Cargo placement control method, device, computer equipment and storage medium

Abstract

The present application relates to a cargo placement control method, device, computer equipment and storage medium. The method comprises: obtaining first point cloud data obtained by laser scanning the front surface of a target shelf rail; determining the relative position information of the target shelf rail relative to the handling equipment based on the first point cloud data; obtaining second point cloud data obtained by laser scanning the upper surface of the target shelf rail; determining the cargo placement plane corresponding to the target shelf rail based on the second point cloud data; and performing cargo placement control processing on the handling equipment based on the relative position information and the cargo placement plane. Before directly placing the cargo, the present application performs a laser scan on the target shelf rail and processes the point cloud data to determine the relative position information of the target shelf rail relative to the handling equipment and the cargo placement plane, and controls the handling equipment based on the relative position information and the cargo placement plane to accurately place the cargo on the upper surface of the target rail, thereby improving the reliability of cargo placement.

Description

Technical Field

[0001] The present application relates to the field of logistics application technology, and in particular to a cargo placement control method, device, computer equipment, and storage medium. Background Art

[0002] With the development of industrial technology and the logistics industry, the volume of cargo continues to increase, and the demand for cargo placement is also rising. Currently, cargo placement is primarily performed using handling equipment, such as unmanned forklifts. However, in some challenging cargo placement scenarios, such as shuttle racking, direct cargo placement using handling equipment can lead to operational errors, resulting in low cargo placement reliability. Summary of the Invention

[0003] Based on this, it is necessary to provide a cargo placement control method, device, computer equipment and storage medium that can improve the reliability of cargo placement in order to address the above technical problems.

[0004] In a first aspect, the present application provides a cargo placement control method. The method comprises:

[0005] Acquire first point cloud data obtained by laser scanning the front surface of the target shelf rail;

[0006] Determine relative position information of the target shelf guide rail relative to the handling equipment based on the first point cloud data;

[0007] Obtaining second point cloud data by performing laser scanning on the upper surface of the target shelf guide rail;

[0008] Determine the cargo placement plane corresponding to the target shelf rail according to the second point cloud data;

[0009] The cargo placement control process is performed on the handling equipment according to the relative position information and the cargo placement plane.

[0010] In a second aspect, the present application further provides a cargo placement control device. The device comprises:

[0011] A laser scanning module, configured to obtain first point cloud data obtained by laser scanning the front surface of a target shelf guide rail;

[0012] a data processing module, configured to determine relative position information of the target shelf rail relative to the handling equipment based on the first point cloud data;

[0013] The laser scanning module is further used to obtain second point cloud data by performing laser scanning on the upper surface of the target shelf rail;

[0014] The data processing module is further configured to determine a cargo placement plane corresponding to the target shelf rail based on the second point cloud data;

[0015] The placement control module performs cargo placement control processing on the handling equipment according to the relative position information and the cargo placement plane.

[0016] In some embodiments, the data processing module includes a point cloud slicing unit and a plane recognition unit. The multi-point cloud slicing unit is used to perform point cloud slicing processing based on the second point cloud data to obtain a cutting point cloud layer; the plane recognition unit is used to determine the cargo plane corresponding to the target shelf rail based on multiple cutting point cloud layers.

[0017] In some embodiments, the point cloud slicing unit is further used to obtain the highest scanning parameter and the lowest scanning parameter; the highest scanning parameter is determined by the highest scanning surface obtained by laser scanning the target shelf guide rail, and the lowest scanning parameter is determined by the lowest scanning surface obtained by laser scanning the target shelf guide rail; based on the highest scanning parameter and the lowest scanning parameter, the target point cloud area is determined from the area where the second point cloud data is located; point cloud slicing processing is performed on the point cloud data in the target point cloud area to obtain multiple cut point cloud layers.

[0018] In some embodiments, there are multiple cutting point cloud layers, and the cargo placement plane is determined from the point cloud layer planes where the multiple cutting point cloud layers are located. The plane identification unit is also used to select the current cutting point cloud layer layer by layer from the multiple cutting point cloud layers, and perform cargo placement plane identification on the current point cloud layer plane where the current cutting point cloud layer is located; if it is identified that the current point cloud layer plane is not the cargo placement plane, the next cutting point cloud layer is used as the new current cutting point cloud layer, and the iterative execution of the cargo placement plane identification on the current point cloud layer plane where the current cutting point cloud layer is located is returned to determine the point cloud layer plane that belongs to the cargo placement plane.

[0019] In some embodiments, the plane identification unit is also used to cluster the layer point cloud data in the current cutting point cloud layer to obtain multiple point cloud cluster blocks; determine a bounding box for enclosing the multiple point cloud cluster blocks; determine the point cloud cluster size corresponding to the current cutting point cloud layer based on the size of the bounding box; and perform cargo plane identification on the current point cloud layer plane where the current cutting point cloud layer is located based on the point cloud cluster size.

[0020] In some embodiments, the placement control module is further used to generate a first operation signal to control the handling equipment to cancel the cargo placement operation if it is identified that the point cloud layer planes where the multiple cut point cloud layers are located do not belong to the cargo placement plane.

[0021] In some embodiments, the placement control module is further used to determine the cargo placement height corresponding to the cargo placement plane; the cargo placement height is the actual height used by the handling equipment to lift the cargo to be placed to perform the cargo placement operation; a second operation signal is generated based on the relative position information and the cargo placement height; the second operation signal is sent to the handling equipment so that the handling equipment adjusts its posture according to the second operation signal to place the cargo to be placed on the upper surface of the target shelf rail.

[0022] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned cargo placement control method when executing the computer program.

[0023] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the above-mentioned cargo placement control method.

[0024] In a fifth aspect, the present application further provides a computer program product, which includes a computer program that implements the steps in the above-mentioned cargo placement control method when executed by a processor.

[0025] The above-mentioned cargo placement control method, device, computer equipment, storage medium and computer program product obtain first point cloud data by laser scanning the front surface of the target shelf rail; determine the relative position information of the target shelf rail compared to the handling equipment based on the first point cloud data; obtain second point cloud data by laser scanning the upper surface of the target shelf rail; determine the cargo placement plane corresponding to the target shelf rail based on the second point cloud data; and perform cargo placement control processing on the handling equipment based on the relative position information and the cargo placement plane. Before the handling equipment directly places the cargo, the present application performs two laser scans on the target shelf rail and processes the scanned point cloud data to determine the relative position information of the target shelf rail compared to the handling equipment and the cargo placement plane corresponding to the target cargo placement rail. Based on the relative position information and the cargo placement plane, the handling equipment is controlled to accurately place the cargo on the upper surface of the target rail, thereby improving the reliability of cargo placement. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 A schematic flow chart of a cargo placement control method in some embodiments;

[0027] Figure 2 Schematic diagram of the position of the target shelf rail in some embodiments;

[0028] Figure 3Schematic diagram of the positions of goods to be placed and the cargo placement surface in some embodiments;

[0029] Figure 4 Schematic diagram of the flow of cargo placement control method in other embodiments;

[0030] Figure 5 is a structural block diagram of a cargo placement control device in some embodiments;

[0031] Figure 6 1 is a diagram of the internal structure of a computer device in some embodiments. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0033] In some embodiments, as Figure 1 As shown, a cargo placement control method is provided. This embodiment uses the method applied to a server as an example for illustration. It is understandable that the method can also be applied to transport equipment, and can also be applied to a system including transport equipment and a server, and implemented through the interaction between the transport equipment and the server. In this embodiment, the method includes the following steps:

[0034] Step 102: Acquire first point cloud data obtained by laser scanning the front surface of the target shelf rail.

[0035] Among them, the shelf rail refers to the rail on the shelf used to store goods, the target shelf rail refers to the designated shelf rail where the handling equipment needs to place the goods, and the shelf can be but is not limited to at least one of a shuttle shelf and a through shelf.

[0036] To facilitate understanding, the following example illustrates the basic structure and working principle of a shuttle rack. A shuttle rack is a type of rack used in conjunction with a shuttle trolley. When goods need to be placed, handling equipment is used to place the goods on the rack rails at one end of the shuttle rack. The shuttle trolley then handles the subsequent transportation of the goods. This reduces or prevents damage to the shuttle rack caused by collisions between the handling equipment and the shuttle rack during transportation.

[0037] Drive-through racking, also known as drive-through racking or drive-in racking, is a continuous, integrated racking system that is not divided by aisles. Drive-through racking also utilizes a pallet storage and retrieval system, making it suitable for storing a single variety of goods in large quantities.

[0038] Handling equipment is transportation equipment used to carry goods, wherein the handling equipment may be but is not limited to at least one of an automated guided vehicle (AGV) and a forklift, wherein the forklift may be but is not limited to an unmanned forklift.

[0039] Point cloud data refers to a set of vectors in a three-dimensional coordinate system. These vectors are usually expressed in the form of X, Y, and Z three-dimensional coordinates and are generally used to represent the outer surface shape of an object.

[0040] Specifically, a laser device performs a laser scan on the front surface of the target shelf rail, generating corresponding first point cloud data. The laser device refers to a device capable of emitting laser light. The server then acquires the first point cloud data generated by the laser scan and uses it to subsequently determine the relative position of the target shelf rail and the handling equipment. The front surface of the target shelf rail refers to the surface of the target shelf rail facing the handling equipment.

[0041] In some embodiments, the front surface of the target shelf rail is a plane, and laser scanning based on the plane can obtain relatively flat first point cloud data, thereby ensuring that the relative position information of the target shelf rail determined based on the flat first point cloud data is more accurate than that of the handling equipment.

[0042] The front surface of the target shelf rail can be specifically referred to Figure 2 The first point cloud data refers to the point cloud data obtained by the laser device performing laser scanning on the front surface of the target shelf rail.

[0043] In some embodiments, the laser device can perform an oblique scan on the front surface of the target shelf rail, or can perform a forward scan on the front surface of the target shelf, as long as it can ensure that the point cloud data of the front surface of the target shelf rail is scanned.

[0044] In some embodiments, the laser device can be fixed on the handling device, and the specific fixed position of the laser device is not limited, as long as the fixed laser device can accurately scan the point cloud data.

[0045] In some embodiments, the laser device can be fixed at the midpoint between the roots of two clamping arms in the handling equipment used to clamp or hold goods. This ensures that the laser device will not be blocked by the goods during laser scanning, thereby improving the accuracy of laser scanning. After the laser device is fixed, the handling equipment travels to a preset distance directly in front of the target shelf rail. Generally, the preset distance can be, but is not limited to, 1 to 2 meters. Subsequently, the height of the clamping arm of the handling equipment is adjusted so that the laser emitted by the laser device faces the front surface of the target shelf rail. Next, the target shelf rail is laser scanned by the laser device to obtain the corresponding first point cloud data. Among them, the root of the clamping arm refers to the end of the clamping arm in the handling equipment facing the body of the handling equipment.

[0046] In actual applications, the rack includes multiple layers of rack rails arranged sequentially along the rack's height. Adjusting the height of the handling device's clamping arm refers to adjusting the height of the handling device's clamping arm to match the height of the target rack rail. For example, if the target rack rail is the bottom rack rail in the rack, and the target rack rail height is 2 meters, the height of the handling device's clamping arm needs to be adjusted to 2 meters. If the next target rack rail to be released is the second-bottom rack rail in the rack, and the target rack rail height is 4 meters, the height of the handling device's clamping arm needs to be adjusted to 4 meters.

[0047] In other embodiments, the laser equipment can also be set separately from the handling equipment. Specifically, the laser equipment can be fixedly installed at a position where it can scan the front surface of the target shelf rail. When it is necessary to collect the first point cloud data of the target shelf rail, laser scanning is directly performed through the laser equipment.

[0048] Step 104 : Determine relative position information of the target shelf rail relative to the handling equipment based on the first point cloud data.

[0049] Among them, the relative position information refers to the posture information between the target shelf rail and the handling equipment, including the length of the target shelf rail relative to the coordinate system where the handling equipment is located in the X-axis direction and the width of the target shelf rail relative to the coordinate system where the handling equipment is located in the Y-axis direction, as well as the angle of the target shelf rail compared to the handling equipment. Specifically, the server converts the coordinate system through the first point cloud data, specifically converts the coordinate system where the target shelf rail is located to the coordinate system where the handling equipment is located, and then determines the length of the target shelf rail relative to the coordinate system where the handling equipment is located in the X-axis direction, the width of the target shelf rail relative to the coordinate system where the handling equipment is located in the Y-axis direction, and the angle of the target shelf rail compared to the handling equipment. Among them, the angle of the target shelf rail compared to the handling equipment refers to the angle of the target shelf rail relative to the coordinate system where the handling equipment is located in the X-axis direction.

[0050] In some embodiments, if the transport device is facing the target shelf rail, the relative position information includes the length of the target shelf rail in the X-axis direction of the coordinate system where the transport device is located, the width of the target shelf rail in the Y-axis direction of the coordinate system where the transport device is located, and the angle between the target shelf rail and the coordinate system where the transport device is located in the X-axis direction.

[0051] It should be noted that if the laser device is fixed on the handling device, the relative position information refers to the posture information between the target shelf rail and the laser device, which can be specifically the length of the target shelf rail relative to the laser coordinate system where the laser device is located in the X-axis direction and the width of the target shelf rail relative to the laser coordinate system where the handling device is located in the Y-axis direction, as well as the angle of the target shelf rail relative to the laser coordinate system where the laser device is located in the X-axis direction.

[0052] In some embodiments, the first point cloud data can also be input into a pre-set cargo release detection program, which performs cargo release detection on the first point cloud data and directly returns a detection result, which includes relative position information. The cargo release detection program is a debugging tool that integrates a cargo release detection algorithm module, allowing real-time online cargo release detection and visualization of the detection results of the cargo release detection algorithm.

[0053] Step 106 : Obtain second point cloud data by performing laser scanning on the upper surface of the target shelf rail.

[0054] Specifically, the laser device performs a laser scan on the upper surface of the target shelf rail to obtain corresponding second point cloud data. The server then obtains the second point cloud data obtained by the laser device for subsequent determination of the cargo placement plane.

[0055] In some embodiments, the upper surface of the target rack rail can be specifically referred to Figure 2 The second point cloud data refers to the point cloud data obtained by the laser device performing laser scanning on the upper surface of the target shelf rail.

[0056] It should be noted that the laser light emitted by the laser device is generally emitted at a height higher than the target rack rail so that it can scan the upper surface of the target rack rail. In addition, the upper surface of the target rack rail can also be flat. Setting the upper surface of the target rack rail as a flat surface can ensure that the goods to be placed can be placed smoothly on the upper surface of the target rack rail.

[0057] Step 108: Determine the cargo placement plane corresponding to the target shelf rail based on the second point cloud data.

[0058] The cargo placement plane refers to a plane where one of the multiple point cloud layers obtained after slicing the second point cloud data is located. The cargo placement plane is used for subsequent calculation of the cargo placement height of the cargo to be placed.

[0059] Specifically, the second point cloud data is sliced, and a cargo placement plane corresponding to the target shelf rail is determined from the planes where the multiple point cloud layers obtained after the slicing are located.

[0060] It should be noted that the server executes step 110 to control the handling device to place the cargo only after the server has identified the cargo placement plane of the target shelf rail based on the second point cloud data. In some embodiments, the server may not be able to identify the cargo placement plane of the target shelf rail based on the second point cloud data. This indicates that there may be no cargo placement space on the target cargo rail. In this case, the server may generate a first operation signal to control the handling device to cancel the cargo placement operation. The first operation signal is used to instruct the handling device not to place the cargo to be placed on the upper surface of the target shelf rail.

[0061] It is understood that the cargo space refers to the area on the upper surface of the target shelf rail that can bear cargo, that is, the load-bearing area on the upper surface of the target shelf rail. In some embodiments, if the load-bearing area on the upper surface of the target shelf rail is smaller than the floor space occupied by the cargo to be placed, it indicates that the cargo space on the target shelf rail is insufficient to bear the cargo to be placed. If the load-bearing area on the upper surface of the target shelf rail is greater than or equal to the floor space occupied by the cargo to be placed, it indicates that the cargo space on the target shelf rail can bear the cargo to be placed. The load-bearing area on the upper surface of the target shelf rail can be obtained by multiplying the length of the upper surface of the target shelf rail by the width, and the floor space occupied by the cargo to be placed can be obtained by multiplying the length of the cargo to be placed by the width.

[0062] Step 110 , performing cargo placement control processing on the handling equipment according to the relative position information and the cargo placement plane.

[0063] Specifically, the server controls the transport equipment to perform adaptive adjustment based on the determined relative position information and cargo placement plane, wherein the adaptive adjustment includes adaptive adjustment of at least one of the vehicle body and clamping arm of the transport equipment, so that the adaptively adjusted transport equipment places the cargo on the upper surface of the target shelf rail.

[0064] In some embodiments, if the server determines that the transport device does not need to be adaptively adjusted based on the relative position information and the cargo placement plane, the server can directly control the transport device to place the cargo on the upper surface of the target shelf rail.

[0065] In the above-mentioned cargo placement control method, first point cloud data is obtained by laser scanning the front surface of the target shelf rail; the relative position information of the target shelf rail relative to the handling equipment is determined based on the first point cloud data; second point cloud data is obtained by laser scanning the upper surface of the target shelf rail; the cargo placement plane corresponding to the target shelf rail is determined based on the second point cloud data; and the handling equipment is controlled to place cargo based on the relative position information and the cargo placement plane. This application performs two laser scans on the target shelf rail before the handling equipment directly places cargo, and processes the scanned point cloud data to determine the relative position information of the target shelf rail relative to the handling equipment and the cargo placement plane corresponding to the target cargo placement rail. Based on the relative position information and the cargo placement plane, the handling equipment is controlled to accurately place the cargo on the upper surface of the target rail, thereby improving the reliability of cargo placement.

[0066] In some embodiments, step 108 specifically includes but is not limited to: performing point cloud slicing processing based on the second point cloud data to obtain a cut point cloud layer; and determining a cargo placement plane corresponding to the target shelf rail based on multiple cut point cloud layers.

[0067] In some embodiments, the server can directly slice the second point cloud data to obtain multiple point cloud layers, and determine a target point cloud layer from these multiple point cloud layers, and use the plane where the target point cloud layer is located as the loading plane corresponding to the target shelf rail.

[0068] In other embodiments, the server may further filter the second point cloud data and slice the filtered second point cloud data to obtain multiple point cloud layers. A target point cloud layer is determined from these multiple point cloud layers, and the plane containing the target point cloud layer is used as the loading plane corresponding to the target guide rail. The server may obtain the range of the highest and lowest scanning parameters and filter out the second point cloud data outside of this range. By filtering the second point cloud data, unnecessary point cloud data can be eliminated, further improving the accuracy of the point cloud slices.

[0069] In some embodiments, laser scanning is performed on the upper surface of the target shelf rail to obtain corresponding point cloud data, and the highest scanning surface and the lowest scanning surface are determined from these point cloud data. The highest scanning surface represents the highest plane where the point cloud data is located, and the lowest scanning surface represents the lowest plane where the point cloud data is located.

[0070] It is understood that the maximum scanning parameter is the difference between the height of the highest scanning surface and the height of the upper surface of the target shelf rail, and the minimum scanning parameter is the difference between the height of the lowest scanning surface and the height of the upper surface of the target shelf rail. The maximum scanning parameter and the minimum scanning parameter typically range from -0.3 meters to 0.3 meters.

[0071] In some embodiments, the step of "performing point cloud slicing processing based on the second point cloud data to obtain multiple cut point cloud layers" specifically includes but is not limited to: obtaining the highest scanning parameters and the lowest scanning parameters; determining the target point cloud area from the area where the second point cloud data is located based on the highest scanning parameters and the lowest scanning parameters; performing point cloud slicing processing on the point cloud data in the target point cloud area to obtain multiple cut point cloud layers.

[0072] The target point cloud area refers to the point cloud area formed after filtering out the point cloud data outside the range of the highest scanning parameter and the lowest scanning parameter in the area where the second point cloud data is located. The point cloud data in the target point cloud area is the point cloud data that needs to be processed by the algorithm to determine the delivery plane.

[0073] Specifically, after obtaining the highest and lowest scan parameters, the server uses the difference between the highest and lowest scan parameters as the height of the target point cloud area, the length of the goods to be placed as the length of the target point cloud area, and the width of the goods to be placed as the width of the target point cloud area. Next, the server locates the target point cloud area based on the determined height, length, and width of the target point cloud area, and performs point cloud slicing on the point cloud data in the target point cloud area to obtain multiple sliced ​​point cloud layers. The goods to be placed refer to the goods that the handling equipment is about to place on the upper surface of the target shelf rail.

[0074] In some embodiments, the slicing interval for each cut point cloud layer can be determined by setting a slice interval parameter on the server. In practical applications, point cloud slicing can be performed on the point cloud data in the target point cloud region using both top-down and bottom-up slicing methods. The slice interval parameter can be set to 0.1 cm. It is understood that the slice interval parameter can be adjusted based on actual needs and is not limited in this application.

[0075] In some embodiments, the cargo placement plane is determined from the point cloud layer planes where multiple cutting point cloud layers are located. The step of "determining the cargo placement plane corresponding to the target shelf rail based on multiple cutting point cloud layers" specifically includes but is not limited to: selecting the current cutting point cloud layer layer by layer from the multiple cutting point cloud layers, and identifying the cargo placement plane for the current point cloud layer plane where the current cutting point cloud layer is located; if it is identified that the current point cloud layer plane is not the cargo placement plane, the next cutting point cloud layer is used as the new current cutting point cloud layer, and the iterative execution is returned to identify the cargo placement plane for the current point cloud layer plane where the current cutting point cloud layer is located to determine the point cloud layer plane that belongs to the cargo placement plane.

[0076] Specifically, the server selects a cutting point cloud layer from multiple cutting point cloud layers layer by layer as the current cutting point cloud layer, wherein the server can select the current cutting point cloud layer from multiple cutting point cloud layers layer by layer from top to bottom, and the server can also select the current cutting point cloud layer from multiple cutting point cloud layers layer by layer from top to bottom. It should be noted that this application does not limit the selection method and selection order of the current cutting point cloud layer. After determining the current cutting point cloud layer, the plane where the current point cloud layer is located, that is, the current point cloud layer plane, is identified as the cargo plane. If it is identified that the current point cloud layer plane is a cargo plane, the current point cloud layer plane is directly used as the cargo plane. If it is identified that the current point cloud layer plane is not a cargo plane, the next cutting point cloud layer, that is, the next cutting point cloud layer that needs to be identified as the cargo plane, is used as the new current point cloud layer, and then the iterative execution is returned to identify the cargo plane of the current point cloud layer plane where the current cutting point cloud layer is located to determine the point cloud layer plane that belongs to the cargo plane.

[0077] In other words, the cutting point cloud layers are sequentially identified as the placement plane. If the plane on which a cutting point cloud layer is located is identified as the placement plane, there is no need to identify the placement plane for the remaining cutting point cloud layers. The plane on which the cutting point cloud layer is located is directly used as the placement plane. If the plane on which all cutting point cloud layers are identified is not the placement plane, it means that the placement requirements are not met.

[0078] In some embodiments, in addition to determining the point cloud layer plane belonging to the cargo placement plane by iteratively performing the cargo placement plane identification operation, cargo placement plane identification can also be performed on the planes where all the cut point cloud layers are located, so as to screen out the planes where the point cloud layer planes that meet the cargo placement plane requirements are located, and select one of the planes from the planes where the cut point cloud layers that meet the cargo placement plane requirements are located as the cargo placement plane.

[0079] In some embodiments, the step of "identifying the cargo plane of the current point cloud layer where the current cutting point cloud layer is located" specifically includes but is not limited to: clustering the layer point cloud data in the current cutting point cloud layer to obtain multiple point cloud cluster blocks; determining a bounding box for enclosing the multiple point cloud cluster blocks; determining the point cloud cluster size corresponding to the current cutting point cloud layer based on the size of the bounding box; and identifying the cargo plane of the current point cloud layer where the current cutting point cloud layer is located based on the point cloud cluster size.

[0080] Clustering refers to the process of dividing a collection of physical or abstract objects into multiple classes consisting of similar objects. The cluster generated by clustering is a collection of data objects that are similar to objects in the same cluster and different from objects in other clusters.

[0081] Specifically, the point cloud data in the currently cut point cloud layer, i.e., the layer point cloud data, is clustered to obtain a plurality of point cloud cluster blocks, wherein the density clustering algorithm (Density-Based Spatial Clustering of Applications with Noise, DBSCAN) can be used to cluster the layer point cloud data. Then, a bounding box is used to enclose the plurality of point cloud cluster blocks, wherein the bounding box can be a minimum box that can just enclose a plurality of point cloud cluster blocks, or the bounding box can be a box that is slightly larger than the minimum box and can enclose a plurality of point cloud cluster blocks, which is not limited in this application. After determining the bounding box for enclosing a plurality of point cloud cluster blocks, the size of the bounding box is used as the point cloud cluster size corresponding to the currently cut point cloud layer, wherein the size of the bounding box includes the length, width, and height of the bounding box. Based on the point cloud cluster size (i.e., the length, width, and height of the bounding box), the current point cloud layer's plane containing the currently cut point cloud layer is identified. Specifically, this identifies the minimum plane parameters and determines whether the bounding box's length, width, and height are within these parameters. The minimum plane is the point cloud layer plane that meets these requirements and has the smallest area.

[0082] If the length, width, and height of the bounding box are all within the minimum loading plane parameter range, the current point cloud layer where the cut point cloud layer is located is the loading plane. The minimum loading plane parameter range is usually 4 cm to 8 cm. If any of the length, width, or height of the bounding box is not within the minimum loading plane parameter range, the current point cloud layer where the cut point cloud layer is located is not the loading plane.

[0083] In some embodiments, the cargo placement control method specifically includes but is not limited to: if it is identified that the point cloud layer planes where multiple cutting point cloud layers are located do not belong to the cargo placement plane, a first operation signal is generated to control the handling equipment to cancel the cargo placement operation.

[0084] Specifically, if the server identifies that none of the point cloud planes containing multiple cut point cloud layers are designated as placement planes, this indicates that there is insufficient placement space on the target shelf rail. In this case, the server can generate a first operation signal to control the handling device to cancel the placement operation. This first operation signal instructs the handling device not to place the pending goods on the upper surface of the target shelf rail. Generating this first operation signal prevents placement failures due to insufficient placement space, thereby improving the reliability of placement.

[0085] In some embodiments, step 110 specifically includes but is not limited to: determining the cargo placement height corresponding to the cargo placement plane; generating a second operation signal based on the relative position information and the cargo placement height; and sending the second operation signal to the handling equipment so that the handling equipment adjusts its posture according to the second operation signal to place the cargo to be placed on the upper surface of the target shelf rail.

[0086] The goods to be placed refer to the goods that the handling equipment is about to place on the upper surface of the target shelf rail.

[0087] Specifically, if there is no cargo placed on the target shelf rail, the height of the bounding box corresponding to the point cloud layer plane belonging to the cargo placement plane is used as the cargo placement plane thickness. If there is cargo placed on the target shelf rail, the cargo placement plane thickness is the sum of the height of the bounding box corresponding to the point cloud layer plane belonging to the cargo placement plane and the height of the pre-placed cargo, where the pre-placed cargo is the cargo already placed on the upper surface of the target shelf rail.

[0088] The "placement height" refers to the actual height at which the handling equipment lifts the goods to be placed to perform the placement operation. After the handling equipment lifts the goods to be placed to the placement height, the placement operation is performed to place the goods to be placed on the upper surface of the target shelf rail based on the placement height.

[0089] In some embodiments, the loading height is the sum of the loading surface thickness and the height of the guide rail from the ground, wherein the height of the guide rail from the ground refers to the distance between the guide rail of the target shelf and the ground.

[0090] In some embodiments, in order to prevent the handling equipment from colliding during the cargo placement process, the cargo placement height of the present application can also be the sum of the thickness of the cargo placement plane, the height of the guide rail from the ground, half of the height of the cargo to be placed, and the offset. Among them, the offset refers to the difference between the height of the pre-placed cargo in the vertical direction and the height of the cargo placement plane. The offset is a preset value and can generally be set to 0.05 cm. It can be understood that the offset can be adjusted according to actual needs, and this application does not limit this. Among them, the relationship between the cargo to be placed and the cargo placement plane and the offset can be referred to. Figure 3 .

[0091] In some embodiments, after determining the height for placing the goods, the server generates a second operation signal based on the relative position information and the height for placing the goods, and transmits the second operation signal to the handling device. The second operation signal indicates the specific posture adjustment that needs to be made to the handling device, such as adjusting the horizontal position deviation between the handling device and the guide rails of the target shelf, adjusting the vertical position deviation between the handling device and the guide rails of the target shelf, adjusting the height of the clamping arm of the handling device, and adjusting the angular deviation between the handling device and the guide rails of the target shelf.

[0092] In some embodiments, after receiving the second operating signal, the handling device adaptively adjusts at least one of the vehicle body and the clamping arm based on the second operating signal. For example, the clamping arm can be controlled to adaptively adjust the horizontal error, i.e., the position deviation, between the handling device and the target shelf rail. The vehicle body can also be controlled to adaptively adjust the horizontal and vertical position deviations between the handling device and the target shelf rail. After performing the adaptive adjustment, the handling device can then place the goods to be placed on the upper surface of the target shelf rail, thereby completing the cargo placement operation with high precision.

[0093] In some embodiments, as Figure 4 As shown, the cargo placement control method of the present application specifically includes but is not limited to the following steps:

[0094] Step 402: Install a laser device at the midpoint between the roots of the two clamping arms of the handling device.

[0095] Step 404: Control the transport device to travel to an appropriate distance in front of the target shelf guide rail.

[0096] Step 406 , adjusting the height of the clamping arm of the transport device so that the laser emitted by the laser device is directed toward the front surface of the target shelf rail.

[0097] Step 408 : Acquire first point cloud data of the front surface of the target shelf rail through laser scanning.

[0098] Step 410: Determine relative position information between the target shelf rail and the handling equipment based on the first point cloud data.

[0099] Step 412: Raise the clamping arm so that the laser height is higher than the target shelf rail.

[0100] Step 414 : Acquire second point cloud data of the upper surface of the target shelf rail through laser scanning.

[0101] Step 416: extract the target point cloud area of ​​the second point cloud data.

[0102] In some embodiments, the server may obtain a maximum scanning parameter and a minimum scanning parameter; and determine a target point cloud area from an area where the second point cloud data is located according to the maximum scanning parameter and the minimum scanning parameter.

[0103] In step 418 , the point cloud data in the target point cloud area are sliced ​​from top to bottom to obtain multiple sliced ​​point cloud layers, and a current sliced ​​point cloud layer is selected from the multiple sliced ​​point cloud layers from top to bottom.

[0104] Step 420: cluster the layer point cloud data in the current cut point cloud layer to obtain multiple point cloud cluster blocks; determine a bounding box for enclosing the multiple point cloud cluster blocks; and determine the point cloud cluster size corresponding to the current cut point cloud layer based on the size of the bounding box.

[0105] Step 422 : Determine whether the point cloud cluster size corresponding to the current cut point cloud layer meets the requirements for cargo placement plane recognition.

[0106] It is understood that if the point cloud cluster size corresponding to the current cut point cloud layer does not meet the requirements for cargo plane identification, the next cut point cloud layer is used as the new current cut point cloud layer, and the process returns to step 420 for iterative processing. If the point cloud cluster size corresponding to the current cut point cloud layer meets the requirements for cargo plane identification, the iteration can be stopped and step 424 can be executed. It is understood that if the point cloud cluster size corresponding to the current cut point cloud layer meets the requirements for cargo plane identification, it means that the current cut point cloud layer corresponds to the cargo plane.

[0107] In step 424 , the cargo placement height of the cargo placement plane is obtained according to the point cloud cluster size that meets the cargo placement plane identification requirements.

[0108] It can be understood that if the point cloud cluster size of the cut point cloud layer meets the requirements for identifying the cargo placement plane, then the point cloud layer plane where the cut point cloud layer is located is the cargo placement plane.

[0109] Step 426 , controlling the body and clamping arm of the transport equipment to perform adaptive adjustments based on the relative position information and the height of the cargo placement plane, and controlling the transport equipment to place the cargo on the upper surface of the target shelf guide rail to complete the cargo placement task.

[0110] It can be understood that if the cargo placement plane is not identified, a first operation signal can be generated to control the handling equipment to cancel the cargo placement operation.

[0111] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0112] Based on the same inventive concept, embodiments of the present application also provide a cargo placement control device for implementing the aforementioned cargo placement control method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the cargo placement control device provided below can be found in the aforementioned limitations of the cargo placement control method and will not be further elaborated here.

[0113] In some embodiments, as Figure 5 As shown, a cargo placement control device is provided, comprising: a laser scanning module 502, a data processing module 504 and a placement control module 506, wherein:

[0114] A laser scanning module 502 is configured to obtain first point cloud data obtained by laser scanning the front surface of a target shelf rail;

[0115] A data processing module 504 is configured to determine relative position information of the target shelf rail relative to the handling equipment based on the first point cloud data;

[0116] The laser scanning module 502 is further configured to perform laser scanning on the upper surface of the target shelf rail to obtain second point cloud data;

[0117] The data processing module 504 is further configured to determine a cargo placement plane corresponding to the target shelf rail based on the second point cloud data;

[0118] The placement control module 506 performs cargo placement control processing on the handling equipment according to the relative position information and the cargo placement plane.

[0119] The present application uses the above-mentioned cargo placement control device to obtain first point cloud data obtained by laser scanning the front surface of the target shelf rail; determine the relative position information of the target shelf rail compared to the handling equipment based on the first point cloud data; obtain second point cloud data obtained by laser scanning the upper surface of the target shelf rail; determine the cargo placement plane corresponding to the target shelf rail based on the second point cloud data; and perform cargo placement control processing on the handling equipment based on the relative position information and the cargo placement plane. Before the handling equipment directly places the cargo, the present application performs two laser scans on the target shelf rail and processes the scanned point cloud data to determine the relative position information of the target shelf rail compared to the handling equipment and the cargo placement plane corresponding to the target cargo placement rail. Based on the relative position information and the cargo placement plane, the handling equipment is controlled to accurately place the cargo on the upper surface of the target rail, thereby improving the reliability of cargo placement.

[0120] In some embodiments, the data processing module 504 includes a point cloud slicing unit and a plane recognition unit. The multi-point cloud slicing unit is used to perform point cloud slicing processing based on the second point cloud data to obtain a cut point cloud layer; the plane recognition unit is used to determine the corresponding cargo plane of the target shelf rail based on multiple cut point cloud layers.

[0121] In some embodiments, the point cloud slicing unit is also used to obtain the highest scanning parameter and the lowest scanning parameter; the highest scanning parameter is determined by the highest scanning surface obtained by laser scanning the upper surface of the target shelf guide rail, and the lowest scanning parameter is determined by the lowest scanning surface obtained by laser scanning the upper surface of the target shelf guide rail; based on the highest scanning parameter and the lowest scanning parameter, the target point cloud area is determined from the area where the second point cloud data is located; the point cloud data in the target point cloud area is subjected to point cloud slicing processing to obtain multiple cut point cloud layers.

[0122] In some embodiments, there are multiple cutting point cloud layers, and the cargo placement plane is determined from the point cloud layer planes where the multiple cutting point cloud layers are located. The plane identification unit is also used to select the current cutting point cloud layer layer by layer from the multiple cutting point cloud layers, and perform cargo placement plane identification on the current point cloud layer plane where the current cutting point cloud layer is located; if it is identified that the current point cloud layer plane is not the cargo placement plane, the next cutting point cloud layer is used as the new current cutting point cloud layer, and the iterative execution is returned to perform cargo placement plane identification on the current point cloud layer plane where the current cutting point cloud layer is located to determine the point cloud layer plane that belongs to the cargo placement plane.

[0123] In some embodiments, the plane identification unit is also used to cluster the layer point cloud data in the current cutting point cloud layer to obtain multiple point cloud cluster blocks; determine a bounding box used to enclose the multiple point cloud cluster blocks; determine the point cloud cluster size corresponding to the current cutting point cloud layer based on the size of the bounding box; and perform cargo plane identification on the current point cloud layer plane where the current cutting point cloud layer is located based on the point cloud cluster size.

[0124] In some embodiments, the placement control module 506 is further configured to generate a first operation signal to control the handling equipment to cancel the cargo placement operation if it is identified that the point cloud layer planes where the multiple cut point cloud layers are located do not belong to the cargo placement plane.

[0125] In some embodiments, the placement control module 506 is also used to determine the cargo placement height corresponding to the cargo placement plane; the cargo placement height is the actual height used by the handling equipment to lift the cargo to be placed to perform the cargo placement operation; a second operation signal is generated based on the relative position information and the cargo placement height; the second operation signal is sent to the handling equipment so that the handling equipment adjusts its posture according to the second operation signal to place the cargo to be placed on the upper surface of the target shelf rail.

[0126] Each module in the cargo placement control device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor within a computer device in hardware form, or stored in a computer device memory in software form, allowing the processor to call and execute the corresponding operations of each module.

[0127] In some embodiments, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor, memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store point cloud data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a cargo placement control method is implemented.

[0128] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0129] In some embodiments, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0130] In some embodiments, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0131] In some embodiments, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0132] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0133] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0134] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A cargo placement control method, characterized in that: The method comprises: Acquire first point cloud data obtained by laser scanning a front surface of a target rack rail of a shuttle rack, wherein the shuttle rack includes multiple layers of rack rails, and the target rack rail is a rail at one end of one layer of the shuttle rack; Determine relative position information of the target shelf guide rail relative to the handling equipment based on the first point cloud data; Obtaining second point cloud data by performing laser scanning on the upper surface of the target shelf guide rail; Obtain a maximum scanning parameter and a minimum scanning parameter; the maximum scanning parameter is determined by a maximum scanning surface obtained by laser scanning the upper surface of the target shelf guide rail, and the minimum scanning parameter is determined by a minimum scanning surface obtained by laser scanning the upper surface of the target shelf guide rail; the maximum scanning parameter is the difference between the height of the maximum scanning surface and the height of the upper surface of the target shelf guide rail, and the maximum scanning surface represents the highest plane where the second point cloud data is located; the minimum scanning parameter is the difference between the height of the minimum scanning surface and the height of the upper surface of the target shelf guide rail, and the minimum scanning surface represents the lowest plane where the second point cloud data is located; determining a target point cloud region from a region where the second point cloud data is located according to the highest scanning parameter and the lowest scanning parameter; Performing point cloud layer slicing processing on the point cloud data in the target point cloud area to obtain a cut point cloud layer; Determine the cargo placement plane corresponding to the target shelf rail according to the cutting point cloud layer; According to the relative position information and the cargo placement plane, the cargo is placed on the cargo placement plane by the handling equipment, so that the target shelf guide rail transports the cargo for placement.

2. The method according to claim 1, characterized in that There are multiple cutting point cloud layers, and the cargo placement plane is determined from the point cloud layer planes where the multiple cutting point cloud layers are located; The determining the cargo placement plane corresponding to the target shelf rail according to the cutting point cloud layer includes: Selecting a current cutting point cloud layer from the plurality of cutting point cloud layers layer by layer, and performing cargo placement plane identification on the current point cloud layer plane where the current cutting point cloud layer is located; If it is identified that the current point cloud layer plane is not a cargo placement plane, the next cutting point cloud layer is used as the new current cutting point cloud layer, and the iterative execution of the cargo placement plane identification on the current point cloud layer plane where the current cutting point cloud layer is located is returned to determine the point cloud layer plane that belongs to the cargo placement plane.

3. The method according to claim 2, characterized in that The identifying of the cargo placement plane on the current point cloud layer plane where the current cutting point cloud layer is located includes: Clustering the layer point cloud data in the current cutting point cloud layer to obtain a plurality of point cloud cluster blocks; Determining a bounding box for enclosing the plurality of point cloud cluster blocks; Determining the point cloud cluster size corresponding to the current cut point cloud layer according to the size of the bounding box; A cargo placement plane is identified on a current point cloud layer plane where the current cut point cloud layer is located based on the point cloud cluster size.

4. The method according to claim 2, characterized in that The method further comprises: If it is identified that the point cloud layer planes where the multiple cut point cloud layers are located do not belong to the cargo placement plane, a first operation signal is generated to control the handling equipment to cancel the cargo placement operation.

5. The method according to any one of claims 1 to 4, characterized in that The step of performing cargo placement control processing on the handling equipment according to the relative position information and the cargo placement plane includes: Determine a cargo placement height corresponding to the cargo placement plane; the cargo placement height is the actual height at which the handling equipment is used to lift the cargo to be placed to perform the cargo placement operation; generating a second operation signal according to the relative position information and the cargo placement height; The second operation signal is sent to the transport device, so that the transport device adjusts its posture according to the second operation signal to place the goods to be placed on the upper surface of the target shelf rail.

6. A cargo placement control device, characterized in that: The device comprises: a laser scanning module for acquiring first point cloud data obtained by laser scanning a front surface of a target rack rail of a shuttle rack, wherein the shuttle rack includes multiple layers of rack rails, and the target rack rail is a rail at one end of one layer of the shuttle rack; a data processing module, configured to determine relative position information of the target shelf rail relative to the handling equipment based on the first point cloud data; The laser scanning module is further used to obtain second point cloud data by performing laser scanning on the upper surface of the target shelf rail; a point cloud slicing unit, configured to obtain a maximum scanning parameter and a minimum scanning parameter; the maximum scanning parameter is determined by a maximum scanning surface obtained by laser scanning the upper surface of the target shelf guide rail, and the minimum scanning parameter is determined by a minimum scanning surface obtained by laser scanning the upper surface of the target shelf guide rail; a target point cloud area is determined from an area where the second point cloud data is located based on the maximum scanning parameter and the minimum scanning parameter; point cloud slicing is performed on the point cloud data in the target point cloud area to obtain a cut point cloud layer; the maximum scanning parameter is a difference between a height of the maximum scanning surface and a height of the upper surface of the target shelf guide rail, and the maximum scanning surface represents a maximum plane where the second point cloud data is located; the minimum scanning parameter is a difference between a height of the minimum scanning surface and a height of the upper surface of the target shelf guide rail, and the minimum scanning surface represents a minimum plane where the second point cloud data is located; A plane recognition unit, configured to determine a cargo placement plane corresponding to the target shelf rail according to the cutting point cloud layer; The placement control module places the goods on the cargo placement plane through the handling equipment according to the relative position information and the cargo placement plane, so that the target shelf guide rail transports the goods for placement.

7. The device according to claim 6, characterized in that There are multiple cutting point cloud layers, and the cargo placement plane is determined from the point cloud layer planes where the multiple cutting point cloud layers are located; The plane recognition unit is further configured to select a current cutting point cloud layer from the plurality of cutting point cloud layers layer by layer, and perform cargo placement plane recognition on the current point cloud layer plane where the current cutting point cloud layer is located; If it is identified that the current point cloud layer plane is not a cargo placement plane, the next cutting point cloud layer is used as the new current cutting point cloud layer, and the iterative execution of the cargo placement plane identification on the current point cloud layer plane where the current cutting point cloud layer is located is returned to determine the point cloud layer plane that belongs to the cargo placement plane.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images