Intelligent scheduling system and method for intelligent palletizing robot

Abstract

This invention provides an intelligent scheduling system and method for an intelligent palletizing robot. The method includes the following steps: S1: acquiring material point cloud data and identifying material dimensions using a depth camera, and obtaining material weight; S2: calculating material volume based on material dimensions, and obtaining density value by combining material weight; calculating the stroke parameters of the pneumatic gripper, and generating a palletizing scheme through an intelligent planning algorithm; S3: controlling the opening and closing of the pneumatic gripper based on the stroke parameters to grasp the material, and executing the palletizing scheme to complete material stacking; S4: detecting the shape of the stacked material, so that the WMS storage location scheduling module delivers the material to a suitable storage location based on the detection results. This invention addresses the morphological characteristics of flexible materials by employing a size recognition method combining convex hull analysis and outlier filtering, improving the measurement accuracy of irregular objects and solving the problems of slow shape change, high breakage, and inefficient scheduling of multi-specification flexible bulk materials such as tea in the palletizing process.

Description

Technical Field

[0001] This invention relates to the field of industrial robot control and intelligent logistics scheduling system technology, specifically to an intelligent scheduling system and method for an intelligent palletizing robot, and more particularly to an intelligent scheduling system and method for an intelligent palletizing robot for multi-specification flexible bulk materials. Background Technology

[0002] Existing tea product palletizing technologies mostly employ robots with fixed programs, which have the following core drawbacks:

[0003] 1. Poor specification adaptability: It can only adapt to a single packaging form, with a long changeover time, and cannot meet the needs of materials with multiple specifications such as tea powder and tea extract (e.g., The tea product industry faces the need for flexible production (including mixed packaging). Traditional equipment, due to its fixed mechanical structure, struggles to accommodate fluctuations in material specifications (such as packaging size deviations). ).

[0004] 2. Insufficient visual recognition accuracy: 2D visual positioning has large errors and cannot accurately identify the deformation characteristics of flexible bulk materials (such as the shape fluctuations of tea powder bags due to differences in filling amount), resulting in poor stacking stability (high collapse rate). In severe cases, this can lead to damage to the material packaging.

[0005] 3. Rigid scheduling strategy: The palletizing and warehousing processes are disconnected and not linked to the AGV logistics system, resulting in low equipment utilization. Traditional solutions lack dynamic scheduling models, leading to low warehouse space utilization and high material delivery delays.

[0006] Patent document CN220130470U discloses a tea-dried fruit stacking device for tea-dried fruit production and processing. Its workflow involves conveying the tea-dried fruit via a conveyor belt. During this process, the tea-dried fruit slides smoothly into a storage box on top of a weighing platform via a guide plate and a receiving plate. Once the weight of the tea-dried fruit reaches the set weight of the weighing platform, a first pusher plate pushes the storage box to the stacking platform. Then, a second pusher plate pushes the storage box inside the placement compartment to the top of the weighing platform for further packing. When the number of storage boxes at the stacking platform reaches three, it is pushed to the other end of the stacking platform. However, this patent document still fails to solve the aforementioned technical problem.

[0007] The fundamental reason is that the existing system lacks... The linkage detection mechanism failed to achieve adaptive adjustment of the mechanical structure, and no code was constructed. The integrated scheduling model is difficult to adapt to the multi-specification and non-standard characteristics of flexible bulk materials such as tea. Summary of the Invention

[0008] In view of the deficiencies in the prior art, the purpose of this invention is to provide an intelligent scheduling system and method for intelligent palletizing robots.

[0009] An intelligent scheduling system for an intelligent palletizing robot according to the present invention includes:

[0010] The three-dimensional intelligent size recognition module is used to extract the size data of the material from the collected material point cloud data;

[0011] The material density estimation module calculates the material density based on the material's size data and weight information.

[0012] The pneumatic gripper stroke adaptation module calculates the stroke parameters of the pneumatic gripper and adds a safety margin based on the material's size data and density.

[0013] The adaptive palletizing scheme generation module generates the optimal palletizing scheme based on the material's size data and safety margin through an intelligent planning algorithm.

[0014] The WMS storage location scheduling module filters out candidate storage locations with suitable dimensions from the available storage locations based on the size data of the materials and the safety margin, matches the optimal storage location through a two-layer optimization algorithm, and issues storage location allocation instructions.

[0015] The IoT communication platform is used to complete the interactive control between the WMS software system and the equipment automation control system.

[0016] Preferably, the process of extracting material size data by the three-dimensional size intelligent recognition module includes:

[0017] Outlier filtering is performed on the raw point cloud data, and the Z-score algorithm is used to remove noise points that deviate from the mean by more than 3 times the standard deviation.

[0018] The preprocessed point cloud is projected onto the XY plane to construct a convex hull model to fit the outer contour of the material. The length of the material is determined by calculating the maximum distance between the vertices of the convex hull, and the width is calculated by the projection difference perpendicular to the longest axis.

[0019] The material height is obtained by directly extracting the maximum coordinate difference of the point cloud in the Z-axis direction.

[0020] Preferably, the pneumatic gripper stroke adaptation module extracts the maximum dimension of the material in the length direction as the gripper opening and closing reference, and dynamically increases the bidirectional safety margin based on the density on the basis of the maximum dimension to compensate for the shape changes when gripping flexible materials.

[0021] Preferably, the process of generating the optimal palletizing scheme through the intelligent planning algorithm includes:

[0022] Introduce a safety margin parameter to correct for the actual dimensions of the material;

[0023] The system automatically simulates two placement directions, calculates the amount of material that a single layer can hold, and selects the direction with the larger capacity as the optimal placement method.

[0024] The maximum number of palletizing layers is determined based on the ratio of the pallet height limit to the adjusted height of the material, combined with the maximum allowable layer threshold.

[0025] Preferably, the automatic simulation of two placement orientations includes the original orientation and Rotation direction; calculate the amount of material that can be held in a single layer by integer division of the tray size and the corrected material size.

[0026] Preferably, the WMS storage location scheduling module obtains idle storage location data through the WMS interface and establishes a standardized model including storage location code, region, floor height, size limit and access priority; using the length, width and height of the goods obtained by shape detection as input, a safety margin parameter is introduced to correct the actual needs, and candidate storage locations with suitable size are selected from the idle storage locations.

[0027] Preferably, the WMS storage location scheduling module uses a two-layer optimization algorithm to select the optimal storage location; sorts the storage location groups according to their constraints, calculates the height utilization rate, and selects the storage location that best matches the cargo height requirements; and issues storage location allocation instructions through the WMS interface and returns scheduling results containing storage location information.

[0028] An intelligent scheduling method for an intelligent palletizing robot provided by the present invention includes:

[0029] Step S1: Collect material point cloud data and identify material size using a depth camera to obtain material weight;

[0030] Step S2: Calculate the material volume based on the material size and obtain the density value by combining the material weight; calculate the stroke parameters of the pneumatic gripper and generate a palletizing scheme through an intelligent planning algorithm;

[0031] Step S3: Based on the stroke parameters, control the pneumatic gripper to open and close to grab the material, and execute the palletizing scheme to complete the material stacking;

[0032] Step S4: Detect the shape of the stacked materials, so that the WMS storage location scheduling module can deliver the materials to the appropriate storage location to complete the warehousing based on the detection results.

[0033] Preferably, the calculation process for the material size includes:

[0034] The Z-score algorithm is used to remove noise points that deviate from the mean by more than three times the standard deviation.

[0035] Construct a convex hull model in the XY plane to calculate the length and width of the material;

[0036] The material height is obtained based on the maximum coordinate difference in the Z-axis direction.

[0037] Preferably, the palletizing scheme includes the material placement direction, layout of each layer, quantity of each layer, total number of layers, total capacity, and distribution of remaining space.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] 1. This invention addresses the morphological characteristics of flexible materials by employing a size recognition method that combines convex hull analysis and outlier filtering, thereby improving the measurement accuracy of irregular objects. Through multi-directional simulation and dynamic adaptation of safety margins, it achieves a balance between intelligence and safety in palletizing solutions. Simultaneously, it integrates dimensional data with multi-scenario requirements to form an integrated solution from recognition to execution, solving the problems of slow shape change, high breakage, and inefficient scheduling in the palletizing process of flexible bulk materials such as tea, while reducing manual intervention and improving the flexibility and adaptability of automated production lines.

[0040] 2. This invention constructs a "palletizing posture" The matching algorithm for "warehouse height" is used by the AGV based on the inbound shape detection data (height recognition accuracy). Automatic delivery to suitable storage locations increases warehouse space utilization to a higher level. Equipment utilization rate increased to This solves the problems of slow shape change, high breakage, and inefficient scheduling of flexible bulk materials such as tea in the palletizing process.

[0041] 3. This invention integrates multiple technologies. From the bottom up, the underlying layer adopts a real-time equipment data acquisition system that is compatible with multiple industrial control communication protocols such as MQTT and Siemens S7. It uses a vision camera to detect the length, width, and height of materials, and combines the weight to estimate the density, and intelligently calculates the appropriate palletizing formula. After palletizing, it calculates the appropriate storage location information based on the length, width, and height data detected by the shape, and links the scheduling system to transport the materials to the appropriate storage area.

[0042] 4. The data acquisition platform in this invention adopts the industry-standard industrial control data transmission protocol, which is then encapsulated into an IoT platform. This platform adds device connection configuration management, acquisition attribute group management, and acquisition attribute configuration, and is an infrastructure platform. The IoT platform enables interactive control between the WMS software system and the equipment automation control system.

[0043] 5. In this invention, the various modules of the system form a closed loop through data chain transmission: 3D dimension recognition provides basic parameters for all subsequent modules; palletizing scheme generation relies on accurate dimension data to achieve spatial optimization; density estimation combines size and weight to achieve material characteristic analysis; gripper stroke calculation based on dimension data ensures gripping reliability; storage location scheduling selects a suitable shape detection scheme based on dimension calculation and performs transportation scheduling based on the shape detection results; the system coordinates the timing of each module through unified control logic to achieve full automation from material identification to warehousing processing execution, which is suitable for scenarios such as logistics sorting, warehousing palletizing, and flexible manufacturing, significantly improving processing efficiency and adaptation accuracy. Attached Figure Description

[0044] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0045] Figures 1a-1c This is a schematic diagram of the docking device between the intelligent palletizing robot and the automated warehouse elevator in an embodiment of the present invention.

[0046] Figure 2 This is a schematic diagram of the automated control system for the conveyor line in this invention.

[0047] Figure 3 This is the code used in this embodiment of the invention to extract parameters of flexible materials.

[0048] Figure 4 This is a schematic diagram illustrating the classification and storage of high, medium, and low-grade goods in the warehouse storage location group management system of this invention.

[0049] Figure 5 This is a schematic diagram of the data read / write configuration of the IoT platform in this invention.

[0050] Figure 6 This is a pre-set palletizing recipe template and a palletizing feedback diagram in an embodiment of the present invention.

[0051] Figure 7 This is a schematic diagram illustrating the flexible stroke gripping of a pneumatic gripper achieved using width and material density in an embodiment of the present invention.

[0052] Figure 8 This is a schematic diagram of the system collaboration process of the present invention.

[0053] Figure 9 This is a flowchart illustrating the calculation of the three-dimensional dimensions of materials in this invention.

[0054] Figure 10 This is the palletizing optimization decision tree of the present invention.

[0055] Figure 11 This is a flowchart illustrating the workflow of the pneumatic gripper stroke adaptation module of the present invention.

[0056] Figure 12 This is a flowchart of the WMS storage location scheduling module in this invention. Detailed Implementation

[0057] The present invention will now be described in detail with reference to specific embodiments. These embodiments will help those skilled in the art to further understand the present invention, but do not limit the invention in any way. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all fall within the protection scope of the present invention.

[0058] Example 1

[0059] Figure 1 shows a schematic diagram of the docking device between the intelligent palletizing robot and the automated warehouse elevator in this embodiment. Figure 1a This is a top view. Figure 1b This is a schematic diagram of the three-dimensional structure. Figure 1c This is a side view;

[0060] An intelligent scheduling system for an intelligent palletizing robot includes:

[0061] 3D dimension intelligent recognition module:

[0062] like Figure 2 As shown, the depth camera (positioning error) is installed on the right side of the gripping position. The robot's pneumatic gripper stroke (adjustment range) is dynamically adjusted based on the material density calculated in conjunction with its weight. ), achieving bag sizes from 30kg to 60kg, etc. Changeover without downtime for standard materials (changeover time) (minutes), material breakage rate is 0;

[0063] like Figure 3 As shown, this module takes point cloud data collected by a depth camera as input and achieves accurate extraction of the length, width, and height parameters of flexible materials through multi-step data processing:

[0064] 1. Point cloud preprocessing: The raw point cloud data is filtered for outliers. The Z-score algorithm is used to remove noise points that deviate from the mean by more than 3 times the standard deviation (such as redundant points caused by wrinkles on the material surface) to ensure data validity.

[0065] 2. Convex Hull Analysis: Project the preprocessed point cloud onto the XY plane to construct a convex hull model to fit the outer contour of the material. The material length (longest axis) is determined by calculating the maximum distance between the vertices of the convex hull, and the width (shortest axis) is calculated by the projection difference perpendicular to the direction of the longest axis, adapting to the irregular shape of flexible materials.

[0066] 3. Height Calculation: The maximum coordinate difference of the point cloud in the Z-axis direction is directly extracted to obtain the material height, avoiding measurement deviations caused by local protrusions;

[0067] 4. Output Results: The processed length, width, and height parameters are accurate to 1mm, providing basic data for subsequent processes.

[0068] Adaptive palletizing scheme generation module

[0069] like Figure 6 As shown, based on three-dimensional dimensional data and preset palletizing recipes (pallet length, width, and height limits), an optimal palletizing scheme is generated through an intelligent planning algorithm:

[0070] Parameter adaptation: Introduce a safety margin parameter (default 10mm) to correct the actual size of the material and avoid stacking interference caused by slight deformation of flexible materials;

[0071] Orientation optimization: Automatically simulates two placement orientations (original orientation and...) Calculate the number of materials that a single layer can hold (by dividing the pallet size by the corrected material size by an integer) for each rotation direction, and select the direction with the larger capacity as the optimal placement method;

[0072] Layer Calculation: Based on the ratio of the pallet height limit to the adjusted height of the material, combined with the maximum allowable layer threshold, determine the maximum number of stacking layers to ensure that the height limit is not exceeded;

[0073] Solution output: Generate a complete solution including placement direction, layout (number of rows and columns) of each layer, quantity of each layer, total number of layers, total capacity and distribution of remaining space, providing a basis for execution of automated palletizing equipment.

[0074] Material density estimation module

[0075] 1. By combining three-dimensional dimensions and weight data, rapid calculation of material density can be achieved:

[0076] 2. Volume Conversion: Convert length, width, and height parameters (in millimeters) to centimeters to calculate material volume (length...). Width high);

[0077] 3. Density Calculation: The density is obtained by using the ratio of weight (acquired by sensors) to volume. Density values ​​in units, accurate to [number] ;

[0078] Pneumatic gripper stroke adapter module

[0079] like Figure 7 and Figure 11 As shown, based on three-dimensional size and density data, the stroke parameters of the adapted pneumatic gripper are automatically calculated:

[0080] Reference selection: The maximum dimension in the length direction of the extracted material is used as the reference for the opening and closing of the grippers to ensure the maximum span of the covered material;

[0081] Safety redundancy: Based on the maximum size, a bidirectional safety margin is dynamically increased according to the density (the baseline is 10mm / side) to compensate for the shape changes when gripping flexible materials;

[0082] Stroke output: The calculation results are accurate to 0.1cm and are directly used as parameter inputs for the gripper control system to ensure gripping stability.

[0083] WMS storage scheduling module based on shape detection

[0084] like Figure 12 As shown, available storage space data is obtained through the WMS interface, and a standardized model is established, including storage space code, region, floor height, size restrictions, and access priority. Using the length, width, and height of the goods obtained from shape detection as input, safety margin parameters (height 10mm, length and width 10mm) are introduced to correct for actual needs, and candidate storage spaces with suitable sizes are selected from the available storage spaces.

[0085] like Figure 4 As shown, a "palletizing posture - storage height" matching algorithm is constructed. The AGV uses the incoming shape detection data (height recognition accuracy) to determine the appropriate height. Automatic delivery to suitable storage locations increases warehouse space utilization. Equipment utilization rate increased to This addresses the issues of slow shape change, high breakage rate, and inefficient scheduling in the palletizing process for flexible bulk materials such as tea.

[0086] A two-layer optimization algorithm is used to select the optimal storage location: first, storage locations are sorted according to the constraints of the storage location group, with higher priority locations given priority; then, the height utilization rate is calculated, and the storage location that best matches the height requirements of the goods is selected to reduce space waste. Finally, storage location allocation instructions are issued through the WMS interface, and scheduling results containing storage location information are returned, realizing an automated closed loop from appearance detection to warehousing.

[0087] The modules form a closed loop through data chain transmission: 3D dimension recognition provides basic parameters for all subsequent modules; palletizing scheme generation relies on accurate dimensional data to achieve spatial optimization; density estimation combines size and weight to achieve material characteristic analysis; gripper stroke calculation based on dimensional data ensures gripping reliability; storage location scheduling selects appropriate shape detection schemes based on dimensional calculations and performs transportation scheduling based on shape detection results. The system coordinates the timing of each module through unified control logic, achieving full automation from material identification to warehousing processing execution. It is suitable for scenarios such as logistics sorting, warehouse palletizing, and flexible manufacturing, significantly improving processing efficiency and adaptation accuracy.

[0088] As shown in Table 1, the system components also include:

[0089] Table 1 Components and their corresponding functions

[0090]

[0091] like Figure 5 As shown, the data acquisition platform also adopts the industry-standard industrial control data transmission protocol, which is then encapsulated into an IoT platform. This platform adds features such as device connection configuration management, acquisition attribute group management, and acquisition attribute configuration, making it an infrastructure platform. The IoT platform facilitates the interactive control between the WMS software system and the equipment automation control system.

[0092] The IoT platform is used to access the internal resources of the PLC, including:

[0093] Read and write the status of input / output (I / O) points;

[0094] Read and write data in memory areas (such as the M area and DB area);

[0095] Obtain PLC operating status and fault information;

[0096] Remote control of PLC (such as starting and stopping).

[0097] Example 2

[0098] The system mentioned above includes three operating modes: automatic palletizing and warehousing of raw materials, manual palletizing and warehousing, and palletized warehousing. Operators can select the corresponding production mode and configure material information on the interface (or receive it from the WMS).

[0099] like Figure 8 and Figure 9 As shown, an intelligent scheduling method for an intelligent palletizing robot includes:

[0100] Step 1: Empty pallet groups / empty pallets are put into the online empty pallet loading point, enter the pallet depalletizer to be broken into individual pallets and supplied to the automatic palletizing station, where the pallet barcode information is scanned;

[0101] Step 2: Raw materials are fed from the right telescopic belt conveyor and stop at the automatic palletizing station to wait for the robotic arm to grab them;

[0102] Step 3: Capture the position signal to trigger the change judgment. After the change judgment, visually identify the length, width and height information of the goods and output it to the automatic control program.

[0103] Step 4: The automated control program calculates the material density based on visual recognition information and weight, and adds pneumatic gripper stroke control parameters to the palletizing scheme specified in the formula.

[0104] Step 5: The robotic arm grabs the raw materials and stacks them onto the pallet according to the gripping stroke and palletizing plan provided by the upper-level information system;

[0105] Step 6: After the raw material robot completes the palletizing, the system will bundle the pallet barcode information and the palletized raw material information and upload them to the WMS.

[0106] like Figure 10 As shown in step 7, the WMS matches the appropriate storage location group according to the height of the cargo location and initiates a logistics scheduling instruction; after the AGV arrives at the location and connects, the AGV is scheduled to transport the cargo to the high / medium / low storage location in the warehouse area.

[0107] Those skilled in the art will understand that, besides implementing the system and its various devices, modules, and units provided by this invention in the form of purely computer-readable program code, the same functions can be achieved entirely through logical programming of the method steps, making the system and its various devices, modules, and units of this invention function in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, the system and its various devices, modules, and units provided by this invention can be considered as a hardware component, and the devices, modules, and units included therein for implementing various functions can also be considered as structures within the hardware component; alternatively, the devices, modules, and units for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0108] Specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art can make various changes or modifications within the scope of the claims, which do not affect the essence of the present invention. Unless otherwise specified, the embodiments and features described in this application can be arbitrarily combined with each other.

Claims

1. An intelligent scheduling system for an intelligent palletizing robot, characterized in that, include: The three-dimensional intelligent size recognition module is used to extract the size data of the material from the collected material point cloud data; The material density estimation module calculates the material density based on the material's size data and weight information. The pneumatic gripper stroke adaptation module calculates the stroke parameters of the pneumatic gripper based on the material's size data and density. The pneumatic gripper stroke adaptation module extracts the maximum dimension of the material's length direction as the gripper's opening and closing reference, and dynamically increases the bidirectional safety margin based on the density on the basis of the maximum dimension to compensate for the shape changes when gripping flexible materials. The adaptive palletizing scheme generation module generates the optimal palletizing scheme based on the material's size data and safety margin through an intelligent planning algorithm. The WMS storage location scheduling module filters out candidate storage locations with suitable dimensions from the available storage locations based on the size data of the materials and the safety margin, matches the optimal storage location through a two-layer optimization algorithm, and issues storage location allocation instructions. The WMS storage location scheduling module obtains idle storage location data through the WMS interface and establishes a standardized model that includes storage location code, region, floor height, size limit and access priority; using the length, width and height of the goods obtained by shape detection as input, it introduces safety margin parameters to correct actual needs and selects candidate storage locations with suitable size from the idle storage locations; The WMS storage location scheduling module uses a two-layer optimization algorithm to select the optimal storage location; it sorts the storage location groups according to their constraints, calculates the height utilization rate, and selects the storage location that best matches the height requirements of the goods; it issues storage location allocation instructions through the WMS interface and returns scheduling results containing storage location information. The IoT communication platform is used to complete the interactive control between the WMS software system and the equipment automation control system.

2. The intelligent scheduling system for the intelligent palletizing robot according to claim 1, characterized in that, The process by which the three-dimensional intelligent size recognition module extracts the size data of the material includes: Outlier filtering is performed on the raw point cloud data, and the Z-score algorithm is used to remove noise points that deviate from the mean by more than 3 times the standard deviation. The preprocessed point cloud is projected onto the XY plane to construct a convex hull model to fit the outer contour of the material. The length of the material is determined by calculating the maximum distance between the vertices of the convex hull, and the width is calculated by the projection difference perpendicular to the longest axis. The material height is obtained by directly extracting the maximum coordinate difference of the point cloud in the Z-axis direction.

3. The intelligent scheduling system for the intelligent palletizing robot according to claim 1, characterized in that, The process of generating the optimal palletizing scheme through intelligent planning algorithm includes: Introduce a safety margin parameter to correct for the actual dimensions of the material; The system automatically simulates two placement directions, calculates the amount of material that a single layer can hold, and selects the direction with the larger capacity as the optimal placement method. The maximum number of palletizing layers is determined based on the ratio of the pallet height limit to the adjusted height of the material, combined with the maximum allowable layer threshold.

4. The intelligent scheduling system for the intelligent palletizing robot according to claim 3, characterized in that, The automatic simulation includes two placement directions: the original direction and a 90° rotation direction; the number of materials that can be accommodated in a single layer is calculated by integer division of the tray size and the corrected material size.

5. An intelligent scheduling method for an intelligent palletizing robot, based on the intelligent scheduling system for the intelligent palletizing robot according to any one of claims 1-4, characterized in that, include: Step S1: Collect material point cloud data and identify material size using a depth camera to obtain material weight; Step S2: Calculate the material volume based on the material size and obtain the density value by combining the material weight; calculate the stroke parameters of the pneumatic gripper and dynamically increase the bidirectional safety margin based on the density on the basis of the maximum size to compensate for the shape changes when gripping flexible materials; generate a palletizing scheme through intelligent planning algorithm. Step S3: Based on the stroke parameters, control the pneumatic gripper to open and close to grab the material, and execute the palletizing scheme to complete the material stacking; Step S4: Detect the shape of the stacked materials, so that the WMS storage location scheduling module can deliver the materials to the appropriate storage location to complete the warehousing based on the detection results.

6. The intelligent scheduling method for the intelligent palletizing robot according to claim 5, characterized in that, The calculation process for the material dimensions includes: The Z-score algorithm is used to remove noise points that deviate from the mean by more than three times the standard deviation. Construct a convex hull model in the XY plane to calculate the length and width of the material; The material height is obtained based on the maximum coordinate difference in the Z-axis direction.

7. The intelligent scheduling method for the intelligent palletizing robot according to claim 5, characterized in that, The palletizing scheme includes the material placement direction, layout of each layer, quantity of each layer, total number of layers, total capacity, and distribution of remaining space.

Images