Vehicle position detection method and position detection device

Abstract

To rapidly detect a position of an object to be detected by using a Hough transform of point group data related to position information.SOLUTION: A method of detecting a position of an object to be detected includes: a point group data acquisition step S11 of acquiring preliminary point group data D1 relating to position information on a surface of an object C to be detected; a voxel generation step S12 of generating a plurality of voxels B based on the preliminary point group data D1; a data number reduction step S13 of reducing the number of the preliminary point group data D1 located in each voxel B; a provisional outline detection step S14 of applying a Hough transform to secondary point group data D2 obtained in the data number reduction step S13 to detect provisional outlines Ls1 and Lf1 of the object C to be detected; a main outline detection step S15 of applying the Hough transform to the preliminary point group data D1 located around the provisional outlines Ls1 and Lf1 in the preliminary point group data D1 to detect main outlines Ls2 and Lf2 of the object C to be detected; and a position detection step S16 of detecting a position of the object C to be detected based on the main outlines Ls2 and Lf2.SELECTED DRAWING: Figure 15

Description

[Technical Field]

[0001] The present invention relates to a method and device for detecting the position of a detection target, and more particularly to a position detection technique suitable for use when a vehicle is used as the detection target. [Background technology]

[0002] For example, as a means for efficiently transporting finished vehicles such as automobiles mass-produced in a factory to a predetermined location such as a shipping point, a commonly adopted method is to load multiple finished vehicles into a loading vessel such as a container, transport the loading vessel by land to a port near the destination in a transport vehicle such as a large truck, and then transfer the loading vessel to a transport vessel for water transport to the destination (see, for example, Patent Document 1).

[0003] Furthermore, Patent Document 2 proposes a system in which a transport vehicle that uses an unmanned, automatic towing vehicle to tow multiple carts along a predetermined route within a limited area transports the completed vehicle to be transported to its destination with the completed vehicle loaded onto the cart. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2004-123258 [Patent Document 2] Japanese Patent Application Publication No. 2019-36036 [Patent Document 3] International Publication No. 2013 / 31418 Summary of the Invention [Problem to be solved by the invention]

[0005] In recent years, the manufacturing industry has also been faced with an increasing need to take measures to compensate for labor shortages in preparation for the coming aging society. From this perspective, when considering the efficient transportation of completed vehicles with a small number of people, one possible method would be to make the transport vehicles self-propelled as described in Patent Document 2, manufacture the transport vehicles at low cost, prepare a large number of transport vehicles, and load each completed vehicle onto the transport vehicle for automatic transport.

[0006] On the other hand, when considering loading a completed vehicle onto a transport vehicle and automatically transporting it as described above, it is important to know the exact position of the completed vehicle relative to the transport vehicle in order to quickly approach the completed vehicle.

[0007] Here, when focusing on points on a characteristic outer shape of a completed vehicle, one possible method for detecting the position of the completed vehicle is to use a technique for detecting straight lines contained in an image by applying a Hough transform to points in an image having position coordinate data, as described in Patent Document 3, for example. That is, since the body of a completed vehicle (particularly the front part of the body) generally has a shape close to a box, it would appear that by, for example, acquiring position coordinate data (point cloud data) of the body surface with an appropriate sensor and applying a Hough transform to the acquired position coordinate data, it would be possible to detect straight lines along the sides and front of the body as the body outline from an image containing the position coordinate data as points.

[0008] However, with this method, a large amount of position coordinate data must be acquired by the sensor and the Hough transform must be applied to all of the acquired position coordinate data, which requires a significant amount of time for the calculation processing related to the Hough transform. As described above, in order to quickly approach the completed vehicle, it is necessary to constantly recognize the relative position of the completed vehicle with respect to the guided vehicle and to have the guided vehicle approach the completed vehicle in an appropriate direction and at an appropriate speed. However, if it takes time to detect the position of the completed vehicle, it is difficult to have the guided vehicle approach the completed vehicle smoothly and quickly.

[0009] The above-mentioned problem is not limited to the case where a carrier vehicle is approached to a vehicle, but can occur in any case where the position of a target object needs to be detected in a short time.

[0010] In view of the above circumstances, the technical problem to be solved in this specification is to make it possible to detect the position of an object to be detected in a short time by utilizing the Hough transform on point cloud data relating to position information. [Means for solving the problem]

[0011] The above-mentioned problems are solved by a position detection method for an object to be detected according to the present invention. That is, this position detection method is characterized by comprising: a point cloud data acquisition step of acquiring primary point cloud data relating to position information of the surface of the object to be detected; a voxel generation step of generating a plurality of voxels based on the primary point cloud data; a data number reduction step of reducing the number of primary point cloud data located within each voxel; a provisional outline detection step of detecting a provisional outline of the object to be detected by applying a Hough transform to the secondary point cloud data obtained in the data number reduction step; a final outline detection step of detecting a final outline of the object to be detected by applying a Hough transform to primary point cloud data located around the provisional outline among the primary point cloud data; and a position detection step of detecting the position of the object to be detected based on the final outline.

[0012] As described above, the position detection method according to the present invention generates multiple voxels based on the acquired primary point cloud data, reduces the number of primary point cloud data located within each voxel, and performs a Hough transform on the secondary point cloud data, which is the reduced primary point cloud data, to detect a provisional outline of the object to be detected. This reduces the number of point cloud data used in the Hough transform, shortening the time required to detect the provisional outline. Meanwhile, the position detection of the object to be detected is performed by detecting the actual outline by performing a Hough transform on the original primary point cloud data, thereby enabling highly accurate position detection. Furthermore, by limiting the primary point cloud data used in position detection to the area surrounding the provisional outline, only point cloud data that is likely to be relevant to detecting the actual outline can be used. This makes it possible to efficiently detect the position of the object to a short period of time while achieving high position detection accuracy.

[0013] The position detection method according to the present invention may further include a reliability evaluation step of evaluating the reliability of the outline, in which the reliability evaluation step may obtain a proportion of voxels containing secondary point cloud data for at least voxels through which the outline passes, and the reliability of the outline may be evaluated as being higher the higher the proportion.

[0014] In this way, by providing a reliability evaluation step, it is possible to increase the reliability of the main outline detected in the main outline detection step. Therefore, it is also possible to increase the reliability of the position of the object detected based on the main outline. Furthermore, by obtaining the proportion of voxels where secondary point cloud data exists for at least the voxels through which the main outline passes and evaluating the reliability of the main outline based on this proportion, it is possible to efficiently and quickly evaluate the reliability of the main outline in this step as well.

[0015] Furthermore, in the position detection method according to the present invention, the reliability evaluation step may obtain the proportion of voxels in which secondary point cloud data exists for voxels adjacent to a voxel through which the outline passes on the side farther from the object to be detected, and evaluate the reliability of the outline to be higher the lower the proportion.

[0016] In this way, the reliability of the detected outline can be further increased by evaluating the reliability of the outline based on the proportion of voxels containing secondary point cloud data, not only for the voxels through which the outline passes, but also for the adjacent voxels farther from the detected object. This further increases the reliability of the detected object's position based on the outline.

[0017] In the position detection method according to the present invention, in the reliability evaluation step, the reliability may be evaluated by setting the size of the voxels to a size larger than the size of the voxels generated in the voxel generation step.

[0018] The point cloud data (secondary point cloud data) used in the reliability evaluation process only needs to be the minimum number of data necessary to evaluate the reliability of the outline, so there is no particular problem in terms of evaluation accuracy even if the voxel size used in the reliability evaluation process is larger than the voxel size used in detecting the provisional outline. Therefore, by increasing the voxel size in this way, it is possible to evaluate the reliability of the outline at the required level while also shortening the time required for the reliability evaluation.

[0019] Furthermore, in the position detection method of the present invention, the object to be detected may be a vehicle, and in that case, the provisional outline detection process may detect, as provisional outlines, provisional side lines that are provisional outlines along the sides of the vehicle and provisional front lines that are provisional outlines that are perpendicular to the provisional side lines and along the front of the vehicle, and the actual outline detection process may detect, as actual outlines, actual side lines that are provisional outlines along the sides of the vehicle and actual front lines that are provisional outlines that are perpendicular to the second side lines and along the front of the vehicle.

[0020] As described above, the present invention makes it possible to detect the position of a detected object in a very short time, and is therefore suitable for cases where the detection target (detected object) is a vehicle whose outline is easy to detect as a straight line, such as a side line or a front line. Therefore, by detecting provisional side lines and provisional front lines along the side and front of the vehicle as a provisional outline, and detecting real side lines and real front lines along the side and front of the vehicle as a real outline, it becomes possible to accurately detect the position and attitude of the vehicle.

[0021] Furthermore, in the position detection method according to the present invention, when a vehicle is the object to be detected, the outline detection process may detect the actual sideline and the actual frontline by excluding the primary point cloud data within the voxel among the multiple voxels where the intersection of the provisional sideline and the provisional frontline is located.

[0022] The sides and front of a vehicle are usually connected via a smooth convex curve (corner). Therefore, when point cloud data from the side to the front of a vehicle is acquired using a known point cloud data acquisition sensor such as Lidar, it is possible that the point cloud data will be concentrated in the corner between the side and front. Therefore, by excluding the primary point cloud data within the voxel where the intersection of the provisional sideline and provisional frontline is located, only the primary point cloud data that is important for detecting the actual sideline and the actual frontline can be used. This improves the detection accuracy of the actual sideline and the actual frontline. Furthermore, by excluding some of the primary point cloud data, the time required for detection can be shortened.

[0023] The above-mentioned problems are also solved by a position detection device for a detectable object according to the present invention. That is, this position detection device is characterized by comprising: a point cloud data acquisition unit capable of acquiring primary point cloud data relating to position information of the surface of the detectable object; a voxel generation unit that generates a plurality of voxels based on the primary point cloud data; a data number reduction unit that reduces the number of primary point cloud data located in each voxel; an outline detection unit that applies a Hough transform to the secondary point cloud data obtained by the data number reduction unit to detect a provisional outline of the detectable object, or applies a Hough transform to primary point cloud data located around the provisional outline among the primary point cloud data to detect a real outline of the detectable object; and a position detection unit that detects the position of the detectable object based on the real outline.

[0024] In this way, the position detection device according to the present invention also generates multiple voxels based on the acquired primary point cloud data, reduces the number of primary point cloud data located within each voxel, and performs a Hough transform on the secondary point cloud data, which is the reduced primary point cloud data, to detect a provisional outline of the object to be detected. This reduces the number of point cloud data used in the Hough transform, shortening the time required to detect the provisional outline. Meanwhile, the position of the object to be detected can be detected by detecting the actual outline by performing a Hough transform on the original primary point cloud data, thereby enabling highly accurate position detection. Furthermore, by limiting the primary point cloud data used in this case to the area around the provisional outline, the position of the object to be detected can be efficiently detected in a short time using only valid point cloud data. [Effects of the Invention]

[0025] As described above, according to the present invention, it is possible to detect the position of an object to be detected in a short time by utilizing the Hough transform on point cloud data related to position information. [Brief explanation of the drawings]

[0026] [Figure 1] 1 is a diagram showing the overall configuration of an automatic vehicle transport system according to an embodiment of the present invention; [Figure 2] FIG. 2 is a side view of the automatic transport device shown in FIG. [Figure 3] FIG. 2 is a plan view of the automatic transport device shown in FIG. [Figure 4] FIG. 2 is a front view of the automatic transport device shown in FIG. [Figure 5] 1. FIG. 4 is a side view conceptually showing an example of acquisition of point cloud data relating to position information of a vehicle surface by a point cloud data acquisition unit (detection unit) provided in the automatic transport device shown in FIG. [Figure 6] 2 is a plan view conceptually showing an example of acquisition of point cloud data relating to position information of a vehicle surface by a point cloud data acquisition unit provided in the automatic transport device shown in FIG. 1. FIG. [Figure 7] 1 is a diagram illustrating a configuration of a position detection device according to an embodiment of the present invention. [Figure 8] 3 is a diagram showing an example of point cloud data relating to position information of a vehicle surface acquired by a point cloud data acquisition unit; FIG. [Figure 9] 10 is a diagram conceptually illustrating an example of a distribution pattern of voxels generated by a voxel generating unit. FIG. [Figure 10] FIG. 10 is a diagram conceptually illustrating a state after the number of data items in the primary point cloud data has been reduced by the data number reduction unit. [Figure 11] 10 is a diagram conceptually showing the positional relationship between a provisional outline detected by an outline detection unit, voxels, and secondary point cloud data. FIG. [Figure 12] 10 is a diagram conceptually showing the positional relationship between the outline detected by the outline detection unit, voxels, and primary point cloud data. FIG. [Figure 13] FIG. 10 is a diagram for conceptually explaining details of the process of evaluating the reliability of the outline by the reliability evaluation unit. [Figure 14] 4 is a flowchart illustrating the flow of a mounting operation for a vehicle according to the present embodiment. [Figure 15] 10 is a flowchart illustrating the flow of a relative position detection process according to the present embodiment. [Figure 16] 2 is a side view showing a state in which the front wheels of a vehicle are mounted on a mounting portion of the automatic transporter shown in FIG. 1. DETAILED DESCRIPTION OF THE INVENTION

[0027] Hereinafter, an automatic transport device including a vehicle position evaluation device according to one embodiment of the present invention and an automatic transport system including this automatic transport device will be described with reference to the drawings.

[0028] 1 shows the overall configuration of an automatic vehicle transport system 10 according to one embodiment of the present invention. This automatic transport system 10 is used to transport a vehicle C completed in a factory F to a container yard Y, which is a waiting area for the vehicles, and mainly comprises a plurality of automatic transport devices 11 and a control unit 12 that controls the driving of the plurality of automatic transport devices 11. In this embodiment, the following details will be described, taking as an example a case in which the left and right front wheels of the front-wheel drive vehicle C are mounted on the automatic transport device 11 and the vehicle C is transported with its left and right rear wheels in contact with the ground.

[0029] As shown in FIGS. 2 to 4 , the automatic transport device 11 includes two drive wheels 13, a power applying unit 14 that applies power to each drive wheel 13, a mounting unit 15 that can mount one of the front wheels FW and rear wheels RW of the vehicle C (here, the left and right front wheels FW, which are the drive wheels), a receiver 16 for a satellite positioning system, and a detector 17. In this embodiment, the detector 17 corresponds to the point cloud data acquisition unit of the present invention. Each drive wheel 13 is housed in a casing 18. The two casings 18 are connected to each other by a connector 19. In this case, the mounting units 15 are provided at predetermined widthwise positions on the connector 19, i.e., at two widthwise positions corresponding to the front wheels FW of the vehicle C to be mounted. Therefore, in this case, the mounting unit 15 is disposed between the two drive wheels 13. In other words, the mounting unit 15 is disposed at a position that overlaps with the two drive wheels 13 in the longitudinal direction of the vehicle body (see FIG. 3 ). The width direction here refers to the direction perpendicular to the longitudinal direction of the vehicle body when the vehicle C is mounted, which corresponds to the direction in which the two drive wheels 13 of the automatic conveying device 11 are spaced apart. The vehicle C here also includes not only completed vehicles that are ultimately available for purchase by consumers, but also mass-produced vehicles that do not have an open loading platform or a box-shaped cargo compartment like a light truck, in other words, vehicles that are not yet fitted (vehicles before fitting).

[0030] In this embodiment, as shown in FIGS. 3 and 4 , each drive wheel 13 is composed of two wheels 20 arranged in parallel to each other. The wheels 20 are configured to be rotatable independently of each other and are rotatably supported on a rotation shaft 21 arranged between the wheels 20. The rotation shaft 21 is arranged with its longitudinal direction aligned with the vertical direction when the automatic transport device 11 is traveling. Thus, for example, by rotating the two wheels 20 in opposite directions or by driving only one of the wheels 20 to rotate, the drive wheel 13 having the two wheels 20 rotates around the rotation shaft 21, thereby enabling steering of the automatic transport device 11. Note that in this embodiment, the two wheels 20 serving as the drive wheels 13 are rotatable around the rotation shaft 21 by 90 degrees or more (e.g., 360 degrees). Therefore, for example, although not shown, by rotating these two wheels 20 by 90 degrees, the moving direction of the automatic transport device 11 can be changed from the longitudinal direction of the vehicle body to the width direction.

[0031] In this embodiment, as shown in Figures 3 and 4, the power applying unit 14 is provided in the same number as the wheels 20 and is composed of a plurality of in-wheel motors 22 that apply rotational driving force to each wheel 20. Each in-wheel motor 22 has, for example, a stator and a rotor (not shown), where the stator is fixed to a rotation shaft 21 and the rotor is connected to the wheel 20. As a result, by driving the rotor of the in-wheel motor 22 to rotate, the wheel 20 connected to the rotor can rotate together with the rotor. Furthermore, as will be described later, each in-wheel motor 22 can be electrically controlled independently. Therefore, by configuring the power applying unit 14 as described above, it is possible to independently drive and rotate two wheels 20 arranged in parallel, and it is also possible to independently drive and rotate the drive wheels 13 about a vertical axis and a horizontal axis.

[0032] In this embodiment, the auxiliary wheels 23 are disposed on the vehicle body front side of the connecting portion 19. In this case, the auxiliary wheels 23 are capable of contacting the ground further forward on the vehicle body of the automatic guided vehicle 11 than the drive wheels 13, and rotate (roll on the ground) following the rotational drive of the drive wheels 13 in a ground contact state. Alternatively, as will be described later, when the automatic guided vehicle 11 travels with the front wheels FW of the vehicle C mounted on the mounting portion 15, the auxiliary wheels 23 rotate following the rotational drive of the drive wheels 13 in a ground contact state.

[0033] As described above, the receiver 16 is capable of receiving signals from multiple satellites (not shown) for a satellite positioning system. By performing a predetermined arithmetic process based on the received signals, the position of the vehicle C (of the receiver 16) on Earth at the time of reception can be obtained. The arithmetic process for obtaining the position may be performed by the receiver 16 or by the control unit 12 (specifically, the terminal control unit 24 or the integrated control unit 25, described later). The receiver 16 may be attached to any desired position relative to the automated guided vehicle 11. For example, in consideration of smooth communication with satellites (positioning satellites) for a satellite positioning system such as GPS, it is preferable to attach the receiver 16 as high as possible on the automated guided vehicle 11. In this embodiment, the receiver 16 is disposed at the tip (top end) of an upright portion 26 that extends upright from the top surface of the casing 18 (see FIG. 2, etc.).

[0034] The detection unit 17 is provided at a predetermined position of the automatic guided vehicle 11. As described above, the detection unit 17 corresponds to the point cloud data acquisition unit of the present invention and is used to accurately determine the position of the vehicle C to be transported. In this case, the detection unit 17 is configured to acquire point cloud data related to position information of the surface of the vehicle C. Therefore, a laser sensor such as a LiDAR is suitable for the detection unit 17. Furthermore, as described below, when considering acquiring point cloud data over a wide area of ​​the surface of the vehicle C, a laser sensor that can acquire three-dimensional point cloud data by irradiating or scanning a laser in three dimensions is particularly suitable. Note that the detection unit 17 is not only used to accurately determine the position of the vehicle C to be transported as described above, but may also be used to accurately determine, for example, spatial information around the automatic guided vehicle 11 (such as the presence or absence of approaching objects). In this case, the detection unit 17 may be provided with a device for accurately detecting spatial information around the automatic guided vehicle 11, separate from a device for detecting the position of the vehicle C.

[0035] In this embodiment, the detection unit 17 is used for the purpose of detecting the position of the vehicle C. In consideration of this, as shown in FIG. 6, the detection unit 17 is preferably disposed on both sides in the width direction of the automatic guided vehicle 11 so as to be able to acquire point cloud data of the side surfaces Cs on both the left and right sides and the front surface Cf of the vehicle C to be transported. Furthermore, as will be described later, when attempting to acquire point cloud data of the side surfaces Cs of the vehicle C over as wide an area as possible in the longitudinal direction of the vehicle body, it is preferable to dispose each detection unit 17 at a corresponding height position (lower part) of the automatic guided vehicle 11 so as to be able to detect the lower part of the body B of the vehicle C, as shown in FIG. 5, for example. Of course, the number and arrangement of the detection units 17 are arbitrary as long as point cloud data of the required area on the surface of the vehicle C can be acquired.

[0036] The control unit 12 controls the two drive wheels 13 and the power applying unit 14, thereby enabling the automatic guided vehicle 11 to travel automatically with steering. In this embodiment, the control unit 12 is composed of multiple terminal control units 24 provided in each automatic guided vehicle 11 and an overall control unit 25 that communicates with the multiple terminal control units 24. Here, the terminal control unit 24 controls the drive wheels 13 and the power applying unit 14 based on commands from the overall control unit 25, position information (position data) of the automatic guided vehicle 11 obtained by a satellite positioning system via the receiving unit 16, information on a target route that serves as a target for automatic travel, and spatial information about the surroundings of the automatic guided vehicle 11 obtained by the detecting unit 17, thereby enabling the automatic travel of the automatic guided vehicle 11 with steering. In other words, the terminal control unit 24 can timely control the steering angle and speed (including acceleration, deceleration, and stopping) of the automatic guided vehicle 11 based on the commands, position information, etc.

[0037] In the above case, it is desirable that the power applying unit 14 be a device driven by electricity, such as a motor, from the viewpoint of facilitating control by the control unit 12. Furthermore, if a mechanism that performs the operations necessary for loading the vehicle C and transporting it in the loaded state is provided in the automatic transporting device 11, it is desirable that this mechanism be a mechanism driven by electricity for the same reasons as the power applying unit 14.

[0038] 7, the position detection device 27 for the object to be detected includes a point cloud data acquisition unit (detection unit 17 in this case), a voxel generation unit 28, a data number reduction unit 29, an outline detection unit 30, and a position detection unit 31. In this embodiment, the position detection device 27 further includes a reliability evaluation unit 32. The position detection device 27 configured as described above is incorporated into the terminal control unit 24, for example.

[0039] The voxel generation unit 28 is configured to be able to generate a plurality of voxels B (see FIG. 9) forming a cubic lattice pattern based on point cloud data relating to position information, in this case, the primary point cloud data D1 (see FIG. 8) acquired by the point cloud data acquisition unit. At this time, the voxels B are generated in a unit lattice space in which the primary point cloud data D1 exists in a manner that satisfies a predetermined condition. In addition, at this time, the size of the generated voxels B can be set arbitrarily in principle, and for example, the size of the voxels B can be set to 100 so that 20 to 200 (more preferably 30 to 100) voxels B are generated across the entire width direction of the front surface Cf of the vehicle C. 1 It is set in mm order.

[0040] The data number reduction unit 29 is configured to reduce the number of primary point cloud data D1 located in each voxel B generated by the voxel generation unit 28 (see FIGS. 9 and 10). In this case, the amount of reduction in the number of data in each voxel B is arbitrary. For example, the number of primary point cloud data D1 (secondary point cloud data D2) in each voxel B after reduction may be reduced to one. In this case, the primary point cloud data D1 closest to the center of each voxel B may be left (see FIG. 10, which will be described later). Of course, the position of the secondary point cloud data D2 may be set arbitrarily. For example, although not shown, when the number of secondary point cloud data D2 is one, the secondary point cloud data D2 may be set at the center of each voxel B. Alternatively, the secondary point cloud data D2 may be set at a position that is the center of gravity (average position coordinates) of the primary point cloud data D1 located in each voxel B before reduction by the data number reduction unit 29. The voxel generation unit 28 and the data number reduction unit 29 can be integrated into a single arithmetic processing unit, and one example of such a unit is a voxel grid filter.

[0041] When the secondary point cloud data D2 obtained by the data number reduction unit 29 is input to the outline detection unit 30, the outline detection unit 30 is configured to apply a Hough transform to the input secondary point cloud data D2 to detect tentative outlines Ls1, Lf1 of the vehicle C as the object to be detected (see FIG. 11). Furthermore, when the primary point cloud data D1 located around the tentative outlines Ls1, Lf1 of the primary point cloud data D1 is input, the outline detection unit 30 is configured to apply a Hough transform to the input primary point cloud data D1 around the tentative outlines Ls1, Lf1 to detect real outlines Ls2, Lf2 of the vehicle C (see FIG. 12).

[0042] In this embodiment, the provisional outlines Ls1, Lf1 and the final outlines Ls2, Lf2 are detected based on the primary point cloud data D1 and secondary point cloud data D2 of the side Cs and front Cf of the vehicle C. Therefore, the provisional side line Ls1 and the provisional front line Lf1 are detected as the provisional outlines Ls1, Lf1 (see FIG. 11), and the final side line Ls2 and the final front line Lf2 are detected as the final outlines Ls2, Lf2 (see FIG. 12). Furthermore, in this embodiment, when detecting the final side line Ls2 and the final front line Lf2, a Hough transform is applied to the primary point cloud data D1 in voxel B (hereinafter referred to as first voxel B1) through which the provisional side line Ls1 and the provisional front line Lf1 pass, thereby making it possible to detect the final side line Ls2 and the final front line Lf2 of the vehicle C. Of course, the detection manner of the final side line Ls2 and the final front line Lf2 is not limited to the above manner. In order to shorten the calculation time, the manner in which the primary point cloud data D1 is narrowed down can be arbitrary, as long as a Hough transform is applied to a portion of the primary point cloud data D1. For example, in addition to the primary point cloud data D1 in voxel B1 through which the provisional side line Ls1 and provisional front line Lf1 pass, the primary point cloud data D1 in voxel B adjacent to voxel B1 can be subjected to a Hough transform to detect the actual side line Ls2 and actual front line Lf2 of vehicle C.

[0043] The position detection unit 31 is configured to be able to detect the position of the vehicle C based on the actual outlines Ls2 and Lf2 detected by the outline detection unit 30. In this embodiment, the position detection unit 31 is configured to be able to detect the position of the vehicle C based on the left and right actual sidelines Ls2 and the actual front line Lf2 (see FIG. 6). In principle, the position of the vehicle C to be detected here is arbitrary. For example, as shown in FIG. 6, a point (midpoint M) on the actual front line Lf2 that is equidistant from each intersection I between the actual front line Lf2 and the left and right actual sidelines Ls2 may be set, and the position of this midpoint M may be detected as the position of the vehicle C. In addition, since each intersection I is a point on the actual front line Lf2 (because the positions of multiple predetermined points on the actual front line Lf2 are known), it is also possible to detect the position of the vehicle C along with its posture. Of course, the detection manner shown in FIG. 6 is merely an example, and the detection manner of the position of the vehicle C may be arbitrary as long as it can be detected based on at least one of the actual sidelines Ls2 and the actual front line Lf2.

[0044] The reliability evaluation unit 32 is configured to be able to evaluate the reliability of the main outlines Ls2 and Lf2. In this embodiment, the reliability evaluation unit 32 is configured to evaluate the reliability of the main sideline Ls2 and the main frontline Lf2 as the main outlines Ls2 and Lf2. In this case, as shown in FIG. 13, for example, the reliability evaluation unit 32 acquires a proportion of second voxels B2 containing secondary point cloud data D2 for voxels B (hereinafter referred to as second voxels B2) through which the main sideline Ls2 and the main frontline Lf2 pass among multiple voxels B. The reliability evaluation unit 32 is then configured to evaluate the reliability of the main sideline Ls2 and the main frontline Lf2 as higher, as the proportion of acquired second voxels B2 increases. For example, if the proportion is α [%], the reliability evaluation unit 32 is configured to evaluate the reliability of the main sideline Ls2 and the main frontline Lf2 as higher, as α / 100 approaches 1.

[0045] 13, the reliability evaluation unit 32 is configured to acquire a proportion of the third voxels B3 in which the secondary point cloud data D2 exists for voxels B (hereinafter referred to as third voxels B3) adjacent to the second voxel B2 on the side farther from the vehicle C (the left and bottom side in FIG. 13) among the plurality of voxels B, and evaluates that the reliability of the main side line Ls2 and the main front line Lf2 is higher as the acquired proportion of third voxels B3 is lower. For example, when the proportion is β [%], the reliability evaluation unit 32 is configured to evaluate that the reliability of the main side line Ls2 and the main front line Lf2 is higher as 1-β / 100 is closer to 1.

[0046] In addition, the reliability evaluation unit 32 may also be configured to acquire the proportion of fourth voxels B4 in which secondary point cloud data D2 exists for voxels B (hereinafter referred to as fourth voxels B4) adjacent to the second voxel B2 on the vehicle C side (the center side in Figure 13) among the multiple voxels B, and to evaluate that the higher the proportion of acquired fourth voxels B4, the higher the reliability of the side line Ls2 and the front line Lf2.

[0047] Next, an example of the operation of the automatic transport device 11 equipped with the position detection device 27 configured as described above and the automatic transport system 10 for the vehicle C equipped with this automatic transport device 11 will be described mainly with reference to FIGS.

[0048] First, the central control unit 25 sends commands to the multiple automatic guided vehicles 11 regarding what each automatic guided vehicle 11 should do next. For example, in FIG. 1, the central control unit 25 sends a command to the automatic guided vehicle 11 (11a) located between the container yard Y and the factory F and in an empty state (without a vehicle C loaded thereon) to move toward the factory F. The central control unit 25 also sends a command to the automatic guided vehicle 11 (11b) located within the premises of the factory F to move toward a position where the vehicle C to be transported can be loaded. The central control unit 25 also sends a command to the automatic guided vehicle 11 (11c) located between the factory F and the container yard Y and loaded with a vehicle C to move toward a predetermined waiting position within the container yard Y, and sends a command to the automatic guided vehicle 11 (11d, 11e) after unloading to change its posture relative to the direction of movement as necessary and then retreat from the container yard Y. Each automatic guided vehicle 11 (11a-11e) that received the command controls the drive wheels 13 and the power applying unit 14 via the terminal control unit 24 so as to operate in accordance with the command. In this way, the vehicle C is continuously automatically transported by the plurality of automatic transport devices 11 (11a to 11e).

[0049] Next, an example of the operation of loading the vehicle C onto the automatic transport device 11 will be described in detail.

[0050] 14 is a flowchart showing the flow of work from when the automatic guided vehicle 11 approaches the vehicle C to be transported to when it loads the vehicle C, mainly illustrating the operation of the control unit 12 (here, the terminal control unit 24). According to this flowchart, the loading process of the vehicle C includes a relative position detection process S1 for detecting the position of the vehicle C relative to the automatic guided vehicle 11, a movement process S2 for moving the automatic guided vehicle 11 based on the detected position of the vehicle C, and a loading process S3 for loading the vehicle C at a predetermined position on the automatic guided vehicle 11. The relative position detection process S1 here corresponds to the position detection method according to the present invention. Below, the details of each of the processes S1 to S3 will be explained, focusing on the relative position detection process S1.

[0051] (S1) Relative position detection process 15, the relative position detection process S1 includes a point cloud data acquisition process S11, a voxel generation process S12, a data number reduction process S13, a provisional outline detection process S14, a real outline detection process S15, and a position detection process S16. In this embodiment, the relative position detection process S1 further includes a reliability evaluation process S17. The above-mentioned relative position detection process S1 is performed using a position detection device 27 incorporated in the terminal control unit 24.

[0052] (S11) Point cloud data acquisition process In this step, the point cloud data acquisition unit acquires point cloud data relating to position information on the surface of the vehicle C. In this embodiment, the point cloud data acquisition unit is configured by the detection unit 17. Therefore, as shown in, for example, FIGS. 5 and 6, the detection unit 17 emits a laser L in three dimensions to detect point cloud data relating to position coordinates on the surface of the vehicle C, including the side Cs and front Cf of the vehicle C. FIG. 8 shows an example of an image including the point cloud data (primary point cloud data D1) acquired at this time. This image shows the distribution of the primary point cloud data D1 acquired at the corner Cc of the vehicle C (see FIG. 6) and the side Cs and front Cf around the corner Cc. As such, the actual primary point cloud data D1 does not necessarily represent position coordinates on the surface of the vehicle C, but rather has a form distributed in the longitudinal direction, height direction, or width direction of the vehicle body.

[0053] (S12) Voxel generation process In this step, voxels B are generated based on the primary point cloud data D1 acquired in the point cloud data acquisition step S11. Specifically, the primary point cloud data D1 detected by the detection unit 17 is input to the voxel generation unit 28, which generates three-dimensionally distributed voxels B based on the input primary point cloud data D1. As a result, a plurality of voxels B are generated in the image including the primary point cloud data D1 according to the distribution pattern of the primary point cloud data D1 (see FIG. 9).

[0054] (S13) Data reduction process In this step, the number of pieces of primary point cloud data D1 located in each voxel B is reduced. Specifically, the number of pieces of primary point cloud data D1 in each voxel B in an image in which multiple voxels B have been generated by the data number reduction unit 29 is reduced (see FIG. 10). In this embodiment, regardless of the number of pieces of primary point cloud data D1 located in each voxel B, the number of pieces of primary point cloud data D1 located in all voxels B is reduced to one (see FIG. 10).

[0055] (S14) Temporary outline detection process In this step, the outline detection unit 30 performs a Hough transform on the data-reduced primary point cloud data D1 (secondary point cloud data D2) obtained in the data number reduction step S13, and detects provisional outlines Ls1, Lf1 of the vehicle C, which are characteristic straight lines, from the image including the secondary point cloud data D2. Here, the primary point cloud data D1, which is the source of the secondary point cloud data D2, is acquired as position coordinate data of the side Cs and front Cf of the vehicle C, so that the provisional outlines Ls1, Lf1 are detected as provisional side lines Ls1, which are straight lines along the side Cs, and provisional front line Lf1, which is a straight line along the front Cf (see FIGS. 6 and 11).

[0056] (S15) Main outline detection process In this step, the outline detection unit 30 applies a Hough transform to the primary point cloud data D1 located around the provisional side line Ls1 and provisional front line Lf1 of the primary point cloud data D1, and detects the real outlines Ls2 and Lf2 of the vehicle C, which are characteristic straight lines, from the image including the primary point cloud data D1. In this case, for example, as shown in FIG. 12, the Hough transform may be applied to the primary point cloud data D1 located within a first voxel B1 through which the provisional side line Ls1 and provisional front line Lf1 pass. Also, in the detection step S15, the primary point cloud data D1 to be subjected to the Hough transform is acquired as position coordinate data of the side surface Cs and front surface Cf of the vehicle C, so that the real outlines Ls2 and Lf2 are detected as the real side line Ls2, which is a straight line along the side surface Cs, and the real front line Lf2, which is a straight line along the front surface Cf (see FIG. 12).

[0057] In this case, in order to improve the detection accuracy of the actual sideline Ls2 and the actual frontline Lf2, the primary point cloud data D1 located in voxel B (voxel B shown by cross-hatching in FIG. 12) where the intersection of the provisional sideline Ls1 and the provisional frontline Lf1 is located may be removed, and then the primary point cloud data D1 after removal may be subjected to a Hough transform. Also, the range of the primary point cloud data D1 to be subjected to the Hough transform may be limited to a height direction region around the provisional outlines Ls1 and Lf1.

[0058] (S17) Reliability evaluation process In this step, the reliability evaluation unit 32 evaluates the reliability of the final sideline Ls2 and the final frontline Lf2 detected in the final outline detection step S15. In this embodiment, first, the voxel generation unit 28 generates multiple voxels B based on the primary point cloud data D1. At this time, the primary point cloud data D1 used to generate the voxels B may be limited to a range around the final outlines Ls2 and Lf2 (e.g., a range in the width direction and the front-rear direction of the vehicle body) compared to that used in the voxel generation step S12. Furthermore, due to the nature of the reliability evaluation step S17, if it is considered acceptable to reduce the density of the primary point cloud data D1 used compared to that used when detecting the provisional outlines Ls1 and Lf1, the size of the generated voxels B may be increased compared to that used in the voxel generation step S12. Thereafter, the data number reduction unit 29 reduces the number of primary point cloud data D1 located within each generated voxel B to obtain secondary point cloud data D2. In this case, as in the data number reduction step S13, the number of data items in the primary point cloud data D1 is reduced so that the number of secondary point cloud data items D2 in each voxel B becomes one.

[0059] After generating the multiple voxels B and the secondary point cloud data D2 as described above, the reliability evaluation unit 32 evaluates the reliability of the main sideline Ls2 and the main frontline Lf2. Specifically, as shown in FIG. 13 , for each second voxel B2 through which the main sideline Ls2 and the main frontline Lf2 pass, a proportion α [%] of the second voxels B2 containing the secondary point cloud data D2 is obtained. In this embodiment, for each second voxel B3 adjacent to the second voxel B2 on the side farther from the vehicle C that is the subject of detection, a proportion β [%] of the third voxel B3 containing the secondary point cloud data D2 is obtained. The closer α / 100 × (1 − β / 100) is to 1, the higher the reliability of the main sideline Ls2 and the main frontline Lf2 is evaluated to be.

[0060] In the reliability evaluation process S17, although not shown in the figure, the proportion of voxels in which secondary point cloud data D2 exists may be obtained for voxels B among the multiple voxels generated by the voxel generation unit 28 that are at different positions in the height direction of the side line Ls2, the front line Lf2, and the vehicle C, and based on the obtained proportion, an evaluation may be made as to whether the object from which the primary point cloud data D1 was obtained is vehicle C (the reliability of vehicle C).

[0061] (S16) Position detection process If the reliability of the main side line Ls2 and the main front line Lf2 is evaluated to be high (for example, a value equal to or greater than a predetermined threshold) in the reliability evaluation step S17, the position of the vehicle C is detected based on these main side line Ls2 and main front line Lf2. In this embodiment, the position of a point (midpoint M) on the main front line Lf2 that is equidistant from each intersection I of the main front line Lf2 and the left and right main side lines Ls2 is detected as the position of the vehicle C (see FIG. 6). Furthermore, if the positions and inclinations of the main side line Ls2 and the main front line Lf2 have been acquired, the position together with the attitude of the vehicle C (the relative position of the vehicle C with respect to the automatic guided vehicle 11) is detected from this information.

[0062] In addition, in this embodiment, the exact position of the automatic conveying device 11 is acquired by a satellite positioning system, so the position (absolute position) of vehicle C can be detected from the position (absolute position) of this automatic conveying device 11 and the position (relative position) of vehicle C acquired by the position detection unit 31.

[0063] (S2) Moving process After detecting the position of vehicle C in the above manner, the automatic transporter 11 is moved based on the detected position of vehicle C. Specifically, assuming that the detected vehicle C will be loaded onto the loading unit 15, the automatic transporter 11 is moved toward vehicle C in a predetermined orientation.

[0064] (S4) Installation feasibility determination process Then, when the automatic transporting device 11 has moved a predetermined distance, it determines whether or not the automatic transporting device 11 has moved to a position where the vehicle C can be loaded. If it determines that the automatic transporting device 11 has not yet moved to a position where the vehicle C can be loaded, it performs the relative position detection step S1 and the movement step S2 again. In this way, the relative position detection step S1 and the movement step S2 are repeatedly performed at predetermined time intervals, and if it is determined in the loading possibility determination step S4 that the automatic transporting device 11 has moved to a position where the vehicle C can be loaded, it proceeds to the step of loading the vehicle C onto the automatic transporting device 11 (loading step S3).

[0065] (S3) Vehicle installation process In this step, the automatic guided vehicle 11 and the vehicle C are brought closer to each other based on the position of the vehicle C obtained in the relative position detection step S1, thereby loading the front wheels FW of the vehicle C onto the loading unit 15 (see FIG. 16). As a result, the vehicle C is loaded at a position where it can be automatically transported by the automatic guided vehicle 11. The loading operation described above may be performed by the automatic guided vehicle 11 approaching the vehicle C in a stopped state, or by the vehicle C approaching the automatic guided vehicle 11 in a stopped state. Alternatively, the loading operation may be performed by a moving body different from either the automatic guided vehicle 11 or the vehicle C entering below the vehicle C and lifting (tilting) a part of the vehicle C using a lift-up mechanism provided on the moving body, and then the automatic guided vehicle 11 approaching the vehicle C. Alternatively, the loading operation may be performed by moving the vehicle C above a lift-up mechanism attached to a predetermined position, and then lifting a part of the vehicle C using the lift-up mechanism, and then the automatic guided vehicle 11 approaching the vehicle C. In addition, as in this embodiment, when the detection direction of the detection unit 17 is set toward the forward movement direction of the automatic conveying device 11 (see Figures 5 and 6), the automatic conveying device 11 can be brought close to the vehicle C, stopped at a position where the vehicle C can be mounted, and then the automatic conveying device 11 can be rotated around the vertical axis at the stopped position to flip the vehicle C front to back, thereby making it possible to mount the vehicle C on the mounting unit 15.

[0066] As described above, the position detection device 27 and position detection method according to this embodiment generate multiple voxels B based on the acquired primary point cloud data D1, reduce the number of primary point cloud data D1 located within each voxel B, and perform a Hough transform on the secondary point cloud data D2, which is the reduced primary point cloud data D1, to detect the provisional outlines Ls1 and Lf1 of the vehicle C as the detected object. This reduces the number of primary point cloud data D1 used in the Hough transform, enabling detection of the provisional outlines Ls1 and Lf1 to be completed in a short time. Meanwhile, the position of the vehicle C is detected by detecting the real outlines Ls2 and Lf2 by applying a Hough transform to the original primary point cloud data D1, thereby enabling highly accurate position detection. Furthermore, by limiting the primary point cloud data D1 used for position detection to the area surrounding the provisional outlines Ls1 and Lf1, only the primary point cloud data D1 that is likely to be relevant to the detection of the real outlines Ls2 and Lf2 can be used from the original primary point cloud data D1. Therefore, the position of the vehicle C can be detected efficiently in a short time while obtaining high position detection accuracy, thereby enabling the vehicle C to be loaded onto the automatic transport device 11 accurately and quickly.

[0067] Furthermore, if the object to be detected is a vehicle C as in this embodiment, the outline along the side surface Cs and front surface Cf of the vehicle C, i.e., the side lines Ls1, Ls2 and front lines Lf1, Lf2, can be accurately detected with a very high probability by the Hough transform of the outline detection unit 30. Therefore, by applying the position detection device 27 or position detection method according to this embodiment to the position detection of the vehicle C, it becomes possible to accurately detect the position of the vehicle C together with its attitude.

[0068] Furthermore, when the object to be detected is a vehicle C as described above, in this outline detection process S15, the primary point cloud data D1 located within voxel B (voxel B shown by cross-hatching in Figure 12) where the intersection of the provisional side line Ls1 and the provisional front line Lf1 is located, in other words, the primary point cloud data D1 on the surface of the corner portion Cc of the vehicle C, is removed, and then a Hough transform is applied to the primary point cloud data D1 after removal, thereby further improving the accuracy of position detection of the actual side line Ls2 and the actual front line Lf2.

[0069] Furthermore, the automated guided vehicle 11 according to this embodiment further includes a reliability evaluation step S17 for evaluating the reliability of the main sideline Ls2 and the main frontline Lf2. This increases the reliability of the main sideline Ls2 and the main frontline Lf2 detected in the main outline detection step S15. This also increases the reliability of the position of the vehicle C detected based on the main sideline Ls2 and the main frontline Lf2. Furthermore, for at least the voxels B (second voxels B2) through which the main sideline Ls2 and the main frontline Lf2 pass, a proportion α of the second voxels B2 containing secondary point cloud data D2 is obtained. By evaluating the reliability of the main sideline Ls2 and the main frontline Lf2 based on this proportion α, the reliability of the main sideline Ls2 and the main frontline Lf2 can be efficiently and quickly evaluated in this step S17.

[0070] Although one embodiment of the present invention has been described above, the position detection method and position detection device according to the present invention can also adopt configurations other than those described above without departing from the spirit of the invention.

[0071] For example, in the above embodiment, a reliability evaluation process S17 is provided after the main outline detection process S15, and the reliability of the main side line Ls2 and main front line Lf2 detected in the main outline detection process S15 is evaluated before the position of the vehicle C is detected. However, depending on the conditions, the reliability evaluation process S17 may be omitted, and the position detection process S16 may be provided immediately after the main outline detection process S15.

[0072] In the above embodiment, the control unit 12 is configured with the terminal control unit 24 and the general control unit 25, but of course this is not limiting. For example, the general control unit 25 may be omitted, and the automatic travel of the automatic transport device 11 may be controlled only by the terminal control unit 24. In this case, for example, for the automatic transport device 11, a program related to automatic transport involving loading and unloading may be stored in advance in the terminal control unit 24, and the drive wheels 13 and the power applying unit 14 may be driven and controlled based on the program by a predetermined operation by an operator.

[0073] 1 illustrates an example in which only the front wheels FW are mounted on the mounting portion 15 as some of the wheels of the vehicle C, but the present invention is not limited to this. For example, although not shown, the present invention may be applied to a case in which only the rear wheels RW of the vehicle C are mounted on the mounting portion 15. Alternatively, the present invention may be applied to a case in which both the front wheels FW and rear wheels RW of the vehicle C are mounted on the mounting portion 15.

[0074] Furthermore, in the above embodiment, the automatic guided vehicle 11 for automatically transporting a vehicle C is provided with the position detection device 27 according to the present invention, and the automatic guided vehicle 11 is moved toward the vehicle C while detecting the position of the vehicle C using the position detection device 27. However, the present invention is not limited to this. For example, the present invention may be applied when the vehicle C is moved toward the automatic guided vehicle 11 in a stopped state. Alternatively, the present invention may be applied when a moving body other than the automatic guided vehicle 11 is moved toward the vehicle C, such as when a moving body is brought toward the vehicle C in a factory to perform a predetermined task on the vehicle C, and the position detection device 27 according to the present invention is provided on the moving body. Of course, the present invention may be applied when an object other than the vehicle C is the position detection target (detectable object) as long as it has an outer shape whose outline can be detected by a Hough transform. [Explanation of symbols]

[0075] 10 Automatic transport system 11 Automatic transport device 12 Control Unit 13 Drive wheels 14 Power supply unit 15 Mounting section 16 Receiving unit 17 Detector 18 Casing 19 Connecting part 20 wheels 21 Rotation axis 22 In-wheel motor 23 Training wheels 24 Terminal control unit 25 General Control Unit 26 Standing section 27 Position detection device 28 Voxel generation unit 29 Data Reduction Section 30 Outline detection section 31 Position detection unit 32 Reliability evaluation unit B, B1, B2, B3, B4 voxels C vehicle Cc Corner Cf side Cs side D1 Primary point cloud data D2 secondary point cloud data F factory FW front wheel L Laser Lf1 Provisional Frontline Lf2 Frontline Ls1 Temporary Sideline Ls2 Sideline S1 Relative position detection process S11 Point cloud data acquisition process S12 Voxel generation process S13 Data reduction process S14 Temporary outline detection process S15 Book outline detection process S16 Position detection process S17 Reliability evaluation process S2 Moving process S3 installation process S4 Installation feasibility determination process Y Container Yard

Claims

1. A point cloud data acquisition step of acquiring primary point cloud data relating to position information of the surface of a vehicle as a detected object by a point cloud data acquisition unit; a voxel generation step of generating a plurality of voxels based on the primary point cloud data by a voxel generation unit; a data number reduction step of reducing the number of the primary point cloud data located in each of the voxels by a data number reduction unit; a tentative outline detection step of detecting a tentative outline of the object to be detected by applying a Hough transform to the secondary point cloud data obtained in the data number reduction step by an outline detection unit; a main outline detection step of detecting a main outline of the object by applying a Hough transform to the primary point cloud data located around the provisional outline among the primary point cloud data by the outline detection unit; a position detection step of detecting the position of the object to be detected based on the outline by a position detection unit, In the provisional outline detection step, a linear provisional side line is detected as the provisional outline based on the secondary point cloud data of the side of the vehicle, and a linear provisional front line that is perpendicular to the provisional side line is detected based on the secondary point cloud data of the front of the vehicle, A vehicle position detection method in which, in the main outline detection process, a linear main side line is detected as the main outline based on primary point cloud data of the side of the vehicle, and a linear main front line that is perpendicular to the main side line is detected based on primary point cloud data of the front of the vehicle.

2. The method further comprises a reliability evaluation step of evaluating the reliability of the outline by a reliability evaluation unit, The position detection method described in claim 1, wherein the reliability evaluation process obtains the proportion of voxels in which the secondary point cloud data exists for at least the voxels through which the outline passes among the plurality of voxels, and evaluates that the reliability of the outline is higher the higher the proportion.

3. a point cloud data acquisition unit capable of acquiring primary point cloud data relating to position information of the surface of a vehicle as a detected object; a voxel generation unit that generates a plurality of voxels based on the primary point cloud data; a data number reduction unit that reduces the number of the primary point cloud data located in each of the voxels; an outline detection unit that applies a Hough transform to the secondary point cloud data obtained by the data number reduction unit to detect a provisional outline of the object to be detected, and applies the Hough transform to primary point cloud data located around the provisional outline among the primary point cloud data to detect a real outline of the object to be detected; a position detection unit capable of detecting the position of the object to be detected based on the outline, The outline detection unit is a vehicle position detection device configured to detect, as the temporary outline, a linear temporary side line based on secondary point cloud data of the side of the vehicle, and a linear temporary front line that is perpendicular to the temporary side line based on secondary point cloud data of the front of the vehicle, and to detect, as the real outline, a linear actual side line based on primary point cloud data of the side of the vehicle, and a linear actual front line that is perpendicular to the real side line based on primary point cloud data of the front of the vehicle.

Images