Multi-AGV equipment cooperative scheduling method and system based on artificial intelligence

Abstract

The invention relates to an intelligent scheduling technology, and discloses a multi-AGV device cooperative scheduling method and system based on artificial intelligence, and the method comprises the steps: obtaining the motion parameters of each AGV device in real time, obtaining the task path data of each AGV device, building a digital twinborn simulation model according to the motion parameters and the task path data, and carrying out the calculation of the digital twinborn simulation model. Simulating a future path of each AGV device based on the digital twin simulation model to obtain simulated path data based on a time sequence, identifying time data of each AGV device arriving at each preset key node according to the simulated path data, obtaining an arrival time set of each key node, and obtaining an arrival time set of each key node; and carrying out AGV equipment collision analysis according to the arrival time set to obtain a collision analysis result, and carrying out cooperative scheduling on the AGV equipment according to the collision analysis result. According to the invention, the multi-AGV equipment scheduling efficiency can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent scheduling, and particularly to a multi-AGV device collaborative scheduling method and system based on artificial intelligence. Background Art

[0002] With the rapid development of industrial automation and intelligent manufacturing, Automated Guided Vehicles (AGVs) are increasingly widely used in fields such as logistics, warehousing, and manufacturing. However, with the complexity of application scenarios and the diversification of task requirements, traditional AGV scheduling methods have gradually revealed some limitations and cannot meet the requirements of efficient and intelligent multi-AGV collaborative work.

[0003] Traditional scheduling methods usually rely on simple rules or fixed priorities, making it difficult to dynamically adapt to changes in task requirements in complex environments, resulting in unreasonable task allocation and unbalanced loads of AGVs. In a dynamic environment, traditional path planning methods are difficult to adjust paths in real time to cope with emergencies such as the appearance of obstacles or traffic jams, easily leading to path conflicts and task delays. In a multi-AGV system, traditional scheduling methods lack effective coordination mechanisms and cannot achieve efficient cooperation between AGVs, easily resulting in resource waste and low efficiency. Summary of the Invention

[0004] The present invention provides a multi-AGV device collaborative scheduling method and system based on artificial intelligence, and its main purpose is to solve the problem of low efficiency of existing AGV device scheduling methods.

[0005] To achieve the above objective, a multi-AGV device collaborative scheduling method based on artificial intelligence provided by the present invention includes:

[0006] Real-time obtain the motion parameters of each AGV device and obtain the task path data of each AGV device;

[0007] Establish a digital twin simulation model according to the motion parameters and the task path data;

[0008] Simulate the future paths of each AGV device based on the digital twin simulation model to obtain simulation path data based on time series;

[0009] Identify the time data when each AGV device arrives at each preset key node according to the simulation path data to obtain the arrival time set of each key node;

[0010] Perform AGV device collision analysis according to the arrival time set to obtain a collision analysis result;

[0011] Perform collaborative scheduling on the AGV devices according to the collision analysis result.

[0012] Optionally, establishing a digital twin simulation model based on the motion parameters and the task path data includes:

[0013] Obtain the physical parameters of the AGV device;

[0014] Establish a digital model of the AGV device according to the physical parameters;

[0015] Construct a path geometry model according to the task path data;

[0016] Set the digital model of the AGV device into the path geometry model to obtain an initial digital twin simulation model;

[0017] Perform AGV device motion simulation in the initial digital twin simulation model according to the motion parameters to confirm the digital twin simulation model.

[0018] Optionally, performing AGV device motion simulation in the initial digital twin simulation model according to the motion parameters to confirm the digital twin simulation model includes:

[0019] Perform operation simulation on the initial digital twin simulation model based on preset motion constraint parameters and the motion parameters;

[0020] Obtain the simulated position of the AGV device after the initial digital twin simulation model simulates a preset duration;

[0021] Use a preset radar device to obtain the real position of the AGV device after the simulated preset duration;

[0022] Perform position error analysis based on the simulated position and the real position to obtain an error value;

[0023] Determine whether the error value is greater than a preset error threshold;

[0024] If the error value is greater than the error threshold, then after adjusting the motion constraint parameters according to the error value, return to the step of performing motion simulation on the digital model of the AGV device in the path geometry model based on the preset motion constraint parameters and the motion parameters;

[0025] If the error value is less than or equal to the error threshold, then confirm the initial digital twin simulation model as the final digital twin simulation model.

[0026] Optionally, simulating the future path of each AGV device based on the digital twin simulation model to obtain simulation path data based on a time series includes:

[0027] Perform AGV device motion simulation based on the digital twin simulation model according to the motion parameters;

[0028] Confirm the corresponding relationship between each AGV device and the upcoming preset key node according to the moving direction included in the moving parameters;

[0029] Obtain the distance data between each AGV device and the corresponding preset key node in the simulation process in real time according to the corresponding relationship;

[0030] Judge in real time whether the distance between each AGV device and the corresponding preset key node is less than a preset distance threshold according to the distance data;

[0031] If the distance between the AGV device and the corresponding preset key node is greater than or equal to the distance threshold, return to the step of obtaining the distance data between each AGV device and the corresponding preset key node in the simulation process in real time according to the corresponding relationship

[0032] If the distance between the AGV device and the corresponding preset key node is less than the distance threshold, obtain the path position data of the AGV device according to a preset time interval to obtain simulation path data.

[0033] Optionally, identifying the time data when each AGV device arrives at each preset key node according to the simulation path data to obtain the arrival time set of each key node, including:

[0034] Obtain the adjacent time points before and after each key node according to the simulation path data to obtain the pre-node time point and the post-node time point;

[0035] Obtain the distance data between each key node and the pre-node time point and the post-node time point to obtain the pre-node distance and the post-node distance;

[0036] Confirm the arrival time of each key node based on the ratio relationship between the pre-node distance and the post-node distance to obtain the arrival time set.

[0037] Optionally, the collaborative scheduling of AGV devices according to the collision analysis result includes:

[0038] Confirm any two AGV devices with collision risks according to the collision analysis result to obtain the first risk device and the second risk device;

[0039] Perform path complexity analysis on the first risk device and the second risk device according to the task path data to obtain a path complexity coefficient;

[0040] Obtain the cargo transportation volume, the distance to the target point, and the current running speed of the first risk device and the second risk device;

[0041] Calculate the equipment priorities of the first risk equipment and the second risk equipment according to the volume of goods transported, the distance to the target point, the current running speed, and the path complexity coefficient;

[0042] Perform collaborative scheduling on the first risk equipment and the second risk equipment according to the equipment priorities.

[0043] Optionally, the path complexity analysis of the first risk equipment and the second risk equipment based on the task path data to obtain the path complexity coefficient includes:

[0044] Confirm the target paths of the first risk equipment and the second risk equipment according to the task path data;

[0045] Confirm the number of all equipment passing through the target path according to the task path data to obtain the number of co-path equipment;

[0046] Obtain the total number of task paths according to the task path data;

[0047] Calculate the ratio of the number of co-path equipment to the total number of task paths to obtain the path complexity coefficient.

[0048] Optionally, the calculation formula of the equipment priority is as follows:

[0049]

[0050] Where K is the equipment priority, V is the current running speed, W is the volume of goods transported, α is a preset complex coefficient weight parameter, S is the path complexity coefficient, L is the distance to the target point, and L max is the maximum path included in the task path data.

[0051] Optionally, the collaborative scheduling of the first risk equipment and the second risk equipment according to the equipment priority includes:

[0052] Confirm the low-priority equipment and the high-priority equipment according to the equipment priority;

[0053] Confirm the time difference between the low-priority equipment and the high-priority equipment arriving at the preset key node according to the arrival time set;

[0054] Calculate the deceleration data according to the current speed of the low-priority equipment and the time difference;

[0055] Perform deceleration scheduling on the low-priority equipment according to the deceleration data.

[0056] To solve the above problems, the present invention also provides a multi-AGV device collaborative scheduling system based on artificial intelligence, and the system includes:

[0057] A data acquisition module, configured to acquire the motion parameters of each AGV device in real time and acquire the task path data of each AGV device;

[0058] A model establishment module, configured to establish a digital twin simulation model according to the motion parameters and the task path data;

[0059] A path simulation module, configured to simulate the future path of each AGV device based on the digital twin simulation model to obtain simulation path data based on a time series;

[0060] ]>A collision analysis module, configured to identify the time data of each AGV device reaching each preset key node according to the simulation path data, obtain a set of arrival times of each key node, and perform AGV device collision analysis according to the set of arrival times to obtain a collision analysis result;

[0061] A collaborative scheduling module, configured to perform collaborative scheduling on the AGV devices according to the collision analysis result.

[0062] In the embodiment of the present invention, by acquiring the motion parameters of each AGV device in real time, acquiring the task path data of each AGV device, establishing a digital twin simulation model according to the motion parameters and the task path data, simulating the future path of each AGV device based on the digital twin simulation model to obtain simulation path data based on a time series, identifying the time data of each AGV device reaching each preset key node according to the simulation path data, obtaining a set of arrival times of each key node, performing AGV device collision analysis according to the set of arrival times to obtain a collision analysis result, and performing collaborative scheduling on the AGV devices according to the collision analysis result. Therefore, the multi-AGV device collaborative scheduling method and system based on artificial intelligence proposed by the present invention can solve the problem of low efficiency of the existing AGV device scheduling method. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 is a schematic flowchart of a multi-AGV device collaborative scheduling method based on artificial intelligence provided by an embodiment of the present invention;

[0064] Figure 2 is a functional module diagram of a multi-AGV device collaborative scheduling system based on artificial intelligence provided by an embodiment of the present invention.

[0065] The implementation, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0066] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0067] An embodiment of the present application provides a method for collaborative scheduling of multiple AGV devices based on artificial intelligence. The execution subject of the method for collaborative scheduling of multiple AGV devices based on artificial intelligence includes, but is not limited to, at least one of electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for collaborative scheduling of multiple AGV devices based on artificial intelligence can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to: a single server, a server cluster, a cloud server, or a cloud server cluster, etc. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms.

[0068] Refer to Figure 1 As shown, it is a flowchart of a method for collaborative scheduling of multiple AGV devices based on artificial intelligence provided by an embodiment of the present invention. In this embodiment, the method for collaborative scheduling of multiple AGV devices based on artificial intelligence includes:

[0069] S1. Real-time obtain the motion parameters of each AGV device and obtain the task path data of each AGV device.

[0070] In an embodiment of the present invention, the AGV (Automated Guided Vehicle) device is an unmanned automated transportation tool and is widely used in fields such as logistics, warehousing, and manufacturing.

[0071] Specifically, a navigation system is installed in the AGV device to be responsible for guiding the driving route and positioning of the AGV. Common navigation methods include magnetic stripe navigation, laser navigation, inertial navigation, and visual navigation.

[0072] Specifically, a vehicle-mounted controller is installed in the AGV device to process sensor data and execute navigation, path planning, and task instructions.

[0073] In an embodiment of the present invention, the task path data refers to the transportation route preset by the AGV device in a preset warehousing environment.

[0074] In the embodiments of the present invention, the motion parameters generally include the current speed, acceleration, motion direction, angular velocity (if there is motion such as turning, etc.) of the AGV device. These parameters can accurately describe the motion state of the AGV device and are crucial for establishing a digital twin simulation model and simulating its operation path subsequently. For example, the speed parameter of the AGV device affects its travel time on the path, and the acceleration parameter comes into play when starting, stopping, or changing speed.

[0075] In the embodiments of the present invention, by obtaining the motion parameters of each AGV device in real time and obtaining the task path data of each AGV device, the efficiency and accuracy of establishing a digital twin simulation model subsequently can be improved.

[0076] S2. Establish a digital twin simulation model according to the motion parameters and the task path data.

[0077] In the embodiments of the present invention, the digital twin simulation model is a technology that creates a virtual model of a physical entity through digital means and uses real-time data for simulation, analysis, and optimization, and can simulate the operation of the AGV device according to the motion parameters and the task path data.

[0078] In the embodiments of the present invention, establishing a digital twin simulation model according to the motion parameters and the task path data includes:

[0079] Obtain the physical parameters of the AGV device;

[0080] Establish a digital model of the AGV device according to the physical parameters;

[0081] Construct a path geometry model according to the task path data;

[0082] Set the digital model of the AGV device into the path geometry model to obtain an initial digital twin simulation model;

[0083] Confirm the digital twin simulation model by simulating the motion of the AGV device in the initial digital twin simulation model according to the motion parameters.

[0084] Specifically, the physical parameters of the AGV device generally include the dimensions (length, width, height), weight, maximum load capacity, battery capacity, motor power, etc. of the device. These parameters determine the physical characteristics of the AGV device and need to be accurately considered when establishing a digital model. For example, the dimensions of the device affect its passability on the path, the maximum load capacity is related to the cargo transportation volume, and the battery capacity and motor power affect the endurance and operating speed of the device, etc.

[0085] In an embodiment of the present invention, the method of performing AGV device motion simulation in the initial digital twin simulation model according to the motion parameters to confirm the digital twin simulation model includes:

[0086] Performing a running simulation on the initial digital twin simulation model based on preset motion constraint parameters and the motion parameters;

[0087] Obtaining the simulated position of the AGV device after the initial digital twin simulation model simulates a preset duration;

[0088] Using a preset radar device to obtain the real position of the AGV device after the simulated preset duration;

[0089] Performing position error analysis based on the simulated position and the real position to obtain an error value;

[0090] Determining whether the error value is greater than a preset error threshold;

[0091] If the error value is greater than the error threshold, then after adjusting the motion constraint parameters according to the error value, returning to the step of performing motion simulation on the AGV device digital model in the path geometric model based on the preset motion constraint parameters and the motion parameters;

[0092] If the error value is less than or equal to the error threshold, then confirming the initial digital twin simulation model as the final digital twin simulation model.

[0093] In an embodiment of the present invention, the motion constraint parameters may include the maximum speed limit, minimum turning radius, maximum acceleration limit, maximum deceleration limit, etc. of the AGV device. These parameters are to enable the digital model to more realistically simulate the physical limitations of the AGV device during actual operation. For example, the minimum turning radius limits the path selection of the AGV device when turning, and the maximum speed limit ensures that the device does not exceed its safe operating speed.

[0094] Specifically, the radar device generally refers to a sensor for detecting the position and distance of an object, such as a lidar, millimeter-wave radar, etc. These radar devices determine the position of the AGV device by emitting signals and receiving reflected signals. For example, a lidar can emit laser beams and calculate the distance to an object (AGV device) based on the time when the laser beams are reflected back, thereby determining its position.

[0095] S3. Simulating the future path of each AGV device based on the digital twin simulation model to obtain simulation path data based on a time series.

[0096] In the embodiment of the present invention, the simulation of the future path of each AGV device based on the digital twin simulation model is a simulation based on a time series, that is, a time point sequence is obtained by setting a time interval, and the position of each AGV device at each time point is simulated according to the digital twin simulation model to obtain the simulated path data.

[0097] In the embodiment of the present invention, the simulation of the future path of each AGV device based on the digital twin simulation model to obtain the simulated path data based on a time series includes:

[0098] Performing AGV device motion simulation based on the digital twin simulation model according to the motion parameters;

[0099] According to the motion direction included in the motion parameters, confirming the corresponding relationship between each AGV device and the preset key nodes to be passed;

[0100] According to the corresponding relationship, obtaining the distance data between each AGV device and the corresponding preset key node in the simulation process in real time;

[0101] Judging in real time whether the distance between each AGV device and the corresponding preset key node is less than a preset distance threshold according to the distance data;

[0102] If the distance between the AGV device and the corresponding preset key node is greater than or equal to the distance threshold, return to the step of obtaining the distance data between each AGV device and the corresponding preset key node in the simulation process according to the corresponding relationship

[0103] If the distance between the AGV device and the corresponding preset key node is less than the distance threshold, obtain the path position data of the AGV device according to a preset time interval to obtain the simulated path data.

[0104] Specifically, the distance threshold needs to be set in combination with the operation data of the AGV device in the working scenario. For example, the higher the running speed of the AGV device in the working scenario, the larger the distance threshold.

[0105] Specifically, the preset time interval can be 0.1 second.

[0106] In the embodiment of the present invention, the preset key nodes refer to the nodes in the preset warehousing environment where collisions are likely to occur between AGV devices, such as intersections and T-shaped intersections in the warehousing environment.

[0107] In the embodiments of the present invention, by simulating the future paths of each AGV device based on the digital twin simulation model, simulation path data based on a time series can be obtained, which can improve the accuracy of subsequent analysis of the arrival time of each key node.

[0108] S4. Identify the time data of each AGV device arriving at each preset key node according to the simulation path data, and obtain the arrival time set of each key node.

[0109] In the embodiments of the present invention, since the path position data of the AGV device is obtained at preset time intervals, it may not be possible to accurately collect the time data of arriving at the preset key node. For example, the arrival time of the preset key node is between two time collections. Therefore, it is necessary to accurately calculate the arrival time of the key node by combining the adjacent time points before and after the key node.

[0110] In the embodiments of the present invention, the step of identifying the time data of each AGV device arriving at each preset key node according to the simulation path data and obtaining the arrival time set of each key node includes: obtaining the adjacent time points before and after each key node according to the simulation path data, and obtaining the pre-node time point and the post-node time point;

[0111] Obtain the distance data between each key node and the pre-node time point and the post-node time point, and obtain the pre-node distance and the post-node distance;

[0112] Confirm the arrival time of each key node based on the ratio relationship between the pre-node distance and the post-node distance, and obtain the arrival time set.

[0113] Specifically, the step of confirming the arrival time of each key node based on the ratio relationship between the pre-node distance and the post-node distance is to calculate the accurate arrival time based on the ratio of the pre-node distance and the post-node distance and the preset time interval. For example, if the ratio of the pre-node distance and the post-node distance is 4:6 and the preset time interval is 0.1 second, the accurate arrival time of the key node is the time of the pre-node time point plus 0.1×0.4 second.

[0114] S5. Perform collision analysis on the AGV devices according to the arrival time set, and obtain the collision analysis result.

[0115] In the embodiments of the present invention, the step of performing collision analysis on the AGV devices according to the arrival time set is to analyze the arrival times of all AGV devices arriving at the same key node. If the arrival time difference is less than the preset time difference threshold, it is determined that there is a collision risk.

[0116] Specifically, the time difference threshold needs to be set according to the size and speed of the AGV device.

[0117] S6. Perform collaborative scheduling on the AGV device according to the collision analysis result.

[0118] In the embodiment of the present invention, the performing collaborative scheduling on the AGV device according to the collision analysis result is to perform collaborative scheduling between any two AGV devices with collision risks.

[0119] In the embodiment of the present invention, the performing collaborative scheduling on the AGV device according to the collision analysis result includes:

[0120] Confirm any two AGV devices with collision risks according to the collision analysis result to obtain a first risk device and a second risk device;

[0121] Perform path complexity analysis on the first risk device and the second risk device according to the task path data to obtain a path complexity coefficient;

[0122] Obtain the cargo transportation volume, distance to the target point, and current running speed of the first risk device and the second risk device;

[0123] Calculate the device priorities of the first risk device and the second risk device according to the cargo transportation volume, distance to the target point, current running speed, and the path complexity coefficient;

[0124] Perform collaborative scheduling on the first risk device and the second risk device according to the device priorities.

[0125] In the embodiment of the present invention, the performing path complexity analysis on the first risk device and the second risk device according to the task path data to obtain a path complexity coefficient includes:

[0126] Confirm the target paths of the first risk device and the second risk device according to the task path data;

[0127] Confirm the number of devices passing through the target path according to the task path data to obtain the number of devices on the same path;

[0128] Obtain the total number of task paths according to the task path data;

[0129] Calculate the ratio of the number of devices on the same path to the total number of task paths to obtain the path complexity coefficient.

[0130] In the embodiment of the present invention, the calculation formula of the device priority is as follows:

[0131]

[0132] Wherein, K is the device priority, V is the current running speed, W is the cargo transportation volume, α is a preset complex coefficient weight parameter, S is the path complexity coefficient, L is the distance to the target point, and L max is the maximum path included in the task path data.

[0133] Specifically, the complex coefficient weight parameter can be taken as 0.8.

[0134] In the embodiment of the present invention, the collaborative scheduling of the first risk device and the second risk device according to the device priority is to perform deceleration scheduling on the device with a lower priority based on the device priority to ensure that the device with a higher priority passes first.

[0135] In the embodiment of the present invention, the collaborative scheduling of the first risk device and the second risk device according to the device priority includes:

[0136] Identifying the low-priority device and the high-priority device according to the device priority;

[0137] Identifying the time difference between the low-priority device and the high-priority device arriving at the preset key node according to the arrival time set;

[0138] Calculating the deceleration data according to the current speed of the low-priority device and the time difference;

[0139] Performing deceleration scheduling on the low-priority device according to the deceleration data.

[0140] In the embodiment of the present invention, by performing collaborative scheduling on the AGV device according to the collision analysis result, it ensures that the AGV device with a higher priority communicates first, and guarantees the operation efficiency of the AGV device.

[0141] As Figure 2 shown, it is a functional module diagram of a multi-AGV device collaborative scheduling system based on artificial intelligence provided by an embodiment of the present invention.

[0142] The multi-AGV device collaborative scheduling system 100 based on artificial intelligence of the present invention can be installed in an electronic device. According to the implemented functions, the multi-AGV device collaborative scheduling system 100 based on artificial intelligence can include a data acquisition module 101, a model establishment module 102, a path simulation module 103, a collision analysis module 104, and a collaborative scheduling module 105. The modules of the present invention can also be referred to as units, which refer to a series of computer program segments that can be executed by the processor of the electronic device and can complete fixed functions, and are stored in the memory of the electronic device.

[0143] In this embodiment, the functions of each module / unit are as follows:

[0144] The data acquisition module 101 is used to obtain the motion parameters of each AGV device in real time and obtain the task path data of each AGV device;

[0145] The model establishment module 102 is used to establish a digital twin simulation model according to the motion parameters and the task path data;

[0146] The path simulation module 103 is used to simulate the future path of each AGV device based on the digital twin simulation model to obtain simulation path data based on time series;

[0147] The collision analysis module 104 is used to identify the time data of each AGV device reaching each preset key node according to the simulation path data, obtain the arrival time set of each key node, and perform AGV device collision analysis according to the arrival time set to obtain a collision analysis result;

[0148] The collaborative scheduling module 105 is used to perform collaborative scheduling on the AGV devices according to the collision analysis result.

[0149] Specifically, each module in the multi-AGV device collaborative scheduling system 100 based on artificial intelligence in the embodiment of the present invention adopts the same technical means as those Figure 1 described in the above-mentioned multi-AGV device collaborative scheduling method based on artificial intelligence and can produce the same technical effects, which will not be elaborated here.

[0150] In the embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0151] The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0152] In addition, in each embodiment of the present invention, the functional modules can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of a combination of hardware and software function modules.

[0153] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-described exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention.

[0154] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be embraced within the present invention. Any reference signs in the claims should not be construed as limiting the claims involved.

[0155] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is a theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results.

[0156] In addition, it is obvious that the term "including" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units or systems stated in the system claims can also be implemented by one unit or system through software or hardware. The terms first, second, etc. are used to denote names and do not denote any particular order.

[0157] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A collaborative scheduling method for multi-AGV devices based on artificial intelligence, characterized in that, The method includes: Obtaining the motion parameters of each AGV device in real time and obtaining the task path data of each AGV device; Establishing a digital twin simulation model according to the motion parameters and the task path data; Simulating the future path of each AGV device based on the digital twin simulation model to obtain simulation path data based on time series; Identifying the time data when each AGV device reaches each preset key node according to the simulation path data to obtain a set of arrival times for each key node; Performing AGV device collision analysis according to the set of arrival times to obtain a collision analysis result; Performing collaborative scheduling on the AGV devices according to the collision analysis result.

2. The collaborative scheduling method for multiple AGV devices based on artificial intelligence according to claim 1, wherein The establishing a digital twin simulation model according to the motion parameters and the task path data includes: Obtaining the physical parameters of the AGV device; Establishing a digital model of the AGV device according to the physical parameters; Constructing a path geometry model according to the task path data; Setting the digital model of the AGV device into the path geometry model to obtain an initial digital twin simulation model; Performing AGV device motion simulation in the initial digital twin simulation model according to the motion parameters to confirm the digital twin simulation model.

3. The collaborative scheduling method for multi-AGV devices based on artificial intelligence according to claim 2, characterized in that, Performing AGV device motion simulation in the initial digital twin simulation model according to the motion parameters to confirm the digital twin simulation model includes: Performing a running simulation on the initial digital twin simulation model based on preset motion constraint parameters and the motion parameters; Obtaining the simulated position of the AGV device after the initial digital twin simulation model simulates a preset duration; Using a preset radar device to obtain the real position of the AGV device after the simulated preset duration; Performing position error analysis according to the simulated position and the real position to obtain an error value; Judging whether the error value is greater than a preset error threshold; If the error value is greater than the error threshold, then after adjusting the motion constraint parameters according to the error value, return to the step of performing motion simulation on the digital model of the AGV device in the path geometry model based on the preset motion constraint parameters and the motion parameters; If the error value is less than or equal to the error threshold, then confirm the initial digital twin simulation model as the final digital twin simulation model.

4. The collaborative scheduling method for multiple AGV devices based on artificial intelligence according to claim 1, characterized in that, The simulating the future path of each AGV device based on the digital twin simulation model to obtain simulation path data based on time series includes: Performing AGV device motion simulation based on the digital twin simulation model according to the motion parameters; Confirming the corresponding relationship between each AGV device and the upcoming preset key node according to the motion direction included in the motion parameters; Obtaining the distance data between each AGV device and the corresponding preset key node in real time during the simulation process according to the corresponding relationship; Judging in real time whether the distance between each AGV device and the corresponding preset key node is less than a preset distance threshold according to the distance data; If the distance between the AGV device and the corresponding preset key node is greater than or equal to the distance threshold, return to the step of obtaining the distance data between each AGV device and the corresponding preset key node in the simulation process in real time according to the corresponding relationship; If the distance between the AGV device and the corresponding preset key node is less than the distance threshold, obtain the path position data of the AGV device according to a preset time interval to obtain simulation path data.

5. The collaborative scheduling method for multiple AGV devices based on artificial intelligence according to claim 1, wherein Identifying the time data when each AGV device reaches each preset key node according to the simulation path data to obtain a set of arrival times for each key node, including: Obtain the adjacent time points before and after each key node according to the simulation path data to obtain the pre-node time point and the post-node time point; Obtain the distance data between each key node and the pre-node time point and the post-node time point to obtain the pre-node distance and the post-node distance; Based on the ratio relationship between the pre-node distance and the post-node distance, confirm the arrival time of each key node to obtain the set of arrival times.

6. The collaborative scheduling method for multiple AGV devices based on artificial intelligence according to claim 1, wherein, The collaborative scheduling of the AGV device according to the collision analysis result includes: According to the collision analysis result, confirm any two AGV devices with collision risks to obtain the first risk device and the second risk device; Perform path complexity analysis on the first risk device and the second risk device according to the task path data to obtain a path complexity coefficient; Obtain the cargo transportation volume, the distance to the target point, and the current running speed of the first risk device and the second risk device; Calculate the device priorities of the first risk device and the second risk device according to the cargo transportation volume, the distance to the target point, the current running speed, and the path complexity coefficient; Perform collaborative scheduling on the first risk device and the second risk device according to the device priorities.

7. The collaborative scheduling method for multiple AGV devices based on artificial intelligence according to claim 6, characterized in that, The path complexity analysis of the first risk device and the second risk device according to the task path data to obtain a path complexity coefficient includes: Confirm the target paths of the first risk device and the second risk device according to the task path data; Confirm the number of devices passing through the target path according to the task path data to obtain the number of same-path devices; Obtain the total number of task paths according to the task path data; Calculate the ratio of the number of same-path devices to the total number of task paths to obtain the path complexity coefficient.

8. The collaborative scheduling method for multi-AGV devices based on artificial intelligence according to claim 7, wherein, The calculation formula of the device priority is as follows: Among them, K is the device priority, V is the current running speed, W is the cargo transportation volume, α is a preset complex coefficient weight parameter, S is the path complexity coefficient, L is the distance to the target point, and L max is the maximum path included in the task path data.

9. The collaborative scheduling method for multi-AGV devices based on artificial intelligence according to claim 6, characterized in that, The collaborative scheduling of the first risk device and the second risk device according to the device priority includes: Confirm the low-priority device and the high-priority device according to the device priority; Confirm the time difference between the low-priority device and the high-priority device reaching the preset key node according to the set of arrival times; Calculate the deceleration data according to the current speed of the low-priority device and the time difference; Perform deceleration scheduling on the low-priority device according to the deceleration data.

10. A multi-AGV device collaborative scheduling system based on artificial intelligence, characterized in that, The system includes: A data acquisition module, which is used to acquire the motion parameters of each AGV device in real time and obtain the task path data of each AGV device; A model establishment module, which is used to establish a digital twin simulation model according to the motion parameters and the task path data; A path simulation module, which is used to simulate the future path of each AGV device based on the digital twin simulation model to obtain simulation path data based on time series; A collision analysis module, which is used to identify the time data of each AGV device arriving at each preset key node according to the simulation path data, obtain the arrival time set of each key node, and perform AGV device collision analysis according to the arrival time set to obtain a collision analysis result; A collaborative scheduling module, which is used to perform collaborative scheduling on the AGV devices according to the collision analysis result.

Images