Article stacking method and device

Abstract

The invention provides an article stacking method and device.The method comprises the steps that a plurality of candidate stacking schemes are determined according to container information and size information of an article set; an article position dependency relationship in the candidate stacking schemes is extracted, and a first article pair and a second article pair of each candidate stacking scheme are determined based on the article position dependency relationship; and based on the first article pair and the second article pair of each candidate stacking scheme, a target stacking scheme is determined from the candidate stacking schemes, and articles in the article set are stacked based on the target stacking scheme. According to the embodiment, two objects can be continuously grabbed and stacked, and the object stacking efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of logistics technology, and more specifically, to a method and apparatus for stacking goods. Background Technology

[0002] In current item stacking and packing scenarios, items are typically stacked one by one using a pick-and-place end effector. This involves four steps: grabbing, moving, placing, and returning the item to its original position. This results in low efficiency for item stacking and packing. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide at least one method, apparatus, electronic device and storage medium for stacking items, which can continuously grasp two items and stack them, thereby improving the efficiency of item stacking.

[0004] In a first aspect, embodiments of the present invention provide a method for stacking items, including: Based on the container information and the size information of the item set, multiple candidate stacking schemes are determined; Extract the item position dependencies in the candidate stacking schemes, and determine the first item pair and the second item pair for each candidate stacking scheme based on the item position dependencies; Based on the first and second item pairs of each candidate stacking scheme, the target stacking scheme is determined from the candidate stacking schemes, and the items in the item set are stacked based on the target stacking scheme.

[0005] Optionally, based on the container information and the size information of the item set, multiple candidate stacking schemes are determined, including: The container information and size information are used as input data to feed into multiple pre-trained agents so that the agents can output corresponding candidate stacking schemes. The reward functions for different agents are different; the candidate stacking schemes include the length, width, height and corresponding coordinate data of each item in the item set.

[0006] Optionally, the agent obtains the corresponding candidate staging scheme through the following steps: Based on the stacking status within the container, the size information of the item set, and the reward function corresponding to the agent, the reward value for the candidate code position corresponding to each item in the item set is determined. Based on the reward value, the target code position with the highest reward value is determined from multiple sets of candidate code positions corresponding to the item set, and a candidate code placement scheme corresponding to the agent is generated based on the target code position.

[0007] Optionally, determining the first and second item pairs for each candidate stacking scheme based on item location dependencies includes: Based on the positional dependencies of items, the pose information and upper surface height of each item in the item set, the load of the gripping tool, and the stacking status in the container, determine whether any two items in the item set meet the first matching condition in the continuous gripping and stacking mode, and output the first item pair that meets the first matching condition. Determine whether the items in the item set other than the first item pair meet the second matching condition under the continuous grab and separate stacking mode, and obtain the second item pair that meets the second matching condition; All items in the item set except for the first item pair and the second item pair will be treated as individual grab items.

[0008] Optionally, based on the first item pair and the second item pair of each candidate stacking scheme, a target stacking scheme is determined from the candidate stacking schemes, including: Compare the number of first item pairs and second item pairs in each candidate stacking scheme in turn, and take the candidate stacking scheme with the most first item pairs as the target stacking scheme. If there are at least two candidate stacking schemes with the same number of first item pairs, take the candidate stacking scheme with the most second item pairs among the at least two candidate stacking schemes as the target stacking scheme. In response to the existence of at least two candidate stacking schemes where the number of items in the first item pair and the second item pair are the same, the target stacking scheme is determined based on the volume of the items in the first item pair.

[0009] Optionally, the items in the item set are stacked according to the target stacking scheme, including: The first item pair, the second item pair, and the individually grabbed items in the target stacking scheme are sorted, and the items in the item set are stacked according to the sorting results.

[0010] Secondly, embodiments of the present invention provide an item stacking device, comprising: The determination module is used to determine multiple candidate stacking schemes based on container information and the size information of the item set; The extraction module is used to extract the item position dependency relationship in the candidate stacking scheme, and determine the first item pair and the second item pair of each candidate stacking scheme based on the item position dependency relationship; The stacking module is used to determine the target stacking scheme from the candidate stacking schemes based on the first item pair and the second item pair of each candidate stacking scheme, and to stack the items in the item set based on the target stacking scheme.

[0011] Thirdly, embodiments of the present invention also provide an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the computer device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the steps of the first aspect or any optional implementation of the first aspect are performed.

[0012] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the first aspect or any optional implementation thereof.

[0013] Fifthly, embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the method of any of the above embodiments.

[0014] By analyzing the container information and the size information of the item set, any of the above-mentioned aspects or any implementation methods can generate multiple candidate stacking schemes under the same container space constraints. Each candidate stacking scheme can clearly define the expected position, orientation, and relative layout relationship between items in the item set in three-dimensional space. After generating candidate stacking schemes, the positional dependencies of items in the candidate stacking schemes can be further extracted to reflect whether items can be continuously grasped during actual stacking, and whether they need to rely on preceding items to provide support positions or form stable contact surfaces. Based on the extracted positional dependencies of items, a first pair of items that can be continuously grasped and stacked and a second pair of items that can be continuously grasped and stacked separately can be determined. After determining the first and second pair of items, the candidate stacking schemes can be comprehensively evaluated based on the graspability, stability, and quantity of the first and second pair of items in each candidate stacking scheme, and the target stacking scheme that can optimally support continuous grasping actions can be determined. Once the target stacking scheme is determined, continuous grabbing operations can be performed on the first and second item pairs, thereby reducing the number of switching operations and idle travel distance between grabbing actions, and significantly improving the overall stacking efficiency of the item set while ensuring the stability of item stacking.

[0015] The beneficial effects of the aforementioned item stacking device, electronic equipment, and storage medium are described in the description of the aforementioned item stacking method, and will not be repeated here. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below. These drawings are incorporated in and constitute a part of this specification. They illustrate embodiments conforming to the present invention and, together with the specification, serve to explain the technical solutions of the present invention. It should be understood that the following drawings only show some embodiments of the present invention and should not be considered as a limitation of the scope. For those skilled in the art, other related drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 A flowchart of an article stacking method provided by an embodiment of the present invention is shown; Figure 2 The diagram illustrates different grabbing modes provided in embodiments of the present invention; Figure 3 A flowchart illustrating an item stacking method provided by an embodiment of the present invention is shown; Figure 4 A schematic diagram of the grasping tool provided in an embodiment of the present invention is shown; Figure 5 A schematic diagram of an item stacking device provided in an embodiment of the present invention is shown; Figure 6 An exemplary system architecture in which embodiments of the present invention can be applied is shown; Figure 7 A schematic diagram of the structure of a computer system used to implement embodiments of the present invention is shown. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0019] It should be noted that the collection, use, storage, sharing and transfer of user personal information involved in the technical solution of the present invention all comply with the provisions of relevant laws and regulations, and require notification to users and obtaining their consent or authorization. When applicable, user personal information is subjected to de-identification and / or anonymization and / or encryption technical processing.

[0020] The above problems and solutions are the result of the inventor's practice and careful research. The discovery process of the above problems and the solutions proposed for the above problems should be considered as the inventor's contribution to the invention.

[0021] The technical solutions of this invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are merely some, not all, of the embodiments of this invention. The components of this invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention.

[0022] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0023] To facilitate understanding of this embodiment, a detailed description of the item stacking method disclosed in this invention will be provided first. The execution entity of the item stacking method provided in this invention is generally a computer device with a certain computing capability. This computer device may include, for example, a terminal device, a server, or other processing devices. The terminal device may be a user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, vehicle-mounted device, wearable device, etc. In some possible implementations, this item stacking method can be implemented by a processor calling computer-readable instructions stored in memory.

[0024] See Figure 1 The diagram shows a flowchart of an item stacking method provided in an embodiment of the present invention. The method includes steps S101 to S103, wherein: S101: Based on the container information and the size information of the item set, determine multiple candidate stacking schemes.

[0025] In embodiments of the present invention, such as Figure 2As shown, the grabbing and stacking of items can be divided into continuous grabbing and simultaneous stacking mode, continuous grabbing and individual stacking mode, and single-item grabbing and stacking mode. Specifically, when there are two items that can be grabbed continuously, and their final placement positions are adjacent and there is a collision-free movement path to complete the stacking, the grabbing tool can grab both items continuously and stack them simultaneously. When there are two items that can be grabbed continuously, and there is a collision-free movement path to complete the stacking, the grabbing tool can grab them continuously and then stack them separately. However, when none of the above conditions are met—that is, when the two items cannot be grabbed continuously, and their positions are not adjacent and there is no collision-free movement path—the grabbing tool can perform the traditional single-item grabbing and stacking steps.

[0026] In this embodiment of the invention, the container information may include the container volume of the items to be stacked and the current stacking state inside the container. The execution subject of this embodiment can determine multiple candidate stacking schemes based on the container information and the item dimensions of the set of items to be stacked. Specifically, determining multiple candidate stacking schemes based on the container information and the size information of the item set includes: inputting the container information and size information as input data into multiple pre-trained agents, so that the agents output corresponding candidate stacking schemes; wherein, different agents have different reward functions; the candidate stacking schemes include the length, width, height, and corresponding coordinate data of each item in the item set.

[0027] In practical implementation, the container's size data, the current stacking state within the container, and the length, width, and height of each item in the item set can be uniformly encoded into a computer-recognizable state vector. This encoded vector is then used as input data and fed into multiple pre-trained agents. Each agent can develop a stable policy through extensive interaction with the simulation environment offline. Different agents can employ differentiated reward functions to emphasize different optimization objectives in the stacking task. Due to the different reward functions, agents may arrive at inconsistent decisions under the same input data, thus generating corresponding candidate stacking schemes. For example... Figure 3As shown, the reward function of agent 1 can be set based on the loading rate, and the reward value can be the increase in loading rate caused by the current stacking of items; the reward function of agent 2 can be set based on the height map variance, which is the result of discretizing the longitudinal section of the container into a two-dimensional height map, with each point representing the corresponding height value, and the change in height map variance serving as the reward value; agent 3 can use the maximum height value within the container as the reward; agent 4 can set its corresponding reward function by weighting the above three dimensions. In addition to the above reward functions, other reward functions can be introduced to enhance the adaptability of the agents in different scenarios. For example, a stability reward can be introduced to encourage the agent to choose a stacking method with a larger support area and smaller center of gravity offset; a grasping accessibility reward can be introduced, which evaluates whether the current stacking position is convenient for continuous grasping and placement based on the kinematic model of the robotic arm, thereby reducing the cost of replanning subsequent actions; a contact conflict penalty can be introduced, which assigns negative rewards to actions that cause collisions, penetrations, or unreasonable contact between items, thereby improving the physical feasibility of the stacking scheme, etc.

[0028] It should be noted that the above description of different reward functions for different agents is only an example of a possible implementation in the embodiments of the present invention and does not constitute an improper limitation of the present invention. In practical applications, the corresponding reward function can be set according to the actual situation and needs. The embodiments of the present invention do not make specific limitations in this regard, and the function should be achieved as the standard.

[0029] The agent can output an action based on the current environmental state; this action is the 3D placement coordinates of the item. After the action is executed, the remaining space inside the container and the surface height information are updated, and a reward value is fed back to drive the agent's policy iteration. In practical applications, although different agents correspond to different reward functions, their candidate placement schemes may still have the same characteristics. Therefore, before finally outputting the candidate placement scheme, duplicate solutions obtained by each agent can be removed, and then the deduplicated, complete candidate placement scheme can be output. The candidate placement scheme can be represented by a six-tuple representing the size and placement coordinates of each item in the item set to guide subsequent item placement steps.

[0030] In this embodiment of the invention, the agent obtains the corresponding candidate stacking scheme through the following steps: based on the stacking state in the container, the size information of the item set, and the reward function corresponding to the agent, the reward value of the candidate code position corresponding to each item in the item set is determined; according to the reward value, the target code position with the largest reward value is determined from multiple sets of candidate code positions corresponding to the item set, and a candidate stacking scheme corresponding to the agent is generated according to the target code position.

[0031] In practical implementation, during the generation of candidate stacking schemes, the agent can evaluate the position of each item in the item set one by one under the constraints of a unified environmental state and its own independent reward function, and form a complete solution through multiple iterations. Specifically, a three-dimensional space occupancy map can be constructed based on the current stacking state within the container, and a set of possible candidate stacking positions for each item can be generated by combining the size information of the item set. These positions can be determined by the remaining space shape inside the container, the support surface conditions, feasible placement postures, and collision detection results. Subsequently, the agent can score the placement effect of each item at each candidate stacking position based on its corresponding reward function. For example, if the agent adopts a reward function that maximizes the loading rate, then for a larger item, the agent will prioritize giving a higher reward value to the position that minimizes fragmentation of the remaining space and increases the overall volume utilization rate; if the agent adopts a reward function that prioritizes stability, the same item may receive a higher score because it is more stable on a certain support surface and does not cause spikes to form on the container surface. After calculating the reward values ​​of all candidate stacking positions, these scores can be compared to determine the target stacking position of the item, i.e., the position with the highest reward value. Once the target placement location is determined, its location and dimensions can be written into the current scheme, and the surface height and remaining space structure of the container can be updated to provide a new environmental state for the evaluation of the next item's location. By continuously repeating this cyclical process of "calculating reward - selecting the highest reward location - updating environmental state" for all items in the item set, the agent can eventually generate candidate placement schemes consistent with its policy preferences.

[0032] S102: Extract the item position dependency relationship in the candidate stacking scheme, and determine the first item pair and the second item pair of each candidate stacking scheme based on the item position dependency relationship.

[0033] In this embodiment of the invention, after generating multiple candidate stacking schemes, the first item pair and the second item pair in each candidate scheme can be further determined based on the item position dependency relationship, so as to clarify which items can be stacked simultaneously or sequentially in continuous grasping mode, thereby improving the overall processing efficiency. Specifically, determining the first item pair and the second item pair of each candidate stacking scheme based on the item position dependency relationship includes: judging whether any two items in the item set meet the first matching condition in the continuous grasping simultaneous stacking mode according to the item position dependency relationship, the pose information and upper surface height of each item in the item set, the load of the grasping tool, and the stacking state in the container, and outputting the first item pair that meets the first matching condition; judging whether the items in the item set other than the first item pair meet the second matching condition in the continuous grasping individual stacking mode, and obtaining the second item pair that meets the second matching condition; and treating the items in the item set other than the first item pair and the second item pair as individually grasped items.

[0034] In specific implementation, such as Figure 3 As shown, an item position dependency graph can be constructed first using the item pose information, hexahedral boundary, upper surface height, and support relationships between items in the candidate schemes. This dependency graph reflects whether each item at the target code selection position depends on other items for support, whether it is constrained by container boundary conditions, and whether its upper surface can serve as a stable bearing surface for other items. For example... Figure 4 As shown, based on the positional dependence of the items, the load capacity of the gripping tool, the feasible pose range of the suction cup array, and the current stacking state of the container can be further combined to determine whether any two items in the item set can meet the first matching condition in the continuous gripping and simultaneous stacking mode. Specifically, it can be analyzed whether the height difference of the upper surfaces of the two items in the target stacking state is within a preset threshold, whether the placement posture allows for adsorption at the same or compatible relative rotation angle during the gripping phase, whether the gripping tool can simultaneously bear the weight of the two items within its load range, and whether a collision-free path exists between the two items during the handling process. For example, when two items are of similar height in the stacking scheme and can both be stably gripped within the same adsorption range of the suction cup array, and do not touch the container wall or other placed items on the handling path, then the item pair can be considered to meet the first matching condition and output as the first item pair for continuous gripping and simultaneous stacking. After identifying all items that can be used as the first item pair, the remaining unmatched items in the item set can be analyzed to determine whether they can meet the second matching condition for continuous gripping but separate stacking. In this mode, it is no longer required that the two items be completely identical in pose, rotation angle, or placement height. It is only necessary to verify whether the gripping tool can stably adsorb both items in a single gripping action, and whether there are collision-free feasible paths when the transport paths lead to their respective placement positions. For example, two items with drastically different shapes, inconsistent upper surface heights, but relatively light weight and capable of occupying different adsorption areas on the left and right sides of the suction cup array can be determined to meet the second matching condition and be designated as the second item pair. This allows the gripping tool to simultaneously remove both items from the item supply area in a single gripping action, but during the transport phase, the two items are placed sequentially to non-adjacent target selection positions. After the above two types of matching processes, items that are still not included in the first or second item pair can be automatically classified into a separate gripping item set, indicating that they cannot form stable continuous gripping pairs with other items under the current candidate placement scheme and need to be executed using the traditional single-item gripping method.

[0035] S103: Based on the first item pair and the second item pair of each candidate stacking scheme, determine the target stacking scheme from the candidate stacking schemes, and stack the items in the item set based on the target stacking scheme.

[0036] In this embodiment of the invention, after obtaining multiple candidate stacking schemes and the corresponding item pairs for each candidate stacking scheme, it is necessary to determine the final target stacking scheme from the multiple candidate stacking schemes. Specifically, determining the target stacking scheme from the candidate stacking schemes based on the first item pair and the second item pair of each candidate stacking scheme includes: sequentially comparing the number of the first item pair and the second item pair in each candidate stacking scheme, and taking the candidate stacking scheme with the most first item pairs as the target stacking scheme; if there are at least two candidate stacking schemes with the same number of first item pairs, taking the candidate stacking scheme with the most second item pairs among the at least two candidate stacking schemes as the target stacking scheme; in response to the existence of at least two candidate stacking schemes with the same number of both first item pairs and second item pairs, determining the target stacking scheme based on the volume of the items in the first item pair.

[0037] In practice, we can first iterate through all candidate stacking schemes and count and compare the number of first item pairs identified in each scheme. Since the first item pair refers to the pair of items that can be stacked simultaneously in continuous grasping mode, the existence of such item pairs often means that the number of grasps and placements can be reduced in pairs, resulting in the most significant improvement in overall processing efficiency. Therefore, we can prioritize the candidate stacking scheme with the largest number of first item pairs and use it as the first choice for the target stacking scheme. If there are at least two candidate schemes with the same number of first item pairs, to avoid missing potential better strategies, we can further compare the number of second item pairs in these candidate schemes. The second item pair corresponds to the mode of continuous grasping but separate stacking, which can also reduce the number of grasps and significantly improve the working speed of the grasping tool. Therefore, when the number of first item pairs is equal, we can use the scheme with the largest number of second item pairs as the target scheme to ensure that the overall continuous grasping efficiency is maximized. If there are at least two candidate schemes with the same number of first and second item pairs, we can further judge using item attributes. Specifically, we can calculate the volume values ​​of the two items in all first item pairs in these candidate stacking schemes and prioritize the combination of item pairs with larger volumes. The reason is that when tall items can be stacked using a simultaneous gripping mode, the time cost and path planning overhead reduced per operation are far greater than for small items. It also has a more positive impact on the stability of the container height map and the control of center of gravity changes. For example, if two schemes both contain the same number of three pairs of first items and two pairs of second items, but one scheme's first item pair contains two large boxes while the other scheme's first item pair mainly consists of small, lightweight items, the system will prioritize the first scheme as the target stacking scheme. This ensures that the final target stacking scheme achieves optimal continuous gripping efficiency, operational stability, and overall operational value, ultimately guiding the gripping tool to efficiently complete the gripping and stacking of item sets.

[0038] In this embodiment of the invention, stacking items in an item set based on a target stacking scheme includes: sorting the first item pair, the second item pair, and the individually grabbed items in the target stacking scheme, and stacking the items in the item set according to the sorting results.

[0039] In practical implementation, after determining the target stacking scheme, the item set can be actually stacked based on the target stacking scheme. This requires first uniformly sorting the first item pair, the second item pair, and individually grasped items in the target stacking scheme to form a directly executable work sequence. Specifically, all item pairs and individual items can be topologically processed to obtain a final sorting result that satisfies structural support relationships and spatial feasibility. During the sorting process, the first item pair, as the most efficient continuously grasped and stacked object, can be prioritized at the beginning of the sequence to minimize the number of round trips by the grasping tool. The second item pair can be inserted after it as continuously grasped but separately stacked objects, and adjusted appropriately based on its corresponding transport path length, changes in remaining space within the container, and its height map influence with the first item pair. Individually grasped items are placed sequentially at the end of the sequence without affecting container stability and the feasibility of subsequent grasping paths, optimizing the overall work rhythm. After obtaining the final sorting, grasping and placing actions can be performed one by one according to the sorting result, thus completing the stacking of the item set.

[0040] According to a second aspect of the embodiments of the present invention, such as Figure 5 As shown, an item stacking device 500 is provided, comprising: The determination module 501 is used to determine multiple candidate stacking schemes based on the container information and the size information of the item set; The extraction module 502 is used to extract the item position dependency relationship in the candidate stacking scheme, and determine the first item pair and the second item pair of each candidate stacking scheme based on the item position dependency relationship; The stacking module 503 is used to determine the target stacking scheme from the candidate stacking schemes based on the first item pair and the second item pair of each candidate stacking scheme, and to stack the items in the item set based on the target stacking scheme.

[0041] Optionally, the determination module 501 is specifically used for: The container information and size information are used as input data to feed into multiple pre-trained agents so that the agents can output corresponding candidate stacking schemes. The reward functions for different agents are different; the candidate stacking schemes include the length, width, height and corresponding coordinate data of each item in the item set.

[0042] Optionally, the agent obtains the corresponding candidate staging scheme through the following steps: Based on the stacking status within the container, the size information of the item set, and the reward function corresponding to the agent, the reward value for the candidate code position corresponding to each item in the item set is determined. Based on the reward value, the target code position with the highest reward value is determined from multiple sets of candidate code positions corresponding to the item set, and a candidate code placement scheme corresponding to the agent is generated based on the target code position.

[0043] Optionally, the extraction module 502 is specifically used for: Based on the positional dependencies of items, the pose information and upper surface height of each item in the item set, the load of the gripping tool, and the stacking status in the container, determine whether any two items in the item set meet the first matching condition in the continuous gripping and stacking mode, and output the first item pair that meets the first matching condition. Determine whether the items in the item set other than the first item pair meet the second matching condition under the continuous grab and separate stacking mode, and obtain the second item pair that meets the second matching condition; All items in the item set except for the first item pair and the second item pair will be treated as individual grab items.

[0044] Optionally, the stacking module 503 is specifically used for: Compare the number of first item pairs and second item pairs in each candidate stacking scheme in turn, and take the candidate stacking scheme with the most first item pairs as the target stacking scheme. If there are at least two candidate stacking schemes with the same number of first item pairs, take the candidate stacking scheme with the most second item pairs among the at least two candidate stacking schemes as the target stacking scheme. In response to the existence of at least two candidate stacking schemes where the number of items in the first item pair and the second item pair are the same, the target stacking scheme is determined based on the volume of the items in the first item pair.

[0045] Optionally, the stacking module 503 is specifically used for: The first item pair, the second item pair, and the individually grabbed items in the target stacking scheme are sorted, and the items in the item set are stacked according to the sorting results.

[0046] According to a third aspect of the present invention, an electronic device for stacking items is provided, comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method provided in the first aspect of the present invention.

[0047] According to a fourth aspect of the present invention, a computer-readable medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method provided in the first aspect of the present invention.

[0048] According to a fifth aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method of any of the above embodiments.

[0049] Figure 6 An exemplary system architecture 600 is shown that can be applied to the item stacking method or item stacking device implemented in this invention.

[0050] like Figure 6 As shown, system architecture 600 may include terminal devices 601, 602, and 603, a network 604, and a server 605. Network 604 serves as the medium for providing communication links between terminal devices 601, 602, and 603 and server 605. Network 604 may include various connection types, such as wired or wireless communication links or fiber optic cables, etc.

[0051] Users can use terminal devices 601, 602, and 603 to interact with server 605 via network 604 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 601, 602, and 603, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0052] Terminal devices 601, 602, and 603 can be various electronic devices with displays and web browsing capabilities, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0053] Server 605 can be a server that provides various services, such as a backend management server (for example only) that supports shopping websites browsed by users using terminal devices 601, 602, and 603. The backend management server can process received item placement requests and send the processing results (for example only) back to the terminal devices.

[0054] It should be noted that the item stacking method provided in this embodiment of the invention is generally executed by server 605, and correspondingly, the item stacking device is generally installed in server 605. The item stacking method provided in this embodiment of the invention can also be executed by terminal devices 601, 602, and 603, and correspondingly, the item stacking device can be installed in terminal devices 601, 602, and 603.

[0055] It should be understood that Figure 6 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0056] The following is for reference. Figure 7It shows a schematic diagram of the structure of a computer system 700 suitable for implementing a terminal device of the present invention. Figure 7 The terminal device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0057] like Figure 7 As shown, the computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 702 or programs loaded from storage section 708 into random access memory (RAM) 703. The RAM 703 also stores various programs and data required for the operation of the system 700. The CPU 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0058] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, mouse, etc.; an output section 707 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 710 as needed so that computer programs read from it can be installed into the storage section 708 as needed.

[0059] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 709, and / or installed from removable medium 711. When the computer program is executed by central processing unit (CPU) 701, it performs the functions defined above in the system of this invention.

[0060] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0061] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0062] The modules described in the embodiments of the present invention can be implemented in software or hardware. The described modules can also be housed in a processor. For example, a processor may include a determining module, an extracting module, and a stacking module. The names of these modules do not necessarily limit the specific module itself. For instance, the determining module may be described as "a module that determines multiple candidate stacking schemes based on container information and the size information of the item set."

[0063] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, and when the one or more programs are executed by the device, the device implements the following method: determining multiple candidate stacking schemes based on container information and the size information of the item set; extracting the item position dependencies in the candidate stacking schemes, and determining a first item pair and a second item pair for each candidate stacking scheme based on the item position dependencies; determining a target stacking scheme from the candidate stacking schemes based on the first item pair and the second item pair of each candidate stacking scheme, and stacking the items in the item set based on the target stacking scheme.

[0064] Finally, it should be noted that the above embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An article stacking method, characterized by, The method comprises the following steps: determining a plurality of candidate storage schemes according to container information and size information of an article set; extracting article position dependency in the candidate storage schemes, and determining first article pairs and second article pairs of each candidate storage scheme based on the article position dependency; determining a target storage scheme from the candidate storage schemes based on the first article pairs and the second article pairs of each candidate storage scheme, and storing articles in the article set based on the target storage scheme.

2. The method of claim 1, wherein, The method comprises the following steps: inputting the container information and the size information as input data into a plurality of agents trained in advance, so that the agents output corresponding candidate storage schemes; wherein the reward functions of different agents are different; the candidate storage scheme includes the length, width, height and corresponding coordinate data of each article in the article set.

3. The method of claim 2, wherein, The agent obtains the corresponding candidate storage scheme through the following steps: determining the reward value of the candidate storage position corresponding to each article in the article set based on the storage state in the container, the size information of the article set, and the reward function corresponding to the agent; determining the target candidate storage position with the maximum reward value from a plurality of groups of candidate storage positions corresponding to the article set according to the reward value, and generating the candidate storage scheme corresponding to the agent according to the target candidate storage position.

4. The method of claim 1, wherein, The method comprises the following steps: determining the first article pairs and the second article pairs of each candidate storage scheme based on the article position dependency, the pose information, the upper surface height, the load of the grabbing tool, and the storage state in the container of each article in the article set; judging whether any two articles in the article set satisfy the first matching condition in the continuous grabbing and simultaneous storage mode according to the article position dependency, the pose information, the upper surface height, the load of the grabbing tool, and the storage state in the container of each article in the article set, and outputting the first article pairs satisfying the first matching condition; judging whether the articles in the article set except the first article pairs satisfy the second matching condition in the continuous grabbing and separate storage mode, and obtaining the second article pairs satisfying the second matching condition; 5. The method of claim 4, wherein, regarding the articles in the article set except the first article pairs and the second article pairs as separate grabbing articles. The method comprises the following steps: comparing the number of the first article pairs and the second article pairs in each candidate storage scheme in turn, regarding the candidate storage scheme with the most first article pairs as the target storage scheme, and regarding the candidate storage scheme with the most second article pairs as the target storage scheme in the case that there are at least two candidate storage schemes with the same number of first article pairs; 6. The method according to any one of claims 1 to 5, characterized in that, in response to there being at least two candidate storage schemes with the same number of first article pairs and second article pairs, determining the target storage scheme according to the volume of the articles in the first article pairs. The method comprises the following steps: sorting the first article pairs, the second article pairs, and the separate grabbing articles in the target storage scheme, and storing the articles in the article set according to the sorting result.

7. An item stacking device, characterized in that, Comprising: a determining module configured to determine a plurality of candidate storage schemes according to the container information and size information of the item set; an extracting module configured to extract item position dependency in the candidate storage schemes, and determine first item pair and second item pair of each candidate storage scheme based on the item position dependency; a storage module configured to determine a target storage scheme from the candidate storage schemes based on the first item pair and the second item pair of each candidate storage scheme, and store the items in the item set based on the target storage scheme.

8. An electronic device, comprising: Comprising: one or more processors; a memory device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1-6.

9. A computer readable medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the method according to any one of claims 1-6.

10. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-6.

Images