Warehouse goods automatic stacking system and method

Abstract

The present application relates to the technical field of logistics warehousing automation, and proposes a warehouse goods automatic stacking system, comprising: a data acquisition module for acquiring task instructions and collecting goods state information; an algorithm optimization module for matching the task instructions and the goods state information to obtain goods stacking sequence information; a central control scheduling module for scheduling AGV, stacking robots and conveying lines based on the goods stacking sequence information; a stacking control module for controlling the movement and reloading of the stacking robot clamp; and a visualization module. The present application also proposes a warehouse goods automatic stacking method based on the above warehouse goods automatic stacking system. The present application identifies different categories of goods through the vision module, and coordinates the stacking robots and various transport devices through the central control scheduling module, thereby achieving the rapid sorting and stacking of different categories of goods, realizing the unmanned sorting and stacking of warehouse goods, reducing labor costs and reducing the possibility of employee injuries caused by contact with heavy objects.

Description

Technical Field

[0001] This invention relates to the field of logistics and warehousing automation technology, and in particular to an automated warehouse goods stacking system and method. Background Technology

[0002] With the rapid development of modern industry driven by the commodity economy and the widespread adoption of digitalization, the intelligent upgrading of traditional large warehouses is particularly important. Most manufacturing enterprises have diverse storage needs, requiring various transport vehicles and corresponding storage spaces to classify, transport, and store different types of pallets. Existing intelligent warehousing systems are not yet mature enough in terms of scheduling and data processing intelligence, and lack the ability to respond in real time to environmental changes.

[0003] Moreover, unmanned logistics is an inevitable trend, which can not only save more labor costs, but also prevent employees from handling heavy objects, reduce the occurrence of accidents, and protect the health of employees. Upgrading a warehouse to automation and unmanned operation has urgent needs and extremely high economic potential.

[0004] Existing AVG warehouse conveyor systems are too specialized, requiring extensive manual design for routes and deployment, resulting in high costs. They also handle a limited range of products and cannot process large quantities of diverse goods simultaneously. Therefore, there is an urgent need for an automated warehouse stacking system that can simultaneously identify, sort, and stack different types of goods and is easy to deploy. Summary of the Invention

[0005] This invention provides an automated warehouse goods stacking system and method. Its main purpose is to visually identify different categories of goods and coordinate stacking robots and various transportation devices through a central control scheduling module to achieve rapid sorting and stacking of different categories of goods.

[0006] The automated warehouse goods stacking system is characterized by comprising: a data acquisition module, an algorithm optimization module, a central control scheduling module, a stacking control module, and a visualization module;

[0007] The data acquisition module is used to collect task instructions and cargo status information;

[0008] The algorithm optimization module is used to match the task instructions and the cargo status information to obtain cargo stacking order information;

[0009] The central control and scheduling module, based on the cargo stacking sequence information, schedules the AGV carts to transport goods, the stacking robots to move, and the conveyor lines to transport goods at different speeds.

[0010] The stacking control module is used to control the movement and changing of the stacking robot's grippers;

[0011] A visualization module is used to display the completion status of the data collection task instructions and the cargo status information in real time;

[0012] The data acquisition module includes a visual recognition device, which collects real-time cargo status information at a fixed location.

[0013] Preferably, there are at least two visual recognition devices, one of which is aligned with the base plate to obtain the status information of the goods on the base plate, and the other is aligned with the raw material goods to obtain the status information of the raw material goods.

[0014] Preferably, the method for identifying cargo status information by the visual recognition device includes the following steps:

[0015] S1, the visual recognition device takes pictures of a fixed position at a preset time interval to obtain an image photograph at the fixed position;

[0016] S2, upload each of the aforementioned image photos to the server in chronological order;

[0017] S3, perform object recognition on each of the aforementioned image photos, and match each recognized object with the cargo information stored in the server;

[0018] S4, superimpose each of the aforementioned image photographs in chronological order to construct three-dimensional cargo status information at the fixed location.

[0019] The algorithm optimization module includes an identification optimization model and a decision optimization model. The identification optimization model uses the pyramid algorithm, which in step S4 constructs and updates the three-dimensional information of the stack of goods by using the cargo information in chronological order. The decision optimization model uses the simulated annealing algorithm to achieve the optimal solution for the cargo stacking order.

[0020] Preferably, the algorithm optimization module further includes an edge measurement algorithm, which measures the outline dimensions of each discrete item in the image photograph.

[0021] Preferably, there are at least two stacking robots, including a general stacking robot and a special stacking robot. The general stacking robot can identify and sort all goods, while the special stacking robot can only identify and sort one type of goods.

[0022] Preferably, the data acquisition module further includes site path information, which is collected by a vision acquisition device or a radar acquisition device located on the AGV.

[0023] Preferably, it also includes an automatic obstacle avoidance module, which calculates the running path of the AGV. Based on the site path information, the automatic obstacle avoidance uses dynamic replanning, ant colony algorithm or genetic algorithm to calculate the running path.

[0024] Preferably, the data acquisition module further includes a height measuring device, which includes at least two positioning devices, including a visual recognition device or radar. The height information of the cargo is measured and collected by the identification of the same cargo by at least two positioning devices.

[0025] Preferably, the formula for the pyramid algorithm includes:

[0026] Collect cargo status information in chronological order; the information at the beginning of the sequence is the downsampled information. The information listed later in the sequence is the upsampled information. ;

[0027] (x,y)= (2x, 2y);

[0028] = -upsample( +1), where k is the cargo status information of layer k.

[0029] Based on the above system, the present invention also provides a method for automatic stacking of goods in a warehouse, including...

[0030] S11, the data acquisition module acquires task instructions;

[0031] S12, the central control scheduling module schedules the AGV vehicle to transport goods to a designated location;

[0032] S13, the stacking robot collects cargo status information through a visual recognition device and uploads the cargo status information to a server containing the algorithm optimization module;

[0033] S14, the algorithm optimization module calculates the cargo stacking order information;

[0034] S15, based on the cargo stacking order information and cargo status information, the central control scheduling module controls the stacking robot to adjust the gripper and move the cargo onto the conveyor belt;

[0035] S16, the central control scheduling module regulates the conveyor belt to transport the goods to another stacking robot;

[0036] S17, the central control scheduling module controls the stacking robot to place goods from the conveyor belt to the designated location, thereby realizing the automatic stacking of warehouse goods.

[0037] This invention proposes an automated warehouse goods stacking system and method. By visually identifying different categories of goods and coordinating stacking robots and various transportation devices through a central control scheduling module, it achieves rapid sorting and stacking of different categories of goods. Furthermore, the AVG vehicle has an automatic obstacle avoidance module that can calculate suitable running paths in real time. The system is simple to deploy and can realize unmanned sorting and stacking of goods in the warehouse, reducing labor costs and lowering the possibility of employees being injured due to contact with heavy objects. Attached Figure Description

[0038] Figure 1 This is a schematic diagram of the automated warehouse goods stacking system of the present invention;

[0039] Figure 2 This is a flowchart of the method for recognizing cargo status information using the visual recognition model of the present invention;

[0040] Figure 3 This is a flowchart of the automatic warehouse goods stacking method of the present invention;

[0041] Figure 4 This is a schematic diagram of one embodiment of the automated warehouse goods stacking system of the present invention;

[0042] Figure 5 This is a schematic diagram of another embodiment of the automated warehouse goods stacking system of the present invention.

[0043] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0044] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0045] like Figure 1 As shown, an automated warehouse goods stacking system includes: a data acquisition module, an algorithm optimization module, a central control and scheduling module, a stacking control module, and a visualization module;

[0046] The data acquisition module is used to collect task instructions and cargo status information;

[0047] The algorithm optimization module is used to match task instructions and cargo status information to obtain cargo stacking order information;

[0048] The central control and scheduling module, based on the cargo stacking sequence information, schedules the AGV carts to transport goods, the stacking robots to move, and the conveyor lines to transport goods at different speeds.

[0049] The stacking control module is used to control the movement and changing of the stacking robot's grippers;

[0050] The visualization module is used to display the completion status of data collection tasks and cargo status information in real time.

[0051] The data acquisition module includes a visual recognition device, which collects real-time status information of goods at fixed locations.

[0052] The algorithm optimization module includes an identification optimization model and a decision optimization model. The identification optimization module uses the pyramid algorithm to perform image optimization processing on the cargo status information, while the decision optimization model uses the simulated annealing algorithm to achieve the optimal solution for the stacking order.

[0053] Furthermore, there are at least two visual recognition devices. One visual recognition device is aligned with the base plate to obtain the status information of the goods on the base plate, and the other visual recognition device is aligned with the raw material goods to obtain the status information of the raw material goods.

[0054] Furthermore, such as Figure 2 As shown, the method for recognizing cargo status information using a visual recognition model includes the following steps:

[0055] S1, The visual recognition device takes pictures of a fixed position at a preset time interval to obtain an image photo at the fixed position;

[0056] S2 uploads each image photo to the server in chronological order;

[0057] S3 performs object recognition on each image photo and matches each recognized object with the cargo information stored in the server.

[0058] S4 uses the pyramid algorithm to overlay each image photo in chronological order to construct three-dimensional cargo status information at a fixed location.

[0059] Furthermore, in step S3, an edge detection algorithm is used to identify objects in the image, measuring the outline size of each discrete individual in the image.

[0060] Furthermore, the formula for the pyramid algorithm includes:

[0061] Collect cargo status information in chronological order; the information at the beginning of the sequence is the downsampled information. The information listed later in the sequence is the upsampled information. ;

[0062] (x,y)= (2x, 2y);

[0063] = -upsample( +1), where k is the cargo status information of layer k.

[0064] In one embodiment, the image is preprocessed first. The purpose is to address the issues that may arise in the original image acquired by the camera during the acquisition, digitization, and transmission of the image, due to environmental conditions (such as light intensity, light uniformity, and shooting angle), equipment performance, and random interference. These issues include image blurring, poor contrast, and noise contamination. To improve the effectiveness of feature extraction, matching, and recognition, grayscale transformation is first used to enhance the contrast between the target and the image background. Then, a filtering algorithm is used to remove interference points. Finally, an edge detection algorithm is used to extract the geometric edges of the target object. By comparing the geometric edges and contour dimensions of the object with the dimensions in a standard cargo library, the type of cargo can be identified more accurately.

[0065] Furthermore, there are at least two types of stacking robots: a general stacking robot and a special stacking robot. The general stacking robot can identify and sort all goods, while the special stacking robot can only identify and sort one type of goods.

[0066] Furthermore, the data acquisition module also includes the acquisition of site path information, which is collected by a vision acquisition device or a radar acquisition device located on the AGV.

[0067] Furthermore, it also includes an automatic obstacle avoidance module, which calculates the running path of the AGV. Based on the site path information, the automatic obstacle avoidance uses dynamic replanning, ant colony algorithm or genetic algorithm to calculate the running path.

[0068] Furthermore, the data acquisition module also includes a height measurement device, which includes at least two positioning devices, including a visual recognition device or radar. By identifying the same cargo through at least two positioning devices, the height information of the cargo is measured and collected.

[0069] Furthermore, such as Figure 3 As shown, based on the above-mentioned automated warehouse goods stacking, an automated warehouse goods stacking method includes the following steps:

[0070] S11, Data acquisition module acquires task instructions;

[0071] S12, the central control scheduling module schedules AGV carts to transport goods to designated locations;

[0072] S13, the stacking robot collects cargo status information through a visual recognition device and uploads the cargo status information to a server containing an algorithm optimization module;

[0073] S14, The algorithm optimization module calculates the cargo stacking order information;

[0074] S15, based on the cargo stacking order information and cargo status information, the central control scheduling module controls the stacking robot to adjust the gripper and move the cargo onto the conveyor belt;

[0075] S16, the central control scheduling module regulates the conveyor belt to transport goods to another stacking robot;

[0076] S17, the central control scheduling module directs the stacking robot to place goods from the conveyor belt to the designated location, realizing the automatic stacking of goods in the warehouse.

[0077] like Figure 4 As shown, this is one embodiment of the present invention. The goods are relatively simple, and the AGV trolley only brings one or two kinds of goods. The stacking robot's working arm has a certain circumferential range, so only one stacking robot is needed to complete the sorting.

[0078] like Figure 5 The illustration shows another embodiment of the invention. The goods are relatively complex, and multiple stacking robots are used. After the first main stacking robot identifies and moves the goods onto the conveyor belt, the central control module controls the conveyor belt to transport each item forward. This allows specialized robots, designed for stacking only a single item, to accurately pick up and stack the goods, achieving rapid sorting of complex goods. In other embodiments, the types of goods may be even more complex, or more specialized stacking robots can be deployed to increase stacking speed. The entire warehouse goods sorting and stacking system is simple to deploy, highly modular, and has low subsequent expansion costs.

[0079] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, apparatus, article, or method. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0080] The above are merely preferred embodiments of the present invention and do not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. An automated warehouse goods stacking system, characterized in that, include: Data acquisition module, algorithm optimization module, central control and scheduling module, stacking control module, and visualization module; The data acquisition module is used to collect task instructions and cargo status information; The algorithm optimization module is used to match the task instructions and the cargo status information to obtain cargo stacking order information; The central control and scheduling module, based on the cargo stacking sequence information, schedules the AGV carts to transport goods, the stacking robots to move, and the conveyor lines to transport goods at different speeds. The stacking control module is used to control the movement and changing of the stacking robot's grippers; A visualization module is used to display the completion status of the data collection task instructions and the cargo status information in real time; The data acquisition module includes visual recognition devices, at least two of which are used. One visual recognition device is aligned with the base plate to obtain the status information of the goods on the base plate, and the other visual recognition device is aligned with the raw material goods to obtain the status information of the raw material goods. The method for identifying cargo status information using the visual recognition device includes the following steps: S1, the visual recognition device takes pictures of a fixed position at a preset time interval to obtain an image photograph at the fixed position; S2, upload each of the aforementioned image photos to the server in chronological order; S3, perform object recognition on each of the aforementioned image photos, and match each recognized object with the cargo information stored in the server; S4, superimpose each of the image photographs in chronological order to construct three-dimensional cargo status information at the fixed location; The algorithm optimization module includes an identification optimization model and a decision optimization model. The identification optimization model uses the pyramid algorithm, which in step S4 constructs and updates the three-dimensional information of the stack of goods by using the cargo information in chronological order. The decision optimization model uses the simulated annealing algorithm to achieve the optimal solution for the cargo stacking order.

2. The automated warehouse goods stacking system according to claim 1, characterized in that, In step S3, the edge detection algorithm is used to identify objects in the image photograph and measure the outline size of each discrete individual in the image photograph.

3. The automated warehouse goods stacking system according to claim 1, characterized in that, The stacking robot is at least two in number, including a general stacking robot and a special stacking robot. The general stacking robot can identify and sort all goods, while the special stacking robot can only identify and sort one type of goods.

4. The automated warehouse goods stacking system according to claim 1, characterized in that, The data acquisition module also includes site path information, which is collected by a vision acquisition device or a radar acquisition device located on the AGV.

5. The automated warehouse goods stacking system according to claim 4, characterized in that, It also includes an automatic obstacle avoidance module, which calculates the running path of the AGV. Based on the site path information, the automatic obstacle avoidance module uses dynamic replanning, ant colony algorithm or genetic algorithm to calculate the running path.

6. The automated warehouse goods stacking system according to claim 1, characterized in that, The data acquisition module also includes a height measuring device, which includes at least two positioning devices, including a visual recognition device or radar. The height information of the cargo is measured and collected by identifying the same cargo through at least two of the positioning devices.

7. The automated warehouse goods stacking system according to claim 1, characterized in that, The formula for the pyramid algorithm includes: Collect cargo status information in chronological order; the information at the beginning of the sequence is the downsampled information. The information listed later in the sequence is the upsampled information. ; (x,y)= (2x,2y); = -upsample( +1), where k is the cargo status information of layer k.

8. A method for automatically stacking warehouse goods, based on the automatic warehouse goods stacking system according to any one of claims 1-7, characterized in that, include S11, the data acquisition module acquires task instructions; S12, the central control scheduling module schedules the AGV vehicle to transport goods to a designated location; S13, the stacking robot collects cargo status information through a visual recognition device and uploads the cargo status information to a server containing the algorithm optimization module; S14, the algorithm optimization module calculates the cargo stacking order information; S15, based on the cargo stacking order information and cargo status information, the central control scheduling module controls the stacking robot to adjust the gripper and move the cargo onto the conveyor belt; S16, the central control scheduling module regulates the conveyor belt to transport the goods to another stacking robot; S17, the central control scheduling module controls the stacking robot to place goods from the conveyor belt to the designated location, thereby realizing the automatic stacking of warehouse goods.

Images