Warehouse control management system and method based on computer vision and mobile robot technology

Abstract

The invention relates to the technical field of visual identification, in particular to a warehouse control management system and method based on computer vision and mobile robot technologies, and the method comprises the steps: training a target detection model for identifying a line bucket based on a computer vision algorithm, and deploying the target detection model to an AI control box; a camera, an AI control box, a warehouse management system, a robot management system and a robot are integrated through communication; the AI control box obtains a storage location image captured by a camera, inputs the storage location image into a target detection model, and identifies the line barrel and the state thereof to obtain identification data; and after the warehouse management system stores and updates the data, tasks are sent to the robot management system according to requirements, and the robot management system schedules one or more robots to carry the wire buckets. According to the method, automatic identification of the wire barrel and the state of the wire barrel is achieved, the robot can be accurately dispatched to move and place the wire barrel, automatic management of the wire barrel is achieved, workshop management efficiency is greatly improved, and manual errors and safety risks are reduced.

Description

Technical Field

[0001] The present invention relates to the field of visual recognition technology, and in particular to a warehouse control management system and method using computer vision and mobile robot technology. Background Art

[0002] In traditional workshops, wire barrels are often used to store and transport industrial materials such as wires, ropes, etc., which are essential in the manufacturing process. Accurate wire barrel tracking and inventory management can prevent material shortages or surpluses, and efficient storage and movement of wire barrels can improve space utilization and internal logistics efficiency. However, many workshops still rely on manual inspection of the status of wire barrels (empty or full), as well as manual movement and placement of wire barrels, which is not only inefficient and prone to errors, but also poses safety risks.

[0003] Therefore, there is an urgent need for a warehouse control management system and method based on computer vision and robotics technology to solve the current problems of low efficiency, easy errors and safety risks in manual identification and moving line barrels. Summary of the invention

[0004] The purpose of the present invention is to provide a warehouse control management system and method based on computer vision and mobile robot technology, aiming to solve the current problems of low efficiency, easy errors and safety risks in manual identification and moving line barrels.

[0005] To achieve the above objectives, in a first aspect, the present invention provides a warehouse control management method using computer vision and mobile robot technology, comprising the following steps:

[0006] Train a target detection model for identifying wire barrels based on computer vision algorithms, and deploy the target detection model to the AI ​​control box;

[0007] Integrate the camera, the AI ​​control box, the warehouse management system, the robot management system and the plurality of robots through communication;

[0008] The AI ​​control box obtains the storage location image captured by the camera and inputs it into the target detection model, identifies the wire barrel and its status, and sends the identification data to the warehouse management system;

[0009] The warehouse management system stores and updates the identification data, and sends tasks to the robot management system;

[0010] The robot management system dispatches a single or multiple robots to transport line barrels.

[0011] The target detection model for training recognition line buckets includes image acquisition, image annotation, data preprocessing and enhancement, data set grouping and model training.

[0012] The data preprocessing and enhancement method is to adjust the image brightness, exposure, saturation, grayscale, hue, noise, tilt angle, blur and magnification.

[0013] Among them, the workflow of the warehouse management system 3 includes model deployment, system integration, real-time image acquisition, image processing, data storage and update, system scheduling, task allocation, robot operation and task completion confirmation.

[0014] In a second aspect, the present invention also provides a warehouse control and management system using computer vision and mobile robot technology, including an AI control box, a camera, a warehouse management system, a robot management system, and a robot;

[0015] The camera is used to capture images for processing by the visual recognition system;

[0016] The AI ​​control box is used to obtain the image captured by the camera and identify the state and position of the wire barrel through the target detection model;

[0017] The warehouse management system is used to store and update the identification data and send tasks to the robot management system;

[0018] The robot management system is used to assign tasks and schedule single or multiple robots;

[0019] The robot is used to locate and navigate to a specified wire barrel, and to pick up and place the wire barrel.

[0020] The warehouse control and management method of computer vision and mobile robot technology of the present invention is based on computer vision algorithm training to identify the target detection model of wire barrels, and deploys the target detection model to the AI ​​control box; the camera, the AI ​​control box, the warehouse management system, the robot management system and multiple robots are integrated through communication; the AI ​​control box obtains the storage location image captured by the camera and inputs it into the target detection model, identifies the wire barrels and their status, and sends the identification data to the warehouse management system; the warehouse management system stores and updates the identification data, and sends tasks to the robot management system; the robot management system dispatches a single or multiple robots to transport wire barrels. The method realizes automatic identification of wire barrels and their status (empty barrels or full barrels), and can accurately dispatch robots to perform tasks of moving and placing wire barrels, thereby realizing automated wire barrel management, greatly improving workshop management efficiency, reducing manual errors and safety risks, and solving the current problems of low efficiency, easy errors and safety risks in manual identification and movement of wire barrels. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 It is a flow chart of the warehouse control management method using computer vision and mobile robot technology provided by the present invention.

[0023] Figure 2 It is a schematic diagram of the automated process of line barrel management.

[0024] Figure 3 It is a schematic diagram of the training process of the target detection model.

[0025] Figure 4 It is a schematic diagram of a warehouse control management system using computer vision and mobile robot technology provided by the present invention.

[0026] In the picture: 1-AI control box, 2-camera, 3-warehouse management system, 4-robot management system, 5-robot. DETAILED DESCRIPTION

[0027] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0028] See also Figures 1 to 3 In a first aspect, the present invention provides a warehouse control management method using computer vision and mobile robot technology, comprising the following steps:

[0029] S1 trains a target detection model for identifying wire barrels based on a computer vision algorithm, and deploys the target detection model to the AI ​​control box 1;

[0030] Specifically, the target detection model of the training recognition line bucket includes image acquisition, image annotation, data preprocessing and enhancement, data set grouping and model training, so that the training data is richer and covers more usage scenarios. The target detection algorithm is then used for training to obtain the best model that can adapt to a variety of light, angles and image qualities.

[0031] The trained target detection model is deployed in the AI ​​control box 1. The AI ​​control box 1 reads the image of the camera 2 at a specific frequency. The image is input into the model, and the model will output the status (empty or full) and pixel coordinates of the line barrel in each storage location.

[0032] Image acquisition: Collect high-quality images containing the target detection objects (empty and full buckets), ensuring that the images have diverse backgrounds, lighting conditions, and angles to simulate the various scenarios that may be encountered in the actual working environment;

[0033] Image annotation: Use high-precision annotation tools to mark in detail the location and status (empty or full) of each wire bucket in the image, ensuring that each annotation has clear boundaries and the status label is accurate;

[0034] Dataset grouping: The labeled image dataset is divided into training set, test set and validation set with a ratio of 70%, 20% and 10%, ensuring that each dataset contains images under different lighting and background conditions to verify the robustness of the model in different environments;

[0035] Data preprocessing and enhancement: Perform various preprocessing and enhancement operations on the training set images, such as random cropping, scaling, color adjustment (brightness, exposure, saturation, grayscale, hue), adding synthetic noise, rotation and occlusion processing, etc., to simulate various possible disturbances in the real environment;

[0036] Model training: Apply deep learning frameworks and algorithms for model training, select the appropriate neural network structure, and adjust hyperparameters through a large number of experiments to optimize the model's recognition accuracy of line bucket states.

[0037] Model optimization and validation: Perform multiple rounds of validation and adjustment, use test set and validation set data to evaluate model performance, ensure that the model has at least 95% recognition accuracy in the actual environment, record and analyze cases of misidentification, and further adjust the model to correct these errors.

[0038] S2 integrates the camera 2, the AI ​​control box 1, the warehouse management system 3, the robot management system 4, and the robot 5 through communication;

[0039] Specifically, the warehouse management system 3 obtains the robot status and task status by communicating with the robot management system 4 , and the robot management system 4 obtains the status of the robot 5 by communicating with the robot 5 .

[0040] S3: the AI ​​control box 1 obtains the storage location image captured by the camera 2, inputs the target detection model, identifies the line barrel and its status, and sends the identification data to the warehouse management system 3;

[0041] S4 the warehouse management system 3 stores and updates the identification data, and sends the task to the robot management system 4;

[0042] S5 The robot management system 4 dispatches a single robot or multiple robots 5 to transport the wire barrels.

[0043] Specifically, the warehouse management system 3 (WMS) workflow includes model deployment, system integration, real-time image acquisition, image processing and display, data storage and update, robot scheduling and operation, and task completion confirmation.

[0044] Model deployment: Deploy the trained and verified target detection model to the AI ​​control box 1. Ensure that the model can run efficiently on actual hardware with short response time and meet actual industrial needs;

[0045] System integration: Install the cameras 2 at strategic locations in the workshop and install the user interface on the operation console to ensure that all devices are well connected to the central server and communicate through secure network protocols;

[0046] Real-time image acquisition: configure the AI ​​control box 1 to periodically acquire images from the camera 2. The frequency can be adjusted according to actual needs to ensure that the system can monitor the status of the workshop in real time;

[0047] Image processing and display: The acquired images are input into the target detection model to identify the barrels and their status in each storage location in real time;

[0048] Data storage and update: send recognition results and related data (such as timestamps, coordinates, etc.) to the WMS database, update inventory status and operation records in real time, and ensure data integrity and accuracy;

[0049] Sending tasks: WMS sends tasks to the robot management system 4 according to the warehouse's demand for line barrels;

[0050] Assigning tasks and scheduling: The robot management system 4 assigns tasks and schedules single or multiple robots 5;

[0051] Operation of robot 5: According to the instructions of robot management system 4, robot 5 moves accurately to the designated storage location through the built-in positioning and navigation system, and uses the robotic arm to pick up and carry the wire barrel;

[0052] Task completion confirmation: After the task is completed, the robot 5 feeds back the operation result to the WMS, updates the system status, and prepares to receive the next instruction.

[0053] See also Figure 4, In a second aspect, the present invention also provides a warehouse control and management system based on computer vision and mobile robot technology, including an AI control box 1, a camera 2, a warehouse management system 3, a robot management system 4, and a robot 5;

[0054] The camera 2 is used to capture images for processing by the visual recognition system;

[0055] The AI ​​control box 1 is used to obtain the image captured by the camera 2 and identify the state and position of the wire barrel through the target detection model;

[0056] The warehouse management system 3 is used to store and update the identification data and send tasks to the robot management system 4;

[0057] The robot management system 4 is used to assign tasks and schedule a single robot or multiple robots 5;

[0058] The robot 5 is used to locate and navigate to the specified wire barrel, pick up and place the wire barrel.

[0059] In this embodiment, the camera 2 captures images for processing by the visual recognition system, the AI ​​control box 1 obtains the images captured by the camera 2, and identifies the state and position of the wire barrel through the target detection model, the warehouse management system 3 stores and updates the identification data and sends tasks to the robot management system 4, the robot management system 4 assigns tasks and dispatches single or multiple robots 5, the robot 5 locates and navigates to the specified wire barrel, picks up and places the wire barrel.

[0060] The above disclosure is only a preferred embodiment of the warehouse control management system and method of the computer vision and mobile robot technology of the present invention. Of course, this cannot be used to limit the scope of rights of the present invention. Ordinary technicians in this field can understand that all or part of the processes of the above embodiments and equivalent changes made according to the claims of the present invention still fall within the scope of the invention.

Claims

1. Warehouse control management method based on computer vision and mobile robotics technology, It is characterized in that The following steps are involved: Train a target detection model for identifying wire barrels based on computer vision algorithms, and deploy the target detection model to the AI ​​control box; Integrate the camera, the AI ​​control box, the warehouse management system, the robot management system and the plurality of robots through communication; The AI ​​control box obtains the storage location image captured by the camera and inputs it into the target detection model, identifies the wire barrel and its status, and sends the identification data to the warehouse management system; The warehouse management system stores and updates the identification data, and sends tasks to the robot management system; The robot management system dispatches a single or multiple robots to transport line barrels.

2. The warehouse control management method of computer vision and mobile robot technology as claimed in claim 1, It is characterized in that The target detection model for training recognition line buckets includes image acquisition, image annotation, data preprocessing and enhancement, data set grouping and model training.

3. The warehouse control management method of computer vision and mobile robot technology as claimed in claim 2, It is characterized in that The data preprocessing and enhancement method is to adjust the image brightness, exposure, saturation, grayscale, hue, noise, tilt angle, blur degree and magnification degree.

4. The warehouse control management method of computer vision and mobile robot technology as claimed in claim 1, It is characterized in that The workflow of the warehouse management system 3 includes model deployment, system integration, real-time image acquisition, image processing, data storage and update, system scheduling, task allocation, robot operation and task completion confirmation.

5. A warehouse control management system using computer vision and mobile robot technology, applied to a warehouse control management method using computer vision and mobile robot technology as claimed in any one of claims 1 to 4, It is characterized in that Including AI control box, camera, warehouse management system, robot management system, robot; The camera is used to capture images for processing by the visual recognition system; The AI ​​control box is used to obtain the image captured by the camera and identify the state and position of the wire barrel through the target detection model; The warehouse management system is used to store and update the identification data and send tasks to the robot management system; The robot management system is used to assign tasks and schedule single or multiple robots; The robot is used to locate and navigate to a specified wire barrel, and to pick up and place the wire barrel.

Images