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

Abstract

Provided is a position estimation device capable of properly determining the position of a moving body. A position estimation device (10) according to the present disclosure is provided with: an acquisition unit (11) that acquires shape information of the surface of a structure around a moving body; an extraction unit (12) that extracts, from the shape information, feature portions representing shape changes on the surface of the structure, and extracts feature information including the position and size of the feature portions; a holding unit (13) that holds, in advance, reference information including the position and size of a reference portion that serves as a reference for position estimation; and an estimation unit (14) that compares the feature information with the reference information to estimate the current position of the moving body.

Description

[Technical Field]

[0001] The present disclosure relates to a position estimation device, a mobile system, a position estimation method, and a non-transitory computer-readable medium. [Background technology]

[0002] In recent years, vehicle navigation systems that use signals transmitted from GPS (Global Positioning System) satellites have come into use. Using such systems allows users to grasp the vehicle's location in real time while it is moving. However, in areas such as tunnels, signals from GPS satellites cannot be received by the vehicle's on-board device. As a result, users are unable to accurately grasp the vehicle's location. In such cases, it may be possible to use current location estimation technologies based on sensor data, such as SLAM (Simultaneous Localization and Mapping). However, unlike urban areas, the surrounding environment in tunnels and other areas changes little, making it difficult for sensor data to change. Therefore, even with SLAM, it is difficult to determine the vehicle's location in tunnels and other areas.

[0003] As a related technique, Patent Document 1 discloses a train position detection device capable of detecting the position of a train inside a tunnel or the like. The device includes a train device and a central management device. The train device has a light emitting means capable of emitting light at different angles relative to the train's traveling direction onto a predetermined area on a plane in front of the train, and a light receiving means capable of receiving light reflected from an object. The train device also determines the outer shape of an object ahead of the train based on the light emitting angle and the time between emitting the light and receiving the reflected light. The train device then detects the train's position based on the determined outer shape of the object and a pre-stored object information database and position information database. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2021-024521 Summary of the Invention [Problem to be solved by the invention]

[0005] When using the technology disclosed in Patent Document 1, an object to be illuminated by light is required ahead of the train. Therefore, if such an object is not installed in the tunnel, new equipment to be illuminated for train position detection must be installed, which increases costs. Furthermore, in some cases, such equipment cannot be easily installed, for example, in a water conduit.

[0006] In view of these problems, an object of the present disclosure is to provide a position estimation device, a mobile body system, a position estimation method, and a non-transitory computer-readable medium that are capable of appropriately determining the position of a mobile body. [Means for solving the problem]

[0007] The position estimation device according to the present disclosure comprises: A position estimation device that estimates a current position of a moving object, An acquisition means for acquiring shape information of the surface of a structure around the moving object; an extraction means for extracting characteristic locations that indicate shape changes on the surface of the structure from the shape information and extracting characteristic information including the positions and sizes of the characteristic locations; a storage means for storing in advance reference information including the position and size of a reference point that serves as a reference for position estimation; and an estimation means for estimating the current position of the mobile object by comparing the characteristic information with the reference information.

[0008] The mobile system according to the present disclosure includes: A moving object and a position estimation device mounted on the moving body, the position estimation device, An acquisition means for acquiring shape information of the surface of a structure around the moving object; an extraction means for extracting characteristic points that indicate shape changes on the surface of the structure from the shape information and extracting characteristic information including the positions and sizes of the characteristic points; a storage means for storing in advance reference information including the position and size of a reference point that serves as a reference for position estimation; and an estimation means for estimating the current position of the mobile object by comparing the characteristic information with the reference information.

[0009] The location estimation method according to the present disclosure includes: A position estimation method for estimating a current position of a moving object, comprising: Obtaining shape information of the surface of structures around the moving object, extracting characteristic locations that indicate shape changes on the surface of the structure from the shape information, and extracting characteristic information including the positions and sizes of the characteristic locations; The current position of the mobile object is estimated by comparing the characteristic information with reference information including the position and size of a reference point that serves as a reference for position estimation.

[0010] A non-transitory computer-readable medium storing a program according to the present disclosure includes: A non-transitory computer-readable medium storing a program for causing a computer to execute a position estimation method for estimating a current position of a moving object, An acquisition process for acquiring shape information of the surface of a structure around the moving object; an extraction process for extracting characteristic locations that indicate shape changes on the surface of the structure from the shape information and extracting characteristic information including positions and sizes of the characteristic locations; an estimation process for estimating the current position of the moving object by comparing the characteristic information with reference information including the position and size of a reference point that serves as a reference for position estimation; Have the computer run it. [Effects of the Invention]

[0011] The present disclosure makes it possible to provide a position estimation device, a mobile body system, a position estimation method, and a non-transitory computer-readable medium that are capable of appropriately determining the position of a mobile body. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a block diagram showing a configuration of a position estimation device according to a first embodiment. [Figure 2] 4 is a flowchart showing a position estimation process according to the first embodiment. [Figure 3] FIG. 10 is a schematic diagram of a mobile body system according to a second embodiment. [Figure 4] FIG. 10 is a block diagram showing the configuration of a mobile system according to a second embodiment. [Figure 5] FIG. 10 is a diagram showing an example of a reference point according to the second embodiment. [Figure 6] 6 is a diagram showing an example of reference information corresponding to the reference location shown in FIG. 5. FIG. [Figure 7] 10A and 10B are diagrams illustrating an example of an outline of sensing performed by a sensor according to a second embodiment and an example of characteristic points. [Figure 8] 8 is a diagram showing an example of characteristic information corresponding to the characteristic location shown in FIG. 7. FIG. [Figure 9] 10 is a flowchart showing a position estimation process according to the second embodiment. [Figure 10] FIG. 10 is a block diagram showing the configuration of a mobile system according to a third embodiment. [Figure 11] FIG. 10 is a diagram illustrating an outline of sensing performed by a first sensor and a second sensor according to a third embodiment. [Figure 12] FIG. 13 is a diagram showing an example of reference information according to the fourth embodiment. [Figure 13] 13A and 13B are diagrams illustrating an example of an outline of sensing by a sensor according to a fourth embodiment, a reference location, and a characteristic location. [Figure 14] 10 is a flowchart showing a position estimation process according to the fourth embodiment. [Figure 15] FIG. 2 is a block diagram illustrating an example of a hardware configuration. DETAILED DESCRIPTION OF THE INVENTION

[0013] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In each drawing, the same or corresponding elements are designated by the same reference numerals. For clarity of explanation, duplicated explanations will be omitted as necessary.

[0014] <Embodiment 1> Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. 1 is a block diagram showing the configuration of a position estimation device 10 according to this embodiment. The position estimation device 10 is an information processing device that estimates the current position of a moving object. The position estimation device 10 includes an acquisition unit 11, an extraction unit 12, a storage unit 13, and an estimation unit 14.

[0015] The acquisition unit 11 acquires shape information of the surface of structures around the moving object. The extraction unit 12 extracts characteristic locations that indicate changes in the shape of the surface of the structure from the shape information, and extracts characteristic information including the positions and sizes of the characteristic locations. The storage unit 13 stores in advance reference information including the position and size of a reference point that serves as a reference for position estimation. The estimation unit 14 compares the feature information with the reference information to estimate the current position of the moving object.

[0016] 2 is a flowchart showing the position estimation process performed by the position estimation device 10 according to this embodiment. Note that the storage unit 13 is assumed to store in advance reference information including the position and size of a reference point.

[0017] First, the acquisition unit 11 acquires shape information of the surface of structures around the moving object (S11). Next, the extraction unit 12 extracts characteristic features from the shape information and extracts characteristic information including the positions and sizes of the characteristic features (S12). Then, the estimation unit 14 compares the characteristic information with reference information to estimate the current position of the moving object (S13).

[0018] As described above, the position estimation device 10 according to this embodiment estimates the current position of a moving object based on pre-stored reference information and feature information extracted from the surfaces of structures around the moving object. The feature information includes information indicating changes in the shape of the surfaces of the structures. With this configuration, the position estimation device 10 according to this embodiment can appropriately determine the position of the moving object.

[0019] <Embodiment 2> Next, a description will be given of a configuration example of a mobile system 1000 according to the second embodiment. This embodiment is a specific example of the first embodiment described above. The mobile body system 1000 includes a mobile body and a position estimation device 100 mounted on the mobile body. The mobile body system 1000 estimates the current position of the mobile body by performing a position estimation process in the position estimation device 100.

[0020] In this embodiment, the position of a moving object can be estimated even in an environment where signals from GPS satellites cannot be received, and therefore, this method is applicable to cases where a moving object moves inside a hollow structure such as a tunnel or a waterway.

[0021] A mobile body is equipped with a means of transportation for moving within a space. The means of transportation may include, for example, a drive mechanism for moving on the ground, in the air, on the water surface, or underwater. The mobile body may be, for example, an automobile, a train, or a drone. The mobile body may also be a person. For example, the mobile body system 1000 may be realized by a person carrying the position estimation device 100. Alternatively, the position estimation device 100 may be placed on a cart or the like, and the person may walk around pushing the cart.

[0022] An overview of the mobile system 1000 will be described with reference to FIG. 3 is a schematic diagram of a mobile body system 1000 according to this embodiment. As shown in the figure, in this embodiment, the structure is a tunnel 20 for vehicles, and the mobile body is a vehicle 200 traveling in the tunnel 20.

[0023] The vehicle 200 is equipped with the position estimation device 100. The vehicle 200 also includes a sensor 111 capable of sensing the inside of the tunnel 20. The sensor 111 scans the inner wall W of the tunnel 20 to obtain shape information of the surface of the inner wall W. The shape information will be described later.

[0024] In this embodiment, the positional relationship of the components may be explained using the coordinate system shown in FIG. 3. Here, the axial direction of the tunnel 20 is the x-axis, the width direction is the y-axis, and the vertical direction is the z-axis. These axial directions are common to the subsequent drawings. In FIG. 3, the vehicle 200 enters the tunnel 20 from the right side of the paper and travels in the x-axis direction as indicated by the white arrow. The vehicle 200 travels inside the tunnel 20 while scanning the inner wall W of the tunnel 20 using the sensor 111.

[0025] The position estimation device 100 scans the inner wall W in the order of, for example, each of the sections S1, S2, S3, ... shown in Fig. 3. The sections S1, S2, S3, ... are regions obtained by dividing the traveling direction of the vehicle 200 (the positive direction of the x-axis) at predetermined distance intervals, and are shown for convenience of explanation. The position estimation device 100 acquires the scan results for each section and performs a position estimation process, which will be described later, using the scan results. In this way, the position estimation device 100 estimates the current position of the vehicle 200.

[0026] Next, the configuration of the mobile system 1000 will be described. 4 is a block diagram showing the configuration of a mobile system 1000 according to this embodiment. The mobile system 1000 includes a vehicle 200 and a position estimation device 100 mounted on the vehicle 200.

[0027] The configuration shown in the figure is merely an example, and the mobile system 1000 may be configured using a device in which multiple components are integrated. For example, each functional unit in the position estimation device 100 may be distributed and processed using multiple devices. Also, in the figure, the sensor 111 is shown inside the position estimation device 100, but the location where the sensor 111 is installed is not limited. For example, the sensor 111 may be installed on the exterior surface of the vehicle 200.

[0028] Vehicle 200 is an example of a moving object that moves inside tunnel 20. Vehicle 200 may be an autonomous vehicle. As described above, vehicle 200 may also be another moving object such as a drone. Vehicle 200 moves inside tunnel 20 in the positive direction of the x-axis while scanning inner wall W with sensor 111.

[0029] The position estimation device 100 corresponds to the position estimation device 10 of the first embodiment. The position estimation device 100 is an information processing device that estimates the current position of a vehicle 200. As shown in FIG. 4, the position estimation device 100 includes a sensor 111, an acquisition unit 110, an extraction unit 120, a reference information DB (Database) 130, and an estimation unit 140.

[0030] First, the reference information DB 130 will be described. The reference information DB 130 corresponds to the storage unit 13 in the first embodiment. The reference information DB 130 functions as a storage unit that stores reference information of a reference location that serves as a reference for position estimation. Here, the reference location is a location where a shape change has been detected on the surface of the inner wall W. The shape change may be detected by the extraction unit 120 using a well-known image recognition technique or may be detected by a person through visual inspection.

[0031] The shape change may include a change over time in the surface of the inner wall W. The shape change may indicate, for example, deterioration of the surface of the inner wall W. The shape change may include, for example, pitting (surface bubbles), peeling, flaking, or cracks that have occurred on the surface of the inner wall W. Without being limited to these, the shape change may include depressions, protrusions, or other changes that indicate deterioration of the surface of the inner wall W.

[0032] The reference information is information indicating the characteristics of a reference point, and is, for example, a reference point ID 131, a position 132, a size 133, and a reference point characteristic amount 134 associated with each other.

[0033] The reference point ID 131 is information for identifying the reference point. The position 132 is information indicating the position of the reference point. The position 132 may be indicated by, for example, xyz coordinates with the entrance of the tunnel 20 as the origin.

[0034] Size 133 is information indicating the size of the shape change at the reference location. Size 133 may include, for example, the vertical length, horizontal length, and depth of the shape change at the reference location. In the following description, the size of the shape change at the reference location may be simply referred to as the "size of the reference location." Similarly, the size of the shape change at a characteristic location, which will be described later, may be simply referred to as the "size of the characteristic location."

[0035] The reference location feature 134 is information indicating the feature of a shape change at the reference location. For example, the reference location feature 134 may indicate the shape, size, and degree of a pockmark, peeling, or the like. The reference location feature 134 is calculated, for example, based on the size 133 of the shape change. The reference location feature 134 may also be calculated taking the position 132 into consideration. The reference location feature 134 can be acquired using well-known techniques such as artificial intelligence (AI). For example, the reference location feature 134 is acquired by learning a large number of images (for example, deep learning) and generating a model for detecting the feature of the shape change. The reference location feature 134 may be extracted by the extraction unit 120 or may be stored in advance in the reference information DB 130 by another means.

[0036] Specific examples of reference information will be described using Fig. 5 and Fig. 6. Fig. 5 is a diagram showing an example of reference locations. Fig. 6 is a diagram showing an example of reference information corresponding to the reference locations shown in Fig. 5. As shown in Fig. 5, reference locations 31a to 31c are detected on the surface of the inner wall W. The reference locations 31a to 31c are, for example, detected by a past inspection of the tunnel 20. The past inspection may be performed using the position estimation device 100 or by another method. For example, the results may be the results of a visual inspection by a person or the results of an inspection using another device.

[0037] 6 shows reference information corresponding to reference locations 31a to 31c. As shown in the figure, the reference information DB 130 stores a reference location ID 131, a position 132 of each reference location, a size 133, and a reference location characteristic amount 134 in association with each other. The reference information DB 130 may update the reference information when the tunnel 20 is inspected again. Furthermore, when a reference location is repaired, the reference information DB 130 may delete the reference information of the reference location.

[0038] Returning to Figure 4, the explanation continues. The acquisition unit 110 corresponds to the acquisition unit 11 in the first embodiment. The acquisition unit 110 includes a sensor 111. The acquisition unit 110 acquires shape information of the surface of an inner wall W around the vehicle 200 using the sensor 111. The shape information is information about the shape of the surface of the inner wall W. The shape information may be, for example, three-dimensional point cloud data that is a collection of three-dimensional coordinates of the surface of the inner wall W. The surroundings of the vehicle 200 is a space that can be sensed using the sensor 111.

[0039] The sensor 111 senses the surroundings of the vehicle 200. The sensor 111 detects the shapes of objects present in the space around the vehicle 200 and acquires shape information of the objects. The sensor 111 outputs the shape information to the acquisition unit 110.

[0040] An overview of sensing performed by the sensor 111 will be described using FIG. 7. FIG. 7 is a diagram illustrating an overview of sensing by the sensor 111 and an example of characteristic locations, which will be described later. The sensor 111 performs sensing on the sides of the vehicle 200. The sides of the vehicle 200 include the radial direction of the tunnel 20 from the vehicle 200 on which the sensor 111 is installed. The sides of the vehicle 200 are not limited to the horizontal direction but also include the area above the vehicle 200. For example, when the vehicle 200 is located in section S1, the sensor 111 can perform sensing on the inner wall W included in section S1 in any direction, up, down, left, or right, from the vehicle 200. The sensor 111 performs sensing in each of sections S1, S2, S3, ... while traveling within the tunnel 20, and outputs the sensing results for each section to the acquisition unit 110.

[0041] The sensor 111 is, for example, a LiDAR (Light Detection and Ranging, Laser Imaging Detection and Ranging) that can three-dimensionally scan the space outside the vehicle 200 and acquire three-dimensional point cloud data of the interior wall W. However, the sensor 111 is not limited to this, and may be a stereo camera or a depth camera that can measure the distance to the interior wall W. In this embodiment, the sensor 111 will be described as being a LiDAR.

[0042] The sensor 111 is installed at an arbitrary location on the vehicle 200. The sensor 111 is installed, for example, on the top surface of the vehicle 200. The sensor 111 irradiates a laser light L around the vehicle 200 and detects the laser light L reflected by a surrounding object. Here, the surrounding object is described as an inner wall W. The sensor 111 measures the time difference between when the laser light L is irradiated and when the laser light L hits the inner wall W and bounces back. Based on the measured time difference, the sensor 111 detects the position of the inner wall W, the distance from the inner wall W, and the shape of the inner wall W. The sensor 111 acquires three-dimensional point cloud data including this information and outputs it to the acquisition unit 110.

[0043] The sensor 111 can perform sensing at any timing. In this embodiment, the sensor 111 is described as performing sensing in real time and outputting shape information to the acquisition unit 110. The sensor 111 is mounted on the vehicle 200, and its position is fixed. Therefore, the current position of the sensor 111 at the time of sensing can be regarded as the current position of the vehicle 200.

[0044] Returning to Figure 4, the explanation continues. The extraction unit 120 corresponds to the extraction unit 12 in the first embodiment. The extraction unit 120 extracts characteristic locations that indicate shape changes on the surface of the inner wall W from the shape information acquired by the acquisition unit 110. Similar to the reference locations, the characteristic locations are locations on the surface of the inner wall W where shape changes have been detected.

[0045] Similar to the reference location, the shape change at the characteristic location may be, for example, a pockmark (surface bubble), peeling, flaking, or crack that has occurred on the surface of the inner wall W. The shape change is not limited to these, but may also include a depression, a protrusion, or other change that indicates deterioration of the surface of the inner wall W. The characteristic location may be a location corresponding to the reference location stored in the reference information DB 130, or may be a location where a new shape change (deterioration) has occurred on the surface of the inner wall W after the reference location was extracted.

[0046] The extraction unit 120 extracts characteristic points based on the rate of change in the direction of the normal vector and the error from the approximation curve, using the 3D point cloud data acquired by the acquisition unit 110. The extraction unit 120 also extracts characteristic information including the position and size of the characteristic points.

[0047] Specific examples of characteristic information will be described with reference to Fig. 7 and Fig. 8. Fig. 7 shows an example of a characteristic location. Fig. 8 is a diagram showing an example of characteristic information corresponding to the characteristic location shown in Fig. 7.

[0048] 7, the extraction unit 120 acquires three-dimensional point cloud data for each of sections S1, S2, S3, ... from the acquisition unit 110. The extraction unit 120 may acquire the three-dimensional point cloud data for each section from the acquisition unit 110 at any time in accordance with the travel of the vehicle 200. The extraction unit 120 extracts characteristic points that indicate changes in the shape of the inner wall W in each section from the three-dimensional point cloud data and outputs the extracted points to the estimation unit 140.

[0049] For example, the extraction unit 120 extracts characteristic locations 32a and 32b based on the 3D point cloud data in section S2. The extraction unit 120 also extracts feature information for each of the characteristic locations 32a and 32b. Similarly, the extraction unit 120 extracts characteristic location 32c based on the 3D point cloud data in section S9, and extracts feature information for characteristic location 32c.

[0050] 8 is a diagram showing an example of feature information corresponding to the feature points 32a to 32c. The feature information associates a feature point ID 151 with the position 152, size 153, and feature amount 154 of each feature point. The extraction unit 120 may store this information in a storage device (not shown) as appropriate.

[0051] The characteristic location ID 151 is information for identifying the characteristic location. The position 152 is information indicating the position of the characteristic location. The position 152 may be calculated based on the direction of the characteristic location and the distance to the characteristic location, for example, with the sensor 111 as the reference. The size 153 is information indicating the size of the shape change at the characteristic location. The size 153 may include, for example, the vertical length, horizontal length, and depth of the shape change at the characteristic location.

[0052] The characteristic location feature amount 154 is information indicating the feature amount of the shape change at the characteristic location. For example, the characteristic location feature amount 154 may indicate the shape, size, and degree of a pockmark, peeling, etc. The characteristic location feature amount 154 is calculated based on the size 153 of the shape change, for example. Feature location feature quantity 154may be calculated taking into account the position 152. As with the reference portion feature amount 134, the characteristic portion feature amount 154 can be acquired using, for example, artificial intelligence. For example, the extraction unit 120 acquires the characteristic portion feature amount 154 by learning (for example, deep learning) a large number of images and generating a model for detecting feature amounts of shape changes.

[0053] Returning to Figure 4, the explanation continues. The estimation unit 140 corresponds to the estimation unit 14 in the first embodiment. The estimation unit 140 compares the feature information extracted by the extraction unit 120 with the reference information held in the reference information DB 130 to estimate the current position of the vehicle 200 .

[0054] 7, the estimation unit 140 acquires feature information of the feature location 32a extracted by the extraction unit 120. As shown in FIG. 8, the feature information includes, for example, a feature location ID 151, a position 152, a size 153, and a feature location feature amount 154 of the feature location 32a.

[0055] The estimation unit 140 compares the reference information held in the reference information DB 130 with the characteristic information of the extracted characteristic location 32a. For example, the estimation unit 140 refers to the reference information DB 130 and compares a characteristic location feature 154 included in the characteristic information of the characteristic location 32a with a reference location feature 134 included in the reference information in the reference information DB 130. The estimation unit 140 determines whether a reference location feature 134 that matches the characteristic location feature 154 exists in the reference information DB 130.

[0056] If there is a reference location feature 134 that matches the characteristic location feature 154, the estimation unit 140 determines that the feature information and the reference information match. Note that the estimation unit 140 may determine that the characteristic location feature 154 and the reference location feature 134 match when they match by a predetermined threshold or more.

[0057] Here, even if the reference location feature amount 134 and the characteristic location feature amount 154 do not match by more than the threshold, the estimation unit 140 may make a determination taking into account the sizes of the characteristic location and the reference location. For example, even if the sizes of the characteristic location and the reference location differ, the estimation unit 140 determines that the feature information and the reference information match. Specifically, if the size of the characteristic location is larger than the size of the reference location, the estimation unit 140 determines that the two match.

[0058] For example, in FIG. 6, the size 133 of the reference location 31a is "0.2 × 0.3 × 0.1". Also, in FIG. 8, the size 153 of the characteristic location 32a is "0.28 × 0.4 × 0.15". Thus, the characteristic location 32a has a larger shape change than the reference location 31a. The estimation unit 140 compares the characteristic information with the reference information, taking into account such variations in the magnitude of the shape change. In comparing the characteristic information with the reference information, the estimation unit 140 does not require that the magnitude of the shape change exactly matches as a condition for determining whether the two match. For example, if elements other than size match by a predetermined threshold or more and the size of the characteristic location is larger than the size of the reference location, the estimation unit 140 determines that the characteristic information matches the reference information.

[0059] For example, assume that the characteristic location 32a and the reference location 31a match in elements other than their size by a predetermined threshold or more. As described above, the size 153 of the characteristic location 32a is larger than the size 133 of the reference location 31a. Therefore, the estimation unit 140 determines that the characteristic information of the characteristic location 32a matches the reference information of the reference location 31a.

[0060] When the estimation unit 140 determines that the feature information and the reference information match, the estimation unit 140 associates the feature location with the reference location. Here, the estimation unit 140 associates the feature location 32a with the reference location 31a. The position of the reference location 31a is stored in advance in the reference information DB 130. The estimation unit 140 estimates the current position of the vehicle 200 based on the distance and positional relationship between the reference location 31a and the corresponding feature location 32a.

[0061] In this way, even when the reference location and the characteristic location are different in size, the estimation unit 140 can associate them as if they were at the same position and estimate the position of the vehicle 200. In this way, even when the deterioration of the inner wall W progresses and pockmarks or the like become larger, the estimation unit 140 can correctly associate the reference location and the characteristic location and appropriately estimate the position.

[0062] 6 and 8, the cases where all of the vertical length, horizontal length, and depth have increased are used, but this is not limited thereto. The estimation unit 140 may determine that the feature information matches the reference information even when only some of these have increased. Furthermore, for example, when multiple adjacent pockmarks have formed a single large pockmark due to deterioration, the estimation unit 140 may associate multiple reference locations with one feature location. Furthermore, when maintenance has been performed on a deteriorated location, the estimation unit 140 may not refer to that location. Furthermore, the method of comparing the feature information with the reference information is not limited to the above-described method. For example, color information of the interior wall W may be acquired from the sensor 111 and added to the determination conditions.

[0063] In the above description, only one feature portion 32a is used, but the present invention is not limited to this. The estimation unit 140 may compare multiple pieces of feature information with reference information and estimate the current location based on the multiple comparison results.

[0064] 7, the extraction unit 120 extracts characteristic location 32b in addition to characteristic location 32a in section S2. The estimation unit 140 compares the characteristic information of characteristic locations 32a and 32b with reference information and determines whether there is reference information that matches the characteristic information. Based on the determination result, the estimation unit 140 associates characteristic location 32a with reference location 31a, and characteristic location 32b with reference location 31b.

[0065] The estimation unit 140 estimates the current position of the vehicle 200 based on the distance and positional relationship between the vehicle 200 and the characteristic locations 32a and 32b. For example, the estimation unit 140 may appropriately correct the current position estimated based only on the characteristic location 32a in accordance with the position estimated based on the characteristic location 32b. In this way, by comparing multiple pieces of characteristic information and reference information, the estimation unit 140 can estimate the current position with higher accuracy.

[0066] Although the description here uses characteristic points 32a and 32b in the same section S2, the estimation unit 140 may perform multiple comparisons using characteristic points in different sections. For example, in the example of Fig. 7, the extraction unit 120 extracts characteristic points 32a and 32b in section S2, and then extracts characteristic point 32c in section S9. The estimation unit 140 may estimate the current location using the estimation result in section S2 and the estimation result in section S9.

[0067] The estimation unit 140 may update the reference information DB 130 as appropriate based on the matching result. For example, the estimation unit 140 updates the reference information of the reference location 31a with the characteristic information of the characteristic location 32a. Furthermore, when a new characteristic location that does not exist in the reference information DB 130 occurs, the estimation unit 140 may add reference information. In this way, the most recent data can be used in position estimation during the next inspection, etc.

[0068] Next, the position estimation process performed by the position estimation device 100 will be described with reference to Fig. 9. Fig. 9 is a flowchart showing the position estimation process. Here, as in the example shown in Fig. 7, an example will be described in which the vehicle 200 travels through sections S1, S2, S3, etc. in the tunnel 20. The position estimation device 100 detects characteristic locations for each section and compares them with reference locations to estimate the current position. The description will be made with reference to Figs. 4 to 8 as appropriate.

[0069] The reference information DB 130 (see FIG. 4) is assumed to hold reference information in advance. The reference information is, as shown in the example of FIG. 6, a reference portion ID 131, a position 132, a size 133, and a reference portion feature amount 134, etc., associated with each other.

[0070] First, the acquisition unit 110 acquires shape information of the surface of the interior wall W around the vehicle 200 from the sensor 111 (S101). The shape information is, for example, three-dimensional point cloud data of the surface of the interior wall W. The sensor 111 performs sensing on the side of the vehicle 200, acquires the three-dimensional point cloud data of the surface of the interior wall W, and outputs the data to the acquisition unit 110.

[0071] Next, the extraction unit 120 extracts characteristic locations on the surface of the inner wall W from the shape information (S102). Characteristic locations are locations where shape changes are detected on the surface of the inner wall W. Shape changes include, for example, pockmarks, peeling, flaking, and cracks on the surface of the inner wall W. Shape changes are not limited to these, but may also include changes that indicate deterioration of the inner wall W. The extraction unit 120 extracts characteristic locations based on the rate of change in the direction of the normal vector and the error from the approximation curve.

[0072] Next, the extraction unit 120 extracts feature information including the position and size of the feature location (S103). The feature information associates feature location ID 151, position 152, size 153, and feature location feature amount 154, as in the example shown in Fig. 8. The extraction unit 120 acquires 3D point cloud data for each of sections S1, S2, S3, ... from the acquisition unit 110, and extracts feature information of the feature location in each section.

[0073] 7, the extraction unit 120 extracts characteristic locations 32a and 32b in section S2 and extracts characteristic information about the characteristic locations 32a and 32b. Similarly, the extraction unit 120 extracts characteristic location 32c based on the 3D point cloud data in section S9 and extracts characteristic information about the characteristic location 32c.

[0074] Then, the estimation unit 140 compares the feature information with the reference information (S104). The estimation unit 140 refers to the reference information DB 130 and compares the feature information extracted in step S103 with the reference information. For example, the estimation unit 140 compares the feature information of the extracted characteristic portion 32a with the reference information in the reference information DB 130. The estimation unit 140 determines that the feature information and the reference information match not only when they match perfectly but also when they match by a predetermined threshold or more.

[0075] Furthermore, even when the size 153 included in the feature information differs from the size 133 included in the reference information, the estimation unit 140 determines that the feature information matches the reference information. Here, as shown in Figures 6 and 8, the magnitude of the shape change is greater for the feature location 32a than for the reference location 31a. However, the estimation unit 140 determines whether the feature information for the feature location 32a matches the reference information for the reference location 31a, taking into account factors other than size.

[0076] The estimation unit 140 determines whether the characteristic information matches the reference information (S105). If they do not match (NO in S105), the processing ends. If the characteristic information matches the reference information (YES in S105), the estimation unit 140 associates the characteristic location with the reference location. The estimation unit 140 estimates the current position of the vehicle 200 based on the distance and positional relationship with the characteristic location (S106).

[0077] Here, the description has been given using only one characteristic location 32a, but this is not limiting. As already described, the estimation unit 140 may compare the characteristic information with the reference information multiple times and estimate the current location based on the multiple comparison results. The estimation unit 140 may compare the characteristic information with the reference information for each of the characteristic locations 32a and 32b extracted in section S2. Furthermore, the estimation unit 140 may also perform the comparison using the characteristic information and the reference information for the characteristic location 32c extracted in section S9.

[0078] As described above, the position estimation device 100 according to this embodiment acquires shape information on the surface of the inner wall W and extracts shape changes on the surface of the inner wall W from the shape information. The shape changes include deterioration of the surface of the inner wall W. The position estimation device 100 extracts feature information including the position and size of the deterioration and compares the feature information with pre-stored reference information. Even if the size of a feature location is larger than the size of the corresponding reference location, the position estimation device 100 associates the feature location with the reference location as if they were located at the same position. The position estimation device 100 estimates the current position of the vehicle 200 based on the positions of the reference locations associated with the feature locations.

[0079] In this way, position estimation device 100 does not require a strict match in size between the reference location and the characteristic location when comparing them. As a result, even if the characteristic location is larger than the reference location measured in the past, the current location of vehicle 200 can be appropriately determined based on the position of the reference location associated with the characteristic location.

[0080] <Embodiment 3> Next, a mobile system 1001 according to the third embodiment will be described. In the second embodiment, an example has been described in which the position estimation device 100 includes one sensor 111. In the present embodiment, the position estimation device 100 includes a plurality of sensors.

[0081] 10 is a block diagram showing the configuration of a mobile body system 1001 according to this embodiment. Similar to the mobile body system 1000 described in the second embodiment, the mobile body system 1001 includes a vehicle 200 and a position estimation device 100 mounted on the vehicle 200. The configuration of the position estimation device 100 is the same as that of the mobile body system 1000, except that the position estimation device 100 includes a first sensor 111a and a second sensor 111b.

[0082] The first sensor 111a and the second sensor 111b sense the surroundings of the vehicle 200 and output the sensing results to the acquisition unit 110. The first sensor 111a and the second sensor 111b detect the shapes of objects present in the space outside the vehicle 200 and acquire shape information of the objects.

[0083] The first sensor 111a corresponds to the sensor 111 of the second embodiment. ,car Sensing is performed on the sides of both 200. The second sensor 111b is a sensor that performs sensing in a direction different from that of the first sensor 111a. The second sensor 111b performs sensing, for example, ahead of the vehicle 200. The ahead of the vehicle 200 is the traveling direction of the vehicle 200 (positive direction of the x-axis).

[0084] 11 is a diagram illustrating an overview of sensing performed by the first sensor 111a and the second sensor 111b. As in the second embodiment, the first sensor 111a and the second sensor 111b may be a LiDAR, a stereo camera, a depth camera, or the like. Here, the first sensor 111a and the second sensor 111b are assumed to be LiDAR. The first sensor 111a and the second sensor 111b are installed on the top surface of the vehicle 200, for example. The first sensor 111a and the second sensor 111b irradiate the periphery of the vehicle 200 with laser light L and detect the laser light L reflected on the surface of the inner wall W, respectively.

[0085] 11, the vehicle 200 is located in section S2. The areas ahead of the vehicle 200 are sections S3, S4, S5, and so on, which are located in the traveling direction of the vehicle 200. For example, the first sensor 111a scans the inner wall W of section S2, and the second sensor 111b scans the inner walls W of sections S3, S4, S5, and so on, which are located ahead of section S2. The first sensor 111a and the second sensor 111b output their respective sensing results to the acquisition unit 110.

[0086] Returning to FIG. 10, the explanation will be continued. As in the second embodiment, the extraction unit 120 extracts characteristic locations indicating shape changes on the surface of the inner wall W from the shape information acquired by the acquisition unit 110. For example, the extraction unit 120 extracts characteristic locations 32a and 32c shown in Fig. 11 from the shape information acquired by the first sensor 111a and the second sensor 111b, respectively. The extraction unit 120 also extracts characteristic information about each of the characteristic locations 32a and 32c.

[0087] The estimation unit 140 compares the feature information of the feature portions 32a and 32c with the reference information stored in the reference information DB 130. Feature information If the characteristic locations match the reference information, the current position of the vehicle 200 is estimated by associating the characteristic locations with the corresponding reference locations. As in the second embodiment, even if the size of each characteristic location differs from the reference information, the estimation unit 140 can associate the characteristic location with the reference location by assuming that the characteristic location and the reference location are in the same position. The details of the processing, including the flowchart, are the same as those in the second embodiment. Therefore, redundant explanations will be omitted.

[0088] As described above, the mobile body system 1001 according to this embodiment can estimate the position by taking into account not only characteristic information about the sides of the vehicle 200 but also characteristic information about the front of the vehicle 200. Therefore, the same effects as those of the second embodiment can be obtained.

[0089] <Embodiment 4> Next, a mobile system 1002 according to the fourth embodiment will be described. In the second and third embodiments, the extraction unit 120 extracted characteristic features such as pockmarks that appeared on the surface of the inner wall W based on the rate of change in the direction of the normal vector on the inner wall W. In the present embodiment, the extraction unit 120 extracts characteristic features on the inner wall W based on the intensity of the reflected light of the beam irradiated onto the inner wall W.

[0090] In this embodiment, the characteristic location indicates an area on the interior wall W where the reflectance is significantly different from the surrounding area. The characteristic location is, for example, paint applied to the interior wall W. The paint may be applied to the interior wall W for position estimation, or may be applied in advance to the interior wall W for another purpose. The paint is, for example, paint applied to the interior wall W. Note that tiles, tape, etc. may be used as the characteristic location instead of paint.

[0091] A mobile system 1002 according to this embodiment will be described. The configuration of the mobile system 1002 is similar to the configuration of the mobile system 1000 described using Fig. 4. Therefore, the description will be made with reference to Fig. 4.

[0092] 4, the mobile system 1002 includes a vehicle 200 and a position estimation device 100 mounted on the vehicle 200. The position estimation device 100 also includes a sensor 111, an acquisition unit 110, an extraction unit 120, a reference information DB 130, and an estimation unit 140.

[0093] The sensor 111 irradiates the surface of the inner wall W with laser light L (beam) and receives the light reflected from the inner wall W. The sensor 111 outputs the intensity of the reflected light to the acquisition unit 110. The acquisition unit 110 acquires, from a sensor 111, the reflected light intensity of the laser light L irradiated onto the surface of the inner wall W. The extraction unit 120 extracts characteristic portions based on the intensity of the reflected light acquired by the acquisition unit 110. The extraction unit 120 also extracts characteristic information including the positions of the characteristic portions. The reference information DB 130 functions as a storage unit that stores reference information of reference locations that serve as a reference for position estimation. A specific example of the reference information DB 130 will be described later. The estimation unit 140 compares the feature information extracted by the extraction unit 120 with the reference information held in the reference information DB 130 to estimate the current position of the vehicle 200 .

[0094] 12 is a diagram showing an example of the reference information DB 130. The reference information DB 130 stores reflected light intensity 135 in association with reference point ID 131, position 132, size 133, and reference point feature amount 134 described in the second embodiment. Note that the contents of the reference information DB 130 are not limited to those shown in the figure.

[0095] An overview of sensing performed by the sensor 111 according to this embodiment will be described using Fig. 13. Fig. 13 is a diagram showing an overview of sensing by the sensor 111. The same figure also shows an example of a reference location and a characteristic location according to this embodiment. Note that, as in the second embodiment, the sensor 111 may perform sensing to the side of the vehicle 200, but here, an example in which sensing is performed in front of the vehicle 200 will be described.

[0096] 13, paint is applied to sections S4 and S8. The painted areas are reference areas 41a and 41b, respectively. The reference information of the reference areas 41a and 41b is stored in advance in the reference information DB 130, as in the example of FIG.

[0097] First, the sensor 111 irradiates the surface of the inner wall W with laser light L. Here, as shown in FIG. 13 , it is assumed that the laser light L is irradiated at the position of the characteristic location 42a. The sensor 111 receives the light reflected from the inner wall W, detects the intensity of the reflected light, and outputs the detected intensity to the acquisition unit 110. The acquisition unit 110 acquires the intensity of the reflected light of the laser light L from the sensor 111.

[0098] The extraction unit 120 extracts a characteristic location based on the reflected light intensity. The extraction unit 120 extracts a characteristic location 42a based on the difference in reflected light intensity from other regions. The extraction unit 120 also extracts characteristic information including the position of the characteristic location 42a. The characteristic information may include the reflected light intensity at the characteristic location 42a in addition to the information described in FIG. 8. The extraction unit 120 associates, for example, a characteristic location ID 151, a characteristic location position 152, a size 153, a characteristic location feature amount 154, and a reflected light intensity to generate characteristic information. Note that the content of the characteristic information is not limited to these. The extraction unit 120 may also store this information in a storage device (not shown) as appropriate.

[0099] The estimation unit 140 compares the feature information extracted by the extraction unit 120 with the reference information held in the reference information DB 130 to estimate the current position of the vehicle 200. For example, the estimation unit 140 compares the feature information of the feature location 42a with the reference information. The estimation unit 140 determines whether the feature location 42a matches the reference location 41a. If the feature location 42a matches the reference location 41a by a threshold or more, the estimation unit 140 determines that the two match. The comparison between the feature information and the reference information is the same as in the second embodiment, and therefore a detailed description thereof will be omitted.

[0100] Contrary to the second embodiment, the estimation unit 140 may determine that the reference information and the feature information match even when the size of the feature has decreased. In this way, the estimation unit 140 can identify the position of the feature even when the paint has peeled off. Furthermore, the estimation unit 140 may make the determination taking into account changes in the intensity of reflected light that occur due to deterioration of the paint, etc.

[0101] The estimation unit 140 associates the characteristic location 42a with the reference location 41a, and thereby estimates the current location of the vehicle 200 based on the distance and positional relationship with the characteristic location 42a. Note that, similar to the second embodiment, the estimation unit 140 may estimate the current location of the vehicle 200 using a plurality of characteristic locations 42a and 42b.

[0102] 14 is a flowchart showing the position estimation process according to this embodiment. Descriptions of the same parts as in the second embodiment will be omitted where appropriate.

[0103] The sensor 111 irradiates a beam onto the surface of the inner wall W. The acquisition unit 110 acquires the reflected light intensity of the beam irradiated onto the surface of the inner wall W (S201). The extraction unit 120 extracts characteristic locations on the surface of the inner wall W from the reflected light intensity (S202). The characteristic locations are, for example, paint applied to the inner wall W. The characteristic locations are not limited to paint, and tiles with reflectance significantly different from other areas may also be used. The extraction unit 120 extracts characteristic information including the positions of the characteristic locations (S203).

[0104] The estimation unit 140 compares the feature information with the reference information (S204). The estimation unit 140 refers to the reference information DB 130 and compares the reference information with the feature information extracted in step S203. For example, in the example of FIG. 13, the estimation unit 140 compares the feature information of the extracted characteristic portion 42a with the reference information in the reference information DB 130. The estimation unit 140 determines that the reference information and the feature information match not only when they completely match, but also when they match by a predetermined threshold or more.

[0105] The estimation unit 140 determines whether the reference information and the feature information match (S205). If they do not match (NO in S205), the processing ends. If the reference information and the feature information match (YES in S205), the estimation unit 140 associates the feature location with the reference location. For example, the estimation unit 140 associates the feature location 42a with the reference location 41a. The estimation unit 140 estimates the current position of the vehicle 200 based on the distance and positional relationship with the feature location 42a (S206).

[0106] As described above, the mobile body system 1002 according to this embodiment can achieve the same effects as those of the second embodiment. Furthermore, since the position is estimated using paint or the like applied to the interior wall W, it is possible to easily estimate the position even when there are no past inspection results. Furthermore, by estimating the position in combination with changes in the shape of the surface of the interior wall W, it is possible to estimate the current position of the vehicle 200 with higher accuracy.

[0107] The above-described first to fourth embodiments can be used in combination with some or all of them as appropriate. Furthermore, each device is not limited to being a single physical device, but may be composed of multiple devices. Furthermore, the functions of each device can be realized by multiple processing devices performing distributed processing.

[0108] <Hardware configuration example> Each functional component of the position estimation device 100 may be realized by hardware that realizes the functional component (e.g., a hardwired electronic circuit, etc.), or may be realized by a combination of hardware and software (e.g., a combination of an electronic circuit and a program that controls it, etc.). Below, a case where each functional component of the position estimation device 100 is realized by a combination of hardware and software will be further described.

[0109] 15 is a block diagram showing an example of the hardware configuration of a computer 900 that realizes the position estimation device 100. The computer 900 may be a dedicated computer designed to realize the position estimation device 100, or may be a general-purpose computer. The computer 900 may also be a portable computer such as a smartphone or a tablet terminal.

[0110] For example, by installing a predetermined application on the computer 900, the functions of the position estimation device 100 are realized by the computer 900. The application is configured by a program for realizing the functional components of the position estimation device 100.

[0111] The computer 900 includes a bus 902, a processor 904, a memory 906, a storage device 908, an input / output interface 910, and a network interface 912. The bus 902 is a data transmission path that allows the processor 904, the memory 906, the storage device 908, the input / output interface 910, and the network interface 912 to transmit and receive data to and from each other. However, the method of connecting the processor 904 and other components to each other is not limited to a bus connection.

[0112] The processor 904 is a variety of processors, such as a central processing unit (CPU), a graphics processing unit (GPU), or a field-programmable gate array (FPGA). The memory 906 is a main storage device realized using a random access memory (RAM) or the like. The storage device 908 is an auxiliary storage device realized using a hard disk, a solid state drive (SSD), a memory card, or a read-only memory (ROM) or the like. At least one of the memory 906 and the storage device 908 can be used as the reference information DB 130 (see FIGS. 4 and 10).

[0113] The input / output interface 910 is an interface for connecting the computer 900 to an input / output device. For example, the input / output interface 910 is connected to an input device such as a keyboard and an output device such as a display device.

[0114] The network interface 912 is an interface for connecting the computer 900 to a network. This network may be a LAN (Local Area Network) or a WAN (Wide Area Network).

[0115] The storage device 908 stores a program (a program that realizes the above-mentioned application) that realizes each functional component of the position estimation device 100. The processor 904 reads this program into the memory 906 and executes it, thereby realizing each functional component of the position estimation device 100.

[0116] Each processor executes one or more programs containing instructions for causing a computer to perform the algorithms described with reference to the figures. The programs contain instructions (or software code) that, when loaded into a computer, cause the computer to perform one or more functions described in the embodiments. The programs may be stored on a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable media or tangible storage media include random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technology, CD-ROM, digital versatile disc (DVD), Blu-ray disc or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The programs may also be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, transitory computer-readable media or communication media include electrical, optical, acoustic, or other forms of propagated signals.

[0117] The present disclosure is not limited to the above-described embodiments, and can be modified as appropriate within the scope of the present disclosure.

[0118] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes.

[0119] (Appendix 1) A position estimation device that estimates a current position of a moving object, An acquisition means for acquiring shape information of the surface of a structure around the moving object; an extraction means for extracting characteristic points that indicate shape changes on the surface of the structure from the shape information and extracting characteristic information including the positions and sizes of the characteristic points; a storage means for storing in advance reference information including the position and size of a reference point that serves as a reference for position estimation; and an estimation means for estimating a current position of the moving object by comparing the characteristic information with the reference information. Location estimation device. (Appendix 2) The shape change includes deterioration of the surface of the structure. 2. The location estimation device of claim 1. (Appendix 3) The size of the characteristic portion is different from the size of the reference portion. 3. The position estimation device according to claim 1 or 2. (Appendix 4) The moving body moves inside the hollow structure. 4. A position estimation device according to any one of appendices 1 to 3. (Appendix 5) the acquiring means acquires a reflected light intensity of a beam irradiated onto the surface of the structure, The extraction means extracts the characteristic portion based on the reflected light intensity. 5. A position estimation device according to any one of appendices 1 to 4. (Appendix 6) The estimation means compares the characteristic information with the reference information multiple times and estimates the current location based on the multiple comparison results. 6. A position estimation device according to any one of appendixes 1 to 5. (Appendix 7) The acquisition means a first sensor that senses the side of the moving object; a second sensor that senses the area in front of the moving body; 7. A position estimation device according to any one of appendixes 1 to 6. (Appendix 8) A moving object and a position estimation device mounted on the moving body, the position estimation device, An acquisition means for acquiring shape information of the surface of a structure around the moving object; an extraction means for extracting characteristic points that indicate shape changes on the surface of the structure from the shape information and extracting characteristic information including the positions and sizes of the characteristic points; a storage means for storing in advance reference information including the position and size of a reference point that serves as a reference for position estimation; and an estimation means for estimating a current position of the moving object by comparing the characteristic information with the reference information. Mobile systems. (Appendix 9) The shape change includes deterioration of the surface of the structure. 9. The mobile system of claim 8. (Appendix 10) A position estimation method for estimating a current position of a moving object, comprising: Obtaining shape information of the surface of structures around the moving object, extracting characteristic locations that indicate shape changes on the surface of the structure from the shape information, and extracting characteristic information including the positions and sizes of the characteristic locations; The characteristic information is compared with reference information including the position and size of a reference point that serves as a reference for position estimation, thereby estimating the current position of the moving object. Location estimation method. (Appendix 11) A non-transitory computer-readable medium storing a program for causing a computer to execute a position estimation method for estimating a current position of a moving object, An acquisition process for acquiring shape information of the surface of a structure around the moving object; an extraction process for extracting characteristic locations that indicate shape changes on the surface of the structure from the shape information and extracting characteristic information including positions and sizes of the characteristic locations; an estimation process for estimating the current position of the moving object by comparing the characteristic information with reference information including the position and size of a reference point that serves as a reference for position estimation; A non-transitory computer-readable medium that stores a program to be executed by a computer. [Explanation of symbols]

[0120] 10 Position estimation device 11 Acquisition Department 12 Extraction part 13 Holding part 14 Estimation part 20 Tunnel 31a, 31b, 31c, 41a, 41b Reference points 32a, 32b, 32c, 42a, 42b Characteristic parts 100 Position estimation device 110 Acquisition Department 111 Sensors 111a First sensor 111b Second sensor 120 Extraction part 130 Standard information DB 131 Reference Point ID 132 positions 133 Size 134 Reference Location Features 135 Reflected Light Intensity 140 Estimation part 151 Characteristic Location ID 152 positions 153 Size 154 Feature Location Feature Amount 200 vehicles 900 Computers 902 Bus 904 processor 906 memory 908 Storage Devices 910 Input / Output Interface 912 Network Interface 1000, 1001, 1002 Mobile Systems L laser light S1~S10 section W Inner wall

Claims

1. A position estimation device that estimates the current position of a moving object moving inside a hollow structure, an acquisition means for acquiring shape information of the surface of the inner wall of the structure around the moving object using a sensor that scans the inner wall of the structure; an extraction means for extracting characteristic points that indicate shape changes on the surface of the inner wall of the structure from the shape information and extracting characteristic information including the positions and sizes of the characteristic points; a storage means for storing in advance reference information including the position and size of a reference point that serves as a reference for position estimation; an estimation means for estimating a current position of the moving object by comparing the characteristic information with the reference information, The acquisition means includes a sensor that scans the inner wall of the structure, a first sensor that senses a side of the moving object; a second sensor that senses the area in front of the moving body; Location estimation device.

2. The shape change includes deterioration of the surface of the inner wall of the structure. The position estimation device according to claim 1 .

3. The size of the characteristic portion is different from the size of the reference portion. The position estimation device according to claim 1 or 2.

4. the acquiring means acquires scan results for each section obtained by dividing the traveling direction of the moving object into sections at predetermined distance intervals; The extraction means extracts the characteristic portion in each of the sections. The position estimation device according to any one of claims 1 to 3.

5. the acquiring means acquires a reflected light intensity of a beam irradiated onto a surface of an inner wall of the structure, The extraction means extracts the characteristic portion based on the reflected light intensity. The position estimation device according to any one of claims 1 to 4.

6. The estimation means compares the characteristic information with the reference information multiple times and estimates the current location based on the multiple comparison results. The position estimation device according to any one of claims 1 to 5.

7. a moving body that moves inside a hollow structure; a position estimation device mounted on the moving body, the position estimation device, an acquisition means for acquiring shape information of the surface of the inner wall of the structure around the moving object using a sensor that scans the inner wall of the structure; an extraction means for extracting characteristic points that indicate shape changes on the surface of the inner wall of the structure from the shape information and extracting characteristic information including the positions and sizes of the characteristic points; a storage means for storing in advance reference information including the position and size of a reference point that serves as a reference for position estimation; an estimation means for estimating a current position of the moving object by comparing the characteristic information with the reference information, The acquisition means includes a sensor that scans the inner wall of the structure, a first sensor that senses a side of the moving object; a second sensor that senses the area in front of the moving body; Mobile systems.

8. A position estimation method for estimating a current position of a moving object moving inside a hollow structure, comprising: acquiring shape information of the surface of the inner wall of the structure around the moving object using a sensor that scans the inner wall of the structure; extracting characteristic points that indicate shape changes on the surface of the inner wall of the structure from the shape information, and extracting characteristic information including the positions and sizes of the characteristic points; estimating a current position of the moving object by comparing the characteristic information with reference information including the position and size of a reference point that serves as a reference for position estimation; In acquiring the shape information, a sensor for scanning the inner wall of the structure includes: a first sensor that senses a side of the moving object; a second sensor for sensing the area in front of the moving body; Location estimation method.

9. A program for causing a computer to execute a position estimation method for estimating the current position of a moving object moving inside a hollow structure, comprising: an acquisition process of acquiring shape information of the surface of the inner wall of the structure around the moving object using a sensor that scans the inner wall of the structure; an extraction process of extracting characteristic points that indicate shape changes on the surface of the inner wall of the structure from the shape information and extracting characteristic information including the positions and sizes of the characteristic points; an estimation process for estimating the current position of the moving object by comparing the characteristic information with reference information including the position and size of a reference point that serves as a reference for position estimation; Let the computer run In the acquisition process, a sensor for scanning the inner wall of the structure includes: a first sensor that senses a side of the moving object; a second sensor for sensing the area in front of the moving body; program.

Images