Equation

[0079] Furthermore, according to the above formula (5), E1E2 in formula (3) * is transformed as shown in the following formula (7).

Number

[0080] Note that generally, the received power obtained by cellular terminals such as 5G and local 5G is, for example, RSRP (Reference Signal Received Power). Since this RSRP is an average value over frequency, the band average of the total received power P shown in the above formula (3) T is expressed as shown in the following formula (8).

Number

[0081] Here, when the frequency is single or narrowband, neither the direct wave nor the reflected wave changes significantly in phase with respect to the frequency. In this case, since the average values of the second and third terms on the right side of the above formula (8) (i.e., e j(θ2-θ1) and e j(θ1-θ2) ) have vector values, the second and third terms on the right side of the formula (8) are non-zero. On the other hand, when the frequency is broadband, the phase varies significantly with respect to the frequency. In this case, when e j(θ2-θ1) and e j(θ1-θ2) are added together, they approach 0 vectorially, and the second and third terms on the right side of formula (8) can be approximated as 0. That is, the above formula (8) can be treated as the following formula (9). The above has been explained as an average with respect to frequency, but e j(θ2-θ1) and e j(θ1-θ2) may also be considered as time averages or position averages on the order of the wavelength of the carrier wave.

Number

[0082] Although the propagation channel between transmission and reception has been described here for the case of two waves, consider the case where the propagation channel is three waves. Assume that these three waves include, for example, directly, a reflected wave from a radio wave shielding body (a relatively strong reflected wave) and a ground reflected wave. The total received power on the receiving side in this case is expressed as the following equation (10), similar to the above equation (3).

Equation

[0083] Equation (10) has an increased number of terms compared to equation (3), but it can be considered in the same way as the case where the propagation channel is two waves. Specifically, in the case of a wideband, the terms after the third term on the right side of equation (10) (i.e., the mutual terms) are approximated to be 0.

[0084] Furthermore, when the propagation channel is four waves or more and the waves after the fourth wave are scattered waves with a long path length, their intensity is small and their randomness is high. Therefore, it is considered that the waves after the fourth wave can be ignored.

[0085] According to the above, the following equation (11) obtained by expanding equation (1) assuming that the number of the above dominant waves j is k corresponds to equation (12). Thus, it can be said that the model of equation (1) can be theoretically explained.

Equation

[0086] Here, in the present embodiment, the presence or absence of a radio wave shielding body disposed in the target space is estimated. In FIG. 8, assuming that the moving body 1 moves along the path 400A in a state where the obstacle 402 which is a radio wave shielding body is disposed, the moving body 1 receives the reflected wave of the signal (radio wave) transmitted from the antenna 2a from the obstacle 402. On the other hand, assuming that the moving body 1 moves along the path 400A in a state where the obstacle 402 which is a radio wave shielding body is not disposed, the moving body 1 does not receive the reflected wave of the signal (radio wave) transmitted from the antenna 2a from the obstacle 402. That is, estimating the presence or absence of the above-described radio wave shielding body is synonymous with estimating the presence or absence of the reflected wave from the radio wave shielding body.

[0087] Hereinafter, starting from Equation (1), a method for estimating the presence or absence of the reflected wave from the radio wave shielding body will be described. First, consider the following Equation (13) which is the matrix expression of Equation (1).

Number

[0088] In Equation (13), each row represents each element of the position (i = 1, 2,..., n) on the path along which the moving body 1 moves, and each column represents each element of the dominant wave (j = 1, 2,..., k). From the left side of both sides of this Equation (13), multiplying by the inverse matrix or the pseudo-inverse matrix of the matrix having the power of each dominant wave (that is, p ij ) as a component at each position on the path along which the moving body 1 moves, Equation (13) is transformed into the following Equation (14). Note that the pseudo-inverse matrix corresponds to the inverse matrix of a matrix that is not a square matrix.

Number

[0089] Furthermore, by changing the notation of Equation (14), it becomes Equation (15).

Number

[0090] Here, by extracting and generalizing one line of Equation (15), Equation (16) is obtained.

Number

[0091] What should be noted in this embodiment is the presence or absence of the reflected wave from the radio wave shielding body, and it is assumed that the index j indicating the reflected wave (dominant wave) from the radio wave shielding body is 2. In this case, let C2 be y and P i be the explanatory variable x i . According to this, the above-mentioned Equation (16) is expressed as Equation (17).

Number

[0092] β1,…,β in the above-mentioned Equation (17) n are regression coefficients and can be calculated based on the received power (explanatory variable x i ) measured in a state where the presence or absence of the radio wave shielding body (reflected wave) is known. In Equation (17), when there is a radio wave shielding body (reflected wave), y = 1, and when there is no radio wave shielding body (reflected wave), y = 0.

[0093] Note that in the above-mentioned Equation (16), even when C1 (direct wave) and C3 (ground reflected wave) are set to y, the equation is the same as Equation (17). Therefore, in this embodiment, it is important to calculate the regression coefficient β (β1,…,β n ) associated with the reflected wave from the radio wave shielding body.

[0094] When the moving body 1 makes m rounds (m laps) along the path 400A shown in FIG. 8 and measures the received power (RSRP represented by a linear value) at each position, and associates the measured received power with the presence or absence of the radio wave shielding body (the value of y indicating this) at the time of this round, the above-mentioned Equation (17) is expressed as the following Equation (18).

Number

[0095] Also, when the expression (18) is matrix-formatted, the expression (18) is represented as the following expression (19).

Number

[0096] Here, assuming that the expression (19) is expressed as Y = Xβ, in X in the expression (19), the received power measured at each position (location) on the path every time the moving body 1 orbits the path is arranged as a component. Specifically, x 11 , …, x 1n corresponds to the received power measured by the moving body 1 at positions 1, …, n on the path when the number of orbits is 1 (that is, in the first round). Similarly, x m1 , …, x mn corresponds to the received power measured by the moving body 1 at positions 1, …, n on the path when the number of orbits is m (that is, in the m-th round).

[0097] When calculating (deriving) the regression coefficient β in such an expression (19), as shown in FIG. 9, while the moving body 1 orbits the path m times (m rounds), the received power measured at each position on the path from 1 to n is substituted into X. Further, a value (y = 1 or y = 0) indicating the presence or absence of a radio wave shielding body, which is known when the path is being moved, is substituted into Y. The above explanation is based on the case where there is one (single unit) moving body 1. However, when a plurality of moving bodies 1 orbit, the received power for the number of moving bodies 1 × m rounds may be substituted into X.

[0098] In this case, for example, it is possible to calculate the regression coefficient β by multiplying both sides of the expression (19) by the pseudo-inverse matrix X + of the matrix X from the left. However, in the scenario assumed in the present embodiment, attention should be paid to the presence or absence of reflected waves from the radio wave shielding body, and it cannot be said that the regression coefficient β calculated in this way is appropriate.

[0099] Therefore, in this embodiment, PLS (Partial Least Squares) regression is applied to calculate the regression coefficient β. In PLS regression, both the above-mentioned X and Y are considered, and the eigenvectors of X T and Y are derived to extract the principal components. Note that X T is the transposed matrix of matrix X. In PLS regression, in order to extract the principal components highly correlated with Y, it can be said that it is suitable for the scenario of this embodiment that focuses only on specific reflected waves (that is, the reflected waves from the radio wave shielding body). Also, generally, when there is a strong correlation (multicollinearity) between the columns of matrix X, the regression coefficient β becomes unstable. In the scenario of this embodiment, since each column of matrix X is composed of components corresponding to each position on the path, depending on the radio wave propagation environment, the spatial correlation between the positions (the received power measured at these positions) may become high. However, in PLS regression, since orthogonal components, that is, components with low correlation, are extracted, it is possible to avoid the regression coefficient β becoming unstable due to the influence of multicollinearity.

[0100] Here, a specific calculation method of the regression coefficient in PLS regression will be described. First, matrices E and F are defined, and X and Y are substituted into their initial values.

[0101] Next, by singular value decomposition, E T F = U svd ΣV svd is set, and the first column vectors of U svd and V svd are set as column vector w and column vector c, respectively. Note that " T " represents the transposed matrix.

[0102] Furthermore, w T is normalized so that w = 1, c T is normalized so that c = 1, and t and u are obtained from t = Ew and u = Fc. Also, t T is normalized so that t = 1, u T is normalized so that u = 1, and p = E T t and q = F T t are used to obtain p and q. Thus, the extraction of the first component is completed.

[0103] Subsequently, subtract tp from E T , subtract tq from F T to update E and F respectively, and repeat the process to extract the second and subsequent components.

[0104] Assuming that, for example, L components are extracted by repeating the process as described above, matrices W, P, and Q are defined as in the following equation (20).

Equation

[0105] The regression coefficient β in the above equation (19) is calculated by the following equation (21) using the matrices W, P, and Q defined in this way.

Equation

[0106] In this embodiment, the radio wave propagation environment in the factory or warehouse where the mobile body 1 moves is complex and difficult to clearly classify. However, assuming that the first principal component is the direct wave and the second principal component is the reflected wave, the contribution degree of the third principal component and subsequent components is lower than that of the first and second principal components and is considered to include noise components. Based on this, the number of components extracted by PLS regression is determined.

[0107] In this embodiment, when estimating the presence or absence of a radio wave shielding body (radio wave propagation environment) during the operation of the mobile body control system, the regression coefficient calculated during learning (β1,..., β

[0108] In this embodiment, when estimating the presence or absence of a radio wave shielding body (radio wave propagation environment) during the operation of the mobile body control system, as in the following equation (22), for the regression coefficients (β1,..., β n ) newly measured on the same path with respect to the received power (x1,..., xn Multiply by ().

Number

[0109] The value of y calculated by the above formula (22) corresponds to a value indicating the presence or absence of a radio wave shielding body. By performing a threshold determination on the value of y, the presence or absence of a radio wave shielding body can be estimated (analogized).

[0110] Incidentally, in the present embodiment, the presence or absence of a radio wave shielding body is estimated by paying attention to the fluctuation of the received power (RSRP) due to the reflected wave from the radio wave shielding body. However, the received power may vary due to other factors. When the presence or absence of a radio wave shielding body is estimated using a regression coefficient calculated based on the received power in which such variation due to other factors (that is, undesired variation) has occurred, it is assumed that the estimation accuracy will decrease. For this reason, in the present embodiment, it is necessary to distinguish the difference between the fluctuation of the received power due to the reflected wave from the radio wave shielding body and the variation of the received power due to other factors.

[0111] For example, when the received power is measured by a plurality of mobile bodies 1 (AMRs), the variation due to the above-described other factors is caused by individual differences of the wireless devices (receivers) mounted on the mobile bodies 1, differences in the positions of the wireless devices (receiving antennas) mounted on the mobile bodies 1 on the order of wavelengths, and disturbances in the propagation environment caused by the running intervals of the plurality of mobile bodies 1.

[0112] Also, even when controlling a plurality of mobile bodies 1 to travel along the same route, it is difficult for the plurality of mobile bodies 1 to travel exactly at the same position, and there is also a deviation on the order of wavelengths in the positions where each of the plurality of mobile bodies 1 measures the received power. Such a deviation in the position where the received power is measured is also one of the factors causing the above-described variation in the received power.

[0113] Furthermore, in each of the plurality of moving bodies 1, the map creation data is output from the distance measurement unit 13 realized by the LRF, and the received power data is output from the received power measurement unit 14 realized by the radio device. Therefore, in the information processing device 1, the position where the fluctuation of the received power due to the reflected wave from the radio wave shielding body is grasped (that is, the timing when the received power increases) may be different in each round of the moving body 1. Also, in the present embodiment, when calculating the regression coefficient and estimating the presence or absence of the radio wave shielding body, the received power measured at each position on the path is used. However, the lag that occurs in the association between the position and the received power may also be a factor in the variation of the received power.

[0114] Note that in the present embodiment, it is assumed that a relatively inexpensive radio device (such as a mobile terminal) is mounted on the moving body 1 to measure the received power in consideration of the cost of constructing the system. In such a case, it is often not possible to acquire the amplitude and phase components of each frequency, and only the averaged amplitude component (received power) can be acquired.

[0115] Therefore, in the present embodiment, in order to suppress the decrease in the estimation accuracy of the presence or absence of the radio wave shielding body due to the variation of the received power as described above, a target area is set based on an index related to the variation of the received power according to the presence or absence of the radio wave shielding body, and the received power measured in the target area is used to execute the process related to the control of the moving body 1.

[0116] Hereinafter, the operation of the information processing device 3 according to the present embodiment will be described. Here, the process of the information processing device 3 when calculating the above-described regression coefficient (hereinafter referred to as learning process) and the process of the information processing device 3 when estimating the presence or absence of the radio wave shielding body (hereinafter referred to as estimation process) will be described.

[0117] First, with reference to the flowchart of FIG. 10, an example of the processing procedure of the above-described learning process will be described.

[0118] In the learning process, as a preprocessing (preparation) for calculating the regression coefficient, a process of creating map data and a received power map is executed (step S1).

[0119] First, the process of creating map data will be described. When the target space (environment) is a relatively static space, fixed map data indicating the map of the target space may be prepared in advance. However, in a target space such as the factory or warehouse described above, since the arrangement of obstacles (goods such as cardboard boxes) changes over time, it is necessary to dynamically create (update) the map data.

[0120] In this case, the processing unit 31 (control unit 31g) included in the information processing apparatus 3 generates a control signal for controlling the mobile body 1 to move throughout the range where the mobile body 1 can move within the target space. The control signal (downlink) generated in the processing unit 31 in this way is output from the processing unit 31 (output unit 31h) to the base station 2 and transmitted from the base station 2 to the mobile body 1. In this case, the control signal is received by the receiving unit 11 included in the mobile body 1, and the control unit 12 controls the moving speed and direction of the mobile body 1 based on the control signal. As a result, the mobile body 1 moves throughout the target space.

[0121] Here, the distance measurement unit 13 included in the mobile body 1 measures the distance to an object (for example, a wall and an obstacle, etc.) existing around the mobile body 1 moving within the target space by measuring the TOF with an LRF or the like.

[0122] The transmitting unit 15 transmits map creation data (uplink) including the distance measured by the distance measurement unit 13 in this way, the moving speed and direction of the mobile body 1 controlled by the control unit 12, to the information processing apparatus 3 via the base station 2. Note that the map creation data is transmitted to the information processing apparatus 3 each time the mobile body 1 moves based on, for example, the control signal (that is, for each position within the target space).

[0123] As described above, the map creation data transmitted from the moving body 1 (transmission unit 15) is received by the base station 2 and output to the information processing device 3. The processing unit 31 (acquisition unit 31a) included in the information processing device 3 acquires the map creation data output from the base station 2. The processing unit 31 (map data creation unit 31b) creates map data indicating a map of the target space based on the distance, the moving speed, and the direction of the moving body 1 included in the acquired map creation data. The map data created by the processing unit 31 in this way is data indicating a map such as a plan view representing walls forming the target space, passages through which the moving body 1 can move, and obstacles arranged in the target space.

[0124] Note that the map data may be created by updating, for example, an initial layout of the target space where no obstacles or the like are arranged (map data representing only walls and passages).

[0125] As described above, the map data created by the processing unit 31 (map data creation unit 31b) is stored in the storage unit 32.

[0126] Next, the process of creating a received power map will be described. In this case, the processing unit 31 (control unit 31g) included in the information processing device 3 generates a control signal for controlling the moving body 1 to move along all the passages on the map indicated by the map data stored in the storage unit 32 as described above. The control signal generated by the processing unit 31 in this way is output from the processing unit 31 (output unit 31h) to the base station 2 and transmitted from the base station 2 to the moving body 1. As a result, the moving body 1 moves throughout the target space.

[0127] Here, in 5G (local 5G), a synchronization signal is broadcast from the base station 2. The receiving unit 11 included in the moving body 1 receives the synchronization signal broadcast from the base station 2 in this way.

[0128] The received power measurement unit 14 measures the received power of the synchronization signal received by the receiving unit 11. In this embodiment, for example, RSRP is used as the received power to be measured, but the received power may be, for example, RSSI (Received Signal Strength Indicator), SSS-RSRP (Secondary Synchronization Signal-Reference Signal Received Power), PSS-RSRP (Primary Synchronization Signal-Reference Signal Received Power), or the like.

[0129] Also, although it has been described here that the received power of the synchronization signal broadcast from the base station 2 is measured, for example, in 5G (local 5G), a plurality of reference signals such as CSI-RS (Channel State Information Reference Signal), which is a reference signal for channel information estimation, and DM-RS (Demodulation Reference Signal), which is a reference signal for demodulation, are prepared. Therefore, the received power may be measured using these reference signals. In this case, the received power of one of the plurality of reference signals in which at least one of the frequency, time, and antenna is different may be measured, or the average value of the received powers of each of the plurality of reference signals may be measured.

[0130] The transmission unit 15 transmits received power data indicating the received power measured by the received power measurement unit 14 in this way to the information processing device 3 via the base station 2. Note that the received power data is transmitted to the information processing device 3, for example, each time the mobile body 1 moves (for each point in the target space) based on a control signal.

[0131] Furthermore, although detailed description is omitted here, also in the process of creating the received power map, each time the mobile body 1 moves, the above-described map creation data (the distance to the object existing around the mobile body 1, the moving speed and direction of the mobile body 1) is transmitted from the mobile body 1 to the information processing device 3.

[0132] As described above, the map creation data and the received power data transmitted from the moving body 1 (transmission unit 15) are received by the base station 2 and output to the information processing device 3. The processing unit 31 (acquisition unit 31a) included in the information processing device 3 acquires the map creation data and the received power data output from the base station 2.

[0133] Here, the processing unit 31 can acquire (grasp) the position of the moving body 1 on the map shown by the map data based on the distance to the object existing around the moving body 1 included in the map creation data, the moving speed and direction of the moving body 1. The processing unit 31 (received power map creation unit 31c) creates a received power map (heat map of the received power at each position of the moving body 1) by mapping the position of the moving body 1 thus acquired and the received power indicated by the received power data. Specifically, the processing unit 31 creates a received power map by assigning the received power measured at each position as the moving body 1 moves to the position (corresponding pixel). The received power map created in this way corresponds to a radio wave map showing the radio wave propagation environment in the target space. In addition, when a person intervenes in the control on the information processing device 3 (MEC) side, a received power map in a mode that is easy to visually recognize may be created.

[0134] The received power map created by the processing unit 31 (received power map creation unit 31c) as described above is stored in the storage unit 32.

[0135] In addition, in the process of creating the received power map, the map creation data is used to acquire the position to which the received power indicated by the received power data is assigned, and the map creation data is also used to update the map data (that is, the arrangement of obstacles, etc.) stored in the storage unit 32 described above.

[0136] Also, although the description here has been made assuming that the received power map is created based on the received power of the downlink signal (synchronization signal), in general wireless communication, since there is a relativity (symmetrical relationship) between the downlink and the uplink, the received power map may be created based on the received power of the uplink signal, or may be created based on the result of merging the received power of the downlink signal and the received power of the uplink signal.

[0137] In addition, in this embodiment, the process of creating map data and the process of creating the received power map have been described separately (that is, it has been described that the received power map is created after the map data is created), but the map data and the received power map may be created simultaneously (in parallel).

[0138] Also, in this embodiment, as long as it is possible to grasp the propagation environment of radio waves (signals) in the target space, instead of the received power map, a map in which the signal throughput or bit error rate is assigned to each position on the map may be created.

[0139] Furthermore, for example, when obstacles (such as radio wave shielding bodies) arranged in the target space are known, information such as the positions of the obstacles grasped by pre-measurement or the like may be registered (held) in the map data and the received power map.

[0140] When the process of step S1 is executed, the processing unit 31 (control unit 31g) included in the information processing apparatus 3 selects a path within the target space in which a plurality of moving bodies 1 orbit (that is, measure the received power) in order to calculate the regression coefficient (step S2). Note that the path selected in step S2 is a path that includes a position within the line of sight from the antenna 2a even when a radio wave shielding body is arranged (that is, a path that passes between the antenna 2a and the radio wave shielding body). In this embodiment, the regression coefficient used to estimate the presence or absence of a radio wave shielding body is calculated using the received power measured by a plurality of moving bodies 1 orbiting such a path.

[0141] In step S2, for example, a path may be automatically selected based on the position where the radio wave shielding body is arranged or the position where the radio wave shielding body may be arranged, with reference to the map data and the received power map stored in the storage unit 32, or a path designated by the administrator of the movement control system may be selected.

[0142] Specifically, for example, as shown in FIG. 11, the area 501 in the target space corresponds to a position within the line of sight from the antenna 2a. Also, the areas 502 and 503 in the target space have an obstacle 401 arranged between them and the antenna 2a (that is, on the back side of the obstacle 401). However, when the obstacle 401 is not a radio wave shielding body (is non-metallic), from the perspective of radio waves, it corresponds to a position within the line of sight from the antenna 2a. In this case, in step S2, for example, a path 400A including a position within the line of sight from the antenna 2a with respect to the obstacle 402 that is a radio wave shielding body is selected. Note that when an obstacle 402 that is a radio wave shielding body is arranged in the area 504 in the target space, since it is a position outside the line of sight from the antenna 2a, the path 400B is not selected.

[0143] When the process of step S2 is executed, the processing unit 31 (control unit 31g) controls the moving body 1 to move along the path selected in step S2 (step S3). The control of the moving body 1 in step S3 is realized by outputting a control signal for controlling the moving body 1 generated by the processing unit 31 to the base station 2, and transmitting the control signal from the base station 2 to the moving body 1.

[0144] Here, when the process of step S3 described above is executed, the moving body 1 moves along the path selected in step S2. However, the moving body 1 shall transmit received power data indicating the received power measured at each position during the movement to the information processing device 3 via the base station 2.

[0145] In this case, the processing unit 31 (acquisition unit 31a) included in the information processing apparatus 3 acquires the received power data transmitted from the moving body 1 that has moved along the path selected in step S2 (that is, the received power measured by the moving body 1) from the base station 2 (step S4). The received power data acquired in step S4 is held by the processing unit 31 (setting unit 31d). Although the received power data has been described here, the processing unit 31 also receives the map creation data together with the received power data.

[0146] Next, it is determined whether or not to end the movement of the moving body 1 (that is, the measurement of the received power) (step S5).

[0147] Here, in the present embodiment, the received power measured by causing a plurality of moving bodies 1 to circle the same path (make a plurality of round trips) in a state where it is known that a radio wave shielding body is arranged in the target space as described above, and the received power measured by causing a plurality of moving bodies 1 to circle the path in a state where it is known that no radio wave shielding body is arranged in the target space are used to calculate the regression coefficient.

[0148] Therefore, the processing unit 31 causes the plurality of moving bodies 1 to circle the path 400A until reaching a predetermined number of times in a state where the obstacle 402, which is a radio wave shielding body, is arranged as shown in FIG. 12, for example. Then, further, in a state where the obstacle 402, which is the radio wave shielding body, is not arranged (that is, removed), the plurality of moving bodies 1 are caused to circle the path 400A until reaching a predetermined number of times, thereby collecting the received power (received power data indicating the same) measured at each position on the path 400A.

[0149] In this embodiment, a plurality of mobile bodies 1 repeatedly circulate along a path. However, the density of the plurality of mobile bodies 1 and the distance between the plurality of mobile bodies 1 may affect the received power (fluctuation) measured by the mobile body 1. Specifically, for example, as shown in FIG. 13, when the distance between two mobile bodies 1 is short (that is, the density is high), the received power measured by one mobile body 1 may be affected by the reflected wave from the other mobile body 1. Therefore, the plurality of mobile bodies 1 may be controlled under conditions such that the distance between two mobile bodies is equal to or greater than a threshold value (or the density is less than the threshold value), as shown in FIG. 14, for example.

[0150] Furthermore, the received power (intensity) may be able to be improved in stability by measuring it while each of the plurality of mobile bodies 1 is in a stopped state. Therefore, the plurality of mobile bodies 1 may be controlled under conditions such that they repeatedly move and stop during the circulation of the path and measure the received power at the timing of the stop.

[0151] In this embodiment, the received power is measured in each of the state where a radio wave shielding body is arranged in the target space and the state where no radio wave shielding body is arranged in the target space. However, it is preferable that the plurality of mobile bodies 1 measure the received power under the same conditions as much as possible in each state.

[0152] For example, as shown in FIG. 15, when the mobile body 1 is configured to be able to travel in a plurality of directions, the conditions for the plurality of mobile bodies 1 to measure the received power may include making the direction (travel direction) in which the mobile body 1 travels the same. Furthermore, the conditions for the plurality of mobile bodies 1 to measure the received power may include making the position of the radio device (antenna installation position, height, etc.) mounted on the mobile body 1 the same.

[0153] However, since it is difficult for the plurality of moving bodies 1 to travel exactly the same path (position) in each round, the positions at which each of the plurality of moving bodies 1 measures the received power in each round may be shifted, for example, on the order of the wavelength. In this embodiment, in consideration of the fact that the path (position) is shifted on the order of the wavelength when the moving body 1 travels on the same path, information on the number of rounds is also acquired in order to grasp the tendency of the shift due to the round.

[0154] In step S5, when it is determined that the movement of the moving body 1 ends when all the received powers for calculating the regression coefficient have been collected (acquired) as described above. On the other hand, in step S5, when it is determined that the movement of the moving body 1 does not end when all the received powers for calculating the regression coefficient have not been collected (acquired) as described above.

[0155] When it is determined that the movement of the moving body 1 does not end (NO in step S5), the process returns to step S3 and the process is repeated.

[0156] On the other hand, when it is determined that the movement of the moving body 1 ends (YES in step S5), the processing unit 31 (setting unit 31d) sets a target area used for processing related to the control of the moving body 1 using the received power data acquired in step S4 (that is, the received power data held by the processing unit 31) (step S6).

[0157] Hereinafter, the process of step S6 will be described in detail. First, FIG. 16 shows an example of the data structure of the received power data held by the processing unit 31.

[0158] As shown in FIG. 16, the received power data held in the processing unit 31 includes, for example, identification information for identifying the moving body 1 (hereinafter referred to as the moving body ID), the number of times the route was traversed when the moving body 1 measured the received power (the number of times the route was traversed), the received power measured by the moving body 1, the time when the received power was measured, and the position of the moving body 1 when the received power was measured, in association with each other. The moving body ID included in the received power data is, for example, an identification number, but it may be other information. Also, the moving body ID, the number of times traversed, the received power, and the time included in the received power data are information obtained from the moving body 1, but the position included in the received power data is obtained based on, for example, the map creation data transmitted from the moving body 1 as described above.

[0159] Note that only a part of the received power data held in the processing unit 31 is shown in FIG. 16, but the processing unit 31 holds all the received power data obtained by repeating the above-described processing of steps S3 and S4.

[0160] Also, here, the received power data shown in FIG. 16 has been described as being held in the processing unit 31, but the received power data may be stored, for example, in the storage unit 32, or may be stored in a storage unit other than the storage unit 32.

[0161] Furthermore, the received power data may have a data structure other than the data structure described in FIG. 16, and may be held (stored) in the form of a received power map in which, for example, the received power and the like are assigned to positions. Note that when the received power data obtained in the learning process is held in the form of a received power map in this way, the received power map may be utilized for stable route control of the moving body 1 during the operation of the moving body control system.

[0162] Here, as described above, the received power data held in the processing unit 31 includes the received power measured while a plurality of moving objects 1 repeatedly circle along a path. It is considered that the received power has fluctuations due to reflected waves from the radio wave shielding body and variations due to other factors as described above.

[0163] Assuming that variations in the received power occur due to displacements in the positions where each of the plurality of moving objects 1 measures the received power in each round, in order to absorb such variations, the processing unit 31 sets a reference position on the path and extracts the received power measured in the vicinity of the reference position from the received power data (the received power indicated thereby) held in the processing unit 31.

[0164] Hereinafter, with reference to FIG. 17, the above-described reference position will be described. In FIG. 17, a plurality of reference positions set on the path along which the moving object 1 circles and a plurality of positions where the received power is measured when the path is circled are shown. In FIG. 17, it is assumed that the moving object 1 circles the path twice.

[0165] In the present embodiment, as shown in FIG. 17, for example, the received power measured in the vicinity of each of the plurality of reference positions (for example, positions within a predetermined range set based on the reference position or positions whose distance from the reference position is equal to or less than a predetermined value) is extracted. Specifically, the received power measured in the vicinity of the reference position is the received power measured at the position having the shortest distance connecting the reference position among the positions where the received power around the reference position is measured.

[0166] In the example shown in FIG. 17, reference positions 601 to 606 are set on the path. In this case, among the received power measured in the first round of the path, the received power measured at the vicinity points of each of the reference positions 601 to 606 is extracted. Similarly, among the received power measured in the second round of the path, the received power measured at the vicinity points of each of the reference positions 601 to 606 is extracted. In FIG. 17, the positions where the received power extracted for each round is measured are marked with asterisks.

[0167] In FIG. 17, the received power measured by one moving body 1 was described. Similarly, for other moving bodies 1, the received power measured in the vicinity of each of a plurality of reference positions is extracted.

[0168] As shown in FIG. 17, even when the same path is repeatedly traversed, there is a deviation in the position where the moving body 1 moves (travels) and the position where the received power is measured each time of the traversal. However, by setting the above-described plurality of reference positions, it is possible to reduce the influence of variations in the received power due to the deviation of the position.

[0169] Note that the plurality of reference positions described above may be set at equal intervals or at unequal intervals (different intervals).

[0170] Here, in the plurality of received powers extracted based on the plurality of reference positions, there are variations due to reflected waves from the radio wave shielding body and variations due to other factors. It is useful to distinguish between the variations (in the received power where they occur) due to reflected waves from the radio wave shielding body and the variations (in the received power where they occur) due to other factors among the plurality of received powers in order to calculate a highly accurate regression coefficient and improve the estimation accuracy using the regression coefficient.

[0171] However, for example, when 100 reference positions are set, it is not easy to grasp which reference position (the received power measured in the vicinity thereof) appropriately represents the variation due to the reflected wave of the radio wave shielding body (that is, contributes to the variation). Specifically, it may be considered to randomly select a combination of some of the 100 reference positions and determine a combination with high estimation accuracy from the selected combinations. However, even when the reference position (the received power measured in the vicinity thereof) determined in this way is used, the estimation accuracy may be good for specific data but may not be sufficient for different data, lacking robustness. Also, in this case, depending on the number of reference positions, the number of combinations becomes extremely large, increasing the processing amount.

[0172] Therefore, in this embodiment, as an example of an index related to the fluctuation caused by the reflected wave of the radio wave shielding body (that is, the fluctuation of the received power caused according to the presence or absence of the radio wave shielding body), VIP (Variable Influence on Projection) used in the component analysis of the spectrum is applied.

[0173] Note that the spectrum is represented like the absorbance with respect to the normal wavelength and is used to obtain an appropriate wavelength. Specifically, for wavelengths with high importance, the VIP (value) becomes large, and whether the VIP is 1 or more is one criterion for discriminating wavelengths with high importance.

[0174] In this embodiment, by using the VIP calculated by treating the received power (the received power measured in the vicinity of the reference position) extracted based on each of a plurality of reference positions like a spectrum, it is considered that a reference position (a partial area on the path including) where the fluctuation caused by the reflected wave from the radio wave shielding body can be appropriately observed is set (selected) as the target area. Note that VIP is calculated by the following formula (23).

Equation

[0175] In formula (23), k is the index of the explanatory variable, and in this embodiment, it represents the index of the reference position. n represents the number of reference positions (explanatory variables). i represents the index of the component extracted by PLS regression. L represents the number of components extracted by PLS regression. W is the n×L correlation matrix of formula (20) obtained in the calculation process of the regression coefficient in PLS regression. In this case, W ki 2 represents the square of the component in the k-th row and i-th column of W. V i is represented as in the following formula (24).

Equation

[0176] As shown in Equation (24), V i is calculated from u i and t i obtained in the calculation process of the regression coefficient in PLS regression. In other words, Vi is a scalar quantity obtained from the matrix U (= [u1…u L ) and the matrix T (= [t1…t L ). Here, u i is the vector of the i-th column of the matrix U, t i is the vector of the i-th column of the matrix T, and " T " represents transpose.

[0177] In the present embodiment, the processing unit 31 generates a matrix having, as components, the received power measured in the vicinity of a plurality of reference positions each time each of the plurality of moving bodies 1 makes a circuit.

[0178] Here, a specific example of the matrix generated by the processing unit 31 will be described. Here, for example, it is assumed that the plurality of moving bodies 1 include the first and second moving bodies, and the first and second moving bodies each make two circuits along the path in a state where the radio wave shielding body is arranged and in a state where the radio wave shielding body is not arranged.

[0179] In this case, the received power measured at positions near each of the plurality of reference positions by the first moving body in the first round of the path in the state where the radio wave shielding body is arranged is used as the component of the first row. Similarly, the received power measured at positions near each of the reference positions by the second moving body in the first round of the path in the state where the radio wave shielding body is arranged is used as the component of the second row. Further, the received power measured at positions near each of the plurality of reference positions by the first moving body in the second round of the path in the state where the radio wave shielding body is arranged is used as the component of the third row. Similarly, the received power measured at positions near each of the plurality of reference positions by the second moving body in the second round of the path in the state where the radio wave shielding body is arranged is used as the component of the fourth row.

[0180] Also, the received power measured by the first moving object at positions near each of the plurality of reference positions in the first round of the path in a state where the radio wave shielding body is not arranged is used as the component in the fifth row. Similarly, the received power measured by the second moving object at positions near each of the reference positions in the first round of the path in a state where the radio wave shielding body is not arranged is used as the component in the sixth row. Further, the received power measured by the first moving object at positions near each of the plurality of reference positions in the second round of the path in a state where the radio wave shielding body is not arranged is used as the component in the seventh row. Similarly, the received power measured by the second moving object at positions near each of the plurality of reference positions in the second round of the path in a state where the radio wave shielding body is not arranged is used as the component in the eighth row.

[0181] According to this, the processing unit 31 can generate a matrix having as components the received power of 8 (rows) × the number of reference positions (columns). Note that the number of rows in the matrix generated by the processing unit 31 corresponds to "the number of moving objects (here, 2) × the number of rounds of the moving object (here, 2 rounds) × the presence or absence of the radio wave shielding body (that is, 2)".

[0182] The processing unit 31, based on the matrix X(x 11 ,…,x mn ) of the formula (19) generated in this way and the corresponding Y(y1,…,y m ), by applying the matrix obtained by the flow of the calculation method of the regression coefficient in the above-described PLS regression to the above-described formula (23), VIP can be calculated for each reference position. The processing unit 31 sets the target area based on the VIP calculated for each reference position in this way.

[0183] Here, referring to FIGS. 18 to 20, the target area set by the processing unit 31 will be specifically described.

[0184] Here, it is assumed that the received power is measured when a plurality of moving bodies 1 repeatedly orbit along a path 701 within a target space 700 shown in FIG. 18. FIG. 19 shows, in the form of a received power map, the received power measured in the vicinity of a plurality of reference positions set on the path 701 shown in FIG. 18. In the example shown in FIG. 19, 42 + 56 + 35 = 133 reference positions are set in the vicinity of the radio wave shielding body 702 shown in FIG. 18, and the received power measured (the received power measured at positions in the vicinity of the relevant reference position) when each of, for example, 10 moving bodies 1 orbits twice for each presence or absence of the radio wave shielding body is shown. FIG. 20 shows the VIP (characteristics) calculated for each of the 133 reference positions shown in FIG. 19.

[0185] When taking the fact that the VIP is 1 or more as one criterion as described above, areas A to C (reference positions included) on the path where the VIP continuously exceeds 1 shown in FIGS. 18 to 20 can be set as appropriate areas (places) to be used for regression. In this case, the processing unit 31 sets (selects) areas A to C as target areas based on the VIP.

[0186] Here, it has been described that the target area is set based on the VIP calculated for each reference position, but there may be cases where an appropriate target area cannot be set only by applying the VIP. Specifically, in the example shown in FIGS. 18 to 20 described above, areas A to C are set as target areas, but according to the reflected waves 703a and 703b from the radio wave shielding body 702 arranged within the target space 700 when the moving body 1 orbits along the path to measure the received power, it cannot be said that areas B and C are areas where the received power that appropriately represents the variation due to the reflected waves can be measured (that is, there is a possibility that factors other than the reflected waves are affecting).

[0187] Therefore, in the present embodiment, the processing unit 31 geometrically obtains the reflected wave from the radio wave shielding body 702 in consideration of the positions of, for example, the antenna 2a which is a signal radiation source and the radio wave shielding body 702. The processing unit 31 may set the target area based on the reflected wave from the radio wave shielding body 702 thus obtained. That is, in the present embodiment, on the premise that the reflected wave from the radio wave shielding body 702 is targeted, it is modeled (formulated) as in Equation (1). By considering the reflected wave from the radio wave shielding body 702 geometrically obtained as described above, areas B and C which are presumed not to have a favorable influence on the estimation of the presence or absence of the radio wave shielding body 702 can be excluded from the target area.

[0188] In order to set an appropriate target area (reference position) as described above, it is possible to consider both the area where the fluctuation of the received power due to the reflected wave geometrically obtained from the positional relationship between the antenna 2a and the radio wave shielding body 702 can be observed and the VIP. In this case, an area where the fluctuation of the received power due to the reflected wave from the radio wave shielding body 702 can be geometrically observed is roughly selected (estimated), and a limited area using the VIP can be set as the target area from among the selected areas. Further, for example, when the layout of the target space 700 (factory or warehouse) is complex and it is difficult to grasp the mechanism of the reflected wave from the radio wave shielding body 702, first, an area is selected (extracted) based on the VIP, and the target area may be set in consideration of the possibility of observing the fluctuation of the received power due to the reflected wave from the radio wave shielding body 702 geometrically obtained from among the selected areas. As an application, not only the reflected wave from the radio wave shielding body 702 but also the diffracted wave or scattered wave may be further considered. Also, in FIG. 19, the reflected wave from the radio wave shielding body 702 is considered two-dimensionally, but the reflected wave may be considered three-dimensionally.

[0189] Returning to FIG. 10 again, the processing unit 31 (calculation unit 31e) calculates a regression coefficient based on the received power measured in the vicinity of the reference position included in the target area set in step S6 (step S7).

[0190] Here, as described above, the received power has been measured in a state where the presence or absence of the radio wave shielding body is known. In step S7, the processing unit 31 forms a matrix of the presence or absence of the radio wave shielding body (a value indicating it) and the received power measured in the vicinity of the reference positions included in the target area. In this case, for each round of the path by the plurality of moving bodies 1, the presence or absence of the radio wave shielding body is substituted into Y(y1,…,y m ) in the above-described formula (19). Specifically, for example, when the radio wave shielding body was arranged when the plurality of moving bodies 1 made one round of the path, 1 is substituted into y1 of Y in formula (19), and when the radio wave shielding body was not arranged when the plurality of moving bodies 1 made the m-th round of the path, 0 is substituted into y m in Y of formula (19).

[0191] Here, although the presence or absence of the radio wave shielding body has been described as being quantitatively represented by y = 1 and y = 0, the value of y when there is a radio wave shielding body may be represented as a decimal such as y = 0.6 or y = 0.4 according to, for example, the radio wave shielding degree of the radio wave shielding body. The same applies to the value of y when there is no radio wave shielding body.

[0192] Furthermore, in step S7, the received power measured in the vicinity of the reference positions included in the target area described above is substituted into X(x 11 ,…,x mn ) in formula (19).

[0193] Here, in formula (19), m corresponds to the total number of rounds made by the plurality of moving bodies 1, and n in formula (19) corresponds to the number of reference positions included in the target area.

[0194] Note that the received power measured in the vicinity of the reference positions included in the target area is regarded as a power spectrum, the received power is converted from a decibel value to a linear value, and substituted into X in formula (19).

[0195] The processing unit 31 substitutes the known presence or absence of the radio wave shielding body into Y(y1,…,y m ), and X(x 11 ,…,xmn ) Based on the formula (19) (hereinafter referred to as learning data) into which the received power measured in the vicinity of the reference position included in the target area is substituted, the regression coefficient β (β1, …, β n ) is calculated. Since the formula (19) is in line with the theories of the above-mentioned formulas (1) to (12), according to the above-mentioned learning data, a good regression coefficient for estimating the presence or absence of a radio wave shielding body can be calculated.

[0196] Note that when calculating the regression coefficient in step S7, PLS regression is used. As described above, in PLS regression, orthogonal components (that is, components with low correlation) are extracted, so the influence of multicollinearity can be suppressed.

[0197] As described above, the regression coefficient calculated in step S7 is held in the processing unit 31 (estimation unit 31f) for use in the estimation process described later.

[0198] Here, in the present embodiment, it has been described that the target area is set using all the number of rounds and all the moving bodies 1 among the received powers (hereinafter referred to as reference received powers) measured in the vicinity of a plurality of reference positions when a plurality of moving bodies 1 repeatedly circle a path, but the target area may be set using some of the number of rounds and some of the moving bodies 1.

[0199] Specifically, as shown in FIG. 16 described above, since the received power data includes the moving body ID, based on the moving body ID, the characteristics of each individual of the moving body 1 in the above-mentioned reference received power (the received power included in the received power data) can be grasped. In terms of efficiency, it is preferable to use all of the reference received powers (that is, the received powers measured by all of the plurality of moving bodies 1), but in view of the variation in the received power due to the individual differences of the moving bodies 1, for example, the received power measured by a specific moving body 1 may be excluded from the reference received power to set the target area.

[0200] Furthermore, based on the time (the time when the received power was measured) and the position (the position of the mobile body 1 when the received power was measured) included in the received power data, the density of a plurality of mobile bodies 1 that are circulating along a route in the same time zone or the distance between the mobile bodies 1 is grasped, and the received power measured in the mobile body 1 in which the density is equal to or higher than a predetermined value or the distance between the mobile bodies 1 is less than a predetermined value is excluded from the reference received power to set a target area.

[0201] Also, in the present embodiment, for example, the received power considered to be an outlier may be excluded from the reference received power to set a target area.

[0202] Specifically, when the tendency of the received power measured by a specific mobile body 1 (the received power included in the received power data including the mobile body ID for identifying the mobile body) is different from the received power measured by other mobile bodies 1, the received power measured by the specific mobile body 1 may be excluded from the reference received power. Whether the tendencies of the received powers are different may be determined, for example, by comparing the average values of the received powers of each mobile body 1 for each reference position, or may be determined by other methods.

[0203] Furthermore, for example, when the tendencies of the received powers measured at a specific number of circulations are different or the positions of the mobile bodies 1 at a specific number of circulations are significantly deviated, the received powers measured at the specific number of circulations may be excluded from the reference received power.

[0204] Also, in the present embodiment, the received power measured at the position where the distance from the reference position is the shortest is used, but when the distance (the shortest distance) is equal to or greater than a threshold value, the received power and the received power measured in the same circulation as the received power may be excluded from the reference received power.

[0205] Note that although the description has been made here as excluding a part of the reference received power, the target area may be set using all of the reference received power by reducing the weight of the received power described as being excluded or applying an offset to the received power.

[0206] Further, a part of the reference received power that meets specific conditions based on the mobile body ID, number of laps, time, and position included in the received power data may be extracted, and the target area may be set using the extracted part of the reference received power. That is, the received power (a part of the reference received power) used to set the target area (calculate the VIP) in the present embodiment may be specified based on at least one of the mobile body ID, number of laps, time, and position included in the received power data.

[0207] Note that although the setting of the target area (calculation of the VIP) using a part of the reference received power has been described here, the number of received powers used when setting the target area is preferably the same (the same number) in each of the state where a radio wave shielding body is arranged in the target space and the state where no radio wave shielding body is arranged in the target space.

[0208] Also, when the target area is set using a part of the reference received power as described above, the regression coefficient shall be calculated within the range of the part of the reference received power used for setting the target area (that is, using the received power measured in the vicinity of the reference position included in the target area among the part of the reference received power).

[0209] Also, for example, when a stationary sensor (a sensor for measuring received power) is arranged on the ceiling, floor surface, or wall surface that forms the target space, etc., the received power measured by the stationary sensor (the received power transmitted from the stationary sensor to the information processing device 3) may be used as at least a part of the above-described reference received power. In other words, a stationary sensor may be used as a part of the function (received power measurement unit 14) for measuring the received power included in the mobile body 1.

[0210] Note that for the setting of the target area and the calculation of the regression coefficient in the present embodiment, for example, a learning model generated based on a technology called artificial intelligence (AI) may be used.

[0211] Next, with reference to the flowchart of FIG. 21, an example of the processing procedure of the above-described estimation process will be described.

[0212] In the estimation process, as a preprocessing (preparation) for estimating the presence or absence of a radio wave shielding body, the process of step S11 corresponding to the process of step S1 in FIG. 10 described above is executed, whereby map data and a received power map are created. The map data and the received power map created in this way are stored in the storage unit 32.

[0213] Note that when the map data and the received power map created in the process shown in FIG. 10 described above can be used in the estimation process, the process of step S11 may be omitted.

[0214] When the process of step S11 is executed, the operation of the movement control system can be started. In this case, the processing unit 31 (control unit 31g) included in the information processing apparatus 3 selects a path along which the moving body 1 in the target space moves based on the map data and the received power map stored in the storage unit 32 (step S12).

[0215] In step S12, the processing unit 31 performs cost calculation considering the received power at a position (space) overlapping the path for each of a plurality of paths from the start point to the goal point set on the map indicated by the map data, for example, and selects an optimal path from among the plurality of paths based on the result of the cost calculation.

[0216] The following briefly describes the cost calculation for route selection. First, the processing unit 31 refers to the received power map and acquires the received power assigned to each position (pixel) corresponding to each of a plurality of routes (such as the shortest route, intermediate route, and longest route) from the start point to the goal point. The processing unit 31 classifies the acquired received power into "strong", "medium", and "weak" based on a plurality of thresholds prepared in advance. In this case, for example, the value (cost) corresponding to "strong" is 1, the value (cost) corresponding to "medium" is 2, and the value (cost) corresponding to "weak" is 3. The processing unit 31 calculates the cost of each route by adding the values corresponding to the result of classification ("strong", "medium", and "weak") of the received power assigned to each position corresponding to each route for each route. The processing unit 31 selects, for example, the route with the lowest cost calculated in this way.

[0217] According to such cost calculation, for example, when there is no dead zone (area where the received power has decreased) in the target space, the cost of the shortest route is the lowest, so the shortest route is selected. On the other hand, for example, when a dead zone occurs on the shortest route, the cost of the shortest route increases, so, for example, an intermediate route is selected. Further, when dead zones occur on both the shortest route and the intermediate route, for example, the longest route is selected.

[0218] Note that it is conceivable to suppress the decrease in received power in the dead zone by using, for example, time diversity, frequency diversity, or space diversity. However, in this embodiment, priority is given to the more stable operation (movement) of the mobile body 1, and a route that avoids the dead zone is selected.

[0219] When the process of step S12 is executed, the processing unit 31 (control unit 31g) controls the mobile body 1 to move along the route selected in step S12 (step S13). Since the process of step S13 is the same as the process of step S3 shown in FIG. 10 described above, the detailed description thereof is omitted here.

[0220] Here, when the process of step S13 described above is executed, the mobile body 1 moves from the start point to the goal point along the path selected in step S12, and the mobile body 1 transmits the above-described map creation data and received power data to the information processing apparatus 3 via the base station 2 at each position during the movement.

[0221] In this case, the processing unit 31 (acquisition unit 31a) included in the information processing apparatus 3 acquires the map creation data and the received power data transmitted from the mobile body 1 that has moved along the path selected in step S12 from the base station 2 (step S14).

[0222] When the process of step S14 is executed, the processing unit 31 (map data creation unit 31b) updates the map data stored in the storage unit 32 based on the map creation data acquired in step S14 (step S15). Note that since only the map creation data on the path selected in step S12 is acquired in step S14, only the peripheral portion of the map indicated by the map data along the path is updated in step S15.

[0223] Furthermore, the processing unit 31 (received power map creation unit 31c) updates the received power map stored in the storage unit 32 based on the map creation data and the received power data acquired in step S14 (step S16).

[0224] Here, assuming that a path (for example, path 400A shown in FIG. 8) that avoids the dead zone is selected in step S12 described above, only the map creation data and the received power data on the path are acquired in step S14. For this reason, in step S16, only the received power assigned to each position on the path that avoids the dead zone of the received power map is updated.

[0225] That is, in the received power map updated in step S16 described above, it is impossible to determine whether the dead zone on the path where the mobile body 1 has not moved has been eliminated.

[0226] The dead zone is eliminated, for example, by removing a radio wave shielding body. However, the mobile body 1 in the present embodiment may be able to detect the presence or absence of obstacles arranged in the target space by the LRF. However, since the LRF cannot determine, for example, the height of an obstacle, the dead zone may be eliminated when the height of an obstacle detected by the LRF is low, for example. Further, for example, when the obstacle detected by the LRF is not a radio wave shielding body, the dead zone may be eliminated even if the obstacle is detected. That is, it is difficult to estimate the elimination of the dead zone (that is, the presence or absence of a radio wave shielding body) by the LRF.

[0227] Therefore, in the present embodiment, the processing unit 31 (estimation unit 31f) uses the regression coefficient calculated by executing the above-described learning process (the regression coefficient held in the processing unit 31) and the received power measured by the mobile body 1 moving along the path selected in step S12 to estimate the presence or absence of a radio wave shielding body (whether the radio wave shielding body has been removed) (step S17).

[0228] When the process of step S17 is executed, the path selected in step S12 is assumed to be the same path as the path selected in step S2 shown in FIG. 10 described above (that is, the path for which the regression coefficient was calculated).

[0229] Hereinafter, the process of step S17 will be described. In step S17, the processing unit 31 acquires, from the received power map, the received power measured at each position on the path by moving along the path selected in step S12.

[0230] Note that the received power acquired by the processing unit 31 here is the received power measured in the vicinity of the reference positions included in the target area among the reference positions set on the path in the above-described learning process. Here, for convenience of explanation, the received power thus acquired by the processing unit 31 is denoted as x1, …, x n Let it be so. Note that the information on the target area (reference positions included therein) set in the learning process is assumed to be held in the processing unit 31 when the learning process is executed.

[0231] Also, the received power acquired by the processing unit 31 may be the received power measured by at least one moving body 1, or may be the received power measured by a plurality of moving bodies 1, or may be the received power measured by one or a plurality of moving bodies 1 repeating the route.

[0232] Next, in step S17, the processing unit 31 substitutes the regression coefficients (β1, …, β n ) held in the processing unit 31 and the received power (x1, …, x n ) acquired as described above into Equation (22) to calculate the value of y (hereinafter referred to as the estimated value), and estimates the presence or absence of a radio wave shielding body based on the calculated estimated value.

[0233] The presence or absence of a radio wave shielding body can be estimated (determined) based on the magnitude of the estimated value with respect to the threshold value. As an example, when the regression coefficients are calculated assuming that y = 1 when there is a radio wave shielding body and y = 0 when there is no radio wave shielding body as described above, for example, 0.5 is set as the threshold value. According to this, the processing unit 31 can estimate that there is a radio wave shielding body when the estimated value is 0.5 or more, and can estimate that there is no radio wave shielding body when the estimated value is less than 0.5.

[0234] When the process of step S17 is executed, the processing unit 31 (estimation unit 31f) reflects the estimation result of the presence or absence of the radio wave shielding body in step S17 in the received power map stored in the storage unit 32 (step S18). Specifically, when it is estimated in step S17 described above that there is no radio wave shielding body, in step S18, it is considered that the radio wave propagation environment in the area including the position facing the antenna 2a across the position where the radio wave shielding body was arranged (that is, the area located on the back side of the radio wave shielding body as viewed from the antenna 2a) has improved, and a process of updating the received power map is executed to increase the received power assigned to the area. On the other hand, when it is estimated in step S17 that there is a radio wave shielding body, in step S18, it is considered that the radio wave propagation environment in the area located on the back side of the radio wave shielding body has not improved, and the received power map is not updated.

[0235] When the process of step S18 described above is executed, the process returns to step S12 and is repeated. According to this, for example, when a dead zone is generated on the path where the moving body 1 has moved due to the newly arranged radio wave shielding body, a path avoiding the dead zone is selected based on the received power map updated in step S16 in response to the decrease in the received power in the dead zone. Also, when a path avoiding the dead zone generated by the radio wave shielding body is selected in step S12 described above, if it is estimated in step S17 that there is no radio wave shielding body, a path (for example, the shortest path) passing through the area located on the back side of the radio wave shielding body can be selected based on the received power map in which the estimation result is reflected in step S18. On the other hand, when it is estimated in step S17 that there is a radio wave shielding body, the received power map is not updated, and since the received power in the area located on the back side of the radio wave shielding body remains low, it is possible to avoid selecting a path passing through the area.

[0236] That is, in the present embodiment, the processing unit 31 (control unit 31g) can select an appropriate path based on the estimation result of the presence or absence of the radio wave shielding body described above and control the moving body 1.

[0237] In FIG. 21, for example, a situation is assumed in which the moving body 1 repeatedly circulates along a route from a start point set on a map shown by map data to a goal point. However, the process shown in FIG. 21 may be terminated at a timing when, for example, the control of the moving body 1 (that is, the transportation of luggage by the moving body 1, etc.) that has been predetermined is terminated.

[0238] Also, in step S18, it has been described that when it is estimated that there is no radio wave shielding body, the reception power map is updated so as to increase the reception power assigned to the area located on the back side of the radio wave shielding body. However, the reception power assigned to the area may be deleted. According to this, when no reception power is assigned, by performing cost calculation so that the cost is 0, it is possible to select a route passing through the area located on the back side of the radio wave shielding body.

[0239] Furthermore, in the process shown in FIG. 21, it has been described that the reception power map is updated based on the estimation result of the presence or absence of the radio wave shielding body in step S17. However, the estimation result may be used for the control of the moving body 1 (for example, selection of a route, etc.). Also, the estimation result of the presence or absence of the radio wave shielding body in step S17 may be used for other processes, or may be output from the information processing device 3 to the external device for use in processes executed in the external device.

[0240] Also, when the setting of the target area and the calculation of the regression coefficient are performed using only a part of the reference reception power in the above-described learning process, similarly in the estimation process, the reception power corresponding to a part of the reference reception power shall be used. Specifically, when the reception power of a specific moving body (moving body ID) is not adopted (excluded) in the learning process (setting of the target area and calculation of the regression coefficient), when estimating the presence or absence of the electric shielding body, the reception power of the moving body may be excluded, or the estimation result using the reception power of the moving body may be discarded.

[0241] Hereinafter, a specific example of the operation of the information processing apparatus 3 during the estimation process will be described using the example shown in FIG. 8 above. Here, it is assumed that the above-described learning process has already been executed, and the regression coefficients have been calculated based on the received power measured by repeatedly orbiting a plurality of moving bodies 1 along the path 400A in a state where the obstacle 402, which is a radio wave shielding body, is arranged and in a state where the obstacle 402 is not arranged.

[0242] First, by moving the moving body 1 within the target space shown in FIG. 8, map data and a received power map are created. Here, it is assumed that the obstacle 402, which is a radio wave shielding body, is not arranged and that there is no dead zone within the target space (the radio wave propagation environment within the target space is good).

[0243] Next, based on the above-described map data and received power map, a path along which the moving body 1 moves is selected. Here, it is assumed that the path 400B is the shortest path compared to the path 400A, and the path 400B is selected.

[0244] When the path 400B is selected as described above, the moving body 1 is controlled to move from the start point to the goal point (carry the load) along the path 400B.

[0245] Note that while the moving body 1 is moving along the path 400B, it transmits map creation data and received power data at each position on the path 400B. In this case, the map data and the received power map are updated based on the map creation data and the received power data transmitted from the moving body 1.

[0246] Here, it is assumed that the obstacle 402 is arranged while the moving body 1 is moving along the path 400B. In this case, the area facing the antenna 2a across the obstacle 402 (the back side of the obstacle 402 as seen from the antenna 2a) becomes a dead zone, and the received power map is updated so as to assign a reduced received power to the area.

[0247] According to such a received power map, a path 400A that avoids the dead zone is selected as the path along which the moving body 1 moves, and the moving body 1 is controlled to move from the start point to the goal point along the path 400A.

[0248] Note that while moving along the path 400A, the moving body 1 transmits map creation data and received power data at each position on the path 400A. In this case, the map data and the received power map are updated based on the map creation data and the received power data transmitted from the moving body 1.

[0249] Here, based on the regression coefficient calculated based on the received power measured by repeatedly orbiting the path 400A during the learning process as described above, and the received power measured by the moving body 1 while moving along the path 400A during the estimation process (that is, during the operation of the movement control system), the presence or absence of a radio wave shielding body (here, the obstacle 402) is estimated.

[0250] If the estimation result is that there is a radio wave shielding body, the area on the path 400B that is out of sight from the antenna 2a due to the radio wave shielding body is regarded as a dead zone, and the path 400A along which the moving body 1 has moved is not changed (that is, the moving body 1 is continuously controlled to move along the path 400A).

[0251] On the other hand, if the estimation result is that there is no radio wave shielding body, it is considered that the area on the path 400B is not a dead zone (the dead zone generated by the radio wave shielding body has been eliminated), and the path 400A along which the moving body 1 has moved is changed to the path 400B (that is, the moving body 1 is controlled to move along the path 400B).

[0252] As described above, in the state where the radio wave shielding body is arranged at the first position in the target space, based on the radio waves radiated from the antenna 2a (signal radiation source), the received power (first received power) is acquired on the path of the moving body 1 passing between the antenna 2a and the radio wave shielding body. In the state where the radio wave shielding body is not arranged at the first position in the target space, the received power (second received power which is the radio wave radiated from the signal radiation source) measured on the path is acquired. Based on the index regarding the variation of the acquired received power (variation between the first received power and the second received power), a partial area on the path is set as a target area used for the process related to the control of the moving body 1.

[0253] In this embodiment, the process related to the control of the moving body 1 is executed based on the received power (third received power) measured in the target area. The process related to the control of the moving body 1 includes, for example, a learning process for calculating a coefficient (regression coefficient) used for estimating the presence or absence of the radio wave shielding body and an estimation process for estimating the presence or absence of the radio wave shielding body using the coefficient.

[0254] In this embodiment, with the above-described configuration, by setting a target area where the variation of the received power due to the reflected wave from the radio wave shielding body can be appropriately observed, it is possible to obtain a highly accurate regression coefficient using the received power measured in the target area.

[0255] Also, in this embodiment, since it is possible to estimate the presence or absence of the radio wave shielding body with high accuracy using such a regression coefficient, it is possible to select a path that can efficiently move the moving body based on the estimation result.

[0256] That is, the information processing apparatus 3 according to this embodiment can estimate the elimination of the dead zone from the safe zone based on the communication or control perspective even when the variation of the received power is large, and it can be said that it is useful for efficiently controlling the moving body 1.

[0257] In addition, in the present embodiment, VIP is used as an index regarding fluctuations in received power. Further, in the present embodiment, the target area may be set based on the positions of the radio wave shielding body and the antenna 2a. According to such a configuration, it is possible to set a target area in which fluctuations in received power due to reflected waves from the radio wave shielding body can be observed more appropriately. Also, in the present embodiment, by using a large number of received powers measured by a plurality of moving bodies 1 that repeatedly orbit the path, it is possible to set a target area with high robustness (or versatility).

[0258] Furthermore, in the present embodiment, the VIP (value) is calculated based on the received power measured at a position where the distance from the reference position set on the path is equal to or less than a predetermined value each time of orbiting (that is, in the vicinity of the reference position). In the present embodiment, with such a configuration, even when received power is measured at different positions on the same path, it is possible to reduce the influence of variations in received power due to the deviation of the position on the calculation of the regression coefficient and the estimation of the presence or absence of the radio wave shielding body.

[0259] Also, in the present embodiment, the VIP is calculated based on a matrix having the received power measured in the vicinity of the reference position each time of orbiting as a component. In the present embodiment, by treating the received power as a matrix of position and orbiting (samples), there is an advantage that it becomes easier to select an area in which fluctuations in received power due to reflected waves from the radio wave shielding body can be observed. Also, such a matrix-form received power is easy to handle in the estimation of the presence or absence of the radio wave shielding body by regression calculation.

[0260] Also, when there is a strong correlation (multicollinearity) between each column of the matrix, the regression coefficient becomes unstable. In the present embodiment, since the PLS regression for extracting orthogonal components, that is, components with low correlation, is applied to calculate the coefficient, it is possible to suppress the influence of the multicollinearity.

[0261] Note that the received power used to calculate the VIP in this embodiment may be a part of the received power measured by a plurality of moving bodies 1 that repeatedly circle a path. Specifically, the received power from which outliers and the like have been excluded is identified based on at least one of the moving body ID, the number of laps, the time, and the position included in the received power data, and the VIP can be calculated using the identified received power. In this embodiment, such a configuration makes it possible to set a more appropriate target area.

[0262] Here, with reference to FIG. 22, the communication state based on the relationship between the presence or absence of an actual radio wave shielding body (obstacle 402) in the target space shown in FIG. 8 described above and the estimation result of the presence or absence of the radio wave shielding body will be described.

[0263] As shown in FIG. 22, when it is estimated that there is a radio wave shielding body when moving along path 400A in a state where there is actually a radio wave shielding body, the estimation result is correct. According to such an estimation result, since the moving body 1 will continue to move along path 400A, it can be said that the communication executed between the moving body 1 and the antenna 2a is good.

[0264] On the other hand, when it is estimated that there is no radio wave shielding body when moving along path 400A in a state where there is actually a radio wave shielding body, the estimation result is incorrect. According to such an estimation result, the path along which the moving body 1 moves is changed from path 400A to path 400B. However, since there is actually a radio wave shielding body (obstacle 402) arranged, the communication executed between the moving body 1 moving behind the radio wave shielding body and the antenna 2a deteriorates.

[0265] Furthermore, when it is estimated that there is a radio wave shielding body when moving along path 400A in a state where there is actually no radio wave shielding body, the estimation result is incorrect. According to such an estimation result, since the moving body 1 will continue to move along path 400A, it can be said that the communication executed between the moving body 1 and the antenna 2a is good.

[0266] On the one hand, if it is estimated that there is no radio wave shielding body by moving along path 400A in a state where there is actually no radio wave shielding body, the estimation result is correct. According to such an estimation result, the path along which the moving body 1 moves is changed from path 400A to path 400B. In this case, since there is actually no radio wave shielding body (obstacle 402) arranged, it can be said that the communication executed between the moving body 1 and the antenna 2a is good.

[0267] That is, there are four possible combinations of the actual presence or absence of a radio wave shielding body and the estimation result of the presence or absence of a radio wave shielding body, but the cases that must be avoided at least are limited. Specifically, for example, when it is estimated that there is a radio wave shielding body when there is actually no radio wave shielding body, the estimation result is incorrect, and path 400A is not changed even though there is actually no radio wave shielding body. However, in this case, although it is not possible to realize an improvement in the cargo transportation efficiency by moving along path 400B, good communication between the moving body 1 and the antenna 2a is maintained. On the other hand, when it is estimated that there is no radio wave shielding body when there is actually a radio wave shielding body, the estimation result is incorrect, and path 400A is changed to path 400B even though there is actually a radio wave shielding body. In this case, since the moving body 1 goes around the back side of the radio wave shielding body by moving along path 400B, the communication between the moving body 1 and the antenna 2a deteriorates, and there is a possibility that the moving body 1 becomes uncontrollable.

[0268] Therefore, it can be said that even if the estimation result is incorrect, if good communication can be maintained, the estimation result will not have a great impact on the operation of the movement control system. However, if the estimation result is incorrect and the communication deteriorates, it will affect the operation of the movement control system. For this reason, in the present embodiment, it is preferable to avoid a case where it is estimated that there is no radio wave shielding body even though there is actually a radio wave shielding body.

[0269] Therefore, in the present embodiment, considering the above circumstances, instead of changing the route based on a single estimation result, a configuration is adopted in which, for example, the route is changed using a plurality of estimation results obtained by executing the estimation process a plurality of times, so as to avoid, as much as possible, a situation where the moving body 1 becomes uncontrollable when it moves to the back side of the radio wave shielding body despite the actual presence of the radio wave shielding body. Specifically, for example, a configuration can be considered in which the route is changed only when an estimation result indicating the absence of a radio wave shielding body is continuously obtained a predetermined number of times.

[0270] Also, in the present embodiment, it has been described that the threshold value compared with the estimated value for estimating the presence or absence of the above-described radio wave shielding body is 0.5, but the threshold value may be other than 0.5. Since it is assumed that the estimated value calculated in the estimation process varies depending on the target space (such as the layout), for example, an estimation of the presence or absence of a radio wave shielding body using the regression coefficient calculated in the learning process is performed a plurality of times in a training period in which the presence or absence of the radio wave shielding body is known, and an appropriate threshold value that matches the known presence or absence of the radio wave shielding body for the estimation results obtained in the training period may be set.

[0271] In the present embodiment, as shown in FIG. 6, the processing unit 31 includes the calculation unit 31e and the estimation unit 31f (that is, the information processing device 3 has both the function of calculating the regression coefficient and the function of estimating the presence or absence of the radio wave shielding body). However, the information processing device 3 according to the present embodiment may be configured to have only one of the functions (that is, execute only one of the above-described learning process and estimation process).

[0272] Furthermore, the information processing device 3 according to the present embodiment may have, for example, a function of setting a target area useful for executing processing related to the control of the moving body 1, and the function of calculating the above-described regression coefficient and the function of estimating the presence or absence of the radio wave shielding body may be arranged outside the information processing device 3.

[0273] In addition, in this embodiment, although mainly described as a case where a plurality of mobile bodies 1 repeatedly orbit (move) along a path, the number and the number of orbits of the mobile bodies 1 may be changed as appropriate. Specifically, this embodiment can be realized, for example, even in a configuration where one mobile body 1 repeatedly orbits along a path, or even in a configuration where a plurality of mobile bodies 1 move along the path once each.

[0274] Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and their modifications are included in the scope and gist of the invention, and are also included in the invention described in the claims and the equivalent scope thereof.

[0275] Regarding the above-described embodiments, the following additional notes are disclosed. [1] First acquisition means for acquiring first received power on the path of a mobile body passing between the signal radiation source and the radio wave shielding body based on radio waves radiated from the signal radiation source in a state where a radio wave shielding body that shields radio waves is disposed at a first position; Second acquisition means for acquiring second received power, which is radio waves radiated from the signal radiation source measured on the path, in a state where the radio wave shielding body is not disposed at the first position; Setting means for setting a partial area on the path as a target area used for processing related to control of the mobile body based on an index related to the variation between the first received power and the second received power An information processing apparatus comprising: [2] The index related to the variation between the first received power and the second received power includes VIP (Variable Influence on Projection). The information processing apparatus according to [1]. [3] The setting means is the information processing apparatus according to [2], which sets a partial area on the path as the target area based on the positions of the radio wave shielding body and the signal radiation source. [4] The first and second received powers are measured by a plurality of moving bodies that circulate along the path. The VIP is calculated based on the first and second received powers measured at positions where the distance from the reference position set on the path is equal to or less than a predetermined value each time the path is circulated. The information processing apparatus according to [2] or [3]. [5] The VIP is calculated based on a matrix having, as components, the first and second received powers measured at positions where the distance from the reference position is equal to or less than a predetermined value each time the path is circulated, according to the information processing apparatus of [4]. [6] The first and second received powers are measured by a plurality of moving bodies that circulate along the path. The first acquisition means further acquires identification information for identifying the moving body that measured the first received power and the position of the moving body. The second acquisition means further acquires identification information for identifying the moving body that measured the second received power and the position of the moving body. The VIP is calculated based on a part of the first and second received powers specified using the position of the moving body and the identification information. The information processing apparatus according to any one of [2] to [5]. [7] The first and second received powers are measured by a plurality of moving bodies that circulate along the path. The first acquisition means further acquires the number of times the path has been circulated when the first received power is measured. The second acquisition means further acquires the number of times the path has been circulated when the second received power is measured. The VIP is calculated based on a part of the first and second received powers specified using the number of times of circulation. The information processing apparatus according to any one of [2] to [6]. [8] The first and second received powers are measured by a plurality of moving objects that circulate along the path. The first acquisition means further acquires the time at which the first received power is measured. The second acquisition means further acquires the time at which the second received power is measured. The VIP is calculated based on a part of the first and second received powers specified using the time. The information processing apparatus according to any one of [2] to [7]. [9] The information processing apparatus according to any one of [1] to [8], further comprising processing means for executing processing related to control of the moving object based on a third received power measured in the target area.

[10] The processing means includes estimation means for executing, as processing related to control of the moving object, a process of estimating the presence or absence of the radio wave shielding body based on a third received power measured in the target area, which is a part of the first and second received powers. The information processing apparatus according to [9].

[11] The information processing apparatus according to

[10] , further comprising control means for controlling the moving object based on the estimation result.

[12] The processing means includes calculation means for executing, as processing related to control of the moving object, a process of calculating a coefficient used for estimating the presence or absence of the radio wave shielding body based on a third received power measured in the target area, which is a part of the first and second received powers. The information processing apparatus according to any one of [9] to

[11] .

[13] The calculation means calculates the coefficient by applying PLS (Partial Least Squares) regression. The information processing apparatus according to

[12] .

[14] An information processing apparatus according to any one of [1] to

[13] , and the signal radiation source A system comprising the same.

[15] The system according to

[14] , further comprising the moving object.

[16] A program executed by a computer of an information processing apparatus, causing the computer to acquire first received power on a path of a moving body passing between the signal radiation source and the radio wave shielding body based on radio waves radiated from the signal radiation source in a state where a radio wave shielding body that shields radio waves is disposed at a first position; acquire second received power, which is radio waves radiated from the signal radiation source measured on the path, in a state where the radio wave shielding body is not disposed at the first position; set, based on an index related to a variation between the first received power and the second received power, a partial area on the path as a target area to be used for processing related to control of the moving body; and a program for causing the above to be executed.

Description of Reference Numerals

[0276] 1... Moving body, 2... Base station, 2a... Antenna (signal radiation source), 3... Information processing apparatus, 11... Receiving unit, 12... Control unit, 13... Distance measuring unit, 14... Received power measuring unit, 15... Transmitting unit, 31... Processing unit, 31a... Acquisition unit, 31b... Map data creation unit, 31c... Received power map creation unit, 31d... Setting unit, 31e... Calculation unit, 31f... Estimation unit, 31g... Control unit, 31h... Output unit, 301... CPU, 302... Non-volatile memory, 303... RAM, 304... Communication device.

Claims

1. With a radio wave shielding body that shields radio waves disposed at a first position, based on the radio waves radiated from a signal radiation source, first acquisition means for acquiring first received power on the path of a moving body passing between the signal radiation source and the radio wave shielding body; Second acquisition means for acquiring second received power, which is radio waves radiated from the signal radiation source measured on the path, in a state where the radio wave shielding body is not disposed at the first position; Setting means for setting, based on an index related to the variation between the first received power and the second received power, a partial area on the path as a target area used for processing related to the control of the moving body An information processing apparatus comprising:

2. The information processing apparatus according to claim 1, wherein the index related to the variation between the first received power and the second received power includes VIP (Variable Influence on Projection).

3. The information processing apparatus according to claim 2, wherein the setting means sets a partial area on the path as the target area based on the positions of the radio wave shielding body and the signal radiation source.

4. The first and second received powers are measured by a plurality of moving bodies that orbit the path, The VIP is calculated based on the first and second received powers measured at positions where the distance from a reference position set on the path each time of orbiting is equal to or less than a predetermined value. The information processing apparatus according to claim 2.

5. The information processing apparatus according to claim 4, wherein the VIP is calculated based on a matrix having, as components, the first and second received powers measured at positions where the distance from the reference position each time of orbiting is equal to or less than a predetermined value.

6. The first and second received powers are measured by a plurality of moving bodies that orbit the path, The first acquisition means further acquires identification information for identifying the mobile body that has measured the first received power and the position of the mobile body. The second acquisition means further acquires identification information for identifying the mobile body that has measured the second received power and the position of the mobile body. The VIP is calculated based on a part of the first and second received powers specified using the position of the mobile body and the identification information. The information processing apparatus according to claim 2.

7. The first and second received powers are measured by a plurality of mobile bodies that orbit the route. The first acquisition means further acquires the number of orbits of the route when the first received power is measured. The second acquisition means further acquires the number of orbits of the route when the second received power is measured. The VIP is calculated based on a part of the first and second received powers specified using the number of orbits. The information processing apparatus according to claim 2.

8. The first and second received powers are measured by a plurality of mobile bodies that orbit the route. The first acquisition means further acquires the time when the first received power is measured. The second acquisition means further acquires the time when the second received power is measured. The VIP is calculated based on a part of the first and second received powers specified using the time. The information processing apparatus according to claim 2.

9. The information processing apparatus according to claim 1, further comprising processing means for executing processing related to the control of the mobile body based on a third received power measured in the target area.

10. The processing means includes estimation means for executing, as processing related to the control of the mobile body, a process of estimating the presence or absence of the radio wave shielding body based on the third received power measured in the target area. The information processing apparatus according to claim 9.

11. The information processing apparatus according to claim 10, further comprising control means for controlling the moving body based on the estimation result.

12. The processing means includes calculation means for executing a process of calculating a coefficient used for estimating the presence or absence of the radio wave shielding body based on a third received power measured in the target area which is a part of the first and second received powers, as a process related to the control of the moving body. The information processing apparatus according to claim 9.

13. The information processing apparatus according to claim 12, wherein the calculation means calculates the coefficient by applying PLS (Partial Least Squares) regression.

14. An information processing apparatus according to any one of claims 1 to 13, and the signal radiation source A system comprising.

15. The system according to claim 14, further comprising the moving body.

16. A program executed by a computer of an information processing apparatus, causing the computer to In a state where a radio wave shielding body that shields radio waves is arranged at a first position, based on radio waves radiated from a signal radiation source, obtaining a first received power on a path of a moving body passing between the signal radiation source and the radio wave shielding body; Obtaining a second received power which is radio waves radiated from the signal radiation source measured on the path in a state where the radio wave shielding body is not arranged at the first position; Setting a partial area on the path as a target area used for processing related to the control of the moving body based on an index related to the variation between the first received power and the second received power A program for causing the execution.

Images