Information processing device, determination method, program, and storage medium

Abstract

To provide an information processing device which can accurately determine whether or not a marine vessel can safely pass under a bridge.SOLUTION: A controller 13 of an information processing device 1 performs position estimation of a marine vessel reference position on the basis of a map DB 10. Then, the controller 13 calculates a predicted interval as an interval between a bridge and a marine vessel on the basis of a height of the bridge based on the map DB 10, an estimation result of the position estimation, and highest point information IH related to the height to a highest point of the marine vessel from the marine vessel reference position. Then, the controller 13 determines whether or not the marine vessel can safely pass under the bridge on the basis of the predicted interval.SELECTED DRAWING: Figure 6

Description

[Technical Field]

[0001] The present disclosure relates to determining whether a ship can pass under a bridge. [Background technology]

[0002] Conventionally, there have been known techniques for estimating the self-position of a moving object by comparing (matching) shape data of surrounding objects measured using a measurement device such as a laser scanner with map information in which the shapes of surrounding objects are stored in advance. For example, Patent Document 1 discloses an autonomous mobile system that determines whether a detected object in a voxel obtained by dividing a space according to a predetermined rule is a stationary object or a moving object, and matches the map information with the measurement data for voxels in which a stationary object exists. Furthermore, Patent Document 2 discloses a scan matching method that estimates the self-position by comparing voxel data including the mean vector and covariance matrix of stationary objects for each voxel with point cloud data output by a LIDAR. Furthermore, Patent Document 3 describes a method for controlling the attitude of a ship in an automatic docking device that automatically docks a ship so that light emitted from the LIDAR is reflected by objects around the docking position and received by the LIDAR. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication WO2013 / 076829 [Patent Document 2] International Publication No. WO2018 / 221453 [Patent Document 3] Japanese Patent Publication No. 2020-59403 Summary of the Invention [Problem to be solved by the invention]

[0004] When deciding on a navigation route, it is common to select a route that allows safe passage under a bridge based on tide forecast information, etc. However, whether a ship can actually pass under the bridge must be confirmed before approaching the bridge, taking into account the possibility that the water level may be higher than the tide forecast. If it is determined in advance that there is a risk in passing under the bridge, it is possible to take measures such as turning back or changing the route when the river is wide and there are no other ships. In this way, determining in advance whether a ship can pass under a bridge is important for safe navigation.

[0005] The present disclosure has been made to solve the above-mentioned problems, and one of its main objectives is to provide an information processing device that can accurately determine whether a ship can safely pass under a bridge. [Means for solving the problem]

[0006] The claimed invention is a position estimation means for estimating a reference position of the ship based on map data; a prediction interval calculation means for calculating a prediction interval, which is a predicted distance between the bridge and the ship, based on the bridge height based on the map data, the estimation result of the position estimation, and highest point information relating to the height from the reference position to the highest point of the ship; a passage possibility determination means for determining whether the vessel can pass under the bridge based on the prediction interval; The information processing device has the following.

[0007] The claimed invention also includes: A computer-implemented determination method comprising: Based on the map data, the ship's reference position is estimated, Calculating a predicted distance between the bridge and the vessel based on the bridge height based on the map data, the result of the position estimation, and highest point information relating to the height from the reference position to the highest point of the vessel; determining whether the vessel can pass under the bridge based on the prediction interval; This is a judgment method.

[0008] The claimed invention also includes: Based on the map data, the ship's reference position is estimated, Calculating a predicted distance between the bridge and the vessel based on the bridge height based on the map data, the result of the position estimation, and highest point information relating to the height from the reference position to the highest point of the vessel; The program causes a computer to execute a process for determining whether the ship can pass under the bridge based on the prediction interval. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a schematic configuration diagram of an operation support system. [Figure 2] FIG. 2 is a block diagram showing a functional configuration of the information processing device. [Figure 3] 2 is a diagram showing a self-position to be estimated by a self-position estimation unit in three-dimensional orthogonal coordinates. FIG. [Figure 4] 1 shows an example of a schematic data structure of voxel data. [Figure 5] 3 is an example of a functional block of a self-position estimation unit. [Figure 6] FIG. 10 is a diagram showing an outline of a process for determining whether or not a bridge can be passed; [Figure 7] (A) shows the frequency distribution of estimated ship heights. (B) shows an example of a graph of the time evolution of the standard deviation of estimated ship heights. [Figure 8] 10 is an example of a functional block of a bridge passability determination unit. [Figure 9] 10 is an example of a flowchart of a process for determining whether or not a bridge can be passed; [Figure 10] This is a view from behind of a ship passing a bridge for which the predicted distance between the ship and the bridge has been calculated. [Figure 11] The frequency distribution of the difference between the predicted interval and the actual measurement interval is shown. DETAILED DESCRIPTION OF THE INVENTION

[0010] According to a preferred embodiment of the present invention, an information processing device includes: a position estimation means for estimating a reference position of a ship based on map data; a prediction interval calculation means for calculating a prediction interval that is a predicted distance between the bridge and the ship based on the height of a bridge based on the map data, the result of the position estimation, and highest point information regarding the height from the reference position to the highest point of the ship; and a passage possibility determination means for determining whether the ship can pass under the bridge based on the prediction interval. According to this aspect, the information processing device can accurately determine whether the ship can pass under the bridge safely.

[0011] In one aspect of the information processing device, the information processing device further includes threshold determination means for determining a threshold to be compared with the prediction interval in the passability determination, the threshold determination means determining the threshold based on an index representing a variance in the estimation result by the position estimation means. According to this aspect, the information processing device can accurately determine whether the ship can pass under the bridge, taking into account the variance in the position estimation result.

[0012] In another aspect of the information processing device, the index is a standard deviation, and the threshold value determining means determines the threshold value based on the maximum value of a plurality of the standard deviations calculated while changing the predetermined period. With this aspect, the information processing device can set a threshold value that accurately reflects the variance in the location estimation results.

[0013] In another aspect of the information processing device, the threshold value determination means calculates the measured interval between the bridge and the ship based on measurement data obtained by measuring the bridge with a measuring device when the ship passes over the bridge, calculates the difference between the measured interval and the predicted interval for multiple bridges, and determines the threshold value based on an index representing the variability of the calculated difference value and an index representing the variability of the estimated results. This aspect makes it possible to determine the threshold value to be compared with the predicted interval by accurately considering the variability of the deviation of the predicted interval from the measured interval. Preferably, the threshold value determination means increases the threshold value as the variability indicated by the index increases.

[0014] In another aspect of the information processing device, the prediction interval calculation means calculates the actual measured interval between the first bridge and the ship based on measurement data obtained by a measurement device measuring the first bridge when the ship passes over the first bridge, and generates correction information for correcting the predicted interval for a second bridge other than the first bridge based on the actual measured interval and the predicted interval for the first bridge. In other words, the above-mentioned correction information is correction information that can correct the predicted interval in a general manner (i.e., without limiting the bridge) rather than depending on a specific bridge. With this aspect, the information processing device can obtain correction information for highly accurately correcting the predicted interval for each bridge used to determine whether the ship can pass under the bridge.

[0015] In another aspect of the information processing device, the map data is voxel data representing the position of an object for each voxel, which is a unit area, the position estimation means performs the position estimation based on a comparison between the voxel data and measurement data obtained by a measurement device, and the prediction interval calculation means calculates the height of the bridge based on the voxel data corresponding to the bridge. With this aspect, the information processing device can preferably estimate the height of a ship and calculate the height of a bridge based on the voxel data.

[0016] In another aspect of the information processing device, the prediction interval calculation means acquires the height of the bridge from the bottom of the bridge above the river, and the information processing device preferably identifies the bridge height based on the part of the bridge that is closest to the ship when the ship passes under the bridge.

[0017] According to another preferred embodiment of the present invention, there is provided a determination method executed by a computer, which performs a position estimation of a reference position of a ship based on map data, calculates a predicted interval between the bridge and the ship based on the height of a bridge based on the map data, the result of the position estimation, and highest point information relating to the height from the reference position to the highest point of the ship, and determines whether the ship can pass under the bridge based on the predicted interval. By executing this determination method, the computer can accurately determine whether the ship can pass under the bridge safely.

[0018] According to yet another preferred embodiment of the present invention, the program causes a computer to execute a process of estimating a reference position of a ship based on map data, calculating a predicted interval between the bridge and the ship based on the bridge height based on the map data, the result of the position estimation, and highest point information related to the height from the reference position to the highest point of the ship, and determining whether the ship can pass under the bridge based on the predicted interval. By executing this program, the computer can accurately determine whether the ship can pass under the bridge safely. Preferably, the program is stored in a storage medium. [Example]

[0019] Hereinafter, preferred embodiments of the present invention will be described with reference to the drawings. For convenience, any symbol followed by a "^" or "-" will be represented as "A^" or "A-" (where "A" is any character) in this specification.

[0020] (1) Overview of the flight support system Figures 1(A) to 1(C) show a schematic configuration of a navigation assistance system according to this embodiment. Specifically, Figure 1(A) shows a block diagram of the navigation assistance system, Figure 1(B) is a top view illustrating a ship included in the navigation assistance system and a field of view (range measurement range) 90 of a lidar 3 (described later), and Figure 1(C) is a rear view of the ship and the field of view 90 of the lidar 3. The navigation assistance system has an information processing device 1 that moves with the ship, which is a mobile object, and a sensor group 2 mounted on the ship.

[0021] The information processing device 1 is electrically connected to the sensor group 2, and estimates the position of the ship on which the information processing device 1 is installed (also referred to as "self-position") based on the outputs of various sensors included in the sensor group 2. Then, the information processing device 1 performs operation support such as automatic operation control of the ship based on the result of estimating the self-position. In this embodiment, as an example of operation support, the information processing device 1 determines whether the ship can pass under a bridge that it is scheduled to pass, and executes processing according to the determination result. Note that operation support may also include berthing support such as automatic berthing (docking). The information processing device 1 may be a navigation device installed on the ship, or may be an electronic control device built into the ship.

[0022] The information processing device 1 also stores a map database (DB: DataBase) 10 that includes voxel data "VD." The voxel data VD is data that records position information and the like of stationary structures for each voxel, which represents a cube (regular lattice), the smallest unit in three-dimensional space. The voxel data VD includes data that expresses measured point cloud data of stationary structures within each voxel using a normal distribution, and is used for scan matching using NDT (Normal Distribution Transform), as described below. The information processing device 1 estimates, for example, the ship's planar position, height position, yaw angle, pitch angle, and roll angle through NDT scan matching. Unless otherwise specified, the self-position is assumed to also include the ship's attitude angle, such as the yaw angle.

[0023] The sensor group 2 includes various external and internal sensors provided on the ship. In this embodiment, the sensor group 2 includes a Lidar (Light Detection and Ranging, or Laser Illuminated Detection and Ranging) 3, a speed sensor 4 that detects the speed of the ship, a GPS (Global Positioning Satellite) receiver 5, and an Inertial Measurement Unit (IMU) 6 that measures the acceleration and angular velocity of the target moving ship in three axial directions.

[0024] The LIDAR 3 is an external sensor that emits a pulsed laser beam within a predetermined horizontal angle range (see FIG. 1(B)) and a predetermined vertical angle range (see FIG. 1(C)) to discretely measure the distance to an object in the external world and generate three-dimensional point cloud data indicating the position of the object. In the examples of FIGS. 1(B) and 1(C), the ship is provided with two LIDARs 3, one facing the left side of the ship and the other facing the right side of the ship. The number of LIDARs 3 installed on the ship is not limited to two, and may be one, three, or more. The LIDAR 3 includes an irradiation unit that irradiates laser light while changing the irradiation direction, a light receiving unit that receives reflected light (scattered light) of the irradiated laser light, and an output unit that outputs scan data based on the light receiving signal output by the light receiving unit. The data measured for each direction (scanning position) of laser light irradiation is generated based on the irradiation direction corresponding to the laser light received by the light receiving unit and the response delay time of the laser light identified based on the above-mentioned light receiving signal. The LIDAR 3 is not limited to the above-described scan-type LIDAR, but may be a flash-type LIDAR that generates three-dimensional data by irradiating a field of view of a two-dimensional array sensor with diffused laser light. The LIDAR 3 is an example of a "measurement device" in the present invention. The speed sensor 4 may be, for example, a speedometer that uses Doppler or a speedometer that uses GNSS.

[0025] Instead of the GPS receiver 5, the sensor group 2 may include a receiver that generates positioning results of a GNSS other than GPS.

[0026] (2) Configuration of information processing device 2 is a block diagram showing an example of the hardware configuration of the information processing device 1. The information processing device 1 mainly includes an interface 11, a memory 12, and a controller 13. These elements are connected to each other via a bus line.

[0027] The interface 11 performs interface operations related to the exchange of data between the information processing device 1 and an external device. In this embodiment, the interface 11 acquires output data from each sensor in the sensor group 2, such as the LIDAR 3, the speed sensor 4, the GPS receiver 5, and the IMU 6, and supplies the data to the controller 13. The interface 11 also supplies, for example, signals related to vessel control generated by the controller 13 to each component of the vessel that controls the operation of the vessel. For example, the vessel includes a drive source such as an engine or an electric motor, a screw that generates a forward thrust based on the drive force of the drive source, a thruster that generates a lateral thrust based on the drive force of the drive source, and a rudder, which is a mechanism for freely determining the direction of travel of the vessel. During automatic operation, such as automatic docking, the interface 11 supplies a control signal generated by the controller 13 to each of these components. Note that, if the vessel is equipped with an electronic control device, the interface 11 supplies the control signal generated by the controller 13 to the electronic control device. The interface 11 may be a wireless interface, such as a network adapter for wireless communication, or a hardware interface for connecting to an external device via a cable or the like. The interface 11 may also perform interface operations with various peripheral devices such as an input device, a display device, and a sound output device.

[0028] The memory 12 is configured by various types of volatile and non-volatile memory, such as a RAM (Random Access Memory), a ROM (Read Only Memory), a hard disk drive, and a flash memory. The memory 12 stores programs for the controller 13 to execute predetermined processes. The programs executed by the controller 13 may be stored in a storage medium other than the memory 12.

[0029] The memory 12 also stores a map DB 10 including voxel data VD and highest point information IH.

[0030] The map DB 10 includes, in addition to the voxel data VD, information on docking locations (including shores and piers), information on waterways that ships can navigate, and the like. The map DB 10 may be stored in an external storage device of the information processing device 1, such as a hard disk connected to the information processing device 1 via the interface 11. The storage device may be a server device that communicates with the information processing device 1. The storage device may also be composed of multiple devices. The map DB 10 may also be updated periodically. In this case, for example, the controller 13 receives partial map information on the area to which its own position belongs from a server device that manages map information via the interface 11, and reflects the information in the map DB 10.

[0031] The highest point information IH is information about the height of the part of the ship (highest point) that is located at the highest position in the ship coordinate system, which is a coordinate system based on the ship. For example, the highest point information IH represents the height (distance in the vertical direction) from the reference position of the ship (also called the "ship reference position") in the self-position estimation performed by the information processing device 1 to the highest point. In other words, the ship reference position is the representative position of the ship whose position is to be estimated in the self-position estimation. The highest point information IH is generated based on prior measurement results and is pre-stored in memory 12.

[0032] The memory 12 also stores information necessary for the processing executed by the information processing device 1 in this embodiment, in addition to the map DB 10. For example, the memory 12 stores information used to set the downsampling size when downsampling is performed on point cloud data obtained when the LIDAR 3 performs one scanning cycle. In another example, the memory 12 stores navigation route information regarding the navigation route that the ship should take.

[0033] The controller 13 includes one or more processors such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), and a TPU (Tensor Processing Unit), and controls the entire information processing device 1. In this case, the controller 13 executes programs stored in the memory 12 or the like to perform processing related to self-position estimation, operation support, and the like.

[0034] Moreover, the controller 13 functionally has a self-position estimation unit 15 and a bridge passability determination unit 16. The controller 13 functions as a "position estimation means," a "prediction interval calculation means," a "passability determination means," a "threshold value determination means," and a computer that executes a program.

[0035] The self-position estimation unit 15 estimates its own position by performing scan matching based on NDT (NDT scan matching) based on the point cloud data based on the output of the LIDAR 3 and the voxel data VD corresponding to the voxels to which the point cloud data belongs. Here, the point cloud data to be processed by the self-position estimation unit 15 may be point cloud data generated by the LIDAR 3, or may be point cloud data obtained by downsampling the point cloud data.

[0036] The bridge passage possibility determination unit 16 determines whether the ship can pass under a bridge that exists on the navigation route that the ship is scheduled to pass, based on the self-position estimation result by the self-position estimation unit 15, the voxel data VD, and the highest point information IH.

[0037] (3) NDT scan matching Next, the position estimation based on NDT scan matching executed by the self-position estimation unit 15 will be described.

[0038] FIG. 3 is a diagram showing the self-position to be estimated by the self-position estimation unit 15 in three-dimensional Cartesian coordinates. As shown in FIG. 3, the self-position on a plane defined on the three-dimensional Cartesian coordinates of xyz is expressed by the coordinates "(x, y, z)", the ship's roll angle "φ", pitch angle "θ", and yaw angle (azimuth) "ψ". Here, the roll angle φ is defined as the rotation angle around the axis of the ship's traveling direction, the pitch angle θ is defined as the elevation angle of the ship's traveling direction with respect to the xy plane, and the yaw angle ψ is defined as the angle between the ship's traveling direction and the x-axis. The coordinates (x, y, z) are, for example, absolute positions corresponding to a combination of latitude, longitude, and altitude, or world coordinates indicating a position with a predetermined point as the origin. The self-position estimation unit 15 then performs self-position estimation using these x, y, z, φ, θ, and ψ as estimation parameters.

[0039] Next, we will explain the voxel data VD used in NDT scan matching. The voxel data VD includes data in which measured point cloud data of a stationary structure in each voxel is expressed using a normal distribution.

[0040] 4 shows an example of a schematic data structure of the voxel data VD. The voxel data VD includes information on parameters when expressing a point group in a voxel using a normal distribution, and in this embodiment includes, for each voxel, a "voxel ID," "voxel coordinates," "attribute information," "mean vector," and "covariance matrix."

[0041] "Voxel ID" indicates identification information for each voxel. "Voxel coordinates" indicate the absolute three-dimensional coordinates of a reference position, such as the center position of each voxel. Each voxel is a cube that divides space into a grid, and since its shape and size are predetermined, it is possible to identify the space of each voxel using its voxel coordinates. Voxel coordinates may also be used as a voxel ID.

[0042] "Attribute information" indicates information related to the attributes of the target voxel. For example, in this embodiment, the "attribute information" of a voxel corresponding to a bridge includes information indicating that it is a bridge part. Note that the "attribute information" of a voxel corresponding to the underside of the bridge girder (i.e., the bottom surface of the structural part above the river) may further include information indicating that it is the underside of the girder.

[0043] The "mean vector" and "covariance matrix" refer to the mean vector and covariance matrix, which are parameters when expressing the point cloud in the target voxel as a normal distribution. Note that the coordinates of an arbitrary point "i" in an arbitrary voxel "n" are Xn(i)=[xn(i), yn(i), zn(i)]T and the number of points in voxel n is "Nn", the mean vector "μn" and covariance matrix "Vn" in voxel n are expressed by the following formulas (1) and (2), respectively.

[0044]

number

[0045]

number

[0046] Next, an overview of NDT scan matching using voxel data VD will be explained.

[0047] Scan matching using NDT assuming a ship is performed using estimated parameters that are based on the amount of movement in three-dimensional space (here, xyz coordinates) and the orientation of the ship. P=[tx, ty, tz, tφ, tθ, tψ]T Here, "tx" is the amount of movement in the x direction, "ty" is the amount of movement in the y direction, "tz" is the amount of movement in the z direction, "tφ" is the roll angle, "tθ" is the pitch angle, and "tψ" is the yaw angle.

[0048] In addition, the coordinates of the point cloud data output by the lidar 3 are XL(j)=[xn(j), yn(j), zn(j)]T Then, the average value "L'n" of XL(j) is expressed by the following equation (3).

[0049]

number

[0050] Then, the self-location estimation unit 15 searches for voxel data VD associated with the point cloud data converted into the world coordinate system. Here, the world coordinate system is an absolute coordinate system adopted in the map DB 10 (including the voxel data VD). At this time, the self-location estimation unit 15 may exclude voxel data VD of voxels located below the water surface position (in the height direction) from the search target. This allows the information processing device 1 to omit unnecessary processing when associating point cloud data with voxels, and suppresses a decrease in position estimation accuracy caused by an error in association.

[0051] Then, the self-position estimation unit 15 uses the mean vector μn and covariance matrix Vn included in the searched voxel data VD to calculate an evaluation function value (also called an "individual evaluation function value") "En" relating to matching of the voxel n.

[0052] In this case, the self-position estimation unit 15 calculates the individual evaluation function value En of the voxel n based on the following equation (4).

[0053]

number

[0054] Then, the self-position estimation unit 15 calculates a comprehensive evaluation function value (also called a "score value") "E(k)" for all voxels to be matched, as shown in the following formula (5). The score value E is an index showing the compatibility of the matching.

[0055]

number

[0056]

number

[0057] Fig. 5 is an example of a functional block diagram of the self-location estimation unit 15. As shown in Fig. 5, the self-location estimation unit 15 has a dead reckoning unit 51, a coordinate conversion unit 52, a water surface reflection data removal unit 53, and an NDT position calculation unit 54. Note that in Fig. 5, arrows connect blocks where data is exchanged, but the data flow between blocks is not limited to this. The same applies to other functional block diagrams described later.

[0058] The dead reckoning unit 51 calculates the DR position based on the signal output by the sensor group 2. Specifically, the dead reckoning unit 51 uses the moving speed and angular velocity of the ship based on the outputs of the speed sensor 4, the IMU 6, etc. to determine the moving distance and azimuth change from the previous time. The dead reckoning unit 51 then calculates the DR position XDR(k) at time k by adding the moving distance and azimuth change from the previous time to the estimated self-position X^(k-1) at time k-1, which is the processing time immediately before the current processing time k. This DR position XDR(k) is the self-position calculated at time k based on dead reckoning and corresponds to the predicted self-position X-(k). Note that if there is no estimated self-position X^(k-1) at time k-1 immediately after the start of self-position estimation, the dead reckoning unit 51 determines the DR position XDR(k) based on the signal output by the GPS receiver 5, for example.

[0059] The coordinate conversion unit 52 converts the point cloud data based on the output of the LIDAR 3 into a world coordinate system, which is the same coordinate system as the map DB 10. In this case, the coordinate conversion unit 52 performs coordinate conversion of the point cloud data at time k, for example, based on the predicted self-position output by the dead reckoning unit 51 at time k. Note that the process of converting point cloud data in a coordinate system based on a LIDAR installed on a moving body (a ship in this embodiment) into the coordinate system of the moving body, and the process of converting from the coordinate system of the moving body to the world coordinate system are disclosed in, for example, International Publication WO2019 / 188745.

[0060] The water surface reflection data removal unit 53 removes data (also referred to as "water surface reflection data") erroneously generated by the LIDAR 3 receiving light reflected from the water surface from the point cloud data supplied from the coordinate conversion unit 52. In this case, the water surface reflection data removal unit 53 removes data representing positions below the water surface position (including the same height, the same applies below) (i.e., positions with the same or lower z coordinate value) from the point cloud data as water surface reflection data. Note that the water surface reflection data removal unit 53 may estimate the water surface position based on the z coordinate value after coordinate conversion processing of the point cloud data output by the LIDAR 3 when the ship is located at a position more than a predetermined distance from the shore. Then, the water surface reflection data removal unit 53 supplies the point cloud data obtained by removing the data below the water surface position from the point cloud data supplied from the coordinate conversion unit 52 to the NDT position calculation unit 54.

[0061] The NDT position calculation unit 54 calculates the NDT position based on the point cloud data supplied from the water surface reflection data removal unit 53. In this case, the NDT position calculation unit 54 matches the point cloud data in the world coordinate system supplied from the water surface reflection data removal unit 53 with the voxel data VD expressed in the same world coordinate system, thereby associating the point cloud data with the voxels. Then, for each voxel associated with the point cloud data, the NDT position calculation unit 54 calculates an individual evaluation function value based on equation (4) and calculates an estimated parameter P that maximizes the score value E(k) based on equation (5). Then, the NDT position calculation unit 54 calculates the NDT position XNDT(k) at time k, which is determined by applying the estimated parameter P calculated at time k to the DR position XDR(k) output by the dead reckoning unit 51, based on equation (6). The NDT position calculation unit 54 outputs the NDT position XNDT(k) as the estimated self-position X^(k) at time k.

[0062] (4) Bridge passability determination process Next, the process executed by the bridge passability determination unit 16 to determine whether or not a bridge is passable (also referred to as the "bridge passability determination process") will be described. Briefly, the bridge passability determination unit 16 calculates the height of the bridge (also referred to as the "bridge height") that is the subject of the passability determination and the height of the highest point of the ship (also referred to as the "ship's highest point height"), and predicts the vertical distance between the ship and the bridge below the bridge (also referred to as the "predicted distance") based on these calculation results. The bridge passability determination unit 16 then determines whether or not the bridge is passable based on this predicted distance. The bridge height represents the height of the bridge's bottom surface above the river (i.e., the height of the underside of the girders). The "height" used in calculating the ship's highest point height and the bridge height represents the height (e.g., elevation) in the world coordinate system used in the map DB 10, and refers to, for example, the z coordinate value in the world coordinate system.

[0063] FIG. 6 is a diagram illustrating an overview of the bridge passage possibility determination process. FIG. 6 illustrates a ship passing over a bridge 30, observed from behind. In the example of FIG. 6, the ship is equipped with two lidars 3, and a position at the same height as the lidars 3 is defined as the ship reference position. The ship also has a protrusion 33, which is the highest point of the ship. The bridge 30 has a lower girder 32 that forms the bottom surface of the structure located above the river, forming an under-girder space 31 through which the ship can pass. A dashed rectangular frame 35 indicates the position of each voxel containing voxel data VD. Line L1 indicates a position at the same height as the reference position (i.e., the point where the z-coordinate value in the world coordinate system is 0) for measuring heights such as the bridge height and the ship's highest point height, and line L2 indicates a position at the same height as the ship reference position. Line L3 indicates a position at the same height as the ship's highest point, and line L4 indicates a position at the same height as the lower girder 32 that forms the bottom surface of the bridge 30 above the river.

[0064] In this case, the bridge passability determination unit 16 calculates the heights or widths corresponding to the arrows A1 to A5 in the order of the arrows A1 to A5, as will be described below, to calculate the predicted intervals used to determine whether the bridge is passable.

[0065] First, the bridge passage possibility determination unit 16 extracts voxel data VD of voxels (see rectangular frame 35) corresponding to the bridge to be crossed from the map DB 10, and calculates the bridge height (see arrow A1) based on the extracted voxel data VD. In this case, the bridge passage possibility determination unit 16 refers to attribute information, etc. included in the voxel data VD, and extracts voxel data VD of voxels corresponding to bridges (or the lower part of girders) located on a river through which the ship will pass. Then, the bridge passage possibility determination unit 16 calculates the bridge height based on, for example, the z coordinate value of the average vector of each extracted voxel data VD. At this time, the bridge passability determination unit 16 may extract the voxel data VD of the voxels of the bridge located on the river that has the smallest z coordinate value (i.e., the lowest voxel) for each voxel position on the horizontal plane (xy plane), and determine the bridge height based on that voxel data VD.

[0066] Next, the bridge passage possibility determination unit 16 acquires the result of the self-position estimation performed by the self-position estimation unit 15, and specifies the z coordinate indicated by the self-position estimation result as the height of the ship reference position (the height corresponding to arrow A2, hereinafter also referred to as the "ship reference height"). In Figure 6, as an example, the ship reference position is set to the same height as the position of the LIDAR 3 indicated by line L2.

[0067] Next, the bridge passage possibility determination unit 16 identifies the width in the height direction from the ship reference position to the highest point (see arrow A3) by referring to the highest point information IH from the memory 12. Then, the bridge passage possibility determination unit 16 calculates the ship's highest point height (see arrow A4) which corresponds to the height obtained by adding the width in the height direction from the ship reference position to the highest point (see arrow A3) to the ship's reference height (see arrow A2).

[0068] Then, the bridge passage possibility determination unit 16 calculates the width obtained by subtracting the vessel's highest point height from the bridge height as the prediction interval (see arrow A5).

[0069] Thereafter, the bridge passage possibility determination unit 16 determines that the ship can pass through the bridge if the calculated prediction interval is equal to or greater than a threshold value (also called the "prediction interval threshold Th"), and determines that there is a risk that the ship will not be able to pass through the bridge safely if the prediction interval is less than the prediction interval threshold Th.

[0070] Next, a method for determining the prediction interval threshold Th will be described. As an example, a method for determining the prediction interval threshold Th based on the result of self-location estimation by the self-location estimation unit 15 will be described. Note that instead of being determined based on the method described below, the prediction interval threshold Th may be set to a fixed value stored in advance in the memory 12 or the like.

[0071] The bridge passage possibility determination unit 16 calculates the standard deviation "σ1" of the vessel reference height (z coordinate value) indicated by the multiple self-position estimation results calculated by the self-position estimation unit 15 within the immediately preceding predetermined period. For example, if the self-position estimation is calculated at a cycle of 100 [ms], setting the predetermined period to 5 [s] will result in the standard deviation σ1 of 50 vessel reference height calculation values. Here, the standard deviation σ1 corresponds to the width indicated by the arrow A7 in FIG. 6 (i.e., half the width of the arrow A6 centered on the line L2). Then, the bridge passage possibility determination unit 16 calculates the prediction interval threshold Th by multiplying the maximum value "σ1(max)" of the multiple standard deviations σ1 calculated at predetermined time intervals while changing the above-mentioned predetermined period by a predetermined coefficient "k." That is, the bridge passage possibility determination unit 16 calculates the prediction interval threshold Th based on the following equation (7): Th=k·σ1(max) (7)

[0072] In this case, the coefficient k is set to a fixed value (for example, k=5) that provides a sufficient confidence interval.

[0073] Figure 7(A) shows the frequency distribution of the ship's reference height when the ship's reference height used to calculate the standard deviation σ1 is considered to be a discrete value. Figure 7(B) shows an example of a graph of the time transition of the standard deviation σ1 calculated at predetermined time intervals. In Figure 7(A), "μ1" represents the average ship's reference height obtained as a result of self-location estimation. The bridge passage possibility determination unit 16 calculates the standard deviation σ1 by aggregating a predetermined number of ship's reference height estimation results obtained immediately before, and further identifies the maximum value σ1(max) by monitoring the standard deviation σ1 calculated at predetermined time intervals for a predetermined length of time as shown in Figure 7(B).

[0074] Here, we will provide additional explanation about the effect of determining the prediction interval threshold Th based on the self-location estimation result. The variation in ship height obtained as the self-location estimation result is influenced by errors in the point cloud data output by the LIDAR 3 and the rolling of the ship, but is also caused by large wave height. When wave height is large, the ship's up and down movement in the z direction also becomes large. Taking the above into consideration, the bridge passage possibility determination unit 16 increases the prediction interval threshold Th as the standard deviation σ1 increases, based on equation (7), thereby making it possible to more accurately and safely determine whether or not the bridge can be passed.

[0075] 8 is an example of a functional block of the bridge passage possibility determination unit 16. Functionally, the bridge passage possibility determination unit 16 has a bridge height calculation unit 61, a vessel highest point height calculation unit 62, a prediction interval calculation unit 63, a threshold value determination unit 64, and a passage possibility determination unit 65.

[0076] The bridge height calculation unit 61 extracts voxel data VD of voxels corresponding to the bridge to be crossed from the map DB 10, and calculates the bridge height based on the extracted voxel data VD. The ship highest point height calculation unit 62 calculates the ship highest point height based on the ship reference height indicated by the estimation result of the self-position estimation performed by the self-position estimation unit 15 and the width in the height direction from the ship reference position to the highest point indicated by the highest point information IH.

[0077] The prediction interval calculation unit 63 calculates the prediction interval based on the bridge height calculated by the bridge height calculation unit 61 and the ship's highest point height calculated by the ship's highest point height calculation unit 62. The threshold determination unit 64 calculates the standard deviation σ1 and maximum value σ1(max) based on the ship's reference height indicated by the estimation result of the self-position estimation performed by the self-position estimation unit 15, and determines the prediction interval threshold value Th by referring to equation (7).

[0078] The passage possibility determination unit 65 determines whether the bridge is passable or not based on the prediction interval calculated by the prediction interval calculation unit 63 and the prediction interval threshold Th determined by the threshold determination unit 64. Then, the passage possibility determination unit 65 supplies the determination result of whether the bridge is passable or not to other processing blocks, etc. of the controller 13. Thereafter, the controller 13 may perform display and / or audio output control, etc., based on the determination result of whether the bridge is passable or not, via the interface 11. For example, if the prediction interval is less than the prediction interval threshold, the controller 13 outputs a warning that the ship may not be able to pass the bridge safely. In another example, the controller 13 searches for an alternative route that does not pass over the bridge that has been determined to be unpassable, and outputs guidance information and performs navigation control for the new route that has been found.

[0079] Fig. 9 is an example of a flowchart of the bridge passage possibility determination process executed by the bridge passage possibility determination unit 16. The bridge passage possibility determination unit 16 executes the process of the flowchart shown in Fig. 9 for each bridge for which it is necessary to determine whether the ship can pass, for example, when the ship starts operating based on the navigation route, or when a predetermined user input via the interface 11 is detected.

[0080] First, the bridge passage possibility determination unit 16 calculates the bridge height based on the voxel data VD of the voxels corresponding to the bridge to be crossed (step S11). Next, the bridge passage possibility determination unit 16 specifies the vessel reference height based on the estimation result of the self-position estimation performed by the self-position estimation unit 15 (step S12). Then, the bridge passage possibility determination unit 16 calculates the vessel's highest point height based on the vessel reference height specified in step S12 and the highest point information IH (step S13).

[0081] The bridge passage possibility determination unit 16 then calculates a prediction interval based on the bridge height calculated in step S11 and the vessel's highest point height calculated in step S13 (step S14). The bridge passage possibility determination unit 16 then determines whether the vessel can pass over the target bridge based on the prediction interval calculated in step S14 (step S15). In this case, the bridge passage possibility determination unit 16 preferably sets the prediction interval threshold Th, which is a determination threshold used for comparison with the prediction interval, based on the standard deviation σ1, which is an index representing the variation in the vessel reference height calculated by the vessel's own position estimation unit 15, as described above.

[0082] (5) Variations The following describes preferred modifications of the above-described embodiment. The following modifications may be applied to these embodiments in combination.

[0083] (Variation 1) The bridge passage possibility determination unit 16 may use an adaptively changing value as the coefficient k used to calculate the prediction interval threshold Th, instead of using a fixed value. Specifically, the bridge passage possibility determination unit 16 measures the actual measurement value of the heightwise distance between the ship and the bridge below the bridge (also referred to as the "measured distance"), and sets the coefficient k based on the degree of variation in the difference between the actual distance and the predicted distance. In this way, the bridge passage possibility determination unit 16 sets the prediction interval threshold Th to an appropriate value that is not larger than necessary and that ensures sufficient safety.

[0084] FIG. 10 is a view of a ship passing a bridge 30 for which a prediction interval has been calculated, observed from behind.

[0085] First, when passing over a bridge 30 for which the predicted interval has been calculated, the bridge passage possibility determination unit 16 calculates the height distance (see arrow A8) from the ship reference position to the bridge 30 (more specifically, the girder lower part 32 that forms the bottom surface of the bridge 30 above the river) based on point cloud data of the LIDAR 3 that represents the measurement results above the ship. At this time, to exclude points that detect locations that are not bridges, such as bridge piers, the maximum z-coordinate value of the point cloud data is calculated, and the z-coordinate value of each measurement point that is closest to this maximum value is extracted, thereby obtaining the measurement data of the bridge 30. The distance is then calculated by averaging the z-coordinate values ​​of multiple detection data for the bridge 30. As shown by arrow A8, the above-mentioned distance is the width between line L2, which indicates the ship reference position, and line L4, which indicates the bottom surface position of the bridge above the river. Note that while FIG. 10 illustrates only the measurement points of the LIDAR 3 on one side (the right side), point cloud data of the LIDAR 3 on both sides (the right side and the left side) is actually used.

[0086] Next, the bridge passage possibility determination unit 16 calculates the actual measured distance (see arrow A9) by subtracting the height (see arrow A3) of the highest point from the ship's reference position based on the highest point information IH from the vertical distance (see arrow A8) from the ship's reference position to the bridge 30.

[0087] The bridge passage possibility determination unit 16 then calculates the difference between the predicted interval and the measured interval by subtracting the measured interval from the predicted interval of the bridge 30. The bridge passage possibility determination unit 16 then calculates the above-mentioned difference values ​​for multiple bridges that the ship has passed through within a predetermined period, and calculates the average "μ2" and standard deviation "σ2" of the calculated difference values. Figure 11 shows the frequency distribution of the above-mentioned difference values ​​when they are considered to be discrete values.

[0088] Next, the bridge passage possibility determination unit 16 regards the average μ2 as a constant offset for the prediction interval (i.e., used universally for all bridges), and then corrects the prediction interval by subtracting the average μ2 from the prediction interval for all bridges through which the ship is scheduled to pass. This improves the accuracy of the prediction interval for bridges through which the ship is scheduled to pass, thereby improving the accuracy of the bridge passage determination process. The above-mentioned offset is an example of "correction information." Furthermore, the bridge used to calculate the average μ2 and standard deviation σ2 is an example of a "first bridge," and the bridge for which the prediction interval is corrected (i.e., the bridge through which the ship is scheduled to pass) is an example of a "second bridge."

[0089] Furthermore, the bridge passage possibility determination unit 16 sets the coefficient k in equation (7) so that the prediction interval threshold Th increases as the standard deviation σ2 increases. For example, the bridge passage possibility determination unit 16 sets the coefficient k to "3 + σ2" and determines the prediction interval threshold Th based on the following equation (8). Th=(3+σ2)·σ1(max) (8)

[0090] As described above, according to this modified example, the bridge passability determination unit 16 can improve the prediction accuracy of the prediction interval and adaptively set the prediction interval threshold value Th so that the prediction interval threshold value Th is larger when the prediction interval varies greatly from the actually measured interval, and the prediction interval threshold value Th is smaller when the variation is small.

[0091] (Variation 2) The voxel data VD is not limited to a data structure including a mean vector and a covariance matrix as shown in FIG. 4. For example, the voxel data VD may directly include point cloud data used to calculate the mean vector and covariance matrix. Furthermore, the self-localization method using the voxel data VD is not limited to NDT scan matching. For example, the information processing device 1 may perform self-localization by matching the voxel data VD with point cloud data of the lidar 3 based on ICP (Iterative Closest Point).

[0092] As described above, the controller 13 of the information processing device 1 according to this embodiment estimates the vessel reference position based on the map DB 10. The controller 13 then calculates a predicted interval, which is the distance between the bridge and the vessel, based on the bridge height based on the map DB 10, the position estimation result, and the highest point information IH relating to the height from the vessel reference position to the vessel's highest point. The controller 13 then determines whether the vessel can pass under the bridge based on the predicted interval. This allows the information processing device 1 to accurately determine in advance whether the vessel can safely pass under the bridge over which it is scheduled to pass.

[0093] In the above-described embodiments, the program can be stored using various types of non-transitory computer-readable media and supplied to a controller or the like that is a computer. Non-transitory computer-readable media include various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic storage media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical storage media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (Random Access Memory)).

[0094] Although the present invention has been described above with reference to the examples, the present invention is not limited to the above examples. Various modifications within the scope of the present invention that would be understood by those skilled in the art can be made to the configuration and details of the present invention. In other words, the present invention naturally includes various modifications and alterations that would be possible for those skilled in the art in accordance with the entire disclosure, including the claims, and the technical ideas. Furthermore, the disclosures of the above-cited patent documents and other documents are incorporated herein by reference. [Explanation of symbols]

[0095] 1. Information processing equipment 2 Sensor group 3 Rider 4 Speed ​​Sensor 5 GPS receiver 6 IMU 10 Map DB

Claims

[Claim 1] a position estimation means for estimating a reference position of the ship based on map data; a prediction interval calculation means for calculating a prediction interval, which is a predicted distance between the bridge and the ship, based on the bridge height based on the map data, the estimation result of the position estimation, and highest point information relating to the height from the reference position to the highest point of the ship; a passage possibility determination means for determining whether the vessel can pass under the bridge based on the prediction interval; An information processing device having the above.

Images