Stacking strategy determination method and device, computer equipment and readable storage medium
By simulating the placement process in the three-dimensional storage space, combining voxel occupancy status and material information, and optimizing the placement strategy, the problem of low space utilization in traditional technology is solved, and the accuracy of placement and space utilization is improved.
Patent Information
- Application Number
- CN202411222127.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-02
- Publication Date
- 2024-12-06
AI Technical Summary
Traditional technology is difficult to effectively foresee and optimize the order of placing multiple boxes when placing them, resulting in low space utilization and unable to meet modern warehousing needs.
Based on the size and position information of the target material, combined with the voxel occupancy status of the three-dimensional storage space, the initial placement strategy is determined, and the space utilization is optimized through the simulated placement process, and the placement strategy is adjusted to improve the space utilization.
It achieves higher placement accuracy and space utilization, reduces calculation errors, and optimizes placement strategies to meet warehousing needs.
Smart Images

Figure CN119090309A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of automation technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for determining a stacking strategy. Background Art
[0002] With the rapid development of the global supply chain, the warehousing demand in the industrial sector has grown rapidly. In modern logistics and warehousing management, efficient stacking of materials is a key factor in improving storage space utilization and operational efficiency. Therefore, how to quickly determine the stacking strategy has become one of the key issues.
[0003] In traditional technology, taking boxes as an example, warehouse management mainly relies on manual input of the box dimensions, sizes, stacking order, etc. in advance. Workers then control robots, conveyor belts and other mechanical equipment based on experience or pre-established rules to stack the boxes in designated areas.
[0004] However, when handling multiple boxes, traditional solutions cannot effectively foresee and optimize the stacking order of multiple boxes based solely on workers' experience or simple pre-established rules. As a result, the final stacking strategy cannot meet warehousing needs and there is a problem of low space utilization. Summary of the invention
[0005] Based on this, it is necessary to provide a method, apparatus, computer device, computer-readable storage medium and computer program product for determining a stacking strategy that can improve stacking accuracy in response to the above technical problems.
[0006] In a first aspect, the present application provides a method for determining a stacking strategy, comprising:
[0007] Determine the initial stacking strategy based on the size and location information of the target material and the occupancy status of each voxel in the three-dimensional storable space;
[0008] Based on the initial stacking strategy, simulate the stacking of the target material to determine the space utilization rate corresponding to the initial stacking strategy;
[0009] Based on the space utilization, the initial stacking strategy is adjusted to obtain a target stacking strategy.
[0010] In one embodiment, determining the initial stacking strategy based on the size and position information of the target material and the occupation status of each voxel in the three-dimensional storable space includes:
[0011] Determine a plurality of candidate stacking areas according to the size of the target material and the occupation status of each voxel in the three-dimensional storable space;
[0012] Based on a preset stacking quality scoring standard, determining a stacking quality score when the target material is stacked in each candidate stacking area, wherein the stacking quality scoring standard includes at least one of a space utilization scoring standard, an empty rate scoring standard, and a stack regularity scoring standard;
[0013] Determine the candidate stacking area with the highest stacking quality score as the material stacking area for the target material;
[0014] The initial stacking strategy is determined according to the material stacking area of the target material and the position information.
[0015] In one embodiment, the number of the preset stacking quality scoring standards is multiple;
[0016] The adjusting the initial stacking strategy based on the space utilization to obtain a target stacking strategy includes:
[0017] When the space utilization rate is greater than or equal to a preset space utilization rate threshold, determining the initial stacking strategy as the target stacking strategy;
[0018] When the space utilization rate is less than a preset space utilization rate threshold, adjusting the weights of the plurality of preset stacking quality scoring criteria;
[0019] Returning to the preset stacking quality scoring standard, determining the stacking quality scoring step when stacking the target materials in each candidate stacking area, until a target stacking strategy is obtained in which the space utilization is greater than or equal to a preset space utilization threshold.
[0020] In one embodiment, adjusting the initial stacking strategy based on the space utilization to obtain a target stacking strategy includes:
[0021] With the maximization of the space utilization as the goal, the initial stacking strategy is adjusted to obtain the target stacking strategy when the space utilization is maximized.
[0022] In one embodiment, the initial stacking strategy includes a material stacking area and a placement angle of the target material in the material stacking area;
[0023] The adjusting the initial stacking strategy based on the space utilization to obtain a target stacking strategy includes:
[0024] When the space utilization rate is less than a preset space utilization rate threshold, the placement angle of the target material in the material stacking area is adjusted until a target stacking strategy is obtained in which the space utilization rate is greater than or equal to the preset space utilization rate threshold.
[0025] In one embodiment, the initial stacking strategy includes a material stacking area; after determining the initial stacking strategy, the method further includes:
[0026] Based on the initial stacking strategy, simulating the stacking of the target material, and determining the movement trajectory of the target material during the simulated stacking process;
[0027] When the stacking robot cannot stack the target material in the material stacking area according to the motion trajectory, adjusting the position information of the target material;
[0028] Return to the step of determining the initial stacking strategy based on the size and position information of the target material and the occupancy status of each voxel in the three-dimensional storable space, until the stacking robot stacks the target material in the material stacking area according to the motion trajectory, and obtains the target stacking strategy.
[0029] In one embodiment, obtaining the size of the target material includes:
[0030] Selecting a target material to be stacked from materials of different stack shapes, and obtaining an initial size of the target material;
[0031] Based on a preset camera recognition error, the initial size of the target material is corrected to obtain the size of the target material.
[0032] In a second aspect, the present application further provides a stacking strategy determination device, comprising:
[0033] A strategy determination module, used to determine an initial stacking strategy based on the size and position information of the target material and the occupancy status of each voxel in the three-dimensional storable space;
[0034] A space utilization rate determination module, used to simulate the stacking of the target material based on the initial stacking strategy, and determine the space utilization rate corresponding to the initial stacking strategy;
[0035] The strategy optimization module is used to adjust the initial stacking strategy based on the space utilization to obtain a target stacking strategy.
[0036] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps in the above-mentioned method for determining a coding strategy when executing the computer program.
[0037] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the above-mentioned method for determining a stacking strategy are implemented.
[0038] In a fifth aspect, the present application also provides a computer program product, including a computer program, which implements the steps in the above-mentioned method for determining a stacking strategy when executed by a processor.
[0039] The above-mentioned stacking strategy determination method, device, computer equipment, computer-readable storage medium and computer program product are different from the traditional scheme. The above-mentioned scheme simulates the actual placement space through the three-dimensional storable space, and intuitively presents the occupancy of the placement space through the occupancy status of each voxel, so as to further combine the size and position information of the target material to accurately and quickly generate the initial stacking strategy. Then, based on the initial stacking strategy, the stacking of the target material is simulated, so that the space utilization corresponding to the initial stacking strategy can be quickly determined without the need to actually operate the device to perform the stacking operation, and compared with the actual operation of the device to perform the stacking operation, the accidental error in the calculation of the space utilization can be effectively reduced, and the subsequent adjustment of the initial stacking strategy provides a more accurate space utilization. Finally, based on the space utilization, the initial stacking strategy is adjusted to further optimize the initial stacking strategy, and a more accurate target stacking strategy can be obtained. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0041] FIG1 is an application environment diagram of a stacking strategy determination method in one embodiment;
[0042] Figure 2 A schematic diagram of a flow chart of a method for determining a stacking strategy in an embodiment;
[0043] Figure 3 A schematic flow chart of a method for determining a stacking strategy in another embodiment;
[0044] Figure 4 A schematic diagram of a flow chart of a method for determining a stacking strategy in another embodiment;
[0045] Figure 5 A schematic diagram of a flow chart of a method for determining a stacking strategy in yet another embodiment;
[0046] Figure 6 A schematic diagram of a flow chart of a stacking strategy determination method in a detailed embodiment;
[0047] Figure 7It is a structural block diagram of a stacking strategy determination device in one embodiment;
[0048] Figure 8 It is a structural block diagram of a stacking strategy determination device in another embodiment;
[0049] FIG. 9 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0050] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0051] The method for determining a stacking strategy provided in an embodiment of the present application can be applied in an application environment as shown in FIG1 . In which, the terminal 102 communicates with the server 104 via a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed on a cloud or other network server.
[0052] Specifically, the operator can upload the size and position information of the target material and the occupation status of each voxel in the three-dimensional storable space through the terminal 102. The server 104 simulates the stacking of the target material based on the initial stacking strategy, determines the space utilization corresponding to the initial stacking strategy, and further adjusts the initial stacking strategy based on the space utilization to obtain the target stacking strategy. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 104 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.
[0053] In an exemplary embodiment, Figure 2 As shown, a method for determining a stacking strategy is provided, and the method is applied to the server 104 in FIG. 1 as an example for description, including the following steps:
[0054] S100, determining an initial stacking strategy based on the size and position information of the target material and the occupation status of each voxel in the three-dimensional storable space.
[0055] The target material refers to the material to be stacked, which can be a regular object like a box, or other materials of different sizes and shapes that need to be stacked. The location information of the target material is the initial location of the target material, such as the target material buffer area. The size of the target material can include but is not limited to the length, width, height, shape, etc. of the target material.
[0056] The three-dimensional storable space is obtained by simulating the actual storage space. The actual storage space can be a warehouse, cage car or other space. Specifically, the storage space can be divided into several voxels, each voxel represents a minimum storage unit, and each voxel has three possible occupancy states: open, occupied and supporting. The occupancy state of each voxel can be tracked and managed using a three-dimensional grid system. It should be noted that if the target material is placed in the three-dimensional storable space, the occupancy state of the voxels on the upper surface of the target material is a supporting state, which means that support can be provided for other materials placed above the target material. The initial stacking strategy may include, but is not limited to, the stacking area, stacking order, and orientation of the target material in the stacking area.
[0057] For example, the initial stacking strategy is determined based on the size and position information of the target material and the occupancy status of each voxel in the three-dimensional storable space. It can be based on some basic stacking rules, such as "heavy objects are at the bottom, light objects are at the top", "objects of similar shapes should be placed together as much as possible", etc., or the initial stacking strategy can be quickly determined by using greedy algorithms, heuristic algorithms, etc. The initial stacking strategy can be relatively simple, for example, materials with large volumes are placed at the bottom first, and then gradually stacked upward until all available space is filled. Specifically, assuming that a batch of boxes need to be stacked, the sizes of these boxes are: box A: 1 meter long, 1 meter wide, and 1 meter high; box B: 0.5 meters long, 0.5 meters wide, and 0.5 meters high; box C: 2 meters long, 1 meter wide, and 0.5 meters high. The initial stacking strategy can be to first place box C in a corner of the three-dimensional storable space, because its length is large, it can maximize the use of the bottom space, then place box A next to C, and finally place box B above A, because it is small, it can be placed on the upper layer to make full use of the vertical space.
[0058] S200, based on the initial stacking strategy, simulate the stacking of the target material and determine the space utilization rate corresponding to the initial stacking strategy.
[0059] Among them, the space utilization rate refers to the ratio of the volume of the space where materials have been stacked in the three-dimensional storable space to the total volume of the three-dimensional storable space, which can be used to characterize the utilization of the space.
[0060] Specifically, the process of simulating the stacking of target materials can be realized by controlling the robot to perform simulated movement in the Linux virtual machine. The robot will perform virtual stacking according to the stacking positions corresponding to each target material in the initial stacking strategy and the stacking order specified in the initial stacking strategy. In the process of simulating the stacking of target materials, the Linux virtual machine will calculate the space utilization rate of the current three-dimensional storable space in real time. In addition to recording the specific value of the space utilization rate, it can also record the space utilization of the three-dimensional storable space. For example, if a part of the space is stacked to a certain height, while the other part of the space is still idle, it indicates that some areas of the three-dimensional storable space are not fully utilized, or the target materials are unstable after stacking, such as heavy objects on the upper layer causing the overall center of gravity to be unstable.
[0061] Exemplarily, following the above steps, the simulation is carried out to stack boxes C, A, and B in different areas of the three-dimensional storable space according to the initial stacking strategy. The Linux virtual machine calculates that the current space utilization is 70%, and records the space utilization: box B is stacked on top of A, but the height of A is not high, resulting in a large amount of free space at the top of the three-dimensional storable space. In addition, although box C occupies a large bottom space, its height is relatively low, which also results in the space above it not being fully utilized.
[0062] S300: Based on the space utilization rate, adjust the initial stacking strategy to obtain a target stacking strategy.
[0063] Following the above steps, the initial stacking strategy is adjusted according to the calculated space utilization, and the goal of the adjustment is to improve the overall space utilization and maintain the stacking stability of the target materials. Among them, adjusting the initial stacking strategy may include but is not limited to: rearranging the stacking order of the target materials, such as placing some larger target materials at the bottom and placing smaller target materials on top according to the size and shape of the target materials to make full use of the vertical space; adjusting the placement direction of the materials, such as changing the long strip target materials to vertical placement instead of horizontal placement to save more ground space; stacking in layers, such as stacking the target materials in layers according to weight and size to reduce the situation where heavy objects crush light objects, while improving space utilization.
[0064] For example, following the example in the above steps, the adjustment to the initial stacking strategy can be: reposition box B above C instead of above A to make full use of the space above box C; rotate box A 90 degrees so that its long side is parallel to the long side of the three-dimensional storable space, which can free up more ground space for other target materials.
[0065] The above-mentioned method for determining the stacking strategy is different from the traditional solution. The above-mentioned solution simulates the actual placement space through the three-dimensional storable space, and intuitively presents the occupancy of the placement space through the occupancy status of each voxel, so as to further combine the size and position information of the target material to accurately and quickly generate the initial stacking strategy. Then, based on the initial stacking strategy, the stacking of the target material is simulated, so that the space utilization corresponding to the initial stacking strategy can be quickly determined without actually operating the device to perform the stacking operation, and compared with the actual operation of the device to perform the stacking operation, it can effectively reduce the accidental error in the calculation of the space utilization, and provide a more accurate space utilization for the subsequent adjustment of the initial stacking strategy. Finally, based on the space utilization, the initial stacking strategy is adjusted to further optimize the initial stacking strategy, and a more accurate target stacking strategy can be obtained.
[0066] Based on the above embodiment, there are many ways to determine the initial stacking strategy. In an exemplary embodiment, Figure 3 As shown, S100 includes:
[0067] S110, determining a plurality of candidate stacking areas according to the size of the target material and the occupation status of each voxel in the three-dimensional storable space.
[0068] S120: Based on a preset stacking quality scoring standard, determine a stacking quality score when the target material is stacked in each candidate stacking area.
[0069] S130, determining the candidate stacking area with the highest stacking quality score as the material stacking area for the target material;
[0070] S140: Determine an initial stacking strategy according to the material stacking area and location information of the target material.
[0071] Among them, the stacking quality scoring standard includes at least one of the space utilization scoring standard, the empty rate scoring standard and the stack regularity scoring standard. The candidate stacking area is a potential stacking area that meets the size and shape of the target material. For example, a stacking area that can accommodate the target material may become a candidate stacking area. The space utilization rate refers to the ratio of the space volume occupied by the material in the stacking area to the total available space volume of the stacking area. When all the materials to be stacked are stacked, the space utilization rate is the ratio of the space volume occupied by all materials in the three-dimensional storage space to the total available space volume in the three-dimensional storage space. The empty rate refers to the ratio of the part of the material that is suspended in contact with other materials or the ground after stacking to the overall volume of the material. A high empty rate indicates that there are more parts of the material suspended in the air, and the risk of unstable stacking is high. The stack regularity refers to the neatness of the arrangement of the materials in the stacking area, which can be evaluated by the height difference and inclination angle of the stacked materials. For example, when a certain material is placed in a certain stacking area, the material has a large height difference with its adjacent materials, indicating that the stack regularity is low.
[0072] Specifically, the three-dimensional storable space can be divided into a plurality of small candidate stacking areas according to the size of the target material and the current occupation status of each voxel in the three-dimensional storable space. When determining the candidate stacking area, only the voxels not occupied by other materials will be used as part of the candidate area, and the number and size of the candidate stacking area will vary with the size of the three-dimensional storable space and the size of the target material. Further, based on the preset stacking quality scoring standard, each candidate stacking area is evaluated, and the process includes but is not limited to: according to the space utilization scoring standard, the space utilization of the three-dimensional storable space is evaluated after the target material is stacked in the candidate stacking area, and the higher the space utilization, the higher the score; according to the volley rate scoring standard, the stability of the target material after being stacked in the candidate stacking area is evaluated, if there is an unsupported area under the target material (i.e., volley), the score will be lower, because this will increase the risk of collapse of the material; according to the stack regularity scoring standard, whether the stack shape of the target material after being stacked in the candidate stacking area is regular, if the stack shape after stacking is a regular cube, the height difference of the upper surface is small, which is convenient for subsequent material handling and management, then the score is high.
[0073] Then, the server 104 selects the candidate stacking area with the highest stacking quality score in the above steps as the final material stacking area of the target material, and determines the initial stacking strategy according to the material stacking area and position information of the target material. In this way, the target material can effectively utilize space and maintain good stability and regularity during the stacking process.
[0074] In this embodiment, an initial stacking strategy is formulated in combination with the characteristics of the target material and the three-dimensional storable space. The initial stacking strategy can make the best use of the storage space during the stacking process and reduce potential risks during the operation, such as material dumping or damage, thereby improving the stacking stability and regularity of the target material and providing a basis for subsequent optimization and adjustment.
[0075] After the initial stacking strategy is obtained, the initial stacking strategy will be further optimized and adjusted according to the space utilization. In an exemplary embodiment, Figure 4 As shown, S300 includes:
[0076] S310, determining whether the space utilization is less than a preset space utilization threshold.
[0077] S320: When the space utilization is greater than or equal to a preset space utilization threshold, determine the initial stacking strategy as the target stacking strategy.
[0078] S330, when the space utilization is less than a preset space utilization threshold, adjust the weights of a plurality of preset stacking quality scoring criteria, and return to S120 until a target stacking strategy is obtained in which the space utilization is greater than or equal to the preset space utilization threshold.
[0079] Among them, the weights of the preset space utilization threshold and the preset stacking quality scoring standard can be set according to actual conditions. For example, the warehouse manager comprehensively considers factors such as the type of warehouse, the type of materials, and the difficulty of stacking, and sets the preset space utilization threshold to 80%, and sets the weights of the space utilization scoring standard, the empty rate scoring standard, and the stacking regularity scoring standard to 30%, 30%, and 40%, respectively.
[0080] Continuing with the above embodiment, by evaluating the space utilization of the current initial stacking strategy and comparing it with the preset space utilization threshold, if the current space utilization is greater than or equal to the preset space utilization threshold, it indicates that the current initial stacking strategy has met the actual stacking requirements and no further adjustment is required. The initial stacking strategy is directly determined as the target stacking strategy.
[0081] If the current space utilization is lower than the preset space utilization threshold, it indicates that the current initial stacking strategy does not fully utilize the available storage space and needs to be further optimized. Specifically, assuming that the current initial stacking strategy makes the space utilization of the three-dimensional storable space reach 75%, and the preset space utilization threshold is 80%, the stacking strategy can be optimized by adjusting the weights of the space utilization scoring standard, the empty rate scoring standard, and the stack regularity scoring standard. For example, if the space utilization of the current initial stacking strategy is low, the weight of the space utilization scoring standard can be increased.
[0082] Then, the steps of determining the stacking quality score when stacking the target materials in each candidate stacking area based on the preset stacking quality score standard are re-executed until a target stacking strategy with a space utilization greater than or equal to a preset space utilization threshold is obtained.
[0083] In this embodiment, by setting a space utilization threshold, the initial stacking strategy with low space utilization can be quickly confirmed and adjusted to reduce unnecessary adjustments. In the process of optimizing the initial stacking strategy, by dynamically adjusting the weight of each stacking quality scoring standard, when the space utilization is insufficient, increasing its weight can effectively improve the space utilization. In other scenarios, the weights of other stacking quality scoring standards can also be adjusted according to specific needs, thereby improving the accuracy of the target stacking strategy.
[0084] In addition to adjusting the weights of each stacking quality scoring standard, other methods may be used to optimize the initial stacking strategy. In an exemplary embodiment, S300 includes: adjusting the initial stacking strategy with the goal of maximizing space utilization to obtain a target stacking strategy with maximum space utilization.
[0085] For example, the initial stacking strategy may fail to fully utilize the three-dimensional storable space in order to meet other conditions, such as stacking stability and regularity. Therefore, the core of this embodiment is to optimize and adjust the initial stacking strategy to maximize space utilization. The specific optimization process may include but is not limited to: rearranging materials, by changing the placement angle of the target materials, so that the target materials are arranged more closely together, thereby reducing gaps; using vertical space, stacking the target materials upwards to fully utilize the vertical height of the three-dimensional storable space.
[0086] After each adjustment, the server 104 will analyze the occupancy of each voxel in the three-dimensional storable space to re-evaluate the space utilization of the current initial stacking strategy. If the adjusted initial stacking strategy has a higher space utilization, it will be further optimized until the space utilization can no longer be further improved through adjustment, and the target stacking strategy will be obtained. At this time, the target stacking strategy has reached the optimal state of space utilization.
[0087] In this embodiment, the initial stacking strategy is adjusted with the goal of maximizing space utilization, so that more target materials can be stored in the same three-dimensional storable space, reducing the gaps in the three-dimensional storable space, thereby reducing storage costs, and the target stacking strategy is obtained by continuously optimizing the initial stacking strategy, thereby improving the accuracy of the target stacking strategy.
[0088] In addition to the adjustment method of the initial stacking strategy in the above embodiment, the placement angle of the target material in the material stacking area can also be adjusted to improve the space utilization. In an exemplary embodiment, the initial stacking strategy includes the material stacking area and the placement angle of the target material in the material stacking area, and S300 includes: when the space utilization is less than a preset space utilization threshold, adjusting the placement angle of the target material in the material stacking area until a target stacking strategy with a space utilization greater than or equal to the preset space utilization threshold is obtained.
[0089] Among them, the initial stacking strategy includes two key elements: the material stacking area and the placement angle of the target material in the area. The placement angle determines the specific placement method of the target material in the material stacking area, which will directly affect the space utilization and the degree of coordination between the target materials.
[0090] For example, in the initial stacking strategy, the placement angle may be determined based on some basic principles, such as the shape of the target material, the size and shape of the three-dimensional storable space, and the placement of other materials. When the space utilization rate is lower than the preset space utilization rate threshold, adjusting the placement angle can reduce the gaps between the materials, thereby improving the space utilization rate of the three-dimensional storable space. Specific adjustment methods include but are not limited to: rotating the target material by a certain angle in the horizontal plane; changing the inclination angle of the target material to make it closer to other materials or walls, thereby reducing the gaps in the vertical space; adjusting the angles of multiple target materials at the same time, for example, rotating two adjacent target materials at a certain angle at the same time may form a more compact arrangement, thereby reducing the gaps in the space.
[0091] After each adjustment of the placement angle, the server 104 will recalculate the space utilization and determine whether a preset space utilization threshold is reached, until a target stacking strategy is obtained in which the space utilization is greater than or equal to the preset space utilization threshold.
[0092] In this embodiment, by adjusting the placement angle and changing the arrangement of materials, the gaps between materials can be reduced, thereby more efficiently utilizing the storage space. This is especially suitable for target materials with irregular shapes and can significantly improve the space utilization of the three-dimensional storable space.
[0093] In addition, during the simulated stacking process, the initial stacking strategy can be optimized and adjusted according to the movement trajectory of the target material. Figure 5 As shown, the initial stacking strategy includes the material stacking area, and after S100, it also includes:
[0094] S410, based on the initial stacking strategy, simulate the stacking of the target material and determine the movement trajectory of the target material during the simulated stacking process.
[0095] S420, determining that the stacking robot cannot stack the target material in the material stacking area according to the motion trajectory.
[0096] S430, adjusting the position information of the target material, and returning to S100, until the stacking robot stacks the target material in the material stacking area according to the motion trajectory, and obtaining the target stacking strategy.
[0097] Among them, the motion trajectory refers to the entire motion process of the stacking robot starting from obtaining the target material, through path planning, and moving the target material to the material stacking area.
[0098] Specifically, the server 104 simulates the stacking process based on the initial stacking strategy, performs a series of simulated stacking operations, obtains the motion trajectory of the target material during the stacking process, and then analyzes the motion trajectory of the target material, calculates the dynamic changes of the target material in space, such as displacement and rotation, and determines whether it will collide or get stuck with surrounding obstacles or other materials, and whether it can move according to the motion trajectory within the working range of the stacking robot, so as to evaluate the feasibility of the stacking process.
[0099] If the evaluation results show that the robot cannot complete the stacking task according to the planned trajectory, the location information of the target material can be changed to make it easier for the stacking robot to access the target material, simplify the operation path of the stacking robot, and regenerate the initial stacking strategy until the stacking robot stacks the target material in the material stacking area according to the motion trajectory to obtain the target stacking strategy. In addition, the restriction parameters or hardware parameters of the stacking robot can be manually changed to allow the stacking robot to move according to the motion trajectory.
[0100] In this embodiment, by adjusting and verifying the feasibility of the motion trajectory, the final target stacking strategy is not only effective in theory but also feasible in actual operation, which reduces the failures or problems that may occur in the stacking process, obtains a more accurate target stacking strategy, and improves the efficiency and safety of warehousing operations.
[0101] In an exemplary embodiment, obtaining the size of a target material includes: selecting a target material to be stacked from materials of different stack shapes, obtaining an initial size of the target material, and correcting the initial size of the target material based on a preset camera recognition error to obtain the size of the target material.
[0102] Since in actual storage environments, the stack shapes of target materials are usually diverse, including but not limited to regular cube shapes, rectangular parallelepiped shapes, irregular shapes, etc., in order to be closer to the actual situation, this solution simulates materials of different stack shapes, and randomly selects the target materials to be stacked, and obtains the initial size of the target materials. Furthermore, in the actual stacking process, the size of the target material is usually identified through image recognition technology, cameras or other sensor data. Taking the size of the target material collected by the camera as an example, due to the limited accuracy of the camera, the identified size may deviate from the actual size. Therefore, this solution also randomly corrects the initial size of the target material based on the preset camera recognition error to make it closer to the actual situation and obtain the size of the target material.
[0103] In this embodiment, by introducing a preset camera recognition error, the size of the randomly selected target material is corrected, so that the simulation process is closer to the actual stacking process, thereby more accurately planning the stacking position and method of the target material and obtaining a more accurate stacking strategy.
[0104] In order to make a clearer description of the stacking strategy determination method provided by the present application, the following is a specific embodiment and the attached Figure 6 To illustrate, this specific embodiment includes the following steps:
[0105] S601, selecting a target material to be stacked from materials of different stack shapes, obtaining an initial size of the target material, and correcting the initial size of the target material based on a preset camera recognition error to obtain the size of the target material.
[0106] S602, determining a plurality of candidate stacking areas according to the size of the target material and the occupation status of each voxel in the three-dimensional storable space.
[0107] S603: Based on a preset stacking quality scoring standard, determine a stacking quality score when the target material is stacked in each candidate stacking area.
[0108] S604: Determine the candidate stacking area with the highest stacking quality score as the material stacking area of the target material, and determine an initial stacking strategy according to the material stacking area and position information of the target material.
[0109] S605: Based on the initial stacking strategy, simulate the stacking of the target material and determine the space utilization rate corresponding to the initial stacking strategy.
[0110] S606: Determine whether the space utilization is less than a preset space utilization threshold.
[0111] S607: When the space utilization is greater than or equal to a preset space utilization threshold, the initial stacking strategy is determined as the target stacking strategy;
[0112] S608, when the space utilization is less than the preset space utilization threshold, adjust the weights of multiple preset stacking quality scoring criteria, and return to S603 until a target stacking strategy with a space utilization greater than or equal to the preset space utilization threshold is obtained.
[0113] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0114] Based on the same inventive concept, the embodiment of the present application also provides a stacking strategy determination device for implementing the stacking strategy determination method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more stacking strategy determination device embodiments provided below can refer to the limitations of the stacking strategy determination method above, and will not be repeated here.
[0115] In an exemplary embodiment, Figure 7 As shown, a stacking strategy determination device 700 is provided, comprising: a strategy determination module 710, a space utilization determination module 720 and a strategy optimization module 730, wherein:
[0116] The strategy determination module 710 is used to determine the initial stacking strategy based on the size and position information of the target material and the occupation status of each voxel in the three-dimensional storable space.
[0117] The space utilization rate determination module 720 is used to simulate the stacking of target materials based on the initial stacking strategy and determine the space utilization rate corresponding to the initial stacking strategy.
[0118] The strategy optimization module 730 is used to adjust the initial stacking strategy based on the space utilization rate to obtain the target stacking strategy.
[0119] In an exemplary embodiment, the strategy determination module 710 is also used to determine multiple candidate stacking areas based on the size of the target material and the occupancy status of each voxel in the three-dimensional storable space, and determine the stacking quality score when the target material is stacked in each candidate stacking area based on a preset stacking quality scoring standard. The stacking quality scoring standard includes at least one of a space utilization scoring standard, an empty rate scoring standard, and a stack regularity scoring standard. The candidate stacking area with the highest stacking quality score is determined as the material stacking area of the target material, and the initial stacking strategy is determined based on the material stacking area and location information of the target material.
[0120] In an exemplary embodiment, there are multiple preset stacking quality scoring standards, and the strategy optimization module 730 is also used to determine the initial stacking strategy as the target stacking strategy when the space utilization is greater than or equal to the preset space utilization threshold, and adjust the weights of multiple preset stacking quality scoring standards when the space utilization is less than the preset space utilization threshold. The control strategy determination module 710 again executes the steps of determining the stacking quality score when the target material is stacked in each candidate stacking area based on the preset stacking quality scoring standard until a target stacking strategy with a space utilization greater than or equal to the preset space utilization threshold is obtained.
[0121] In an exemplary embodiment, the strategy optimization module 730 is further configured to adjust the initial stacking strategy with the goal of maximizing space utilization, so as to obtain a target stacking strategy with the maximum space utilization.
[0122] In an exemplary embodiment, the initial stacking strategy includes a material stacking area and a placement angle of a target material in the material stacking area. The strategy optimization module 730 is also used to adjust the placement angle of the target material in the material stacking area when the space utilization is less than a preset space utilization threshold, until a target stacking strategy is obtained in which the space utilization is greater than or equal to the preset space utilization threshold.
[0123] In an exemplary embodiment, Figure 8 As shown, the stacking strategy determination device 700 also includes a motion trajectory determination module 740, which is used to simulate the stacking of the target material based on the initial stacking strategy, determine the motion trajectory of the target material during the simulated stacking process, and adjust the position information of the target material when the stacking robot cannot stack the target material in the material stacking area according to the motion trajectory. The control strategy determination module 710 again executes the step of determining the initial stacking strategy based on the size and position information of the target material and the occupancy status of each voxel in the three-dimensional storable space, until the stacking robot stacks the target material in the material stacking area according to the motion trajectory, and obtains the target stacking strategy.
[0124] In an exemplary embodiment, the strategy determination module 710 is also used to select the target material to be stacked from materials of different stack shapes, obtain the initial size of the target material, and correct the initial size of the target material based on a preset camera recognition error to obtain the size of the target material.
[0125] Each module in the above-mentioned stacking strategy determination device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.
[0126] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG9. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as the size and position information of the target material. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for determining a stacking strategy is implemented.
[0127] Those skilled in the art will understand that the structure shown in FIG. 9 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.
[0128] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps in the above-mentioned embodiments of the method for determining a stacking strategy are implemented.
[0129] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned stacking strategy determination method embodiments are implemented.
[0130] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above-mentioned stacking strategy determination method embodiments when executed by a processor.
[0131] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0132] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.
[0133] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.
[0134] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A method for determining a stacking strategy, characterized in that: The method comprises: Determine the initial stacking strategy based on the size and location information of the target material and the occupancy status of each voxel in the three-dimensional storable space; Based on the initial stacking strategy, simulate the stacking of the target material to determine the space utilization rate corresponding to the initial stacking strategy; Based on the space utilization, the initial stacking strategy is adjusted to obtain a target stacking strategy.
2. The method according to claim 1, characterized in that: The initial stacking strategy is determined based on the size and position information of the target material and the occupation status of each voxel in the three-dimensional storable space, including: Determine a plurality of candidate stacking areas according to the size of the target material and the occupation status of each voxel in the three-dimensional storable space; Based on a preset stacking quality scoring standard, determining a stacking quality score when the target material is stacked in each candidate stacking area, wherein the stacking quality scoring standard includes at least one of a space utilization scoring standard, an empty rate scoring standard, and a stack regularity scoring standard; Determine the candidate stacking area with the highest stacking quality score as the material stacking area for the target material; The initial stacking strategy is determined according to the material stacking area of the target material and the position information.
3. The method according to claim 2, characterized in that The number of the preset stacking quality scoring standards is multiple; The adjusting the initial stacking strategy based on the space utilization to obtain a target stacking strategy includes: When the space utilization rate is greater than or equal to a preset space utilization rate threshold, determining the initial stacking strategy as the target stacking strategy; When the space utilization rate is less than a preset space utilization rate threshold, adjusting the weights of the plurality of preset stacking quality scoring criteria; Returning to the preset stacking quality scoring standard, determining the stacking quality scoring step when stacking the target materials in each candidate stacking area, until a target stacking strategy is obtained in which the space utilization is greater than or equal to a preset space utilization threshold.
4. The method according to claim 1, characterized in that The adjusting the initial stacking strategy based on the space utilization to obtain a target stacking strategy includes: With the maximization of the space utilization as the goal, the initial stacking strategy is adjusted to obtain the target stacking strategy when the space utilization is maximized.
5. The method according to claim 1, characterized in that The initial stacking strategy includes a material stacking area and a placement angle of the target material in the material stacking area; The adjusting the initial stacking strategy based on the space utilization to obtain a target stacking strategy includes: When the space utilization is less than a preset space utilization threshold, the placement angle of the target material in the material stacking area is adjusted until a target stacking strategy is obtained in which the space utilization is greater than or equal to the preset space utilization threshold.
6. The method according to any one of claims 1 to 5, characterized in that: The initial stacking strategy includes a material stacking area. After determining the initial stacking strategy, the method further includes: Based on the initial stacking strategy, simulating the stacking of the target material, and determining the movement trajectory of the target material during the simulated stacking process; When the stacking robot cannot stack the target material in the material stacking area according to the motion trajectory, adjusting the position information of the target material; Return to the step of determining the initial stacking strategy based on the size and position information of the target material and the occupancy status of each voxel in the three-dimensional storable space, until the stacking robot stacks the target material in the material stacking area according to the motion trajectory, and obtains the target stacking strategy.
7. The method according to any one of claims 1 to 5, characterized in that: Obtaining the size of the target material, including: Selecting a target material to be stacked from materials of different stack shapes, and obtaining an initial size of the target material; Based on a preset camera recognition error, the initial size of the target material is corrected to obtain the size of the target material.
8. A stacking strategy determination device, characterized in that: The device comprises: A strategy determination module, used to determine an initial stacking strategy based on the size and position information of the target material and the occupancy status of each voxel in the three-dimensional storable space; A space utilization rate determination module, used to simulate the stacking of the target material based on the initial stacking strategy, and determine the space utilization rate corresponding to the initial stacking strategy; The strategy optimization module is used to adjust the initial stacking strategy based on the space utilization to obtain a target stacking strategy.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
Citation Information
Cited By
Stacking position detection and judgment method, electronic equipment and storage medium
CN120031863A
