JP2024059197A - Loading operation support device, conveyance device, loading operation support method, and loading operation support program - Google Patents

Abstract

To preferably support loading operation with respect to a loading platform with legs.SOLUTION: A forklift 1 includes an imaging unit 24 acquiring an image of a loading platform 30 having at least two legs 32 (a box pallet 30A or a post pallet 30B) and a control unit 27. The control unit 27 acquires a relative posture of the loading platform 30 relative to the imaging unit 24 based on an image of the loading platform 30 and determines whether or not the loading platform 30 faces the imaging unit 24 based on the relative posture of the loading platform 30. The control unit 27 extracts two leg regions G individually including the two legs 32 from the image of the loading platform 30 and obtains the relative posture of the loading platform 30 based on the two leg regions G.SELECTED DRAWING: Figure 3

Description

The present invention relates to a cargo handling assistance device, a transport device, a cargo handling assistance method, and a cargo handling assistance program.

Traditionally, when loading and unloading with a forklift, the driver (operator) would visually check the holes (fork pockets) in the pallet and determine whether or not the forks could be inserted into these holes. As a result, especially when the pallet was placed in a position that was difficult to see from the forklift, the driver had to insert the forks based on prediction.

Therefore, for example, the technology described in Patent Document 1 uses a machine-learned learning model that uses images of pallets as training data to determine whether or not a fork can be inserted into a hole.

Patent No. 6676198

However, the technology described in Patent Document 1 is intended for general flat pallets that have holes (fork pockets), and is not optimized for loading platforms that have legs between which forks can be inserted, such as box pallets and post pallets.
The present invention has been made in consideration of the above circumstances, and has an object to provide an optimal support for loading operations onto a loading platform having legs.

The load collection assistance device according to the present invention is
an imaging means for acquiring an image of a platform having at least two legs;
a calculation means for extracting two leg regions each including the two legs from the image of the loading platform and determining a relative orientation of the loading platform with respect to the imaging means based on the two leg regions;
a determination means for determining whether the loading platform and the imaging means are directly facing each other based on the relative position of the loading platform;
Equipped with.

The present invention can effectively assist with loading operations on loading platforms with legs.

1 is a perspective view showing an appearance of a forklift according to an embodiment; 1 is a block diagram showing a schematic control configuration of a forklift according to an embodiment of the present invention; 10 is a flowchart illustrating a procedure for a cargo collection assistance process according to the embodiment. 11A and 11B are diagrams for explaining the contents of image processing in the cargo collection support process. 11A and 11B are diagrams for explaining the contents of image processing in the cargo collection support process. 11A and 11B are diagrams for explaining the contents of image processing in the cargo collection support process. 11A and 11B are diagrams for explaining the contents of image processing in the cargo collection support process. 11A and 11B are diagrams for explaining the contents of image processing in the cargo collection support process.

The following describes an embodiment of the present invention in detail with reference to the drawings.

[Forklift configuration]
FIG. 1 is a perspective view showing the appearance of a forklift 1 according to this embodiment.
The forklift 1 according to this embodiment is an example of a transport device according to the present invention, and includes a vehicle body 11, forks 12, a lifting body (lift) 13, a mast 14, and wheels 15. The mast 14 is provided at the front of the vehicle body 11, and is driven by a driving source (not shown) to tilt the vehicle body 11 forward and backward. The lifting body 13 is driven by a driving source (not shown) to rise and fall along the mast 14. A pair of left and right forks 12 are attached to the lifting body 13 as holding parts for holding luggage, a loading platform 30, etc.

The loading platform 30 is a platform on which cargo to be handled (picked up) by the forklift 1 is placed and stored. The loading platform 30 has a rectangular bottom plate (base plate) 31 and legs 32 arranged at the four corners of the lower surface thereof. A pair of forks 12 are inserted between two adjacent legs 32 in the space below the bottom plate 31, so that the loading platform 30 is held by the forklift 1. Specifically, the loading platform 30 of this embodiment is a box pallet 30A or a post pallet 30B (see Figs. 4(a) and 4(b)). The box pallet 30A has a rectangular box-shaped wire mesh box 33A fixed on the bottom plate 31. The post pallet 30B has supports 34B integrally formed with the legs 32 at the four corners of the bottom plate 31. Both the box pallet 30A and the post pallet 30B can be stacked in multiple layers by placing the legs 32 on the upper ends of the boxes 33A or supports 34B.
The loading platform according to the present invention includes box pallets and post pallets that have at least two legs, but does not include flat pallets that do not have legs. In other words, the loading platform according to the present invention includes pallets in which forks are inserted between adjacent legs, but does not include pallets that have so-called fork pockets. The legs may be casters.
In addition, in the following description, the configurations of the loading platform 30 may be identified by adding an "A" to the end of the symbol for the box pallet 30A and a "B" to the end of the symbol for the post pallet 30B.

FIG. 2 is a block diagram showing a schematic control configuration of the forklift 1.
As shown in this figure, in addition to the above-mentioned components, the forklift 1 is equipped with a drive unit 21, an operation unit 22, a display unit 23, an image capturing unit 24, a storage unit 26, and a control unit 27. The load-receiving support device according to the present invention is configured to include at least the image capturing unit 24 and the control unit 27.

The drive unit 21 includes a travel motor, a steering motor, and a loading motor (all not shown) which are various drive sources of the forklift 1. The travel motor drives the drive wheels of the wheels 15. The steering motor rotates (performs a steering operation) the steering wheels of the wheels 15. The loading motor is a drive source which performs the operations of raising and lowering the lifting body 13 and tilting the mast 14.
The operation unit 22 is an operation means through which an operator (driver) performs various operations. The operation unit 22 includes, for example, a steering wheel, pedals, levers, various buttons, etc., and outputs operation signals according to the contents of these operations to the control unit 27.

The display unit 23 is, for example, a liquid crystal display, an organic electroluminescence display, or other display, and displays various information based on a display signal input from the control unit 27. The display unit 23 may be a touch panel that also serves as part of the operation unit 22, or may include a speaker capable of audio display (output).
The photographing unit 24 is a camera having a predetermined resolution, and is attached, for example, facing forward on the lifting body 13 or the mast 14. The photographing unit 24 photographs the area in front of the forklift 1 and acquires the image (for example, an RGB image).

The storage unit 26 is a memory configured to include, for example, a RAM (Random Access Memory) and a ROM (Read Only Memory), and stores various programs and data, and also functions as a work area for the control unit 27 .
In the memory unit 26 of this embodiment, a learning model 261 and a loading platform information database (DB) 262 are stored in advance.
The learning model 261 extracts a leg region G (see FIG. 4 ) including the leg 32 from the captured image of the loading platform 30, and is constructed in advance by machine learning and stored in the storage unit 26. The learning model 261 may be an AI (Artificial Intelligence) having a deep learning neural network.
The loading platform information database 262 stores information such as the shape of the loading platform 30 organized by type of loading platform 30 .
Furthermore, the storage unit 26 of this embodiment prestores a cargo collection assistance program 263 for executing a cargo collection assistance process (see FIG. 3) described below.

The control unit 27 is configured with, for example, a CPU (Central Processing Unit) and controls the operation of each part of the forklift 1. Specifically, the control unit 27 operates the drive unit 21 based on the operation content of the operation unit 22, deploys a program pre-stored in the memory unit 26, and executes various processes in cooperation with the deployed program.

[Pickup Assistance Processing]
Next, a load-receiving support process that supports the load-receiving operation when the forklift 1 inserts the forks 12 into the loading platform 30 will be described.
In this loading operation, the posture of the loading platform 30 is determined based on an image of the loading platform 30, and based on the result, the insertion of the forks 12 under the loading platform 30 is suitably assisted.
Fig. 3 is a flow chart showing the procedure for the goods collection assistance process, and Fig. 4 to Fig. 8 are diagrams for explaining the contents of image processing in the goods collection assistance process. In Fig. 4 to Fig. 8, (a) shows an example of a box pallet 30A, and (b) shows an example of a post pallet 30B.

The cargo handling assistance process is a process that predicts the relative posture of the loading platform 30 from an image of the loading platform 30 and determines whether the loading platform 30 is facing the loading platform 30. This cargo handling assistance process is executed by the control unit 27 reading and deploying the cargo handling assistance program 263 from the memory unit 26 based on the operation of the operator. Here, it is assumed that the forklift 1 has traveled to the front of the loading platform 30.

As shown in FIG. 3, when the cargo handling assistance process is executed, the control unit 27 first acquires an image of the cargo handling platform 30 by the photographing unit 24 (step S1).
In this step, the control unit 27 operates the photographing unit 24 based on the operation of the operator to obtain an image including the loading platform 30 in front, and stores the image in the storage unit 26. As a result, a captured image M of the loading platform 30, for example, as shown in Figures 4(a) and 4(b), is obtained. The captured image M may be displayed in real time on the display unit 23.
The timing of photographing does not have to be based on the operation of the operator. For example, the image of the area in front of the forklift 1 may be photographed periodically at a predetermined photographing timing, and the loading platform 30 may be detected from the image.

Next, the control unit 27 inputs the captured image M of the loading platform 30 acquired in step S1 into the learning model 261, and extracts the two leg regions G on the front side (closer to the front) of the captured image M (step S2).
4A and 4B, the leg region G is a region including each leg 32, and is a rectangular local region having four sides along the top, bottom, left, and right of the captured image M. In this step, the control unit 27 extracts two leg regions G each including the two legs 32 on the front side from the captured image M using the learning model 261. As described above, the learning model 261 is a model that is constructed in advance by machine learning using, for example, a neural network, so as to extract the two leg regions G on the front side from the image of the loading platform 30.

Next, the control unit 27 extracts the bottom edge La between the two leg regions G from the captured image M (step S3).
In this step, as shown in Figures 5 (a) and (b), for example, the control unit 27 sets an edge detection area Gw that includes all two leg areas G, and extracts (edge detects) the linear lower edge of the bottom plate 31 as the bottom edge (first edge) La.

Next, the control unit 27 determines the relative attitude of the loading platform 30 with respect to the photographing unit 24 based on the bottom surface edge La extracted in step S3 (step S4).
In this step, the control unit 27 calculates the relative angle θ of the bottom edge La with respect to the horizontal line X of the edge detection area Gw as the relative attitude of the loading platform 30 with respect to the photographing unit 24. The horizontal line X of the edge detection area Gw is a straight line along a direction corresponding to the left-right direction of the photographing unit 24 (i.e., the forklift 1) (hereinafter, sometimes simply referred to as the "left-right direction") in the image of the loading platform 30. The relative angle θ becomes smaller as the photographing unit 24 and the loading platform 30 face each other directly.
In this step, in addition to the relative attitude of the loading platform 30, the relative position of the loading platform 30 with respect to the imaging unit 24 may also be obtained based on the two leg regions G.

Next, the control unit 27 determines whether the image capturing unit 24 (i.e., the forklift 1) and the loading platform 30 are facing each other directly based on the relative attitude of the loading platform 30 obtained in step S4 (step S5).
Specifically, the control unit 27 determines that the photographing unit 24 and the loading platform 30 are facing each other directly when the relative angle θ of the bottom edge La obtained in step S4 as the relative posture of the loading platform 30 is smaller than a predetermined threshold value. The threshold value is set in advance as, for example, an upper limit value of the relative angle θ at which the fork 12 can be inserted into the space below the bottom plate 31.

In step S5, instead of the method based on the relative angle θ of the bottom edge La, the photographing unit 24 may be determined to be facing the loading platform 30 based on the degree of symmetry between the two leg regions G (or edge detection regions Gw). That is, when the degree of symmetry between the two leg regions G (or edge detection regions Gw) is equal to or greater than a predetermined value, it may be determined that the photographing unit 24 and the loading platform 30 are facing each other. More specifically, for example, when the Y coordinates (vertical coordinates of the image) of the intersections between the leg regions G (or edge detection regions Gw) and the bottom edge La match on the left and right, or when the difference between the left and right coordinates is equal to or less than a threshold value, it may be determined that the photographing unit 24 and the loading platform 30 are facing each other. Alternatively, when the distances in the X direction from the center line of the two leg regions G (or edge detection regions Gw) in the X direction (horizontal direction of the image) to the two vertical edges E (see FIG. 7) described later are equal to each other, or when the difference between the distances is equal to or less than a threshold value, it may be determined that the photographing unit 24 and the loading platform 30 are facing each other.
In this case, in step S4 described above, instead of the relative angle θ of the bottom edge La, the above-mentioned numerical values for determining the degree of left-right symmetry of the leg region G (or the edge detection region Gw) may be calculated.

In addition, when depth information is acquired together with the image information from the photographing unit 24, the relative attitude of the loading platform 30 can be calculated with even higher accuracy. The configuration for acquiring the depth information is not particularly limited, and for example, a TOF (Time Of Flight) sensor or the like may be provided separately from (or integrated with) the photographing unit 24, or an RGB-D camera (depth camera) or a stereo camera that can acquire images including three-dimensional point cloud data may be used as the photographing unit 24. Alternatively, if the size of the loading platform 30 is known (if it can be acquired from the loading platform information DB 262), the distance may be calculated based on the scale (and aspect ratio) on the image from the internal parameters of the photographing unit 24.
Specifically, when depth information of the captured image M is available, for example as shown in Figures 6(a) and 6(b), at least two points P are arbitrarily extracted from each leg region G, and three-dimensional coordinates including the depth of each point P are obtained. Then, from the three-dimensional coordinates of the at least two points P, the amount of rotation about the yaw axis Y perpendicular to the bottom plate 31 can be calculated as the relative attitude of the loading platform 30. In this case, three or more points P that are not located on a straight line may be extracted from the region surrounded by the bottom edge La and a lower end edge Lb (see Figure 8) described later, and the relative attitude of the loading platform 30 may be obtained from the three-dimensional coordinates of the three or more points P.
7A and 7B, for example, two vertical edges E in the up-down direction along the edges of the two corners on the front side of the box 33A (or the edges of the two pillars 34B on the front side) are extracted (edge detection).The relative attitude of the loading platform 30 may then be obtained from the three-dimensional coordinates of two intersections between the bottom edge La and the two vertical edges E.
Alternatively, two upper end regions U including the upper end portions of the two corners on the front side of the box 33A (or the two support columns 34B on the front side) are extracted. Then, the relative attitude of the loading platform 30 may be obtained from the three-dimensional coordinates of the two upper end regions U.
These methods make it possible to obtain the three-dimensional relative posture of the loading platform 30, including the tilt angle. The tilt angle can be calculated by obtaining the front surface of the loading platform 30 (a virtual surface in the case of the post pallet 30B) and calculating the inclination. For example, in the case of the box pallet 30A, the front panel 35A may be extracted and its inclination may be obtained.

In step S5, if it is determined that the photographing unit 24 and the loading platform 30 are directly facing each other (step S5; Yes), the control unit 27 causes the display unit 23 to display candidate insertion positions N for the pair of forks 12 (step S6).
The pair of candidate insertion positions N are, for example, two positions that are below the bottom edge La and within the spatial range between the two leg regions G, spaced apart by a predetermined distance (for example, the distance between the current pair of forks 12) in the direction connecting the two leg regions G. In this step, the control unit 27 determines the candidate insertion positions N, and then displays them superimposed on the captured image M displayed on the display unit 23.
In addition to displaying the candidate insertion position N, the operator may be notified that the photographing unit 24 (i.e., the forklift 1) is directly facing the loading platform 30 (for example, by displaying "OK" on the display unit 23).

8(a) and 8(b), instead of (or in addition to) displaying the insertion candidate position N, an insertion space AR (a dot in the figure) into which the fork 12 can be inserted may be displayed on the display unit 23. The insertion space AR is a fork insertion area (excluding the leg area G) surrounded by a bottom edge La, a lower end edge (second edge) Lb parallel to the bottom edge La, and two leg areas G. The lower end edge Lb is extracted from the captured image M as a straight line parallel to the bottom edge La and tangent to the lower end of at least one of the legs 32 (it may be separated from the other leg 32).
This allows the insertion space AR to be specified as the range into which the forks 12 are inserted (in the case of automatic driving, it can be limited to the insertion space AR), thereby reducing the risk of interference between the forks 12 and objects outside the insertion space AR during cargo picking. For example, when picking up cargo from the upper loading platform 30 of a stack, it is possible to avoid a situation in which the forks 12 damage the cargo loaded on the lower loading platform 30. Note that in the case of automatic driving (for example, when the forklift 1 is an unmanned guided vehicle), it is sufficient to control the forks 12 to be inserted into the insertion space AR, and the display of the insertion space AR may be omitted.
At this time, it may be determined whether or not the left-right direction position of the forks 12 is included within the insertion space AR based on the relative posture and position of the loading platform 30 with respect to the photographing unit 24.

In step S6, the center line C of the insertion space AR may be displayed on the display unit 23. The center line C is, for example, a line that passes through the center position of the insertion space AR and is parallel to the depth direction of the loading platform 30. However, it is sufficient that the center line C is at least the center of the insertion space AR in the left-right direction.
This makes it possible to prompt the operator to make the center of the portion between the two leg regions G and the pair of forks 12 correspond (for example, coincide) in the left-right direction (in the case of automatic driving, the pair of forks 12 are controlled in this manner). Therefore, it is possible to improve the stability of the state in which the loading platform 30 is held by the forks 12. In addition, it is possible to suppress problems such as load collapse, and to improve safety. Note that in the case of automatic driving (for example, when the forklift 1 is an unmanned guided vehicle), it is sufficient that the pair of forks 12 are controlled so that the center of the portion between the two leg regions G and the pair of forks 12 correspond in the left-right direction, and the display of the center line C may be omitted.

On the other hand, if it is determined in step S5 that the photographing unit 24 and the loading platform 30 are not facing each other (step S5; No), the control unit 27 notifies the operator that the photographing unit 24 (i.e., the forklift 1) is not facing the loading platform 30 (step S7).
The manner of notification in this case is not particularly limited, and may include displaying a warning message on the display unit 23 (e.g., "You are not facing the pallet!") or outputting a warning sound from a speaker (not shown).
Furthermore, in this case, in order to prevent cargo pick-up work from being performed while not facing the loading platform 30, the forward movement of the forklift 1 may be stopped (restricted), etc.

Next, the control unit 27 judges whether or not to end the goods collection assistance process (step S8), and if it is judged not to end the process (step S8; No), the control unit 27 proceeds to the above-mentioned step S1.
Then, when it is determined that the goods collection assistance process should be ended, for example, due to the completion of the goods collection operation (step S8; Yes), the control unit 27 ends the goods collection assistance process.

[Technical effect of the present embodiment]
As described above, according to this embodiment, two leg regions G each including the two legs 32 are extracted from the captured image M of the loading platform 30, and the relative orientation of the loading platform 30 with respect to the imaging unit 24 is obtained based on the two leg regions G. Then, based on the relative orientation of the loading platform 30, it is determined whether the loading platform 30 and the imaging unit 24 (i.e., the forklift 1) are directly facing each other.
This makes it possible to suitably determine whether the forklift 1 is facing the loading platform 30, such as the box pallet 30A or the post pallet 30B, which has the legs 32. Therefore, the loading operation for the loading platform 30 having the legs 32 can be suitably supported.

In addition, according to this embodiment, based on the two leg regions G, the lower edge of the bottom plate 31 of the loading platform 30 in the edge detection region Gw including the portion between the two leg regions G is extracted as a bottom edge La, and the relative posture of the loading platform 30 is determined based on the bottom edge La.
This makes it possible to suitably extract the bottom edge La and determine the relative attitude of the loading platform 30. In addition, because edge extraction is performed by narrowing down the image range, the occurrence of extraction errors can be reduced compared to when edge extraction is performed on the entire image.

Furthermore, according to this embodiment, when it is determined that the loading platform 30 and the photographing unit 24 (i.e., the forklift 1) are facing each other, a bottom edge Lb that is parallel to the bottom edge La and passes through the bottom end of the leg 32 is extracted from the captured image M. Then, an insertion space AR surrounded by the bottom edge La, the bottom edge Lb, and the two leg regions G is displayed on the display unit 23.
This allows the insertion space AR to be specified as the range into which the forks 12 are inserted, thereby reducing the risk of the forks 12 interfering with an object outside the insertion space AR during cargo pick-up work. For example, when picking up cargo from an upper loading platform 30 of a stack, it is possible to prevent the forks 12 from damaging the cargo loaded on the lower loading platform 30.

Furthermore, according to this embodiment, when it is determined that the loading platform 30 and the photographing unit 24 (i.e., the forklift 1) are facing each other, the pair of forks 12 are controlled so that the centers of the part between the two leg areas G and the pair of forks 12 correspond to each other in the direction corresponding to the left-right direction of the photographing unit 24.
This improves the stability of the state in which the loading platform 30 is held by the forks 12. This in turn makes it possible to prevent problems such as the collapse of the load, and improves safety.

Furthermore, according to this embodiment, if the photographing unit 24 is capable of acquiring a captured image M having depth information, the relative attitude of the loading platform 30 is obtained based on this depth information.
This makes it possible to suitably determine the three-dimensional relative posture of the loading platform 30, including the tilt angle.

Furthermore, according to this embodiment, if it is determined that the loading platform 30 and the image capturing unit 24 (i.e., the forklift 1) are not directly facing each other, the determination result is notified.
This allows the operator of the forklift 1 or the like to be promptly notified of the situation.

[others]
Although the embodiment of the present invention has been described above, the present invention is not limited to the above embodiment.
For example, in the above embodiment, in the load handling support process, the facing determination with respect to the loading platform 30 (step S5) is performed before the display of the insertion position of the fork 12 (step S6). However, the insertion position of the fork 12 may be displayed without performing the facing determination with respect to the loading platform 30.

In addition, in the above embodiment, all of the cargo handling assistance processing is performed on the forklift 1, but at least a part of the cargo handling assistance processing may be performed in external equipment (e.g., a control room at a loading and unloading work site). For example, a communication means may be provided in the external equipment and the forklift 1, and the captured image may be transmitted from the forklift 1 to a computing device in the external equipment, and the results calculated by this computing device may be transmitted to the forklift 1.

Furthermore, the transport device according to the present invention is not limited to a forklift as long as it holds and transports a loading platform, and may be, for example, an automated guided vehicle (e.g., AGV) that transports loads without a driver (automatic), etc. If the transport device is an automated guided vehicle, the display process and notification process in steps S6 and S7 of the load collection support process may be performed on, for example, a display unit (notification unit) of external equipment that can communicate with the forklift 1.
In addition, the details shown in the above embodiment can be modified as appropriate without departing from the spirit of the invention.

1. Forklift (transportation device)
12 Fork (holding part)
23 Display unit 24 Photography unit (imaging means)
26 Memory unit 27 Control unit (calculation means, determination means, display means, control means, notification means)
30 Loading platform 30A Box pallet 30B Post pallet 31 Bottom plate 32 Leg 33A Box 34B Support 35A Panel 261 Learning model 263 Loading support program AR Insertion space (fork insertion area)
C: center line E: vertical edge G: foot area Gw: edge detection area La: bottom edge (first edge)
Lb: Lower edge (second edge)
M: captured image N: insertion candidate position P: point U: upper end area X: horizontal line θ: relative angle

Claims (11)

an imaging means for acquiring an image of a platform having at least two legs;
a calculation means for extracting two leg regions each including the two legs from the image of the loading platform and determining a relative orientation of the loading platform with respect to the imaging means based on the two leg regions;
a determination means for determining whether the loading platform and the imaging means are directly facing each other based on the relative position of the loading platform;
A cargo handling assistance device comprising: The calculation means includes:
Based on the two leg regions, a lower edge of a bottom plate of the loading platform in an area including a portion between the two leg regions is extracted as a first edge;
determining a relative attitude of the loading platform based on the first edge;
The load-receiving assist device according to claim 1. the calculation means calculates, as a relative attitude of the loading platform, an angle between a direction corresponding to a left-right direction of the imaging means and the first edge;
The determination means determines that the loading platform and the imaging means are directly facing each other when the angle is smaller than a predetermined threshold value.
The load-receiving assist device according to claim 2. a display unit that displays a fork insertion area surrounded by the first edge, the second edge, and the two leg areas on a display unit when the determination unit determines that the loading platform and the imaging unit are directly facing each other, the second edge being parallel to the first edge and in contact with the lower end of the leg from the image of the loading platform,
The load-receiving assist device according to claim 2. The calculation means determines a relative position of the loading platform with respect to the imaging means based on the two leg regions.
The load-receiving assist device according to claim 1. a control means for controlling a conveying device having a pair of holding parts for holding the loading platform;
When the determination means determines that the loading platform and the imaging means are directly facing each other, the control means causes the center of a portion between the two leg regions and the pair of holding portions to correspond to each other in a direction corresponding to the left-right direction of the imaging means.
The load-receiving assist device according to claim 1. The imaging means is capable of acquiring the image having depth information,
The calculation means determines the relative attitude of the loading platform based on the depth information.
The load-receiving assist device according to claim 1. a notification means for notifying a result of the determination when the determination means determines that the loading platform and the imaging means are not directly facing each other,
The load-receiving assist device according to claim 1. The load receiving assist device according to claim 1 ,
A pair of holding parts for holding the loading platform;
Conveying device. A control means for a loading assist device including an imaging means for acquiring an image of a loading platform having at least two legs,
a calculation step of extracting two leg regions each including the two legs from the image of the loading platform and determining a relative attitude of the loading platform with respect to the imaging means based on the two leg regions;
a determination as to whether the loading platform and the imaging means are facing each other based on the relative posture of the loading platform;
A cargo handling assistance method. A computer of a loading assist device including an imaging means for acquiring an image of a loading platform having at least two legs,
a computing means for extracting two leg regions each including the two legs from the image of the loading platform and determining a relative attitude of the loading platform with respect to the imaging means based on the two leg regions;
a determination means for determining whether the loading platform and the imaging means are directly facing each other based on the relative position of the loading platform;
A cargo assistance program that serves as a.

Images