Case sorting method, device and equipment for robot palletizing and medium

Abstract

Embodiments of the present application disclose a box sorting method, device, equipment and medium for robot stacking. The method comprises: acquiring position information corresponding to at least two boxes in a stacking scene; determining an initial adjacent relationship result list between the boxes according to an adjacent relationship strategy; performing fine-grained adjacent relationship division between the boxes based on the center coordinate information corresponding to each box to obtain a divided target adjacent relationship result list; and sorting each box in the target adjacent relationship result list based on a preset box sorting rule to obtain a box sorting result, so that the robot performs placement and sorting of the boxes according to the box sorting result. Through the above technical solution, the efficiency of robot stacking can be improved, the risk of collision between boxes can be effectively reduced, the damage and maintenance cost can be reduced, the reliable operation of the automated warehousing system can be ensured, and the overall efficiency and reliability can be improved.

Description

Technical Field

[0001] This invention relates to the field of palletizing technology for robotic handling, and more particularly to a method, apparatus, device, and storage medium for sorting boxes for robotic palletizing. Background Technology

[0002] Robotic palletizing is an automated material handling technology widely used in warehousing and logistics. Its core objective is to use a robotic system to arrange boxes of different pallet types, set via a software interface, in an orderly manner according to specific rules. While this technology has significantly improved warehouse management efficiency, it has also brought a series of challenges, one of the most notable being the potential collision problem between adjacent boxes.

[0003] In palletizing, a robotic system typically receives a signal indicating the arrival of boxes on a conveyor belt. The robot then moves its end effector tray above the box to pick it up and place it on the pallet according to its pre-set position. To prevent collisions caused by misjudging the box placement order, the placement order for different pallet types needs to be manually set in the software interface beforehand. When switching between multiple pallet types, the placement order for each type needs to be manually planned, increasing maintenance costs and the risk of collisions due to improper settings. Summary of the Invention

[0004] In view of this, the present invention provides a method, apparatus, device and storage medium for sorting boxes for robotic palletizing, which can improve the efficiency of robotic palletizing, effectively reduce the risk of collision between boxes, reduce damage and maintenance costs, provide a guarantee for the reliable operation of automated warehousing systems, and improve overall efficiency and reliability.

[0005] According to one aspect of the present invention, an embodiment of the present invention provides a box sorting method for robotic palletizing, the method comprising:

[0006] Obtain the location information of at least two boxes in a pre-built palletizing scene;

[0007] An initial proximity result list between each box is determined according to a pre-configured proximity strategy; wherein the proximity strategy is determined based on the location information corresponding to each of the at least two boxes.

[0008] Based on the center coordinate information corresponding to each box, the initial proximity result list is divided into fine-grained proximity relationships between each box to obtain the target proximity result list after division.

[0009] Based on the preset box sorting rules, each box in the target proximity result list is arranged and sorted to obtain the box sorting result. The box sorting result is then transmitted to the robot so that the robot can perform the arrangement and sorting of each box according to the box sorting result.

[0010] According to another aspect of the present invention, embodiments of the present invention also provide a box sorting device for robotic palletizing, the device comprising:

[0011] The acquisition module is used to acquire the location information of at least two boxes contained in a pre-built palletizing scene.

[0012] An initial relationship determination module is used to determine an initial proximity relationship result list between each of the boxes according to a pre-configured proximity relationship strategy; wherein, the proximity relationship strategy is formulated based on the location information corresponding to each of the at least two boxes;

[0013] The target relationship determination module is used to perform fine-grained neighbor relationship division between each box based on the center coordinate information corresponding to each box in the initial neighbor relationship result list, so as to obtain the divided target neighbor relationship result list;

[0014] The sorting module is used to sort each box in the target proximity result list based on a preset box sorting rule, obtain the box sorting result, and transmit the box sorting result to the robot so that the robot can perform the placement and sorting of each box according to the box sorting result.

[0015] According to another aspect of the present invention, embodiments of the present invention also provide an electronic device, the electronic device comprising:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the box sorting method for robotic palletizing according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, embodiments of the present invention also provide a computer-readable storage medium storing computer instructions for causing a processor to execute and implement the box sorting method for robot palletizing as described in any embodiment of the present invention.

[0020] The technical solution of this invention, through the position information corresponding to at least two boxes in the palletizing scenario, can accurately track the position of each box during the entire robotic palletizing process, providing a foundation for subsequent box sorting. Secondly, it first determines the initial proximity relationship between boxes using a proximity strategy. Based on this, it further refines the initial proximity relationship between boxes using the center coordinate information corresponding to each box, obtaining the target proximity relationship. Then, it sorts each box in the target proximity relationship result list based on a preset box sorting rule, fully considering the vertical, horizontal, and vertical proximity relationships between boxes and arranging them in an orderly manner according to certain principles, achieving intelligent sorting. This eliminates the need for manual setting of the placement order of boxes of different pallet types on the software interface, effectively optimizing the robotic palletizing operation, reducing the probability of collisions, improving palletizing efficiency, significantly reducing damage and maintenance costs, providing important assurance for the reliable operation of automated warehousing systems, bringing substantial benefits to the warehousing and logistics industry, and improving overall efficiency and reliability.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 A schematic diagram illustrating the problems with existing technologies in the palletizing process for boxes;

[0024] Figure 2 A flowchart of a box sorting method for robot palletizing is provided in one embodiment of the present invention;

[0025] Figure 3 This is a reference diagram illustrating a rectangular coordinate system established with the origin of the stack plate as the reference point, according to an embodiment of the present invention.

[0026] Figure 4 This is a schematic diagram of the coordinate information of a box after establishing a rectangular coordinate system with the origin of the stack as the reference point, according to an embodiment of the present invention.

[0027] Figure 5 This is a schematic diagram illustrating the adjacency relationship of each box in a palletizing scenario according to an embodiment of the present invention;

[0028] Figure 6 A flowchart of another box sorting method for robot palletizing provided in an embodiment of the present invention;

[0029] Figure 7 This is a schematic diagram illustrating a rough method for finding the proximity relationship between each box and its neighboring boxes, provided as an embodiment of the present invention.

[0030] Figure 8 This is a schematic diagram of a coarsely grouped proximity relationship network between boxes according to an embodiment of the present invention;

[0031] Figure 9 A schematic diagram illustrating a fine-grained proximity relation partitioning method provided in an embodiment of the present invention;

[0032] Figure 10 This is a schematic diagram of the inter-box proximity relationship network after fine-grained proximity relationship division and group neighbor relationship provided in an embodiment of the present invention;

[0033] Figure 11 This is a schematic diagram illustrating a sorting process for boxes according to an embodiment of the present invention;

[0034] Figure 12 This is a schematic diagram illustrating the sorted box order provided in one embodiment of the present invention;

[0035] Figure 13 This is a schematic diagram of yet another box sorting method for robot palletizing provided in an embodiment of the present invention;

[0036] Figure 14 This is a structural block diagram of a box sorting device for robotic palletizing provided in an embodiment of the present invention;

[0037] Figure 15 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0038] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0039] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0040] In one embodiment, Figure 1 A schematic diagram illustrating the problems with existing technologies in the palletizing process, such as... Figure 1 In the scenario where boxes #1, #2, and #3 have already been stacked, when a box is placed between #2 and #3, due to their adjacent positions, box #4 will collide with boxes #2 and #3, causing damage to the items inside.

[0041] In view of this, the embodiments of the present invention can improve the efficiency of robotic palletizing, effectively reduce the risk of collisions between boxes, reduce damage and maintenance costs, provide a guarantee for the reliable operation of automated warehousing systems, and improve overall efficiency and reliability.

[0042] In one embodiment, Figure 2 This is a flowchart of a box sorting method for robot palletizing provided in an embodiment of the present invention. This embodiment is applicable to the case of intelligent box sorting in robot palletizing. The method can be executed by a box sorting device for robot palletizing. The box sorting device for robot palletizing can be implemented in hardware and / or software and can be configured in an electronic device.

[0043] like Figure 2 As shown, the box sorting method for robot palletizing in this embodiment includes the following specific steps:

[0044] S210. Obtain the location information of at least two boxes contained in the pre-built palletizing scene.

[0045] The palletizing scenario can be understood as a virtual scene in which the robot stacks boxes. There can be multiple boxes in this palletizing scenario, and these boxes can form different stack rows. This implementation does not limit the number of boxes in the scenario.

[0046] In this embodiment, the location information can be understood as the coordinate information corresponding to each box in the palletizing scenario. The coordinate information can include the coordinate information of the upper left corner, the lower right corner, the lower left corner, and the upper right corner of each box. It can be understood that each box corresponds to the corresponding coordinate information, and the coordinate information can be established in a two-dimensional coordinate system with the origin of the pallet as the reference point.

[0047] In one embodiment, the palletizing scene establishes a two-dimensional coordinate system with the pallet origin as the reference point; the palletizing scene has four boundaries, namely the upper boundary, lower boundary, left boundary and right boundary; each box corresponds to a unique box identifier;

[0048] The location information corresponding to at least two boxes includes: the coordinates of the top left corner and the bottom right corner of each box, as well as the coordinates of the bottom left corner and the top right corner of each box.

[0049] In this embodiment, the palletizing scene can be geometrically modeled manually. The established model uses a Cartesian coordinate system with the origin of the pallet as the reference point. This Cartesian coordinate system has certain boundaries, which can be defined manually, including an upper boundary, a lower boundary, a left boundary, and a right boundary. In the established model, each box corresponds to a unique box identifier. The position information corresponding to at least two boxes includes: the coordinates of the upper left corner, the lower right corner, the lower left corner, and the upper right corner of each box. After establishing the Cartesian coordinate system, the position information corresponding to each box in the pre-constructed palletizing scene can be obtained. After establishing the coordinate system, the coordinate information of each box in the coordinate system can be directly obtained. This position information represents the coordinate information of each box in the scene coordinate system, which can accurately track the position of each box during the entire robot palletizing process, providing a basis for subsequent box sorting.

[0050] In this embodiment, to facilitate a better understanding of the geometric modeling of the palletizing scenario, Figure 3 This is a reference diagram illustrating a rectangular coordinate system established with the origin of the stack plate as the reference point, as provided in an embodiment of the present invention. Figure 3 As shown, the origin O0 is the intersection point of the stack boundaries and also the center of the robot base, allowing for the stacking of different shapes. The upper boundary is defined as boundary D4, and the middle interval is boundary D3. Boundaries D3 and D4 have physical spatial limits. The left and right boundaries of the stack are defined as D1, and the lower boundary is defined as D2. The suction cup at the robot's end effector picks up each box at its center, enabling gripping and placement. Figure 3 The rectangles arranged in the diagram represent each box. Figure 3 Establish a Cartesian coordinate system based on the D4 boundary, D3 boundary, and point O0, and instantiate the boxes on the pallet as follows: Figure 4 As shown, Figure 4 This is a schematic diagram illustrating the coordinate information of a box after establishing a rectangular coordinate system with the origin of the stack as the reference point, according to an embodiment of the present invention. Figure 4 The coordinates of the top left and bottom right points of the box in the diagram are denoted as (x, y, y). min ,y min ) and (x max ,y max The unique identifier for this box is represented by the string UUID, where x min Represented as the minimum value of the box along the x-axis, y min Let x represent the minimum value of this box along the y-axis; max Represented as the maximum value of the box along the x-axis; y max This represents the maximum value of the box along the y-axis.

[0051] In this embodiment, for each box in the palletizing scenario, a pre-established proximity table is defined for any box and its surrounding boxes, consisting of: left neighbor, right neighbor, top neighbor, and bottom neighbor. These four proximity relationships are used to store the identifiers of neighboring boxes, the location information of neighboring boxes, or the D1, D2, D3, and D4 boundaries. For example, to facilitate a better understanding of the adjacency relationships of each box in the palletizing scenario, Figure 5 This is a schematic diagram illustrating the adjacency relationship of each box in a palletizing scenario according to an embodiment of the present invention. It is assumed that... Figure 5 The UUID of all boxes is represented by the numerical value in bold.

[0052] S220. Determine the initial proximity result list between each box according to the pre-configured proximity relationship strategy; wherein, the proximity relationship strategy is determined based on the location information corresponding to at least two boxes respectively.

[0053] The proximity strategy can be understood as the strategy for determining the adjacency relationships between boxes that are related to each other on the left, right, top, and bottom. This strategy can be defined based on requirements. The initial proximity result list refers to the result list obtained by performing the initial proximity division on each box. This list includes which side of other boxes each box is located on, or which boundary of D1, D2, D3, or D4 it is located on.

[0054] In this embodiment, the proximity strategy is determined based on the location information of at least two boxes. This can be understood as selecting a reference box and a candidate box from multiple boxes, and determining the proximity relationship based on the first upper left corner coordinate information and the first lower right corner coordinate information of the selected reference box, as well as the second upper left corner coordinate information and the second lower right corner coordinate information of the selected candidate box. Different proximity relationships will result in different coordinate comparisons. Specifically, the proximity strategy in this embodiment may include, but is not limited to, the following situations: the first minimum X-axis information is greater than or equal to the second minimum X-axis information, and the first minimum X-axis information is less than the second maximum X-axis information; or the first maximum X-axis information is greater than the second minimum X-axis information, and the first maximum X-axis information is less than or equal to the second maximum X-axis information, indicating a vertical relationship between the boxes; the first minimum Y-axis information is greater than or equal to the second minimum Y-axis information, and the first minimum Y-axis information is less than the second maximum Y-axis information; or the first maximum Y-axis information is greater than the second minimum Y-axis information, and the first maximum Y-axis information is less than or equal to the second maximum Y-axis information, indicating a horizontal relationship between the boxes; the first minimum Y-axis information is greater than the second maximum Y-axis information, indicating an upper proximity relationship between the boxes; the first maximum Y-axis information is less than the second minimum Y-axis information, indicating a lower proximity relationship between the boxes; the first minimum X-axis information is greater than the second maximum X-axis information, indicating a left proximity relationship between the boxes; the first maximum X-axis information is less than the second minimum X-axis information, indicating a right proximity relationship between the boxes, and so on.

[0055] In this embodiment, each box has a certain proximity relationship. For all boxes included in the palletizing scenario, any box can be taken as the reference box, and the other boxes can be taken as candidate boxes. The proximity relationship between the reference box and other candidate boxes is calculated. The proximity relationship can include vertical proximity, horizontal proximity, or a defined boundary. Then, another reference box is found by traversal, and the other boxes are taken as candidate boxes to calculate the proximity relationship between the reference box and other candidate boxes. This process is repeated for the remaining boxes until all boxes are taken. In some embodiments, the box information can also be put into a dynamic box queue in sequence to establish an information table, find available gaps to place boxes, find all gaps that can accommodate the box in the information table, and use the gaps as the proximity relationship between boxes. This embodiment does not impose any restrictions on this.

[0056] S230. Based on the center coordinate information corresponding to each box, the initial proximity result list is divided into fine-grained proximity relationships between each box to obtain the target proximity result list after division.

[0057] The center coordinate information refers to the coordinates of the center point of the box. These center coordinates can be determined by the box's position information. Optionally, they can be determined by the coordinates of the box's upper left and lower right corners, or the coordinates of the box's lower left and upper right corners.

[0058] In this embodiment, the target proximity result list can be understood as a proximity result list obtained by further refining the initial proximity result list. The target proximity result list specifically includes whether the proximity relationship between boxes is an upper proximity relationship, a lower proximity relationship, a left proximity relationship, a right proximity relationship, or a proximity boundary. Each box in this embodiment has a corresponding proximity result table, and the proximity relationship corresponding to each box can be stored in the proximity result table corresponding to each box. Of course, in addition to including the proximity relationship between boxes, it also includes the coordinate information of the neighboring boxes and the unique identifier of the box.

[0059] In this embodiment, each box corresponds to a specific center coordinate. The initial neighbor relationship result list can be further divided into fine-grained neighbor relationships using the center coordinates of each box, resulting in a target neighbor relationship result list for each box. Specifically, for each box, the distance of the box's center coordinates from the origin of the stack in the Y or X direction is determined. Based on this distance, the nearest boxes in the positive Y-axis, negative Y-axis, positive X-axis, and negative X-axis directions are found, while boxes at other distances are discarded. This yields a fine-grained neighbor relationship result list for each box, which is then used as the final target neighbor relationship result list.

[0060] S240. Based on the preset box sorting rules, each box in the target proximity result list is sorted to obtain the box sorting result, and the box sorting result is transmitted to the robot so that the robot can perform the placement and sorting of each box according to the box sorting result.

[0061] The preset box sorting rules can include multiple box sorting rules, which may include, but are not limited to, sorting boxes in the X-axis direction before boxes in the Y-axis direction, or sorting boxes in the Y-axis direction before boxes in the X-axis direction.

[0062] In this embodiment, for each box in the target proximity result list, the distance between the center coordinates of each box and the origin of the stack can be calculated first. Based on this distance, the target box closest to the origin of the stack is determined. Other boxes adjacent to the target box are found and sorted according to a certain sorting rule. According to a preset box retrieval strategy, boxes that meet the preset requirements are placed into the sorted box queue. The next target box is selected from the other boxes in the sorted box queue. This process continues until all boxes in the target proximity result list have been traversed, and the box sorting result corresponding to all boxes is obtained. The box sorting result is then transmitted to the robot so that the robot can perform the placement and sorting of each box according to the box sorting result. In one embodiment, the box sorting result can also be determined by other methods, which are not limited in this embodiment.

[0063] The technical solution of this invention, through the position information corresponding to at least two boxes in the palletizing scenario, can accurately track the position of each box during the entire robotic palletizing process, providing a foundation for subsequent box sorting. Secondly, it first determines the initial proximity relationship between boxes using a proximity strategy. Based on this, it further refines the initial proximity relationship between boxes using the center coordinate information corresponding to each box, obtaining the target proximity relationship. Then, it sorts each box in the target proximity relationship result list based on a preset box sorting rule, fully considering the vertical, horizontal, and vertical proximity relationships between boxes and arranging them in an orderly manner according to certain principles, achieving intelligent sorting. This eliminates the need for manual setting of the placement order of boxes of different pallet types on the software interface, effectively optimizing the robotic palletizing operation, reducing the probability of collisions, improving palletizing efficiency, significantly reducing damage and maintenance costs, providing important assurance for the reliable operation of automated warehousing systems, bringing substantial benefits to the warehousing and logistics industry, and improving overall efficiency and reliability.

[0064] In one embodiment, Figure 6 This is a flowchart of another box sorting method for robotic palletizing provided by an embodiment of the present invention. Based on the above embodiments, this embodiment further refines the risk control measures by determining an initial proximity result list between boxes according to a pre-configured proximity relationship strategy, dividing the initial proximity result list into fine-grained proximity relationships between boxes based on the center coordinate information corresponding to each box, and obtaining a target proximity result list after division; and by placing and sorting each box in the target proximity result list according to a preset box sorting rule.

[0065] like Figure 6As shown, the box sorting method for robot palletizing in this embodiment may specifically include the following steps:

[0066] S610. Obtain the location information of at least two boxes contained in the pre-built palletizing scene.

[0067] S620: Select any one box from all the boxes contained in the palletizing scene as the base box.

[0068] In this embodiment, for all boxes included in the palletizing scenario, any one box is selected as the reference box. The reference box can be understood as the reference box selected from all boxes. During each traversal, one box is selected as the reference box, and the other boxes are selected as candidate boxes.

[0069] S630: Set the reference box as the current reference box, and the other boxes as candidate boxes. Randomly select one candidate box from the candidate boxes as the current candidate box.

[0070] In this embodiment, since there is a traversal process, a base box is selected each time. Therefore, the selected base box can be used as the current base box, and the other boxes can be used as candidate boxes. The candidate boxes are the boxes other than the base box. There are multiple candidate boxes, and any candidate box can be selected as the current candidate box.

[0071] S640. Determine the first proximity relationship between the current candidate box and the current reference box according to the preset first box proximity relationship strategy.

[0072] In this embodiment, the preset first box proximity strategy may include a top-bottom proximity strategy and a left-right proximity strategy. The first proximity relationship includes either a top-bottom proximity relationship or a left-right proximity relationship.

[0073] In this embodiment, the vertical or horizontal proximity relationship between the current candidate box and the current reference box can be determined based on the vertical proximity strategy and the horizontal proximity strategy. Specifically, the first proximity relationship between the current candidate box and the current reference box can be determined based on the first upper left corner coordinate information and the first lower right corner coordinate information corresponding to the current reference box, as well as the second upper left corner coordinate information and the second lower right corner coordinate information corresponding to the current candidate box.

[0074] In one embodiment, S640 may include S6401 to S6403, as follows:

[0075] S6401. Obtain the coordinate information of the first upper left corner and the first lower right corner corresponding to the current reference box, as well as the coordinate information of the second upper left corner and the second lower right corner corresponding to the current candidate box.

[0076] The first upper left corner coordinate information includes the first minimum X-axis information and the first minimum Y-axis information; the first lower right corner coordinate information includes the first maximum X-axis information and the first maximum Y-axis information; the second upper left corner coordinate information includes the second minimum X-axis information and the second minimum Y-axis information; and the second lower right corner coordinate information includes the second maximum X-axis information and the second maximum Y-axis information.

[0077] In this embodiment, the first upper-left corner coordinates and the first lower-right corner coordinates of the current reference box are obtained, as well as the second upper-left corner coordinates and the second lower-right corner coordinates of the current candidate box. For example, the first upper-left corner coordinates of the current reference box... and the coordinates of the first bottom right corner And the coordinates of the second top-left corner of the current candidate box. Second bottom right corner coordinate information in, This is represented as the minimum value of the current reference box along the x-axis; This represents the minimum value of the current reference box along the y-axis; This represents the maximum value of the current reference box along the x-axis; This represents the maximum value of the current reference box along the y-axis; This is represented as the minimum value of the current candidate bin along the x-axis; This is represented as the minimum value of the current candidate bin along the y-axis; This represents the maximum value of the current candidate bin along the x-axis; This represents the maximum value of the current candidate bin along the y-axis.

[0078] S6402. Under the condition of satisfying the preset first condition, determine that the first proximity relationship between the current candidate box and the current reference box is that there is an upper and lower relationship.

[0079] The preset first condition includes: the first minimum X-axis information is greater than or equal to the second minimum X-axis information, and the first minimum X-axis information is less than the second maximum X-axis information; or, the first maximum X-axis information is greater than the second minimum X-axis information, and the first maximum X-axis information is less than or equal to the second maximum X-axis information.

[0080] In this embodiment, if the first minimum X-axis information is greater than or equal to the second minimum X-axis information, and the first minimum X-axis information is less than the second maximum X-axis information; or if the first maximum X-axis information is greater than the second minimum X-axis information, and the first maximum X-axis information is less than or equal to the second maximum X-axis information, then the first proximity relationship between the current candidate box and the current reference box is determined to be an upper / lower relationship. This can be understood as: if the first upper left corner coordinate information of the current reference box... and the coordinates of the first bottom right corner And the coordinates of the second top-left corner of the current candidate box. Second bottom right corner coordinate information Then, in the case of satisfying and Under any one of these conditions, the first proximity relationship between the current candidate box and the current reference box is determined to be that they have an upper and lower relationship.

[0081] S6403. Under the condition of satisfying the preset second condition, determine that the first proximity relationship between the current candidate box and the current reference box is that there is a left-right relationship.

[0082] The preset second condition includes: the first minimum Y-axis information is greater than or equal to the second minimum Y-axis information, and the first minimum Y-axis information is less than the second maximum Y-axis information; or, the first maximum Y-axis information is greater than the second minimum Y-axis information, and the first maximum Y-axis information is less than or equal to the second maximum Y-axis information.

[0083] In this embodiment, if the first minimum Y-axis information is greater than or equal to the second minimum Y-axis information, and the first minimum Y-axis information is less than the second maximum Y-axis information; or if the first maximum Y-axis information is greater than the second minimum Y-axis information, and the first maximum Y-axis information is less than or equal to the second maximum Y-axis information, then the first proximity relationship between the current candidate box and the current reference box is determined to be a left-right relationship. This can be understood as: if the first upper left corner coordinate information of the current reference box... and the coordinates of the first bottom right corner And the coordinates of the second top-left corner of the current candidate box. Second bottom right corner coordinate information Then, in the case of satisfying and Under any one of these conditions, the first proximity relationship between the current candidate box and the current reference box is determined to be a left-right relationship.

[0084] It should be noted that, The conditions for determining the proximity relationship between the upper and lower parts of the tree and the upper and lower parts of the tree. and The left-right proximity relationship determination condition can be a parallel relationship, or one condition can be determined first, followed by the other. The order of determination can be defined manually, and this embodiment does not impose any restrictions. For example, the vertical proximity relationship between the current candidate box and the current reference box is calculated first, and then the left-right proximity relationship between the current candidate box and the current reference box is calculated; this embodiment does not impose any restrictions.

[0085] S650. Determine the second proximity relationship between the current candidate box and the current reference box according to the preset second box proximity relationship strategy, and write the second proximity relationship into the proximity relationship table pre-configured for the current reference box.

[0086] The second proximity relationship includes: upper proximity relationship, lower proximity relationship, left proximity relationship, right proximity relationship, or a custom boundary in the palletizing scenario; the proximity relationship table includes: the proximity relationship between the current candidate box and the current reference box, the box identifier and location information of the current candidate box, or, when the current reference box is adjacent to a custom boundary, the direction of the boundary adjacent to the current reference box is recorded. In this embodiment, the preset second box proximity relationship strategy may include: upper proximity relationship strategy, lower proximity relationship strategy, left proximity relationship strategy, right proximity relationship strategy, or a custom boundary strategy in the palletizing scenario.

[0087] In this embodiment, the second proximity relationship between the current candidate box and the current reference box can be determined based on the upper proximity relationship strategy, lower proximity relationship strategy, left proximity relationship strategy, right proximity relationship strategy, or a custom boundary strategy in the palletizing scenario, and the second proximity relationship is written into the proximity relationship table pre-configured for the current reference box. Specifically, if the first minimum Y-axis information is greater than the second maximum Y-axis information, the current candidate box is determined to be above the current reference box; if the first maximum Y-axis information is less than the second minimum Y-axis information, the current candidate box is determined to be below the current reference box; if the first minimum X-axis information is greater than the second maximum X-axis information, the current candidate box is determined to be to the left of the current reference box; and if the first maximum X-axis information is less than the second minimum X-axis information, the current candidate box is determined to be to the right of the current reference box.

[0088] In one embodiment, S650 may include S6501 to S6504, as follows:

[0089] S6501. If the preset third condition is met, the current candidate box is determined to be above the current reference box. The current candidate box is recorded as the negative Y-axis direction in the proximity relationship table of the current reference box, and the box identifier of the current candidate box is assigned.

[0090] The preset third condition includes: the first minimum Y-axis information is greater than the second maximum Y-axis information.

[0091] In this embodiment, if the first minimum Y-axis information is greater than the second maximum Y-axis information, then the current candidate box is determined to be above the current reference box. The current candidate box is recorded as being in the negative Y-axis direction in the proximity table of the current reference box, and its box identifier is assigned. This can be understood as, when the following conditions are met... Under the condition that the current candidate box is located above the current reference box, the current candidate box is recorded as being in the negative Y-axis direction in the proximity table of the current reference box, and the box identifier of the current candidate box is assigned.

[0092] S6502. If the preset fourth condition is met, the current candidate box is determined to be below the current reference box. The current candidate box is recorded as the positive direction of the Y-axis in the proximity relationship table of the current reference box, and the box identifier of the current candidate box is assigned.

[0093] The fourth preset condition includes: the first maximum Y-axis information is less than the second minimum Y-axis information.

[0094] In this embodiment, if the first maximum Y-axis information is less than the second minimum Y-axis information, then the current candidate box is determined to be below the current reference box. The current candidate box is then recorded as being in the positive Y-axis direction in the proximity table of the current reference box, and its box identifier is assigned. This can be understood as, when the following conditions are met... Under the condition that the current candidate box is located below the current reference box, the current candidate box is recorded as the positive direction of the Y-axis in the proximity table of the current reference box, and the box identifier of the current candidate box is assigned.

[0095] S6503. If the preset fifth condition is met, the current candidate box is determined to be to the left of the current reference box. The current candidate box is recorded as the negative X-axis direction in the proximity relationship table of the current reference box, and the box identifier of the current candidate box is assigned.

[0096] The fifth preset condition includes: the first minimum X-axis information is greater than the second maximum X-axis information.

[0097] In this embodiment, if the first minimum X-axis information is greater than the second maximum X-axis information, then the current candidate box is determined to be to the left of the current reference box. The current candidate box is recorded as being in the negative X-axis direction in the proximity table of the current reference box, and its box identifier is assigned. This can be understood as, when the following conditions are met... Under the condition that the current candidate box is to the left of the current reference box, the current candidate box is recorded as the negative X-axis direction in the proximity table of the current reference box and the box identifier of the current candidate box is assigned.

[0098] S6504. Under the condition of satisfying the preset sixth condition, the current candidate box is determined to be to the right of the current reference box. The current candidate box is recorded as the positive direction of the X-axis in the proximity relationship table of the current reference box and the box identifier of the current candidate box is assigned. The preset sixth condition includes: the first maximum X-axis information is less than the second minimum X-axis information.

[0099] In this embodiment, under the condition that the preset sixth condition is met, the current candidate box is determined to be to the right of the current reference box. The current candidate box is then recorded as being in the positive X-axis direction in the proximity table of the current reference box, and its box identifier is assigned. The preset sixth condition includes: the first maximum X-axis information is less than the second minimum X-axis information. This can be understood as, under the condition that the preset sixth condition is met, the current candidate box is determined to be to the right of the current reference box. Under the condition that the current candidate box is located to the right of the current reference box, the current candidate box is recorded as the positive direction of the X-axis in the proximity relationship table of the current reference box, and the box identifier of the current candidate box is assigned.

[0100] S660. Select the next candidate box from the candidate boxes, use the next candidate box as the current candidate box, return to step S640, and continue until all candidate boxes have been traversed. Obtain the first proximity result list between the current reference box and all candidate boxes, and use each first proximity result list as the initial proximity result list between each box.

[0101] The next candidate box can be understood as either the first one selected arbitrarily as the first next candidate box corresponding to the current candidate box, or the second next candidate box, and so on, until all candidate boxes have been traversed.

[0102] In this embodiment, the next candidate box is selected from the candidate boxes, and the next candidate box is used as the current candidate box. The process returns to the step of determining the first proximity relationship between the current candidate box and the current reference box according to the preset first box proximity relationship strategy, until all candidate boxes have been traversed. A list of first proximity relationship results between the current reference box and all candidate boxes is obtained, and each list of first proximity relationship results is used as the initial proximity relationship result list between each box.

[0103] S670. Select the next reference box from all the boxes in the palletizing scene, set the next reference box as the current reference box, and then return to step S630 until all reference boxes have been traversed.

[0104] The next reference box can be any first selected reference box, or it can be the second reference box, and so on, until all reference boxes have been traversed.

[0105] In this embodiment, the next reference box is selected from all the boxes included in the palletizing scenario, and the next reference box is used as the current reference box. Then, the process is repeated to select the reference box as the current reference box, and the other boxes are used as candidate boxes. The process of arbitrarily selecting a candidate box from the candidate boxes as the current candidate box continues until all reference boxes have been traversed.

[0106] For example, to better understand how to roughly find the proximity relationship between each box and its neighboring boxes, that is, to determine the first proximity relationship between the current candidate box and the current reference box according to a preset first box proximity relationship strategy, Figure 7 This is a schematic diagram illustrating a rough method for finding the proximity relationship between each box and its neighboring boxes, according to an embodiment of the present invention. Figure 8 This is a schematic diagram of a coarsely grouped proximity network between boxes according to an embodiment of the present invention; as shown. Figure 7 As shown, the coordinates of the top left corner of the current reference box. and bottom right corner coordinate information And the coordinates of the top left corner of the current candidate box. and bottom right corner coordinate information There are a total of 8 conditions, of which condition 1 is or Condition 2 is or Condition 5 is or Condition 6 is or Condition 3 is expressed as: Condition 4 is expressed as: Condition 7 is represented as: Condition 8 is represented as: It should be noted that conditions 1, 2, 5 and 6 in this embodiment can be parallel or can be set in a certain order. The order is not restricted and can be set according to the needs. Similarly, conditions 3, 4, 7 and 8 are also set in a certain order, which will not be described in detail in this embodiment.

[0107] like Figure 7 As shown, in this embodiment, the example of determining the vertical proximity relationship first and then the horizontal proximity relationship is used for illustration: The specific steps are as follows:

[0108] a1. Iterate through all boxes, take one box as the base box, and denote it as box A. [1]

[0109] a2. Take out all the remaining boxes, iterate through each box as a candidate box, and mark it as a box. [2]

[0110] a3, Calculation Box [2] With boxes [1] The relationship between boxes is defined as follows: If two boxes satisfy condition 1, they are considered to be in a vertical relationship; otherwise, condition 2 is applied. If condition 2 is met, they are also considered to be in a vertical relationship. If condition 3 is met, then the boxes are considered to be in a vertical relationship. [2] In the box [1] On the upper side of the box[1] Record "Y-" in the proximity relationship and assign it the value of box. [2] The UUID; if condition 4 is met, it means the box... [2] In the box [1] On the lower side of the box [1] Record "Y+" in the proximity relationship and assign it the value of box. [2] UUID.

[0111] a4. Calculation Box [2] With boxes [1] The left-right proximity relationship is defined as follows: if two boxes satisfy condition 5, they are considered to have a left-right relationship; otherwise, condition 6 is applied. If condition 6 is met, a left-right relationship also exists. If condition 7 is met, then the boxes are considered to have a left-right proximity relationship. [2] In the box [1] On the left side, in the box [1] Record "X-" in the proximity relationship and assign it the value of box. [2] The UUID; if condition 8 is met, it means the box... [2] In the box [1] On the right side, in the box [1] Record "X+" in the proximity relationship and assign it the value of "box". [2] UUID.

[0112] a5. During the processes of a3 and a4, when approaching the boundaries of D1, D2, D3, and D4, these boundaries should also be recorded as "D1", "D2", "D3", and "D4" in their respective adjacent directions.

[0113] a6, jump to a2, and repeat for the remaining boxes until all boxes have been taken.

[0114] a7. Go back to step 1 and repeat the process for the remaining boxes until all boxes have been collected.

[0115] S680. Select any box from the initial proximity result list as the current box.

[0116] In this embodiment, any box is randomly selected from the initial proximity result list as the current box.

[0117] S690. Determine the center coordinates of the current box based on the coordinates of the upper left and lower right corners, and determine the first distance of the center coordinates from the origin of the stack in the Y or X direction.

[0118] In this embodiment, the center coordinates of the current box are determined based on the coordinates of the top left corner and the bottom right corner. Specifically, (x-axis coordinate in the top left corner coordinates + x-axis coordinate in the bottom right corner coordinates) / 2 gives the x-axis coordinate of the center of the current box; (y-axis coordinate in the top left corner coordinates + y-axis coordinate in the bottom right corner coordinates) / 2 gives the y-axis coordinate of the center of the current box.

[0119] The first distance refers to the distance of the x-axis coordinate and y-axis coordinate in the center coordinate information from the origin of the stack in the Y-direction or X-direction, respectively.

[0120] In this embodiment, the first distance of the center coordinate information from the origin of the stack in the Y or X direction is determined. Specifically, the difference between the x-axis coordinate and the y-axis coordinate of the center coordinate information and the origin of the stack in the Y or X direction is the first distance of the center coordinate information from the origin of the stack in the Y or X direction.

[0121] S6100: Based on the first distance, find the boxes that have reached the preset distance threshold in the positive Y-axis direction, negative Y-axis direction, positive X-axis direction, and negative X-axis direction, and discard the remaining boxes that have not reached the preset distance threshold to obtain a fine-grained proximity result list corresponding to the current box, and use each fine-grained proximity result list as the target proximity result list after division.

[0122] In this embodiment, based on the first distance, boxes that reach the preset distance thresholds in the positive Y-axis direction, negative Y-axis direction, positive X-axis direction, and negative X-axis direction can be found respectively, and the remaining boxes that do not reach the preset distance thresholds can be discarded to obtain a fine-grained proximity result list corresponding to the current box, and each fine-grained proximity result list is used as the target proximity result list after division.

[0123] S6110: Select the next box from the initial proximity result list, set the next box as the current box, and return to step S690 until all boxes in the initial proximity result list have been traversed.

[0124] The next box can be the first box selected arbitrarily from the initial proximity result list, or it can be the second next box, and so on, until all boxes in the initial proximity result list have been traversed.

[0125] In this embodiment, the next box is selected from the initial proximity result list, and the next box is taken as the current box. The step of determining the center coordinate information of the current box based on the upper left corner coordinate information and lower right corner coordinate information of the current box is returned until all boxes in the initial proximity result list have been traversed.

[0126] For example, in Figure 7 In the rough neighbor network of boxes, it can be seen that multiple boxes exist in an adjacent direction. Therefore, further fine-tuning is needed to satisfy the nearest neighbor relationship and filter out boxes with far neighbor relationships. To facilitate better understanding, a fine-grained neighbor relationship division is performed between each box in the initial neighbor relationship result list. Figure 9 This is a schematic diagram illustrating a fine-grained proximity relationship partitioning method provided in an embodiment of the present invention. Figure 10 This is a schematic diagram of the inter-box proximity relationship network after fine-grained proximity relationship division in an embodiment of the present invention.

[0127] In this embodiment, as Figure 9 As shown, the specific steps for filtering out boxes with far-nearest relationships are as follows:

[0128] b1. Iterate through each box, taking box number 0 as an example (denoted as Box_0).

[0129] b2. Traverse and find all boxes that are adjacent to Box_0, taking the positive Y direction (Y+) as an example.

[0130] b3. Based on the distance of the center coordinate of box 0 from the origin in the Y direction, find the box 1 (denoted as box Box_1) that is closest in the positive Y direction (Y+), and discard the rest of the boxes (box 2 is discarded here).

[0131] b4. Return to b2 and repeat the adjacent unbinding process in the other three directions (Y-, X+, X-).

[0132] b5. Return to b1 and repeat for the remaining boxes until all box bindings have been traversed.

[0133] S6120. Obtain the target proximity result list. For each box in the target proximity result list, use the preset Euclidean distance formula to calculate the second distance between the center coordinate information of each box and the origin of the stack. Based on the second distance, determine the current target box that is closest to the origin of the stack.

[0134] The second distance refers to the distance between the center coordinates of each box and the origin of the stack. The preset Euclidean distance formula is the same as the Euclidean distance formula in the prior art, which will not be explained in detail in this embodiment.

[0135] In this embodiment, a target proximity result list is obtained. For each box in the target proximity result list, a second distance between the center coordinates of each box and the origin of the stack is calculated using a preset Euclidean distance formula. Based on the second distance, a current target box closest to the origin of the stack is determined. It should be noted that there is only one current target box.

[0136] S6130. Based on the target proximity result list, determine other boxes adjacent to the current target box and form a box list with these other boxes.

[0137] In the target proximity result list, each box corresponds to the box identifier of its neighboring boxes, the coordinates of its top left corner and bottom right corner, and whether it is a custom proximity boundary.

[0138] In this embodiment, other boxes adjacent to the current target box can be determined based on the target proximity result list, and these other boxes can be combined into a box list. It can be understood that the target proximity result list includes a proximity table stored for each box. The proximity table includes the box identifier, upper left corner coordinate information, lower right corner coordinate information, and whether it is a custom proximity boundary of the adjacent box.

[0139] S6140. According to the preset first box sorting rule, put the boxes in the box list into the unsorted box queue in order.

[0140] In this embodiment, the boxes in the box list can be placed into the unsorted box queue in order according to a preset first box sorting rule. The preset first box sorting rule includes: sorting according to whether boxes in the X-axis direction are prioritized over boxes in the Y-axis direction, or sorting according to whether boxes in the Y-axis direction are prioritized over boxes in the X-axis direction.

[0141] S6150. For boxes in the unsorted box queue, according to the preset second box sorting rule, put the boxes that meet the preset requirements into the sorted box queue, get the next target box in the sorted box queue, and take the next target box as the current target box. Return to step S5130 until all boxes in the target proximity result list have been traversed.

[0142] In one embodiment, the preset first box sorting rule includes: sorting according to the X-axis direction taking precedence over the Y-axis direction, or sorting according to the Y-axis direction taking precedence over the X-axis direction; the preset second box sorting rule corresponds one-to-one with the preset requirements. When the preset second box sorting rule is to first sort the set of boxes closer to the positive X-axis direction, and then sort the set of boxes closer to the positive Y-axis direction, the preset requirement is that all adjacent boxes in the negative X-axis direction and the negative Y-axis direction have been placed; when the preset second box sorting rule is to first sort the set of boxes closer to the negative Y-axis direction, and then sort the set of boxes closer to the negative X-axis direction, the preset requirement is that all adjacent boxes in the positive X-axis direction and the positive Y-axis direction have been placed.

[0143] In this embodiment, for boxes in the unsorted box queue, boxes that meet the preset requirements are placed into the sorted box queue according to the preset second box sorting rule. The next target box in the sorted box queue is obtained and used as the current target box. The process of determining other boxes adjacent to the current target box based on the target proximity result list and forming a box list with these other boxes is repeated until all boxes in the target proximity result list have been traversed. It should be noted that if the preset requirements are not met, the boxes that do not meet the preset requirements are placed into the target unsorted box queue. The boxes in the target unsorted box queue are then placed into the aforementioned unsorted box queue in order according to the preset first box sorting rule. The process of placing boxes that meet the preset requirements in the unsorted box queue according to the preset second box sorting rule is repeated until all boxes in the second unsorted box queue have been traversed.

[0144] In one embodiment, to facilitate a better understanding of the box sorting process, Figure 11 This is a schematic diagram illustrating a sorting process for boxes according to an embodiment of the present invention. Figure 12 This is a schematic diagram illustrating the sorted box order according to an embodiment of the present invention. The specific steps of the box sorting process are as follows:

[0145] c1. Get the list of boxes (AllBoxes) that have been grouped with neighboring boxes.

[0146] c2. In the AllBoxes list, use Euclidean distance to calculate the distance from the center point (center coordinates) of each box to the origin, and find the box Pre_One (one box) that is closest to the origin (only a single box can be stored).

[0147] c3. Add the box Pre_One from c2 to the sorted box queue SortBoxes.

[0148] c4. Find other boxes adjacent to the box Pre_One at the position closest to the origin to form a list of boxes NearBoxes.

[0149] c5. Sort the list of boxes NearBoxes according to the strategy that the X-axis direction is superior to the Y-axis direction, i.e., in a clockwise arrangement, and insert the sorted array into the UnsortBoxes queue.

[0150] c6. Take out the set of boxes X+_Set close to the positive X direction (X+) from the list of boxes UnsortBoxes.

[0151] c7. Traverse all the boxes in X+_Set, and first find the boxes for which the adjacent boxes in the negative X direction (X-) and the adjacent boxes in the negative Y direction (Y-) have all been placed.

[0152] c8. Add the boxes that meet the conditions in step c7 to the sorted queue of boxes SortBoxes.

[0153] c9. Return to c7 until all the boxes in X+_Set have been traversed.

[0154] c10. Take out the set of boxes Y+_Set close to the positive Y direction (Y+) from the list of boxes UnsortBoxes.

[0155] c11. Traverse all the boxes in Y+_Set, and first find the boxes for which the adjacent boxes in the negative X direction (X-) and the adjacent boxes in the negative Y direction (Y-) have all been placed.

[0156] c12. Add the boxes that meet the conditions in c11 to the sorted queue of boxes SortBoxes.

[0157] c13. Return to c11 until all the boxes in Y+_Set have been traversed.

[0158] c14. Put the boxes that do not meet the conditions (i.e., the boxes that have not been sorted) in c6 and c10 into the UnSortBoxes queue for the next loop to continue participating in the sorting.

[0159] c15. Take out the nth box (1 < n < N - 1, where N is the total number of all boxes in AllBoxes, and n is incremented by 1 after each traversal) from the sorted list of boxes SortBoxes.

[0160] c16. Replace the box obtained in step 9 with Pre_One (which can only store a single box), and repeat c4 to c15 until all the boxes in AllBoxes have been traversed.

[0161] The technical solution of this invention determines the initial proximity relationship between boxes by pre-setting multiple proximity relationship conditions. Based on this, the initial proximity relationship between boxes is further divided into fine-grained proximity relationships using the center coordinate information corresponding to each box, resulting in the target proximity relationship. Each box in the target proximity relationship result list is then sorted according to a pre-set box sorting rule to obtain the box sorting result. This fully considers the top, bottom, left, and right proximity relationships and boundary proximity relationships between boxes, and arranges them in an orderly manner according to a pre-set first box sorting rule and a pre-set second box sorting rule, achieving intelligent sorting. This eliminates the need for manual setting of the placement order of boxes of different stack types on the software interface, effectively optimizing the robot palletizing operation, reducing the probability of collisions, improving palletizing efficiency, and significantly reducing damage and maintenance costs. This provides an important guarantee for the reliable operation of automated warehousing systems, bringing substantial benefits to the warehousing and logistics industry and improving overall efficiency and reliability.

[0162] In one embodiment, to facilitate a better understanding of the box sorting method for robotic palletizing, Figure 13 This is a schematic diagram of yet another box sorting method for robotic palletizing provided in an embodiment of the present invention, as shown below. Figure 13 As shown, the specific steps are as follows:

[0163] d1. Establish a two-dimensional coordinate system XOY with the origin of the stack as the reference point.

[0164] d2. Find the positional relationship between neighboring boxes and determine which side of another box a box is located on.

[0165] d3. Fix a reference box.

[0166] d4. Coarse grouping strategies, including: upper neighbor, lower neighbor, left neighbor, right neighbor, or custom boundaries in the palletizing scenario.

[0167] d5. Fine-grained proximity relationship partitioning strategy.

[0168] d6. Get the list of boxes (AllBoxes) that have been grouped with neighboring boxes.

[0169] d7. Use Euclidean distance to calculate the distance from the center point (center coordinates) of each box to the origin, and find the box Pre_One that is closest to the origin.

[0170] d8. Based on the box Pre_One that is closest to the origin, find its neighboring boxes and form a box list NearBoxes.

[0171] d9. The strategy of prioritizing the X-axis direction over the Y-axis direction (i.e., clockwise arrangement) is used to sort neighboring boxes.

[0172] d10. Retrieve the information for each box and store them in the UnsortBoxes queue according to the strategy of arranging them clockwise, with the X-axis direction taking precedence over the Y-axis direction.

[0173] d11. From the UnsortBoxes list, first take the set of boxes X+_Set that is closest to the positive X direction (X+), then take the set of boxes Y+_Set that is closest to the positive Y direction (Y+).

[0174] d12. If all neighboring boxes in the negative X direction (X-) and the negative Y direction (Y-) have been placed, put the sorted boxes into the sorted box queue.

[0175] d13. If either the neighboring box in the negative X direction (X-) or the neighboring box in the negative Y direction (Y-) has not been placed, return to d10 until both the neighboring boxes in the negative X direction (X-) and the neighboring boxes in the negative Y direction (Y-) have been placed.

[0176] d14. Determine if the AllBoxes list has been traversed. If yes, the process ends; otherwise, get the next box in the sorted box queue and return to d8, until the AllBoxes list has been traversed.

[0177] In one embodiment, Figure 14 This is a structural block diagram of a box sorting device for robotic palletizing, provided in one embodiment of the present invention. This device is suitable for intelligent box sorting during robotic palletizing and can be implemented in hardware or software. It can be configured in an electronic device to implement a box sorting method for robotic palletizing according to an embodiment of the present invention.

[0178] like Figure 14 As shown, the device includes: an acquisition module 1410, an initial relationship determination module 1420, a target relationship determination module 1430, and a sorting module 1440;

[0179] The acquisition module 1410 is used to acquire the location information of at least two boxes contained in the pre-built palletizing scene.

[0180] The initial relationship determination module 1420 is used to determine an initial proximity relationship result list between each of the boxes according to a pre-configured proximity relationship strategy; wherein the proximity relationship strategy is formulated based on the location information corresponding to each of the at least two boxes;

[0181] The target relationship determination module 1430 is used to perform fine-grained neighbor relationship division between each box based on the center coordinate information corresponding to each box in the initial neighbor relationship result list, so as to obtain the divided target neighbor relationship result list.

[0182] The sorting module 1440 is used to sort each box in the target proximity result list according to a preset box sorting rule, obtain the box sorting result, and transmit the box sorting result to the robot so that the robot can perform the placement and sorting of each box according to the box sorting result.

[0183] In this embodiment of the invention, the acquisition module, by using the position information corresponding to at least two boxes in the palletizing scene, can accurately track the position of each box during the entire robot palletizing process, providing a foundation for subsequent box sorting. Secondly, the initial relationship determination module first determines the initial proximity relationships between boxes using a proximity strategy. Based on this, the target relationship determination module uses the center coordinate information corresponding to each box to perform fine-grained proximity relationship division between the initial proximity relationships of each box, obtaining the divided target proximity relationships. Then, based on preset box sorting rules, each box in the target proximity relationship result list is sorted to obtain the box sorting result. Taking full account of the vertical, horizontal, and vertical proximity relationships between boxes, the sorting module arranges them in an orderly manner according to certain principles, achieving an intelligent sorting effect. This eliminates the need for manual setting of the placement order of boxes of different pallet types on the software interface, effectively optimizing the robot palletizing operation, reducing the probability of collisions, improving palletizing efficiency, and significantly reducing damage and maintenance costs. This provides an important guarantee for the reliable operation of automated warehousing systems, bringing substantial benefits to the warehousing and logistics industry, and improving overall efficiency and reliability.

[0184] In one embodiment, the palletizing scene establishes a two-dimensional coordinate system with the pallet origin as the reference point; the palletizing scene has four boundaries, namely the upper boundary, lower boundary, left boundary, and right boundary; each box corresponds to a unique box identifier;

[0185] The location information corresponding to the at least two boxes includes: the upper left corner coordinates and the lower right corner coordinates of each box, as well as the lower left corner coordinates and the upper right corner coordinates of each box.

[0186] In one embodiment, the initial relationship determination module 1420 includes:

[0187] The reference box determination unit is used to select any one box from all the boxes included in the palletizing scenario as the reference box;

[0188] The candidate box determination unit is used to take the reference box as the current reference box, the other boxes as candidate boxes, and arbitrarily select one candidate box from the candidate boxes as the current candidate box.

[0189] The first proximity relationship determination unit is used to determine the first proximity relationship between the current candidate box and the current reference box according to a preset first box proximity relationship strategy; wherein, the first proximity relationship includes: vertical proximity relationship or horizontal proximity relationship;

[0190] The second proximity relationship determination unit is used to determine the second proximity relationship between the current candidate box and the current reference box according to a preset second box proximity relationship strategy, and write the second proximity relationship into a pre-configured proximity relationship table of the current reference box; wherein, the second proximity relationship includes: upper proximity relationship, lower proximity relationship, left proximity relationship, right proximity relationship, or a custom boundary in the palletizing scenario; the proximity relationship table includes: the proximity relationship between the current candidate box and the current reference box, the box identifier and location information of the current candidate box, or, when the current reference box is adjacent to a custom boundary, the direction of the boundary adjacent to the current reference box is recorded;

[0191] The result list determination unit is used to select the next candidate box from the candidate boxes, take the next candidate box as the current candidate box, return to the step of determining the first proximity relationship between the current candidate box and the current reference box according to the preset first box proximity relationship strategy, until all candidate boxes have been traversed, and obtain the first proximity relationship result list between the current reference box and all candidate boxes, and take each first proximity relationship result list as the initial proximity relationship result list between each box;

[0192] The traversal loop unit is used to select the next reference box from all the boxes included in the palletizing scenario, take the next reference box as the current reference box, return the other boxes as candidate boxes, and arbitrarily select a candidate box from the candidate boxes as the current candidate box, until all reference boxes have been traversed.

[0193] In one embodiment, the first proximity determination unit includes:

[0194] An acquisition subunit is used to acquire the first upper-left corner coordinate information and the first lower-right corner coordinate information corresponding to the current reference box, as well as the second upper-left corner coordinate information and the second lower-right corner coordinate information corresponding to the current candidate box; wherein, the first upper-left corner coordinate information includes the first minimum X-axis information and the first minimum Y-axis information; the first lower-right corner coordinate information includes the first maximum X-axis information and the first maximum Y-axis information; the second upper-left corner coordinate information includes the second minimum X-axis information and the second minimum Y-axis information; and the second lower-right corner coordinate information includes the second maximum X-axis information and the second maximum Y-axis information.

[0195] The up-down relationship determination subunit is used to determine that the first proximity relationship between the current candidate box and the current reference box is an up-down relationship when a preset first condition is met; wherein, the preset first condition includes: the first minimum X-axis information is greater than or equal to the second minimum X-axis information, and the first minimum X-axis information is less than the second maximum X-axis information; or, the first maximum X-axis information is greater than the second minimum X-axis information, and the first maximum X-axis information is less than or equal to the second maximum X-axis information;

[0196] The left-right relationship determination subunit is used to determine that the first proximity relationship between the current candidate box and the current reference box is a left-right relationship when a preset second condition is met; wherein, the preset second condition includes: the first minimum Y-axis information is greater than or equal to the second minimum Y-axis information, and the first minimum Y-axis information is less than the second maximum Y-axis information; or, the first maximum Y-axis information is greater than the second minimum Y-axis information, and the first maximum Y-axis information is less than or equal to the second maximum Y-axis information.

[0197] In one embodiment, the second proximity determination unit includes:

[0198] The upper relationship determination subunit is used to determine that the current candidate box is above the current reference box when a preset third condition is met, and to record the current candidate box as being in the negative Y-axis direction in the proximity relationship table of the current reference box and assign a box identifier to the current candidate box; wherein, the preset third condition includes: the first minimum Y-axis information is greater than the second maximum Y-axis information;

[0199] The lower relation determination subunit is used to determine that the current candidate box is below the current reference box when a preset fourth condition is met, and to record the current candidate box as the positive direction of the Y-axis in the proximity relation table of the current reference box and assign the box identifier of the current candidate box; wherein, the preset fourth condition includes: the first maximum Y-axis information is less than the second minimum Y-axis information;

[0200] The left relation determination subunit is used to determine that the current candidate box is to the left of the current reference box when a preset fifth condition is met, and to record the current candidate box as the negative X-axis direction in the proximity relation table of the current reference box and assign the box identifier of the current candidate box; wherein, the preset fifth condition includes: the first minimum X-axis information is greater than the second maximum X-axis information;

[0201] The right relation determination subunit is used to determine that the current candidate box is to the right of the current reference box under the condition of satisfying the preset sixth condition, and to record the current candidate box as the positive X-axis direction in the proximity relation table of the current reference box and assign the box identifier of the current candidate box; wherein, the preset sixth condition includes: the first maximum X-axis information is less than the second minimum X-axis information.

[0202] In one embodiment, the target relationship determination module 1430 includes:

[0203] The center coordinate determination unit is used to select any box from the initial proximity result list as the current box, and determine the center coordinate information of the current box based on the upper left corner coordinate information and lower right corner coordinate information of the current box.

[0204] A distance determination unit is used to determine the first distance in the Y or X direction from the origin of the stack plate of the center coordinate information;

[0205] The result list determination unit is used to find boxes that reach a preset distance threshold in the positive Y-axis direction, negative Y-axis direction, positive X-axis direction, and negative X-axis direction according to the first distance, and discard the remaining boxes that do not reach the preset distance threshold to obtain a fine-grained proximity result list corresponding to the current box, and use each fine-grained proximity result list as the target proximity result list after division.

[0206] The loop unit is used to select the next box from the initial proximity result list, take the next box as the current box, and return to the step of determining the center coordinate information of the current box based on the upper left corner coordinate information and lower right corner coordinate information of the current box, until all boxes in the initial proximity result list have been traversed.

[0207] In one embodiment, the preset box sorting rules include: a preset first box sorting rule and a preset second box sorting rule; the sorting module 1440 includes:

[0208] The target box determination unit is used to obtain the target proximity result list, and for each box in the target proximity result list, calculates the second distance between the center coordinate information of each box and the origin of the stack using a preset Euclidean distance formula, and determines the current target box that is closest to the origin of the stack based on the second distance;

[0209] The box list component unit is used to determine other boxes adjacent to the current target box based on the target proximity result list, and to form a box list of the other boxes; wherein, each box in the target proximity result list corresponds to the box identifier, upper left corner coordinate information, lower right corner coordinate information of the adjacent boxes, and whether it is a custom proximity boundary;

[0210] An unsorted box queue forming unit is used to place the boxes in the box list into the unsorted box queue in order according to the preset first box sorting rule;

[0211] The loop unit is used to, for the boxes in the unsorted box queue, put the boxes that meet the preset requirements into the sorted box queue according to the preset second box sorting rule, obtain the next target box in the sorted box queue, and take the next target box as the current target box, and return to the step of determining other boxes adjacent to the current target box based on the target proximity result list, until all boxes in the target proximity result list have been traversed.

[0212] In one embodiment, the preset first box sorting rule includes: sorting boxes according to the X-axis direction being superior to boxes according to the Y-axis direction, or sorting boxes according to the Y-axis direction being superior to boxes according to the X-axis direction;

[0213] The preset second box sorting rule corresponds one-to-one with the preset requirements. When the preset second box sorting rule is to first sort the box set closer to the positive X-axis and then sort the box set closer to the positive Y-axis, the preset requirement is that all adjacent boxes in the negative X-axis direction and the negative Y-axis direction have been placed. When the preset second box sorting rule is to first sort the box set closer to the positive and negative Y-axis direction and then sort the box set closer to the positive and negative X-axis direction, the preset requirement is that all adjacent boxes in the positive X-axis direction and the positive Y-axis direction have been placed.

[0214] The box sorting device for robot palletizing provided in this embodiment of the invention can execute the box sorting method for robot palletizing in the financial system provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0215] In one embodiment, Figure 15 This is a schematic diagram of an electronic device provided for an embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0216] like Figure 15 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0217] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0218] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as a box sorting method for robotic palletizing.

[0219] In some embodiments, the box sorting processing method for robotic palletizing can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the box sorting method for robotic palletizing described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the box sorting method for robotic palletizing by any other suitable means (e.g., by means of firmware).

[0220] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0221] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable container sorting device for robotic palletizing, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0222] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0223] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0224] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0225] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0226] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0227] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A box sorting method for robotic palletizing, characterized in that, include: Obtain the location information of at least two boxes in a pre-built palletizing scene; An initial proximity result list between each box is determined according to a pre-configured proximity strategy; wherein the proximity strategy is determined based on the location information corresponding to each of the at least two boxes. Based on the center coordinate information corresponding to each box, the initial proximity result list is divided into fine-grained proximity relationships between each box to obtain the target proximity result list after division. Based on the preset box sorting rules, each box in the target proximity result list is arranged and sorted to obtain the box sorting result, and the box sorting result is transmitted to the robot so that the robot can perform the arrangement and sorting of each box according to the box sorting result; The preset box sorting rules include: a preset first box sorting rule and a preset second box sorting rule; Accordingly, the process of arranging and sorting each box in the target proximity result list based on a preset box sorting rule to obtain the box sorting result includes: Obtain the target proximity result list. For each box in the target proximity result list, use a preset Euclidean distance formula to calculate the second distance between the center coordinate information of each box and the origin of the stack. Based on the second distance, determine the current target box that is closest to the origin of the stack. Based on the target proximity result list, other boxes adjacent to the current target box are determined, and these other boxes are grouped into a box list; wherein, each box in the target proximity result list corresponds to the box identifier, upper left corner coordinate information, lower right corner coordinate information, and whether it is a custom proximity boundary of the adjacent box; According to the preset first box sorting rule, the boxes in the box list are placed into the unsorted box queue in order; For the boxes in the unsorted box queue, according to the preset second box sorting rule, the boxes that meet the preset requirements are placed into the sorted box queue, and the next target box in the sorted box queue is obtained. The next target box is used as the current target box, and the step of determining other boxes adjacent to the current target box based on the target proximity result list is returned until all boxes in the target proximity result list have been traversed.

2. The method according to claim 1, characterized in that, The palletizing scene establishes a two-dimensional coordinate system with the pallet origin as the reference point; the palletizing scene has four boundaries, namely the upper boundary, lower boundary, left boundary and right boundary; each box corresponds to a unique box identifier; The location information corresponding to the at least two boxes includes: the upper left corner coordinates and the lower right corner coordinates of each box, as well as the lower left corner coordinates and the upper right corner coordinates of each box.

3. The method according to claim 1, characterized in that, The step of determining the initial proximity result list between the boxes according to the pre-configured proximity strategy includes: Take any one box from all the boxes included in the palletizing scenario as the base box; The reference box is used as the current reference box, and the other boxes are used as candidate boxes. Then, a candidate box is randomly selected from the candidate boxes as the current candidate box. The first proximity relationship between the current candidate box and the current reference box is determined according to a preset first box proximity relationship strategy; wherein, the first proximity relationship includes: vertical proximity relationship or horizontal proximity relationship; The second proximity relationship between the current candidate box and the current reference box is determined according to a preset second box proximity relationship strategy, and the second proximity relationship is written into the proximity relationship table pre-configured by the current reference box; wherein, the second proximity relationship includes: upper proximity relationship, lower proximity relationship, left proximity relationship, right proximity relationship, or a custom boundary in the palletizing scenario; the proximity relationship table includes: the proximity relationship between the current candidate box and the current reference box, the box identifier and location information of the current candidate box, or, when the current reference box is adjacent to a custom boundary, the direction of the boundary adjacent to the current reference box is recorded; Select the next candidate box from the candidate boxes, use the next candidate box as the current candidate box, return to the step of determining the first proximity relationship between the current candidate box and the current reference box according to the preset first box proximity relationship strategy, until all candidate boxes have been traversed, obtain the first proximity relationship result list between the current reference box and all candidate boxes, and use each first proximity relationship result list as the initial proximity relationship result list between each box; The process involves selecting the next reference box from all the boxes in the palletizing scenario, using the next reference box as the current reference box, returning the other boxes as candidate boxes, and arbitrarily selecting one candidate box from the candidate boxes as the current candidate box, until all reference boxes have been traversed.

4. The method according to claim 3, characterized in that, The step of determining the first proximity relationship between the current candidate box and the current reference box according to a preset first box proximity relationship strategy includes: Obtain the first top-left corner coordinate information and the first bottom-right corner coordinate information corresponding to the current reference box, as well as the second top-left corner coordinate information and the second bottom-right corner coordinate information corresponding to the current candidate box; wherein, the first top-left corner coordinate information includes the first minimum X-axis information and the first minimum Y-axis information; the first bottom-right corner coordinate information includes the first maximum X-axis information and the first maximum Y-axis information; the second top-left corner coordinate information includes the second minimum X-axis information and the second minimum Y-axis information; the second bottom-right corner coordinate information includes the second maximum X-axis information and the second maximum Y-axis information; Under the condition of satisfying a preset first condition, the first proximity relationship between the current candidate box and the current reference box is determined to be that there is an upper and lower relationship; wherein, the preset first condition includes: the first minimum X-axis information is greater than or equal to the second minimum X-axis information, and the first minimum X-axis information is less than the second maximum X-axis information; or, the first maximum X-axis information is greater than the second minimum X-axis information, and the first maximum X-axis information is less than or equal to the second maximum X-axis information; Under the condition of satisfying the preset second condition, the first proximity relationship between the current candidate box and the current reference box is determined to be a left-right relationship; wherein, the preset second condition includes: the first minimum Y-axis information is greater than or equal to the second minimum Y-axis information, and the first minimum Y-axis information is less than the second maximum Y-axis information; or, the first maximum Y-axis information is greater than the second minimum Y-axis information, and the first maximum Y-axis information is less than or equal to the second maximum Y-axis information.

5. The method according to claim 4, characterized in that, The step of determining the second proximity relationship between the current candidate box and the current benchmark box according to a preset second box proximity relationship strategy, and writing the second proximity relationship into the proximity relationship table pre-configured for the current benchmark box, includes: If a preset third condition is met, the current candidate box is determined to be above the current reference box, and the current candidate box is recorded as being in the negative Y-axis direction in the proximity table of the current reference box, and the box identifier of the current candidate box is assigned a value; wherein, the preset third condition includes: the first minimum Y-axis information is greater than the second maximum Y-axis information; If the preset fourth condition is met, the current candidate box is determined to be below the current reference box, and the current candidate box is recorded as the positive Y-axis direction in the proximity table of the current reference box and the box identifier of the current candidate box is assigned; wherein, the preset fourth condition includes: the first maximum Y-axis information is less than the second minimum Y-axis information; If the preset fifth condition is met, the current candidate box is determined to be to the left of the current reference box, the current candidate box is recorded as being in the negative X-axis direction in the proximity table of the current reference box, and the box identifier of the current candidate box is assigned a value; wherein, the preset fifth condition includes: the first minimum X-axis information is greater than the second maximum X-axis information; If the preset sixth condition is met, the current candidate box is determined to be to the right of the current reference box, and the current candidate box is recorded as the positive X-axis direction in the proximity table of the current reference box and the box identifier of the current candidate box is assigned; wherein, the preset sixth condition includes: the first maximum X-axis information is less than the second minimum X-axis information.

6. The method according to claim 1, characterized in that, The initial proximity result list is divided into fine-grained proximity relationships between the boxes based on the center coordinate information corresponding to each box, resulting in a target proximity result list after division, including: Select any box from the initial proximity result list as the current box; Based on the coordinates of the upper left and lower right corners of the current box, determine the center coordinates of the current box, and determine the first distance of the center coordinates from the origin of the stack in the Y or X direction. Based on the first distance, find the boxes that reach the preset distance threshold in the positive Y-axis direction, negative Y-axis direction, positive X-axis direction, and negative X-axis direction, respectively, and discard the remaining boxes that do not reach the preset distance threshold to obtain a fine-grained proximity result list corresponding to the current box, and use each fine-grained proximity result list as the target proximity result list after division; Select the next box from the initial proximity result list, and use the next box as the current box. Then return to the step of determining the center coordinate information of the current box based on the upper left and lower right corner coordinate information of the current box, until all boxes in the initial proximity result list have been traversed.

7. The method according to claim 1, characterized in that, The preset first box sorting rules include: sorting boxes according to the X-axis direction being superior to boxes according to the Y-axis direction, or sorting boxes according to the Y-axis direction being superior to boxes according to the X-axis direction. The preset second box sorting rule corresponds one-to-one with the preset requirements. When the preset second box sorting rule is to first sort the box set closer to the positive X-axis and then sort the box set closer to the positive Y-axis, the preset requirement is that all adjacent boxes in the negative X-axis direction and the negative Y-axis direction have been placed. When the preset second box sorting rule is to first sort the box set closer to the positive and negative Y-axis direction and then sort the box set closer to the positive and negative X-axis direction, the preset requirement is that all adjacent boxes in the positive X-axis direction and the positive Y-axis direction have been placed.

8. A box sorting device for robotic palletizing, characterized in that, include: The acquisition module is used to acquire the location information of at least two boxes contained in a pre-built palletizing scene. An initial relationship determination module is used to determine an initial proximity relationship result list between each of the boxes according to a pre-configured proximity relationship strategy; wherein, the proximity relationship strategy is formulated based on the location information corresponding to each of the at least two boxes; The target relationship determination module is used to perform fine-grained neighbor relationship division between each box based on the center coordinate information corresponding to each box in the initial neighbor relationship result list, so as to obtain the divided target neighbor relationship result list; The sorting module is used to sort each box in the target proximity result list according to a preset box sorting rule, obtain the box sorting result, and transmit the box sorting result to the robot so that the robot can perform the placement and sorting of each box according to the box sorting result; The preset box sorting rules include: a preset first box sorting rule and a preset second box sorting rule; The sorting module includes: The target box determination unit is used to obtain the target proximity result list, and for each box in the target proximity result list, calculates the second distance between the center coordinate information of each box and the origin of the stack using a preset Euclidean distance formula, and determines the current target box that is closest to the origin of the stack based on the second distance; The box list component unit is used to determine other boxes adjacent to the current target box based on the target proximity result list, and to form a box list of the other boxes; wherein, each box in the target proximity result list corresponds to the box identifier, upper left corner coordinate information, lower right corner coordinate information of the adjacent boxes, and whether it is a custom proximity boundary; An unsorted box queue forming unit is used to place the boxes in the box list into the unsorted box queue in order according to the preset first box sorting rule; The loop unit is used to, for the boxes in the unsorted box queue, put the boxes that meet the preset requirements into the sorted box queue according to the preset second box sorting rule, obtain the next target box in the sorted box queue, and take the next target box as the current target box, and return to the step of determining other boxes adjacent to the current target box based on the target proximity result list, until all boxes in the target proximity result list have been traversed.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, which enables the at least one processor to perform the box sorting method for robotic palletizing as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the box sorting method for robotic palletizing as described in any one of claims 1-7.

Images