Tray identification device

Abstract

Provided is a tray recognition device capable of improving the accuracy of estimating the position and posture of a tray regardless of the type of the tray. A tray identification device (10) is provided with: a storage unit (13) for storing positive solution point group data as data indicating a plurality of types of trays (3) acquired in advance; a camera (11) and a tray detection unit (20) for detecting the type of the tray (3); a positive solution point group selection unit (21) that selects positive solution point group data corresponding to the type of the tray (3) detected by the camera (11) and the tray detection unit (20) from the positive solution point group data of the plurality of types of trays (3) stored in the storage unit (13); a laser sensor (12) for acquiring detection point group data of the tray (3); and a matching processing unit (22) that matches the detection point group data acquired by the laser sensor (12) with the positive solution point group data selected by the positive solution point group selection unit (21), and calculates estimated values of the position and orientation of the tray (3).

Description

Technical Field

[0001] The invention relates to a pallet identification device. Background Art

[0002] As a conventional pallet recognition device, for example, the technology described in Patent Document 1 is known. The pallet recognition device described in Patent Document 1 includes: a laser sensor that detects the distance of the pallet to be loaded or unloaded; a camera that captures the pallet to be loaded or unloaded; and a controller that calculates a plane equation of the front surface of the pallet based on image data of the camera and measurement point data of the laser sensor, and estimates the position and posture of the pallet using the plane equation.

[0003] Prior art literature

[0004] Patent Literature

[0005] Patent Document 1: Japanese Patent Application Publication No. 2021-42070 Summary of the invention

[0006] Problem that the invention aims to solve

[0007] However, as pallets used for cargo loading and unloading operations, there are column pallets that can be stacked in layers when cargo is loaded, in addition to the flat pallets described in Patent Document 1. In addition, depending on the way cargo is loaded on the pallet, the location where the pallet is placed, etc., it is sometimes difficult to detect the front surface of the pallet, making it difficult to estimate the position and posture of the pallet.

[0008] An object of the present invention is to provide a pallet recognition device capable of improving the accuracy of estimating the position and posture of a pallet regardless of the type of the pallet.

[0009] Solutions for solving problems

[0010] (1) One embodiment of the present invention is a pallet recognition device for recognizing the position and posture of a pallet, comprising: a storage unit that stores correct answer data representing data of a plurality of pallets acquired in advance; a detection unit that detects the type of the pallet; a selection unit that selects correct answer data corresponding to the type of the pallet detected by the detection unit from the correct answer data of the plurality of pallets stored in the storage unit; a data acquisition unit that acquires detection data of the pallet; and a matching processing unit that matches the detection data acquired by the data acquisition unit with the correct answer data selected by the selection unit to calculate an estimated value of the position and posture of the pallet.

[0011] In such a pallet identification device, correct answer data of multiple types of pallets are acquired in advance and stored in a storage unit. When identifying a pallet, the type of pallet is first detected by the detection unit. Then, correct answer data corresponding to the type of the detected pallet is selected from the correct answer data of the multiple types of pallets stored in the storage unit. Then, the detection data of the pallet acquired by the data acquisition unit is matched with the selected correct answer data to calculate the estimated value of the position and posture of the pallet. By matching the detection data of the pallet with the correct answer data corresponding to the type of the pallet in this way, the resistance to external interference is enhanced. Therefore, even if the type of pallet used changes, it is not easy to make an erroneous estimation of the position and posture of the pallet. As a result, regardless of the type of the pallet, the estimation accuracy of the position and posture of the pallet is improved.

[0012] (2) In the above (1), the pallet recognition device may further include: an evaluation unit that evaluates the estimated values ​​of the position and posture of the pallet calculated by the matching processing unit; and a position and posture determination unit that determines the position and posture of the pallet based on the evaluation result of the evaluation unit.

[0013] In such a configuration, estimated values ​​of the position and posture of the pallet obtained by matching the detection data acquired by the data acquisition unit with the selected correct answer data are evaluated, and the position and posture of the pallet are determined based on the evaluation results, thereby further improving the estimation accuracy of the position and posture of the pallet.

[0014] (3) Alternatively, in the above (2), the matching processing unit matches the detection data with the correct answer data to calculate the estimated value of the position and posture of the pallet, and calculates the consistency of the matching between the detection data and the correct answer data, and the evaluation unit evaluates the estimated value of the position and posture of the pallet by determining whether the consistency of the matching between the detection data and the correct answer data is above a predetermined threshold.

[0015] In such a configuration, the degree of consistency between the detection data acquired by the data acquisition unit and the selected correct answer data is calculated, and it is determined whether the degree of consistency between the detection data and the correct answer data is above a threshold, thereby enabling the estimated values ​​of the position and posture of the tray to be evaluated simply and accurately.

[0016] (4) Alternatively, in the above (3), when the evaluation unit determines that the degree of consistency between the detection data and the correct answer data is greater than a threshold, the position and posture determination unit determines the estimated value of the position and posture of the pallet calculated by the matching processing unit as the position and posture of the pallet, and when the evaluation unit determines that the degree of consistency between the detection data and the correct answer data is lower than the threshold, the position and posture determination unit estimates the position and posture of the pallet based on the detection data acquired by the data acquisition unit.

[0017] In such a configuration, when the degree of consistency between the detection data acquired by the data acquisition unit and the selected correct answer data is above a threshold, the estimated value of the position and posture of the pallet obtained by matching the detection data with the correct answer data is determined as the position and posture of the pallet, thereby more reliably improving the estimation accuracy of the position and posture of the pallet.

[0018] (5) Alternatively, in the above (4), when it is determined that the degree of consistency between the detection data and the correct answer data is lower than a threshold value, the position and posture determination unit extracts the detection data that is consistent with the correct answer data from the detection data acquired by the data acquisition unit, and estimates the position and posture of the tray based on the detection data that is consistent with the correct answer data.

[0019] In such a configuration, when the degree of consistency between the detection data acquired by the data acquisition unit and the selected correct answer data is lower than a threshold value, the detection data consistent with the correct answer data is extracted from the detection data, and the position and posture of the pallet are estimated based on the detection data consistent with the correct answer data, thereby being able to confirm whether the matching of the detection data and the correct answer data has actually failed.

[0020] (6) Alternatively, in any one of the above (1) to (5), the detection unit has a camera for photographing the pallet, and detects the type of the pallet based on image data from the camera, the data acquisition unit detects the distance of the pallet and acquires detection point group data by irradiating a laser toward the pallet and receiving reflected light of the laser, and the storage unit stores correct point group data for the plurality of pallets.

[0021] In such a configuration, by using a camera that captures an image of the pallet, the type of the pallet can be detected easily and inexpensively. In addition, by irradiating the pallet with laser light to acquire detection point group data, the detection data can be easily matched with the correct answer data.

[0022] (7) In any one of (1) to (6) above, one of the plurality of types of correct answer data for the pallets may be correct answer data for a state in which a portion of the pallet is hidden by another member.

[0023] In such a configuration, for example, when a pallet is placed on a conveyor provided with a guard for preventing the pallet from falling, even if a portion of the pallet is obscured by the guard, the accuracy of estimated position and posture of the pallet is improved by pre-storing correct answer data of a state in which a portion of the pallet is obscured by the guard in a storage unit.

[0024] Effects of the Invention

[0025] According to the present invention, it is possible to improve the estimation accuracy of the position and posture of the tray regardless of the type of the tray. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a schematic diagram showing the configuration of a travel control device including a pallet recognition device according to an embodiment of the present invention.

[0027] Figure 2 This is a schematic plan view showing a situation in which a forklift picks up goods from a pallet.

[0028] Figure 3 It is a front view showing a flat pallet and a column pallet as the pallet.

[0029] Figure 4 It is shown by Figure 1 Flowchart of the processing steps of tray recognition and travel control executed by the controller shown.

[0030] Figure 5 This is a diagram showing a state in which the detected point group data acquired by the laser sensor is matched with the selected correct answer point group data.

[0031] Figure 6 This is a diagram showing a state where a flat pallet is placed on a conveyor provided with a guard for preventing the pallet from falling.

[0032] Figure 7 This is a diagram showing a situation in which, when cargo placed on a pallet portion of a post pallet protrudes from the front surface of the post pallet, both side edges of the cargo are erroneously detected as the post portions of the post pallet.

[0033] Description of Reference Numerals

[0034] 3…pallet, 10…pallet identification device, 11…camera (detection unit), 12…laser sensor (data acquisition unit), 13…storage unit, 20…pallet detection unit (detection unit), 21…correct solution point group selection unit (selection unit), 22…matching processing unit, 23…matching evaluation unit (evaluation unit), 24…position posture determination unit, 51…protective part (other components), Dp…detection point group data, Dp0…correct solution point group data. DETAILED DESCRIPTION

[0035] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0036] Figure 1 FIG. 2 is a schematic diagram showing a travel control device including a pallet recognition device according to an embodiment of the present invention. Figure 2 As shown, the travel control device 1 is a device that automatically drives the forklift 2 to the pickup position when the forklift 2 picks up the pallet 3. The forklift 2 has a pair of left and right forks 4 for holding the pallet 3. The pickup position is a position where the forks 4 of the forklift 2 are inserted into the fork holes (described later) of the pallet 3.

[0037] The pallet 3 is loaded on a platform (not shown) of a truck, for example. Figure 3 As shown, a flat pallet 3A and a column pallet 3B are used.

[0038] Figure 3 The flat pallet 3A shown in (a) is made of plastic or wood. The flat pallet 3A is square in plan view. The cargo M is placed on the flat pallet 3A. The flat pallet 3A is provided with two fork holes 5 for inserting the forks 4 of the forklift 2. The fork holes 5 extend from the front surface 3a of the flat pallet 3A to the rear side. The shape of the fork holes 5 is rectangular in the front view (front view).

[0039] Figure 3 The post pallet 3B shown in (b) has a pallet portion 6 that is square in shape when viewed from above and four post portions 7 that are erected at the four corners of the pallet portion 6. The cargo M is placed on the pallet portion 6. The pallet portion 6 is provided with two fork holes 8 into which the forks 4 of the forklift 2 are inserted. The fork holes 8 extend from the front surface 3a of the post pallet 3B to the rear side. The shape of the fork hole 8 is rectangular in the front view (front view). The post portion 7 is in the shape of a quadrangular prism. The post portion 7 is foldably connected to the corners of the pallet portion 6.

[0040] exist Figure 1 In the embodiment, the travel control device 1 is mounted on the forklift 2. The travel control device 1 includes a camera 11, a laser sensor 12, a storage unit 13, a drive unit 14, and a controller 15.

[0041] The camera 11 captures the front surface 3a of the tray 3 to be picked up and acquires image data. As the camera 11, for example, a single-lens reflex camera or the like is used.

[0042] The laser sensor 12 detects the distance of the pallet 3 and obtains point group data by irradiating the front surface 3a of the pallet 3 of the pickup object with a laser and receiving the reflected light of the laser. The point group is a collection of reflection points of the laser on the object including the pallet 3. The laser sensor 12 constitutes a data acquisition unit for acquiring the detection point group data (detection data) of the pallet 3. The laser sensor 12 irradiates a 2D or 3D laser with a high point density. As the laser sensor 12, for example, LIDAR, a laser rangefinder, etc. are used.

[0043] The storage unit 13 stores correct point group data (correct data) of the front surface 3a of various types of pallets 3. The correct point group data is obtained in advance using the laser sensor 12. The correct point group data is data representing various types of pallets 3 obtained in advance. Here, the different types of pallets 3 include not only the case where the types of the pallets 3 themselves are different, but also the case where the appearance of the pallet 3 is different due to changes in the loading method of the cargo M relative to the pallet 3, the placement location of the pallet 3, etc., although the type of the pallet 3 itself is the same, the pallet 3 has a different appearance state, such as a part of the pallet 3 is blocked by other components.

[0044] Specifically, the correct point group data of the front surface 3a of the various types of trays 3 include the flat tray 3A (refer to Figure 3 (a)) of the front surface 3a of the correct solution point group data and the column tray 3B (refer to Figure 3 In addition, the correct point group data of the front surface 3a of the various trays 3 also include the state where a portion of the front surface 3a of the flat tray 3A is blocked by other components (see Figure 6 The correct point group data of (b)).

[0045] Although not particularly shown, the drive unit 14 includes, for example, a travel motor that rotates the drive wheels of the forklift 2 and a steering motor that steers the steering wheels of the forklift 2 .

[0046] The controller 15 is composed of a CPU, RAM, ROM, and an input / output interface, etc. The controller 15 includes a tray detection unit 20 , a correct point group selection unit 21 (selection unit), a matching processing unit 22 , a matching evaluation unit 23 (evaluation unit), a position and posture determination unit 24 , and a travel control unit 25 .

[0047] Here, the pallet detection unit 20, the correct point group selection unit 21, the matching processing unit 22, the matching evaluation unit 23, and the position and posture determination unit 24 cooperate with the camera 11, the laser sensor 12, and the storage unit 13 to form the pallet recognition device 10 of this embodiment. The pallet recognition device 10 is a device for recognizing the position and posture of the pallet 3.

[0048] The tray detection unit 20 detects the type of the tray 3 based on the image data of the camera 11. The tray detection unit 20 and the camera 11 cooperate to form a detection unit that detects the type of the tray 3.

[0049] The correct answer point group selection unit 21 selects correct answer point group data corresponding to the type of the tray 3 detected by the tray detection unit 20 from the correct answer point group data of the plurality of types of trays 3 stored in the storage unit 13 .

[0050] The matching processing unit 22 matches the detection point group data of the tray 3 obtained by the laser sensor 12 with the correct point group data selected by the correct point group selection unit 21 (see Figure 5 ), to calculate the estimated values ​​of the position and posture of the tray 3, and calculate the consistency of the matching between the detected point group data and the correct point group data. The function of the matching processing unit 22 will be described in detail later.

[0051] The matching evaluation unit 23 evaluates the estimated values ​​of the position and posture of the tray 3 calculated by the matching processing unit 22. The matching evaluation unit 23 evaluates the estimated values ​​of the position and posture of the tray 3 by determining whether the degree of consistency between the detected point group data of the tray 3 and the correct point group data is greater than a predetermined threshold.

[0052] The position and posture determination unit 24 determines the position and posture of the tray 3 based on the evaluation result of the matching evaluation unit 23 .

[0053] When the matching evaluation unit 23 determines that the degree of consistency between the detected point group data and the correct point group data is greater than a threshold, the position and posture determination unit 24 determines the estimated value of the position and posture of the tray 3 calculated by the matching processing unit 22 as the position and posture of the tray 3. When the matching evaluation unit 23 determines that the degree of consistency between the detected point group data and the correct point group data is lower than a threshold, the position and posture determination unit 24 estimates the position and posture of the tray 3 based on the detected point group data of the tray 3 obtained by the laser sensor 12.

[0054] When it is determined that the degree of consistency between the detection point group data and the correct answer point group data is lower than the threshold, the position and posture determination unit 24 extracts the detection point group data of the pallet 3 obtained by the laser sensor 12 that is consistent with the correct answer point group data, and estimates the position and posture of the pallet 3 based on the detection point group data that is consistent with the correct answer point group data.

[0055] The travel control unit 25 controls the drive unit 14 to cause the forklift 2 to travel to the pickup position based on the position and posture of the pallet 3 determined by the position and posture determination unit 24 .

[0056] Figure 4 1 is a flowchart showing the processing steps of the tray recognition and travel control performed by the controller 15. Figure 2 As shown, this process is executed when the forklift 2 reaches the front surface 3a side of the pallet 3 to be picked up and is instructed to start picking up. Figure 2 The angle θ in FIG. 1 shows the detection range of the tray 3 .

[0057] exist Figure 4 In the embodiment, the controller 15 first detects the type, quantity and approximate position of the pallet 3 to be picked up based on the image data of the camera 11 (step S101). At this time, the controller 15 detects the type of the pallet 3, etc., by machine learning such as deep learning.

[0058] Next, the controller 15 selects correct point group data corresponding to the type of the pallet 3 detected in step S101 from the correct point group data of various types of pallets 3 stored in the storage unit 13 (step S102). Figure 3When the type of pallet 3 detected is a columnar pallet 3B (refer to Figure 3 In (b)), the correct point group data for column tray 3B is selected.

[0059] Then, if Figure 5 As shown in (a) of FIG. 1 , the controller 15 matches the detection point group data of the tray 3 obtained by the laser sensor 12 with the correct point group data selected in step S102 (step S103). Figure 5 In (a), the detected point group data Dp obtained when the laser is irradiated toward the column pallet 3B is matched with the correct point group data Dp0 for the column pallet 3B. As a matching method, for example, ICP (Iterative closest point) matching is used.

[0060] Then, the controller 15 calculates the estimated value of the position and posture of the pallet 3 of the pickup object according to the matching result of the detected point group data and the correct solution point group data (step S104). Figure 5 As shown in (b), the detected point group data Dp is parallel moved relative to the correct point group data Dp0, or as shown in Figure 5 The position and posture of the tray 3 are estimated by rotating the detected point group data Dp relative to the correct point group data Dp0 as shown in (c). Figure 5 (b) and Figure 5 In (c), for convenience, the deviation amount between the detected point group data Dp and the correct answer point group data Dp0 is shown larger than the actual amount.

[0061] The controller 15 calculates the matching degree between the detected point group data and the correct point group data based on the matching results (step S105). The matching degree is calculated as an evaluation of the estimated values ​​of the position and posture of the tray 3 calculated in step S104.

[0062] Next, the controller 15 determines whether the matching degree between the detected point cloud data and the correct answer point cloud data is equal to or greater than a predetermined threshold value (step S106). The matching degree is expressed as a percentage (%), for example.

[0063] When the controller 15 determines that the degree of matching between the detected point group data and the correct answer point group data is greater than the threshold, the controller 15 determines the estimated values ​​of the position and posture of the pallet 3 calculated in step S104 as the position and posture of the pallet 3 to be picked up (step S107).

[0064] When the controller 15 determines that the degree of consistency between the detected point group data and the correct point group data is lower than the threshold, the controller 15 intercepts the detected point group data that is consistent (matched) with the correct point group data selected in step S102 from the detected point group data obtained by the laser sensor 12 (step S108). Then, the controller 15 estimates the position and posture of the pallet 3 to be picked up based on the detected point group data intercepted in step S108 (step S109).

[0065] Specifically, if Figure 3 As shown in (a), when the pallet 3 is a flat pallet 3A, the controller 15 extracts, for example, two fork holes 5 of the flat pallet 3A based on the detection point group data, and estimates the position and posture of the flat pallet 3A from the positional relationship between the two fork holes 5.

[0066] like Figure 3 As shown in (b), when the pallet 3 is a column pallet 3B, the controller 15 extracts, based on the detection point group data, for example, a horizontal line corresponding to the pallet portion 6 and a vertical line corresponding to the column portion 7, and calculates the position and posture of the column pallet 3B from the positional relationship between the horizontal line and the vertical line.

[0067] In addition, the controller 15 uses the fact that when the matching of the detected point group data and the correct point group data fails, the deviation of the detected point group data that matches the correct point group data becomes larger, and determines that the estimation of the position and posture of the tray 3 has failed based on the deviation of the detected point group data that matches the correct point group data.

[0068] After executing step S107 or step S109, the controller 15 generates a driving path from the forklift 2 to the pickup position based on the position and posture of the pallet 3 of the pickup object (step S110). Then, the controller 15 controls the driving unit 14 to make the forklift 2 drive to the pickup position according to the driving path (step S111).

[0069] Here, the tray detection unit 20 executes step S101. The correct point group selection unit 21 executes step S102. The matching processing unit 22 executes steps S103 to S105. The matching evaluation unit 23 executes step S106. The position and posture determination unit 24 executes steps S107 to S109. The travel control unit 25 executes steps S110 and S111.

[0070] However, if Figure 6 As shown in (a) of FIG. 5 , in order to prevent the flat pallet 3A placed on the inclined conveyor 50 from falling off the conveyor 50, a protection member 51 for preventing falling is sometimes provided on both sides of the top end of the conveyor 50. In this case, as shown in FIG. Figure 6As shown in (b), a portion of the front surface 3a of the flat tray 3A is blocked by the protective member 51. Therefore, when the laser sensor 12 obtains the detection point group data, the front surface 3a of the flat tray 3A is not accurately detected, and the estimation accuracy of the position and posture of the flat tray 3A decreases. Figure 6 In (b), the conveyor 50 is omitted for convenience.

[0071] In addition, if Figure 7 As shown in (a) of FIG. 1 , when a large cargo M placed on the pallet portion 6 of the column pallet 3B protrudes from the front surface 3a of the column pallet 3B (see A in the figure), the cargo M is closer to the laser sensor 12 than the column pallet 3B. Figure 7 As shown in (b), when the laser sensor 12 acquires the detection point group data Dp, the side edges E of the cargo M may be mistakenly detected as the pillars 7 of the pillar pallet 3B. In this case, the estimation accuracy of the position and posture of the pillar pallet 3B decreases.

[0072] In order to solve such a problem, in the present embodiment, correct point group data of various types of pallets 3 are obtained in advance and stored in the storage unit 13. When the pallet 3 is identified, the type of the pallet 3 is first detected using the camera 11. Then, the correct point group data corresponding to the detected type of the pallet 3 is selected from the correct point group data of various types of pallets 3 stored in the storage unit 13.

[0073] For example, when the pallet 3 is a flat pallet 3A and the flat pallet 3A is placed on a platform of a normal truck (see Figure 3 (a)), select the correct point group data of the front surface 3a of the flat pallet 3A. When the pallet 3 is a flat pallet 3A and the flat pallet 3A is placed on the conveyor 50 provided with a protective member 51 for preventing the flat pallet 3A from falling (refer to Figure 6 ), select the correct point group data of the front surface 3a of the flat tray 3A including the two guards 51. In the case where the tray 3 is a column tray 3B (refer to Figure 3 (b) Figure 7 (a)), select the correct point group data of the front surface 3a of the column tray 3B.

[0074] Then, the detection point group data of the pallet 3 obtained by the laser sensor 12 is matched with the selected correct point group data to calculate the estimated value of the position and posture of the pallet 3. By matching the detection point group data of the pallet 3 with the correct point group data that matches the type of the pallet 3, the resistance to external interference becomes stronger. Therefore, even if the type of the pallet 3 used changes, it is not easy to make an erroneous estimation of the position and posture of the pallet 3. As a result, the estimation accuracy of the position and posture of the pallet 3 is improved regardless of the type of the pallet 3. As a result, the forklift 2 can be moved to the pickup position with high accuracy.

[0075] In addition, in the present embodiment, the estimated values ​​of the position and posture of the pallet 3 obtained by matching the detection point group data obtained by the laser sensor 12 with the selected correct point group data are evaluated, and the position and posture of the pallet 3 are determined based on the evaluation results, thereby further improving the estimation accuracy of the position and posture of the pallet 3.

[0076] In addition, in the present embodiment, the degree of consistency between the detection point group data obtained by the laser sensor 12 and the selected correct point group data is calculated, and it is determined whether the degree of consistency between the detection point group data and the correct point group data is above a threshold, thereby enabling the estimated values ​​of the position and posture of the tray 3 to be evaluated simply and accurately.

[0077] In addition, in the present embodiment, when the degree of consistency between the detection point group data obtained by the laser sensor 12 and the selected correct point group data is above a threshold, the estimated value of the position and posture of the pallet 3 obtained by matching the detection point group data with the correct point group data is determined as the position and posture of the pallet 3, thereby more reliably improving the estimated accuracy of the position and posture of the pallet 3.

[0078] In addition, in the present embodiment, when the degree of consistency between the detection point group data obtained by the laser sensor 12 and the selected correct point group data is lower than a threshold value, the detection point group data consistent with the correct point group data is extracted from the detection point group data, and the position and posture of the pallet 3 are estimated based on the detection point group data consistent with the correct point group data, thereby being able to confirm whether the matching of the detection point group data with the correct point group data has actually failed.

[0079] In this embodiment, the type of the tray 3 can be easily and inexpensively detected by using the camera 11 that images the tray 3. In addition, by irradiating the tray 3 with laser light to acquire the detection point group data, the detection point group data can be easily matched with the correct answer point group data.

[0080] In addition, in the present embodiment, when a pallet 3 is placed on a conveyor 50 provided with a protective member 51 for preventing the pallet 3 from falling, even if a portion of the pallet 3 is blocked by the protective member 51, the accuracy of estimated position and posture of the pallet 3 is improved by pre-storing correct point group data of a state in which a portion of the pallet 3 is blocked by the protective member 51 in the storage unit 13.

[0081] In addition, the present invention is not limited to the above-mentioned embodiment. For example, in the above-mentioned embodiment, when the degree of consistency between the detection point group data obtained by the laser sensor 12 and the selected correct point group data is lower than the threshold value, the position and posture of the tray 3 are estimated based on the detection point group data consistent with the correct point group data among the detection point group data obtained by the laser sensor 12, but it is not particularly limited to this method. For example, the position and posture of the tray 3 may also be estimated directly using the detection point group data obtained by the laser sensor 12.

[0082] In addition, in the above-mentioned embodiment, the estimated value of the position and posture of the tray 3 is evaluated by judging whether the consistency of the matching between the detection point group data obtained by the laser sensor 12 and the selected correct point group data is above a predetermined threshold value, but it is not particularly limited to this method. For example, the estimated value of the position and posture of the tray 3 can also be evaluated using the deviation (variance) of the matching between the detection point group data and the correct point group data.

[0083] In addition, in the above embodiment, the position and posture of the pallet 3 are identified when the forklift 2 picks up the pallet 3, but the present invention can also be applied to the situation where the position and posture of the pallet 3 are identified in an operating environment other than cargo loading and unloading by the forklift 2.

Claims

1. A pallet recognition device is a pallet recognition device for recognizing the position and posture of a pallet, characterized in that: have: a storage unit storing correct answer data as data representing a plurality of types of pallets acquired in advance; a detection unit configured to detect the type of the tray; a selection unit that selects correct answer data corresponding to the type of the pallet detected by the detection unit from the correct answer data of the plurality of types of pallets stored in the storage unit; a data acquisition unit for acquiring detection data of the tray; as well as A matching processing unit matches the detection data acquired by the data acquisition unit with the correct answer data selected by the selection unit to calculate estimated values ​​of the position and posture of the tray.

2. The pallet identification device according to claim 1, wherein: The apparatus further comprises: an evaluation unit that evaluates the estimated values ​​of the position and posture of the tray calculated by the matching processing unit; and A position and posture determination unit determines the position and posture of the tray based on the evaluation result of the evaluation unit.

3. The pallet identification device according to claim 2, wherein: The matching processing unit matches the detection data with the correct answer data to calculate estimated values ​​of the position and posture of the tray, and calculates a degree of consistency between the matching of the detection data and the correct answer data. The evaluation unit evaluates the estimated value of the position and posture of the tray by determining whether a degree of consistency between the detection data and the correct answer data is equal to or greater than a predetermined threshold value.

4. The pallet identification device according to claim 3, wherein: When the evaluation unit determines that the degree of consistency between the detection data and the correct answer data is greater than the threshold, the position and posture determination unit determines the estimated value of the position and posture of the pallet calculated by the matching processing unit as the position and posture of the pallet; when the evaluation unit determines that the degree of consistency between the detection data and the correct answer data is lower than the threshold, the position and posture determination unit estimates the position and posture of the pallet based on the detection data acquired by the data acquisition unit.

5. The pallet identification device according to claim 4, wherein: When it is determined that the degree of consistency between the detection data and the correct answer data is lower than the threshold, the position and posture determination unit extracts the detection data that is consistent with the correct answer data from the detection data acquired by the data acquisition unit, and estimates the position and posture of the tray based on the detection data that is consistent with the correct answer data.

6. The pallet identification device according to any one of claims 1 to 5, wherein: The detection unit includes a camera for photographing the pallet, and detects the type of the pallet based on image data from the camera. The data acquisition unit detects the distance of the pallet by irradiating the pallet with laser light and receiving reflected light of the laser light to acquire the detection point group data. The storage unit stores correct solution point group data of the plurality of types of pallets.

7. The pallet identification device according to any one of claims 1 to 6, wherein: One of the correct answer data of the plurality of types of pallets is correct answer data of a state in which a part of the pallet is hidden by another member.

Images