An AGV dispatching system based on laser SLAM navigation

Abstract

The present invention discloses an AGV dispatching system based on laser SLAM navigation, which relates to the technical field of AGV dispatching, and includes the following steps: an information acquisition module, which is used to obtain all AGV working status data when receiving a signal sent by an important cargo, and the working status data includes equipment status data, environmental status data and path status data; a priority evaluation module, which is used to establish an AGV priority dispatching evaluation model based on a neural network for the AGV working status data, and generate an AGV priority dispatching value; an AGV priority dispatching selection module, which is used to calculate the priority dispatching average value according to the AGV priority dispatching value, generate a priority dispatching sorting table, and control the AGV to give priority to the transportation of important cargo according to the priority dispatching sorting table; a transportation route selection module, which is used to obtain an environmental map through laser SLAM, and obtain the optimal path from the current AGV position to the target position based on the A* path planning algorithm. The present invention uses dispatching technology to solve the problem that AGV cannot dispatch important priority tasks in time.

Description

Technical Field

[0001] The present invention relates to the technical field of AGV scheduling, and more specifically, to an AGV scheduling system based on laser SLAM navigation. Background Art

[0002] Laser SLAM is a simultaneous positioning and mapping technology that uses a laser radar sensor to obtain three-dimensional point cloud data of the environment, and uses this data to estimate the robot's pose (position and orientation) and build a map of the environment. Laser SLAM performs well indoors and in closed spaces, provides accurate maps and positioning information, and is very effective for obstacle avoidance and mapping tasks. Laser SLAM has a wide range of applications, including autonomous driving, robot navigation, drone control and other fields. It provides accurate pose estimation and map construction for these applications, and is one of the basic technologies for robots to act autonomously and achieve interaction.

[0003] AGV is an automatic guided vehicle. It is a transport vehicle equipped with an electromagnetic or optical automatic guidance device, which can travel along a specified guide path and has safety protection and various transfer functions. The AGV system is usually composed of an AGV car, a control system, a navigation device, a charging device, and peripheral accessories. Under the monitoring and task scheduling of the control computer, the AGV can accurately follow the preset path and complete a series of tasks at a designated location. AGV is widely used in smart warehousing, smart manufacturing, hospital goods transportation and other fields, which can improve production efficiency, reduce costs, and realize the automation and intelligence of material handling.

[0004] The above disclosed technical solutions have at least the following technical problems: the traditional AGV scheduling algorithm may not be able to handle the dynamically changing environment in real time. When important tasks are transported, the AGV may not be able to identify and manage important priority tasks, resulting in the AGV being unable to be scheduled in time, thus causing important tasks to be delayed. In view of the above problems, the present invention proposes a solution. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an AGV scheduling system based on laser SLAM navigation, which solves the problem that AGV cannot schedule important priority tasks in time through AGV scheduling technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An AGV scheduling system based on laser SLAM navigation includes an information acquisition module, a priority evaluation module, an AGV priority scheduling selection module and a transportation route selection module, wherein the modules are connected: the information acquisition module is used to obtain all AGV working status data when receiving a signal sent by processing important goods, and the working status data includes equipment status data, environmental status data and path status data; the priority evaluation module is used to establish an AGV priority scheduling evaluation model based on a neural network for the AGV working status data, and generate an AGV priority scheduling value; the AGV priority scheduling selection module is used to calculate the priority scheduling average value according to the AGV priority scheduling value, generate a priority scheduling sorting table, and control the AGV to give priority to the transportation of important goods according to the priority scheduling sorting table; the transportation route selection module is used to obtain an environmental map through laser SLAM, and obtain the optimal path from the current AGV position to the target position based on an A* path planning algorithm, so as to obtain the best navigation route for the transportation of important goods.

[0008] In a preferred embodiment, the device state data includes a device state priority coefficient, the environment state data includes an environment state description priority coefficient, and the path state data includes a path state priority coefficient.

[0009] In a preferred embodiment, the specific method for obtaining the device status priority coefficient is as follows: monitor and obtain the first data of the AGV device, the first data including the speed and acceleration of the device, and the cruising range of the device; calculate the loss coefficient of the power supply based on the charging frequency and charging time of the AGV; calculate the kinetic energy of the motor based on the number of motor drives and the kinetic energy formula of the motor drive, and calculate the AGV kinetic energy state coefficient in combination with the load data of the AGV and the friction coefficient of the driving wheel; calculate the device status priority coefficient based on the preset device status data formula in combination with the first data, the loss coefficient of the power supply and the AGV kinetic energy state coefficient.

[0010] In a preferred embodiment, the path state priority coefficient is specifically obtained by the following method: obtaining the starting point of important goods, and based on its own positioning, obtaining the shortest path to the starting point through a navigation algorithm; using sensors to monitor and obtain the obstacle distance and passable width in front of the AGV in real time, and obtaining the congestion impact coefficient based on the congestion impact calculation formula in combination with the average speed of the AGV; obtaining the path state priority coefficient based on a preset path state calculation formula in combination with the shortest path to the starting point and the congestion impact coefficient.

[0011] In a preferred embodiment, the environmental state description priority coefficient is specifically obtained by the following method: real-time monitoring and acquisition of meteorological data of the area where the current AGV is located, wherein the meteorological data includes temperature and wind speed; based on fluid dynamics analysis of the impact of the current AGV wind speed and acquisition of the wind speed obstacle factor to which the current AGV is subject; combining the wind speed obstacle factor and the regional meteorological data to obtain the environmental state description priority coefficient based on a preset environmental state data calculation formula.

[0012] In a preferred embodiment, the method for acquiring the AGV priority scheduling evaluation model is as follows: collect all AGV working status data after receiving the signal, including equipment status data, environmental status data and path status data, and clean and preprocess the data; based on neural network technology, train the preprocessed data in combination with historical data, and automatically adjust the weights through real-time feedback during operation, and assign the trained and adjusted weights to the equipment status data, environmental status data and path status data respectively; input the AGV working status data into the trained AGV priority scheduling evaluation model to generate an AGV priority scheduling value.

[0013] In a preferred embodiment, the priority scheduling average value is calculated according to the AGV priority scheduling value, a priority scheduling sorting table is generated, and according to the priority scheduling sorting table, the AGV is controlled to give priority to the transportation of important goods. The specific steps are as follows: real-time monitoring is obtained and n priority scheduling values ​​of AGVs in all running routes are obtained, the n priority scheduling values ​​are added and divided by n to obtain the priority scheduling average value of each AGV; according to the obtained priority scheduling average value of each AGV, sorting is performed in descending order to generate a priority scheduling sorting table; the priority scheduling sorting table is used to provide the scheduling system with AGVs that can perform important tasks in priority, and control them to transport goods to important task target points.

[0014] In a preferred embodiment, the method for obtaining an environment map through laser SLAM and obtaining an optimal path from the current AGV position to the target position based on the A* path planning algorithm is as follows:

[0015] The environmental point cloud data is generated by scanning with laser SLAM, and the acquired point cloud data is filtered, denoised and feature extracted, and added to the grid map to build a complete environmental map; the location and task destination of the high-priority AGV transporting goods are determined, and the map position is matched based on the constructed map according to the AGV position and task destination; based on the current map position matching, the A* path planning algorithm is used to obtain a safe and effective path from the current AGV position to the task destination; and the planned trajectory is sent to the AGV for control instructions to achieve transportation.

[0016] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0017] 1. Through laser SLAM, it is possible to provide real-time navigation for high-priority AGVs efficiently and safely in a dynamic environment, ensuring the optimal path selection for the transportation of important goods.

[0018] 2. Through AGV scheduling technology, the problem of AGV’s inability to identify and manage important priority tasks, resulting in the inability to schedule AGV in a timely manner, is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A schematic diagram of the structure of an AGV scheduling system based on laser SLAM navigation provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Embodiment 1, Figure 1 A schematic diagram of the structure of an AGV scheduling system based on laser SLAM navigation provided in an embodiment of the present application includes an information acquisition module, a priority evaluation module, an AGV priority scheduling selection module, and a transportation route selection module, and there are connections between the modules:

[0022] S1, information acquisition module, is used to obtain all AGV working status data when receiving the signal sent by processing important goods. The working status data includes equipment status data, environmental status data and path status data.

[0023] The device state data includes a device state priority coefficient, the environment state data includes an environment state description priority coefficient, and the path state data includes a path state priority coefficient.

[0024] The equipment status priority coefficient refers to the overall status parameters of the AGV during its operation, including the current speed and acceleration of the AGV equipment, the equipment's cruising range, the equipment's load data, and the equipment's health status. Understanding the equipment status priority coefficient can help us better judge whether the AGV can meet the basic conditions for the transportation of important goods.

[0025] Analyzing equipment status data to obtain AGV scheduling priorities has the following advantages:

[0026] Equipment health status: By monitoring the battery power, motion status, fault alarm, etc. of the AGV, it is ensured that only AGVs in good health participate in the dispatch. This can reduce the accident rate and improve the dispatch efficiency.

[0027] Task status tracking: Knowing the status of the tasks currently being performed by each AGV can dynamically adjust the scheduling priority based on the urgency and importance of the tasks.

[0028] Load balancing: According to the status and current position of the AGV, the workload is reasonably arranged to avoid overloading some AGVs while other AGVs are idle, thus improving resource utilization.

[0029] Real-time navigation adjustment: Equipment status data can help AGV adjust its driving path in real time, avoid obstacles or adjust its route to avoid high-traffic areas, improving transportation efficiency.

[0030] Task priority adjustment: When the status of certain equipment shows that it is about to fail or require maintenance, the scheduling strategy can be adjusted to prioritize other AGVs to complete urgent tasks.

[0031] Dynamic Scheduling: Equipment status data enables the scheduling system to respond quickly and flexibly adjust task priorities to adapt to emergencies based on the current environment and equipment conditions.

[0032] Multiple scheduling strategies: You can choose different scheduling strategies based on the device status, such as executing high-priority tasks first, or adjusting the priority of tasks based on real-time demand changes.

[0033] The specific method for obtaining the device status priority coefficient is as follows:

[0034] Monitor and obtain first data of the AGV device, where the first data includes the speed and acceleration of the device and the cruising range of the device;

[0035] Calculate the power loss factor based on the charging frequency and charging time of the AGV;

[0036] The kinetic energy of the motor is calculated based on the number of motor drives and the kinetic energy formula of the motor drive, and the kinetic energy state coefficient of the AGV is calculated in combination with the load data of the AGV and the friction coefficient of the drive wheel;

[0037] The equipment state priority coefficient is obtained by combining the first data, the loss coefficient of the power supply and the AGV kinetic energy state coefficient based on a preset equipment state data formula.

[0038] The specific calculation formula of the power loss coefficient is as follows:

[0039]

[0040] The specific calculation formula of the AGV kinetic energy state coefficient is as follows:

[0041]

[0042] The specific calculation formula of the device status priority coefficient is as follows:

[0043]

[0044] In the formula, is the equipment status priority coefficient of the i-th AGV, is the acceleration, is the power loss coefficient of the i-th AGV, is the kinetic energy state coefficient of the i-th AGV, is the speed of the device, The device's battery life. is the charging frequency, T is the charging time, is the kinetic energy of the motor, is the motor drive efficiency of the i-th AGV, is the friction coefficient of the driving wheel, is the load data of the current equipment, and S is the number of driving wheels.

[0045] It should be noted that when dispatching important goods, the basic information of the AGV equipment must be determined first to ensure that there will be no accidents or failures in the process of transporting important goods. For example, the machine suddenly runs out of power during transportation, so the remaining range of the AGV must be determined, or the machine suddenly fails and the transportation task cannot be carried out, delaying the task process. Therefore, analyzing the power loss coefficient and the AGV kinetic energy state coefficient is important for obtaining the equipment state priority coefficient.

[0046] The environmental state description priority coefficient refers to the current environmental state of the AGV when it receives an important cargo transportation signal. For example, whether the current environment is congested, causing the AGV to be unable to quickly return to the cargo receiving location in a short time, or the current weather environment causes the AGV to have a deviation in operation effect. This information plays an important role in analyzing the environmental state description priority coefficient.

[0047] Describing the priority coefficient by analyzing the environmental state has the following advantages for obtaining the priority of AGV scheduling:

[0048] Optimize scheduling based on real-time environment: Through real-time analysis of environmental status, AGV scheduling can be adjusted dynamically. For example, when an AGV approaches the target location, its priority can be increased to reduce unnecessary waiting time. This approach reduces the complexity of global scheduling and improves the response speed of the system.

[0049] Prioritize urgent tasks: The environment state describes the priority factor and can give higher priority to tasks based on their time limit and urgency. For example, if a task has a strict time limit, the scheduling system can automatically assign it a higher priority to ensure timely completion.

[0050] Dynamically adjust the priority: When the environment changes (such as obstacles, path blockage, or other AGVs occupying the channel, etc.), the priority of the AGV can be dynamically adjusted to ensure the smooth operation of the system. For example, if a channel is blocked, the system can automatically adjust the priority of the AGV on other feasible paths to avoid congestion.

[0051] Multi-task priority optimization: In complex environments, AGVs may need to handle multiple tasks at the same time. The priority coefficient based on environmental status can help the scheduling system allocate resources reasonably and give priority to tasks that have a greater impact on the system.

[0052] Avoid collisions and conflicts: In a multi-AGV system, conflicts and collisions between vehicles are common problems. By describing the priority coefficients by environmental status, the scheduling system can monitor the relative positions and movements of AGVs in real time, dynamically adjust the priority of AGVs that may conflict, avoid collisions, and ensure the safety of system operation.

[0053] Optimize path planning: The priority coefficient of the environment description can provide more basis for AGV path planning. For example, if there are many obstacles on a path or the AGVs passing through are dense, the scheduling system can automatically select other paths to reduce the probability of danger.

[0054] Optimize idle resource allocation: In complex production or warehousing environments, the AGV scheduling system may face idle resources. By setting the priority coefficient reasonably, the system can dynamically adjust the task allocation of the AGV to ensure that when the environmental state changes, the waste of resources is minimized and the operating efficiency of the AGV is maximized.

[0055] Balanced task load: When multiple AGVs are performing tasks, the priority factor can help balance the load, preventing some AGVs from being overloaded due to too many tasks, while other AGVs are idle due to too few tasks. By properly allocating tasks and resources, the system can run more efficiently.

[0056] The environmental state describes the priority coefficient, and the specific acquisition method is as follows:

[0057] Real-time monitoring and acquisition of meteorological data of the area where the AGV is currently located, including temperature and wind speed;

[0058] Analyze the impact of current AGV wind speed based on fluid dynamics and obtain the wind speed obstacle factor of current AGV;

[0059] The environmental state description priority coefficient is obtained based on the preset environmental state data calculation formula in combination with the wind speed obstacle factor and the regional meteorological data.

[0060] The specific calculation formula of the wind speed resistance factor is as follows:

[0061]

[0062] The environmental state describes the priority coefficient, and the specific calculation formula is as follows:

[0063]

[0064] In the formula, is the priority coefficient describing the environmental state of the i-th AGV, is the wind speed resistance factor, k is the wind speed kinetic energy, is the wind speed contact cross-sectional area, is the wind speed time, is the meteorological barrier factor, q is the meteorological data, The meteorological temperature.

[0065] It should be noted that when the priority coefficient of the environmental state description becomes larger and larger, it means that the AGV at this time is greatly affected by environmental obstacles, so the AGV is not suitable for the priority transportation task of important goods. When the priority coefficient of the environmental state description becomes smaller and smaller, it means that the AGV under this environmental state is less affected by environmental obstacles, then compared with the higher environmental state description priority coefficient, its priority consideration will be higher.

[0066] The path status priority coefficient refers to a parameter used to evaluate and determine the priority of tasks or vehicles on different paths during the scheduling process. The current AGV's location is far from the target location where important goods need to be transported, and its navigation path status.

[0067] Analyzing the path status priority coefficient has the following advantages for obtaining the priority of AGV scheduling:

[0068] Dynamic path selection: The path status priority coefficient allows the system to evaluate the feasibility of the path in real time, so as to give priority to the path with good current status and strong traffic capacity. This can effectively reduce the running time of AGV and improve the overall scheduling efficiency.

[0069] Optimize task allocation: By analyzing the path status, the system can allocate tasks more reasonably and assign urgent tasks to unobstructed paths first, thereby reducing the waiting time for task completion.

[0070] Congestion prediction and management: The path status priority coefficient can be used to predict congestion. Through real-time monitoring and analysis, the system can dynamically adjust the scheduling strategy to prevent AGVs from entering areas that are about to be congested and reduce delays.

[0071] Prevent collisions: By analyzing the path status in real time, the system can determine whether the AGV will conflict with other vehicles or obstacles, and automatically adjust its priority to reduce the risk of collision.

[0072] Efficient path utilization: The path status priority coefficient can ensure that the AGV gives priority to the path with good current status, reducing stagnation and idle resources caused by path problems, thereby maximizing the utilization efficiency of the AGV.

[0073] Coordinate multiple AGV scheduling: In a multi-AGV system, the path state priority coefficient can help coordinate the tasks between multiple AGVs, ensuring that they can effectively utilize the same path without conflict.

[0074] Real-time path optimization: The path state priority coefficient enables the system to adapt to environmental changes, such as sudden obstacles, emergencies, etc., and automatically adjust the AGV's operating path and priority.

[0075] Enhanced system robustness: By continuously evaluating and adjusting path priorities, the system can resist performance fluctuations caused by path problems and improve the reliability of overall scheduling.

[0076] Reduced energy consumption: By selecting the best path, AGV can complete the task in a shorter time, thereby reducing energy consumption and operating costs and improving overall economy.

[0077] The path state priority coefficient is specifically obtained in the following manner:

[0078] Obtain the starting point of important goods, and based on its own positioning, obtain the shortest path to the starting point through navigation algorithms;

[0079] The sensor monitors and obtains the obstacle distance and passable width in front of the AGV in real time, and obtains the congestion impact coefficient based on the congestion impact calculation formula in combination with the average speed of the AGV;

[0080] The path state priority coefficient is obtained based on the preset path state calculation formula in combination with the shortest path of the starting point and the congestion impact coefficient.

[0081] The specific calculation formula of the congestion impact coefficient is as follows:

[0082]

[0083] The specific calculation formula of the path state priority coefficient is as follows:

[0084]

[0085] In the formula, is the path state priority coefficient of the i-th vehicle, is the congestion impact coefficient, is the obstacle time, r is the shortest path distance, is the signal light interference coefficient, The time taken for the shortest path, is the distance between the AGV and the obstacle in front, is the width of the AGV itself, is the road width, is the average speed.

[0086] It should be noted that during the operation of the AGV, there may be vehicles or obstacles blocking the way ahead, which will prevent the AGV from passing. This will affect the priority of important task scheduling. Therefore, analyzing these data plays a significant role in obtaining the path state priority coefficient.

[0087] S2, the priority evaluation module, is used to establish an AGV priority scheduling evaluation model based on the neural network based on the AGV working status data and generate the AGV priority scheduling value.

[0088] The method for obtaining the AGV priority scheduling evaluation model is as follows:

[0089] Collect all AGV working status data after receiving the signal, including equipment status data, environmental status data and path status data, and clean and pre-process the data;

[0090] Based on neural network technology, the pre-processed data is trained in combination with historical data. Through real-time feedback during operation, the weights are automatically adjusted to assign the trained and adjusted weights to the equipment status data, environmental status data, and path status data respectively.

[0091] The AGV working status data is input into the trained AGV priority scheduling evaluation model to generate the AGV priority scheduling value.

[0092] The specific calculation formula of the AGV priority scheduling evaluation model is as follows:

[0093]

[0094] In the formula, is the priority dispatch value of the i-th AGV, is the priority coefficient describing the environmental state of the i-th AGV, is the equipment status priority coefficient of the i-th AGV, is the path state priority coefficient of the i-th vehicle, , , is the weight coefficient.

[0095] It should be noted that, when the priority coefficient of the environment state description is smaller, the priority coefficient of the equipment state is larger, and the priority coefficient of the path state is larger, it means that the priority value of the AGV is larger, and it can be given priority.

[0096] S3, AGV priority scheduling selection module, is used to calculate the priority scheduling average value according to the AGV priority scheduling value, generate a priority scheduling sorting table, and control the AGV to prioritize the transportation of important goods according to the priority scheduling sorting table. The specific steps are as follows:

[0097] Obtain real-time monitoring and obtain n priority dispatch values ​​of all AGVs in the running route, add the n priority dispatch values ​​and divide them by n to obtain the average priority dispatch value of each AGV;

[0098] According to the obtained average priority scheduling values ​​of each AGV, sort them in descending order to generate a priority scheduling sorting table;

[0099] The priority scheduling table provides the scheduling system with AGVs that can perform important tasks first, and controls them to transport goods to important task destinations.

[0100] It should be noted that during the operation of the AGV, its environmental status and path status are changing in real time, so taking n-segment priority scheduling values ​​and calculating their average values ​​ensures the stability of the priorities of all AGVs and ensures that there are no accidents during the process. Descending sorting means that AGVs with high priority are placed in front and those with low priority are placed in the back, with AGVs with high priority being scheduled first. When multiple AGVs are working at the same time, scheduling is performed based on task priority to ensure that important goods are processed first. This dynamic management strategy can effectively optimize resource allocation and improve the operational efficiency of the overall logistics system.

[0101] S4, the transportation route selection module, is used to obtain the environment map through laser SLAM, and obtain the optimal path from the current AGV position to the target position based on the A* path planning algorithm, so as to obtain the best navigation route for the transportation of important goods. When the AGV with a high priority level returns to the important cargo transportation place through the scheduling system to obtain the goods, the specific steps are as follows:

[0102] Scanning with laser SLAM generates environmental point cloud data, which is then filtered, de-noised, and feature extracted, and added to the grid map to build a complete environmental map.

[0103] Determine the location and task destination of the high-priority AGV transporting goods, and perform map location matching based on the constructed map according to the AGV location and task destination;

[0104] Based on the current map position matching, use the A* path planning algorithm to obtain a safe and effective path from the current AGV position to the task destination;

[0105] The planned trajectory is then sent to the AGV for control instructions to achieve transportation.

[0106] It should be noted that laser SLAM can obtain point cloud data of the environment in real time, and by continuously scanning and updating the environmental map, it ensures that the AGV can quickly adapt and respond to changes in a dynamic environment. This real-time update capability allows the AGV to efficiently identify obstacles and dynamic objects, thereby improving the safety and reliability of navigation. The A* algorithm combines heuristic search and cost calculation to efficiently find the optimal path from the starting position to the target position, avoid unnecessary detours, and improve transportation efficiency. The algorithm performs particularly well in complex environments and can adapt to a variety of different map configurations. This modular design makes the system scalable, and more AGVs or other automated equipment can be easily integrated in the future to meet logistics needs of different scales and complexities.

[0107] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0108] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0109] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0110] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0111] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0112] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An AGV dispatching system based on laser SLAM navigation, characterized in that: It includes information acquisition module, priority assessment module, AGV priority scheduling selection module and transportation route selection module. There are connections between modules: The information acquisition module is used to obtain the working status data of all AGVs when receiving the signal sent by the processing of important goods. The working status data includes equipment status data, environmental status data and path status data; A priority evaluation module is used to establish an AGV priority scheduling evaluation model based on the AGV working status data based on a neural network and generate an AGV priority scheduling value; The AGV priority dispatch selection module is used to calculate the priority dispatch average value according to the AGV priority dispatch value, generate a priority dispatch sorting table, and control the AGV to give priority to the transportation of important goods according to the priority dispatch sorting table; The transportation route selection module is used to obtain the environment map through laser SLAM and obtain the optimal path from the current AGV position to the target position based on the A* path planning algorithm, so as to obtain the best navigation route for the transportation of important goods; The device status data includes a device status priority coefficient, and the specific method for obtaining the device status priority coefficient is as follows: Monitor and obtain first data of the AGV device, where the first data includes the speed and acceleration of the device and the cruising range of the device; Calculate the power loss factor based on the charging frequency and charging time of the AGV; The kinetic energy of the motor is calculated based on the number of motor drives and the kinetic energy formula of the motor drive, and the kinetic energy state coefficient of the AGV is calculated in combination with the load data of the AGV and the friction coefficient of the drive wheel; The device state priority coefficient is calculated based on a preset device state data formula in combination with the first data, the power loss coefficient, and the AGV kinetic energy state coefficient; The specific calculation formula of the power loss coefficient is as follows: The specific calculation formula of the AGV kinetic energy state coefficient is as follows: The specific calculation formula of the device status priority coefficient is as follows: In the formula, is the equipment status priority coefficient of the i-th AGV, is the acceleration, is the power loss coefficient of the i-th AGV, is the kinetic energy state coefficient of the i-th AGV, is the speed of the device, The device's battery life. is the charging frequency, T is the charging time, is the kinetic energy of the motor, is the motor drive efficiency of the i-th AGV, is the friction coefficient of the driving wheel, is the load data of the current equipment, S is the number of driving wheels; The specific calculation formula of the AGV priority scheduling evaluation model is as follows: In the formula, is the priority dispatch value of the i-th AGV, is the priority coefficient describing the environmental state of the i-th AGV, is the equipment status priority coefficient of the i-th AGV, is the path state priority coefficient of the i-th vehicle, , , is the weight coefficient.

2. According to claim 1, an AGV dispatching system based on laser SLAM navigation is characterized in that: The environmental status data includes an environmental status description priority coefficient, and the path status data includes a path status priority coefficient.

3. The AGV dispatching system based on laser SLAM navigation according to claim 2 is characterized in that: The path state priority coefficient is specifically obtained in the following manner: Obtain the starting point of important goods, and based on its own positioning, obtain the shortest path to the starting point through navigation algorithms; The sensor monitors and obtains the obstacle distance and passable width in front of the AGV in real time, and obtains the congestion impact coefficient based on the congestion impact calculation formula in combination with the average speed of the AGV; The path state priority coefficient is obtained based on the preset path state calculation formula in combination with the shortest path of the starting point and the congestion impact coefficient.

4. The AGV dispatching system based on laser SLAM navigation according to claim 2 is characterized in that: The environmental state describes the priority coefficient, and the specific acquisition method is as follows: Real-time monitoring and acquisition of meteorological data of the area where the AGV is currently located, including temperature and wind speed; Analyze the impact of current AGV wind speed based on fluid dynamics and obtain the wind speed obstacle factor of current AGV; The environmental state description priority coefficient is obtained based on the preset environmental state data calculation formula in combination with the wind speed obstacle factor and the regional meteorological data.

5. The AGV dispatching system based on laser SLAM navigation according to claim 1 is characterized in that: The method for obtaining the AGV priority scheduling evaluation model is as follows: Collect all AGV working status data after receiving the signal, including equipment status data, environmental status data and path status data, and clean and pre-process the data; Based on neural network technology, the pre-processed data is trained in combination with historical data. Through real-time feedback during operation, the weights are automatically adjusted to assign the trained and adjusted weights to the equipment status data, environmental status data, and path status data respectively. The AGV working status data is input into the trained AGV priority scheduling evaluation model to generate the AGV priority scheduling value.

6. The AGV dispatching system based on laser SLAM navigation according to claim 1 is characterized in that: According to the AGV priority dispatch value, the priority dispatch average value is calculated, a priority dispatch sorting table is generated, and according to the priority dispatch sorting table, the AGV is controlled to give priority to the transportation of important goods. The specific steps are as follows: Obtain real-time monitoring and obtain n priority dispatch values ​​of all AGVs in the running route, add the n priority dispatch values ​​and divide them by n to obtain the average priority dispatch value of each AGV; According to the obtained average priority scheduling values ​​of each AGV, sort them in descending order to generate a priority scheduling sorting table; The priority scheduling table provides the scheduling system with AGVs that can perform important tasks first, and controls them to transport goods to important task destinations.

7. The AGV dispatching system based on laser SLAM navigation according to claim 1 is characterized in that: The method is used to obtain an environmental map through laser SLAM and obtain the optimal path from the current AGV position to the target position based on the A* path planning algorithm. The specific steps are as follows: Scanning with laser SLAM generates environmental point cloud data, which is then filtered, de-noised, and feature extracted, and added to the grid map to build a complete environmental map. Determine the location and task destination of the high-priority AGV transporting goods, and perform map location matching based on the constructed map according to the AGV location and task destination; Based on the current map position matching, use the A* path planning algorithm to obtain a safe and effective path from the current AGV position to the task destination; The planned trajectory is then sent to the AGV for control instructions to achieve transportation.

Images