Dynamic scheduling method and device for automated guided vehicle, equipment and medium

Abstract

The embodiment of the invention provides a dynamic scheduling method and device for automated guided vehicles, equipment and a medium. The method comprises the following steps: acquiring task path information, task priority information and vehicle electric quantity state information of a plurality of automated guided vehicles for executing a target task and initial weight data of the automated guided vehicles; adjusting initial weight data of each automated guided vehicle according to the task path information, the task priority information and the vehicle electric quantity state information to obtain target weight data of each automated guided vehicle; performing weighted calculation on the task path information, the task priority information and the vehicle electric quantity state information according to the target weight data to obtain task cost information of each automatic guided vehicle; and scheduling the automated guided vehicle with the lowest task cost information to execute the target task. According to the embodiment of the invention, global optimization of multiple factors is realized, the weight is dynamically adjusted, and the dynamic adaptability of scheduling is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of device scheduling, in particular to an automated guided vehicle dynamic scheduling method, an automated guided vehicle dynamic scheduling device, an electronic device and a storage medium. BACKGROUND

[0002] At present, the existing technical scheme is that most of the traditional multi-AGV path planning methods are mostly based on single objective optimization (such as shortest path), which can solve the path planning problem to a certain extent, but still has the following technical bottlenecks: 1. Limitation of single objective optimization: traditional ant colony algorithm or heuristic A-star algorithm only focuses on path length, and cannot optimize energy consumption, path conflict and other multi-objective weights at the same time, resulting in low overall efficiency of the system.

[0003] 2. Lack of global optimization ability: existing methods usually solve path conflict problems through local optimization (such as deadlock resolution algorithm and conflict resolution algorithm), but fail to fully utilize the collaborative optimization ability between multiple AGVs, and the global optimization effect is limited.

[0004] 3. Insufficient dynamic adaptability: under dynamic task demand and complex environmental changes, existing methods are difficult to dynamically adjust optimization objectives and weights, resulting in poor system flexibility and adaptability. SUMMARY

[0005] In view of the above problems, an automated guided vehicle dynamic scheduling method and device, an electronic device and a storage medium are provided to overcome the above problems or at least partially solve the above problems, comprising: An automated guided vehicle dynamic scheduling method, the method comprising: Obtaining task path information, task priority information, vehicle power state information of a plurality of automated guided vehicles for executing target tasks, and initial weight data of the automated guided vehicles; Adjusting the initial weight data of each automated guided vehicle according to the task path information, the task priority information and the vehicle power state information to obtain target weight data of each automated guided vehicle; Performing weighted calculation on the task path information, the task priority information and the vehicle power state information according to the target weight data to obtain task cost information of each automated guided vehicle; Scheduling the automated guided vehicle with the lowest task cost information to execute the target task.

[0006] Optionally, the adjusting the initial weight data of each automated guided vehicle according to the task path information, the task priority information and the vehicle power state information to obtain the target weight data of each automated guided vehicle comprises: determining whether there is a route conflict according to the task path information; when it is determined that there is a route conflict, determining a conflict type of the route conflict; adjusting the initial weight data of each automated guided vehicle according to the conflict type, the task priority information and the vehicle power state information to obtain the target weight data of each automated guided vehicle.

[0007] Optionally, the adjusting the initial weight data of each automated guided vehicle according to the conflict type, the task priority information and the vehicle power state information to obtain the target weight data of each automated guided vehicle comprises: when the conflict type is the relative route conflict or the crossing route conflict, determining whether the task priority information of a target automated guided vehicle is higher than that of other automated guided vehicles; if the task priority information of the target automated guided vehicle is higher than that of other automated guided vehicles, adjusting the initial weight data corresponding to the task path information and the task priority information to obtain the target weight data of each automated guided vehicle.

[0008] Optionally, the adjusting the initial weight data of each automated guided vehicle according to the conflict type, the task priority information and the vehicle power state information to obtain the target weight data of each automated guided vehicle comprises: when the conflict type is the relative route conflict or the crossing route conflict, determining whether the vehicle power state information of a target automated guided vehicle is higher than that of other automated guided vehicles; if the vehicle power state information of the target automated guided vehicle is higher than that of other automated guided vehicles, adjusting the initial weight data corresponding to the task path information and the vehicle power state information to obtain the target weight data of each automated guided vehicle.

[0009] Optionally, the adjusting the initial weight data of each automated guided vehicle according to the conflict type, the task priority information and the vehicle power state information to obtain the target weight data of each automated guided vehicle comprises: when the conflict type is the same direction route conflict, if the automated guided vehicle arrives at the conflict route section and the waiting time exceeds a preset time, adjusting the initial weight data corresponding to the task path information to obtain the target weight data of each automated guided vehicle.

[0010] Optionally, the adjusting the initial weight data of each automated guided vehicle according to the conflict type, the task priority information and the vehicle power state information to obtain target weight data of each automated guided vehicle comprises: obtaining a preset weight adjustment rule; adjusting the initial weight data of each automated guided vehicle according to the conflict type, the task priority information and the vehicle power state information according to the weight adjustment rule to obtain target weight data of each automated guided vehicle.

[0011] Optionally, the method further comprises: obtaining pheromone concentration of a starting point of a path of each automated guided vehicle; determining a shortest route of the automated guided vehicle according to the task path information and the pheromone concentration.

[0012] Optionally, the determining the shortest route of the automated guided vehicle according to the task path information and the pheromone concentration comprises: determining distance information between each node and a set of adjacent nodes of a current node according to the task path information; determining a probability of a next node based on the pheromone concentration, the distance information and the set of adjacent nodes; determining the shortest route of the automated guided vehicle according to the probability of the next node.

[0013] Optionally, the method further comprises: updating the pheromone concentration of the next node according to the pheromone concentration of the current node.

[0014] An automated guided vehicle dynamic scheduling device, the device comprising: a data acquisition module, configured to acquire task path information, task priority information, vehicle power state information and initial weight data of a plurality of automated guided vehicles for performing target tasks; a weight adjustment module, configured to adjust the initial weight data of each automated guided vehicle according to the task path information, the task priority information and the vehicle power state information to obtain target weight data of each automated guided vehicle; a cost calculation module, configured to perform weighted calculation on the task path information, the task priority information and the vehicle power state information according to the target weight data to obtain task cost information of each automated guided vehicle; a scheduling module, configured to schedule an automated guided vehicle with the lowest task cost information to perform the target task.

[0015] An electronic device comprises a processor, a memory, and a computer program stored on the memory and capable of running on the processor, which, when executed by the processor, implements the automated guided vehicle dynamic scheduling method as described above.

[0016] A computer readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the automated guided vehicle dynamic scheduling method as described above.

[0017] Embodiments of the present application have the following advantages: The embodiments of the present application obtain task path information, task priority information, vehicle power state information of a plurality of automated guided vehicles for performing a target task, and initial weight data of the automated guided vehicles; adjust the initial weight data of each automated guided vehicle according to the task path information, the task priority information, and the vehicle power state information to obtain target weight data of each automated guided vehicle; perform weighted calculation on the task path information, the task priority information, and the vehicle power state information according to the target weight data to obtain task cost information of each automated guided vehicle; and schedule the automated guided vehicle with the lowest task cost information to perform the target task, which realizes global optimization from multiple factors such as task path information, task priority information, and vehicle power state information, dynamically adjusts the weight, and improves the dynamic adaptability of the vehicle scheduling. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the present application, the following will briefly introduce the drawings needed to be used in the description of the present application. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0019] Figure 1a is a step flow chart of an automated guided vehicle dynamic scheduling method provided by an embodiment of the present application; Figure 1b is a step flow chart of an automated guided vehicle dynamic scheduling method provided by an embodiment of the present application; Figure 1c is a step flow chart of an automated guided vehicle dynamic scheduling method provided by an embodiment of the present application; Figure 1d is a schematic diagram of path conflict of an automated guided vehicle provided by an embodiment of the present application; Figure 2 is a step flow chart of another automated guided vehicle dynamic scheduling method provided by an embodiment of the present application; is a step flow chart of another automated guided vehicle dynamic scheduling method provided by an embodiment of the present application;Figure 3 This is a schematic diagram of the structure of an automated guided vehicle dynamic scheduling device provided in an embodiment of the present invention. Detailed Implementation

[0020] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0021] Reference Figure 1a The diagram illustrates a flowchart of a dynamic scheduling method for automated guided vehicles according to an embodiment of the present invention, which may specifically include the following steps: Step S101: Obtain task path information, task priority information, vehicle battery status information, and initial weight data of the automated guided vehicles (AGVs) used to perform the target task. In practical applications, when a new transportation task is issued, the current status of multiple automated guided vehicles (AGVs) can be determined, and the AGVs that are currently idle can be identified. This allows for the determination of the global information of the AGV, such as task path information, task priority information, and vehicle battery status information. The task path information includes path length and path conflict information.

[0022] This invention introduces a multi-objective weight optimization mechanism, which includes the following objectives in the optimization scope: Path length: The distance the AGV travels (the shorter the length, the closer the route).

[0023] Health battery level: AGV's battery level information (the lower the battery level, the more urgent the situation and the higher the priority).

[0024] Task priority: The urgency level of the task executed by the AGV (the higher the priority, the more urgent the task, and the more it needs to be completed first).

[0025] Route conflict: Road segments that may conflict with other car routes (the fewer the conflicts, the lower the probability of a conflict and the better the route).

[0026] Step S102: Adjust the initial weight data of each automated guided vehicle according to the task path information, the task priority information and the vehicle battery status information to obtain the target weight data of each automated guided vehicle. In this embodiment of the invention, initial weights are set for the factors affecting scheduling, and the actual weights of each influencing factor can be dynamically adjusted based on the initial weights and the actual scheduling influencing factors.

[0027] Step S103: Perform a weighted calculation on the task path information, the task priority information, and the vehicle battery status information according to the target weight data to obtain the task cost information for each automated guided vehicle. To comprehensively consider the above objectives, a comprehensive objective weighting function was designed:

[0028] Among them, w1, w2, w3, and w4 are dynamic weight coefficients that are adjusted according to real-time task requirements and environmental changes. The initial value is defined as 1 (the initial value does not necessarily have to be strictly set to 1, and can be adjusted according to specific needs. Here, it is set to 1 for ease of understanding and calculation).

[0029] The path length data comes from the actual distance of the feasible route after the ant colony algorithm finds the path, in meters. If it is an inflection point, the cost is increased to 5 (because the car needs to stop, turn and start again when passing through an inflection point, which has an additional time cost compared to straight driving, so an additional cost value is required, the value of which needs to be greater than or equal to 2, to distinguish the cost from the normal distance).

[0030] The health battery value data comes from the battery value returned by the car in real time. The calculation condition is based on the actual battery value of the car divided by 100, so the value range is [0-1]. For example, if the battery value of the car is 90, the result is 0.9.

[0031] The path conflict value is initialized to 0, and is accumulated each time based on the number of conflicting nodes (one node + 1).

[0032] The task priority data is divided into three levels: 1 (normal), 2 (medium), and 3 (urgent). There are two ways to set the priority level: the first is to select the priority level when the task is issued, and the second is to readjust the priority level after the task is created (1. The system automatically calculates the priority level. If the current time has exceeded the deadline for task completion, the priority level will be upgraded to urgent; 2. Manual operation is supported to adjust the task priority level).

[0033] In this embodiment of the invention, the dynamic weight adjustment rule is as follows: The weights of the optimization objectives are dynamically adjusted based on real-time task requirements and environmental changes. Specific implementation methods include: Task Priority: If the urgency of a task is low, increase the weight of the task priority by w3.

[0034] Health battery level: If the AGV's battery level is high, the health battery level weight w2 is increased.

[0035] Path conflict: If there are many path conflicts, increase the weight of path conflict w4.

[0036] In addition, a weight update formula can be set:

[0037] Weight updates can be dynamically adjusted based on real-time feedback, for example: Where α is the learning rate and Δwi is the weight adjustment amount, which can be dynamically calculated according to real-time task requirements and environmental changes.

[0038] Learning rate α: The learning rate α controls the speed at which weights are adjusted. A learning rate that is too high may lead to excessively frequent weight adjustments, making the system unstable; a learning rate that is too low may lead to slow convergence and an unresponsive system.

[0039] Weight adjustment amount Δwi: The specific increment or decrement of the weight in each adjustment. The magnitude of the adjustment directly affects the speed and extent of the weight adjustment.

[0040] Numerical settings: Here, the learning rate α is set to a positive number of 0.5, and the weight adjustment amount Δwi is set to a positive number of 1. These are not strict settings and can be adjusted according to actual operation and needs.

[0041] In practical applications, the scheduling system starts up and initializes all relevant configurations and operational data, such as target weight coefficient configuration, road network and vehicle information, etc. The initial value of the target weight coefficient can be defined as 1, and the learning rate α and weight adjustment Δwi are defined as 0.5 and 1, respectively.

[0042] Step S104: Schedule the automated guided vehicle with the lowest task cost information to perform the target task.

[0043] In one embodiment of the present invention, step S102 may include: determining whether there is a route conflict based on the task path information; when a route conflict is determined to exist, determining the conflict type of the route conflict; adjusting the initial weight data of each automated guided vehicle according to the conflict type, the task priority information, and the vehicle battery status information, to obtain the target weight data of each automated guided vehicle.

[0044] In one embodiment of the present invention, when the conflict type is a relative line conflict or a cross line conflict, it is determined whether the task priority information of the target automated guided vehicle is higher than that of other automated guided vehicles; if the task priority information of the target automated guided vehicle is higher than that of other automated guided vehicles, the initial weight data corresponding to the task path information and the task priority information are adjusted to obtain the target weight data of each automated guided vehicle.

[0045] In another embodiment of the present invention, when the conflict type is a relative line conflict or a cross line conflict, it is determined whether the vehicle battery status information of the target automated guided vehicle is higher than that of other automated guided vehicles; if the vehicle battery status information of the target automated guided vehicle is higher than that of other automated guided vehicles, the initial weight data corresponding to the task path information and the vehicle battery status information are adjusted to obtain the target weight data of each automated guided vehicle.

[0046] In one embodiment of the present invention, when the conflict type is a same-direction route conflict, if the automated guided vehicle arrives at the conflict section and the waiting time exceeds a preset time, the initial weight data corresponding to the task path information is adjusted to obtain the target weight data for each automated guided vehicle.

[0047] In one embodiment of the present invention, step S102 may include: obtaining a preset weight adjustment rule; adjusting the initial weight data of each automated guided vehicle according to the conflict type, the task priority information and the vehicle battery status information, and the weight adjustment rule to obtain the target weight data of each automated guided vehicle.

[0048] like Figure 1b and 1c This is a schematic diagram illustrating the scheduling of a transport vehicle according to an embodiment of the present invention. Dynamic weighting and global optimization are achieved in this embodiment of the invention through path length, battery level, task priority, and path conflicts to obtain the minimum path cost, thereby executing the task.

[0049] In this embodiment of the invention, an information sharing mechanism can also be set up so that AGVs from different populations can periodically exchange information and update their respective optimization objectives and weights. Specific implementation methods include: Pheromones sharing: AGVs from different populations can share path pheromones, accelerating the discovery of the globally optimal path.

[0050] Task priority sharing: AGVs from different populations can share task priorities and path planning strategies.

[0051] Real-time information sharing between AGVs: Different groups of AGVs can share real-time information about the vehicles and the tasks they are performing.

[0052] The following combination Figure 1d Explain the dispatching process for transport vehicles: The scheduling system allocates tasks based on the task queue and the availability of AGVs. When there is an available delivery task, it checks if there are any available AGVs. If the task allocation conditions are met, the scheduling system uses the A* algorithm, which takes into account the inflection point cost, to obtain the initial shortest route for all AGVs based on their current positions and the starting positions of the tasks. By comparing the route distances, the system selects the AGV with the lowest task execution cost.

[0053] like Figure 1d As shown, car A is at point (2,4) and car B is at point (10,4). A delivery task starts at point (4,10). The shortest route is calculated using the improved A* algorithm, as shown in the figure. The red arrow represents the shortest route for car A to point (4,10), and the blue arrow represents the shortest route for car B to point (4,10). By comparison, it can be seen that car A needs to pass through 8 nodes + 1 turning point, while car B needs to pass through 12 nodes + 1 turning point. Therefore, assigning this task to car A is the optimal choice.

[0054] The information sharing and reporting of the vehicle includes basic real-time data (real-time location, battery status, execution status, unique identifier, etc.), task information (task number, task route, task priority, etc.), the target value of the current task being performed by the vehicle, and the weight information of each path.

[0055] Based on globally shared information, an independent thread detects in real time whether there are conflicts in the task routes of each car and compares the weight information. It then searches for a new optimal route based on the real-time updated weight values. When the system detects route conflicts between cars, different strategies are implemented for different conflict types (same-direction conflict, opposite / crossing conflict) to adjust the corresponding weight information. The corresponding weight values ​​are updated according to the dynamic weight adjustment rules, and the pheromone concentration information of the ant colony algorithm is used in real time to find new routes. The total target cost of each feasible route is calculated. Compared with the total target cost of the original route, if the total target cost of the original route is still the lowest (best), the original route is maintained; otherwise, a new optimal route is selected and the target cost is updated synchronously. After completing the task, the pheromone concentration of the route traversed is updated and the weight information is reset.

[0056] Among them, a conflict in the same direction refers to a conflict in which the conflicting road segment is in the same direction as the other car's travel direction. It can also be called a pursuit conflict.

[0057] Among them, head-on conflict / crossing conflict refers to a conflict when cars are traveling in opposite directions or crossing directions (e.g., car A is going north and car B is going east, and a certain section of the road has a cross-shaped conflict).

[0058] If the conflict type is a same-direction conflict, check whether the current car has arrived at the conflict section and waited for a long time. If so, dynamically increase the path conflict weight until a new optimal route is found. Otherwise, do not adjust the path length and the weight value of the path conflict, and continue driving on the original route to avoid unnecessary replanning.

[0059] If the conflict type is opposing / crossing conflict, the weights of health battery value, task priority, path conflict, and path length are dynamically adjusted respectively.

[0060] The weighting of the health battery value is adjusted as follows: if the current car's health battery value is higher than that of other cars, the weight of that road segment is increased in order to find a new optimal route.

[0061] The task priority weight adjustment involves comparing the task priority of the current car with the task priorities of other cars. If the current car has a lower priority, the weight value of the current car for that road segment is increased.

[0062] like Figure 1d As shown, the shaded area represents obstacles (such as walls) that prevent passage. Currently, car B is at point (10,1), and car A is at point (1,6). The battery levels of both cars are set to be the same (100%). Car A at point (1,6) is currently performing a cargo delivery task (priority: urgent), while car B is idle and available to perform a task. A new delivery task is then generated (marked with a blue star at point (2,6) as the starting point of the new task) with a medium priority. Car B meets the task allocation conditions and executes the new task. The shortest route is calculated using the improved A-star algorithm. The black route is the shortest route (passing through 13 nodes + 1 turning point), and the initial total target cost is obtained as F = w1 * path length + w2 * battery level + w3 * task priority + w4 * path conflict. F = 1 * (13 + 5) + 1 * 1 + 1 * 2 + 1 * 0 = 21.

[0063] like Figure 1d As shown, the shaded area represents obstacles (such as walls) that prevent passage. Vehicle A completes its loading task at point (7,6) and needs to proceed to point (7,6) to unload. The red route represents vehicle A's travel route. Vehicle B has already reached the nearest point (10,4). Based on global shared information and real-time conflict thread detection, it is determined that the routes of vehicles A and B conflict. The conflicting route is point (2,6) - point (3,6) - point (4,6) - point (5,6) - point (6,6) - point (7,6), and the travel directions are opposite. Therefore, it is determined to be a head-on conflict. Figure 2 Judgment process: Task priority weight adjustment: Car A performs an emergency-level task, and Car B performs a medium-level task. Therefore, it is necessary to increase the task priority weight of Car B on this route. According to the dynamic weight adjustment formula, learning rate α and weight adjustment amount, the new task priority weight value calculated this time is w3=1+(0.5*1)=1.5.

[0064] Health battery value weighting adjustment: Since the health battery values ​​of the two vehicles are the same, there is no need to adjust the health battery value weight, which remains 1.

[0065] Path length weight and path conflict weight adjustment: Car A performs an emergency mission, and Car B performs a medium-level mission. Therefore, it is necessary to increase the path length weight and path conflict weight of Car B's route. According to the dynamic adjustment weight formula, learning rate α and weight adjustment amount, the new path length weight value calculated this time is w1=1+(0.5*1)=1.5, and the new path conflict weight value is w4=1+(0.5*1)=1.5.

[0066] The total target cost of the new F route can be calculated as F = 1.5*(13+5) + 1*1 + 1.5*2 + 1.5*6 = 40.

[0067] Simultaneously, based on segment weights and pheromone concentration, other shortest routes are found, and the total objective cost of feasible routes is compared with the new total objective cost of the original routes. Figure 1d The blue line segment shown represents the new route. Since the destination still conflicts with car A and it is a cross-over conflict, the weight coefficient adjustment for this route is the same as that for the original route. w1 = 1 + (0.5 * 1) = 1.5 w2=1 w3 = 1 + (0.5 * 1) = 1.5 w4 = 1 + (0.5 * 1) = 1.5 The blue line segment passes through 12 nodes and 2 turning points, with 1 conflict node.

[0068] The total target cost of the new blue route F is calculated to be F = 1.5*(12+10)+1*1+1.5*2+1.5*1=38.

[0069] In summary, the total objective value of the new blue route detected by the global scheduling is lower than that of the original route, indicating fewer conflict sections and a correspondingly shorter task time. Therefore, a new task route (blue route) should be selected for car B, which is a better option.

[0070] In this embodiment of the invention, task path information, task priority information, vehicle battery status information, and initial weight data of multiple automated guided vehicles (AGVs) for executing a target task can be obtained. The initial weight data of each AGV is adjusted based on the task path information, task priority information, and vehicle battery status information to obtain target weight data for each AGV. The task path information, task priority information, and vehicle battery status information are weighted and calculated according to the target weight data to obtain task cost information for each AGV. The AGV with the lowest task cost information is scheduled to execute the target task. This achieves global optimization from multiple factors including task path information, task priority information, and vehicle battery status information, dynamically adjusting weights and improving the dynamic adaptability of scheduling.

[0071] Reference Figure 2 The diagram illustrates a flowchart of another method for dynamic scheduling of automated guided vehicles (AGVs) according to an embodiment of the present invention, which may specifically include the following steps: Step S201: Obtain task path information, task priority information, vehicle battery status information, and initial weight data of the automated guided vehicles (AGVs) used to perform the target task. Step S202: Adjust the initial weight data of each automated guided vehicle according to the task path information, the task priority information and the vehicle battery status information to obtain the target weight data of each automated guided vehicle. Step S203: Perform a weighted calculation on the task path information, the task priority information, and the vehicle battery status information according to the target weight data to obtain the task cost information for each automated guided vehicle. Step S204: Schedule the automated guided vehicle with the lowest task cost information to perform the target task.

[0072] Step S205: Obtain the pheromone concentration at the starting point of each automated guided vehicle path; Step S206: Determine the shortest route of the automated guided vehicle based on the task path information and the pheromone concentration.

[0073] After the task is completed, the route weight information can be reset and the pheromone concentration of the road segment can be updated. After each car reaches the task endpoint and completes the task, the total target cost F of the corresponding car and the relevant weight coefficients w1, w2, w3, and w4 are reset to their initial values. At the same time, the pheromone concentration values ​​of all task route nodes that have been visited by each car are updated. By continuously updating and iterating the pheromone concentration, the ant colony algorithm can select the optimal path during route planning by utilizing the guiding effect of the path pheromone concentration.

[0074] Through the above steps, compared with the traditional ant colony algorithm and the improved A* algorithm, the method of this invention can accelerate the discovery of the global optimal path by combining the fast path search of the A* algorithm and the global optimization capability of the ant colony algorithm through real-time information exchange between AGVs, and by adding the multi-weight concept of the ant colony algorithm, thereby improving the collaborative optimization capability among multiple AGV individuals, reducing path conflicts and task waiting time, and improving global scheduling and delivery efficiency.

[0075] In one embodiment of the present invention, determining the shortest route of the automated guided vehicle based on the task path information and the pheromone concentration includes: determining the distance information between each node and the set of neighboring nodes of the current node based on the task path information; determining the probability of the next node based on the pheromone concentration, the distance information and the set of neighboring nodes; and determining the shortest route of the automated guided vehicle according to the probability of the next node.

[0076] In this embodiment of the invention, the focus is on improving the A* algorithm by combining it with an ant colony algorithm that increases multi-objective weights, and optimizing global scheduling through information sharing. The probability selection rule can be set as follows: When ants choose their next node, they do so based on the pheromone concentration between the current node and the next node, as well as a heuristic factor. The specific probability selection rules are as follows:

[0077] in: Let represent the probability that the k-th ant moves from node i to node j.

[0078] It represents the pheromone concentration between node i and node j.

[0079] It is a heuristic factor, usually the reciprocal of the distance from node i to node j.

[0080] It is the set of all neighboring nodes that can be reached from node i.

[0081] α and β are the weight parameters of pheromone concentration and heuristic factor, respectively, and are usually in the range of [0,1]. They can be adjusted according to actual needs without strict restrictions.

[0082] In another embodiment of the present invention, after determining the pheromone concentration of the current node, the pheromone concentration of the next node can be updated according to the pheromone concentration of the current node.

[0083] When an ant traverses path i→j, the pheromone concentration along that path increases, while also considering pheromone evaporation. The local pheromone update formula is as follows:

[0084] in: It is the sum of pheromone concentrations between node i and node j.

[0085] It is the pheromone evaporation coefficient. ∈(0,1). It determines the evaporation rate of the pheromone and is usually set to a small value to avoid premature convergence of the search space.

[0086] This is the pheromone increment from i to j, updated after all ants have completed their path selection. For each ant k, its pheromone gain on the path from i to j can be expressed as... Q is a constant representing the total amount of pheromones. It is the path length chosen by ant k.

[0087] In summary, the ant colony algorithm, through continuous and iterative updates of pheromones, utilizes the guiding effect of path pheromone concentration to select the optimal path during route planning.

[0088] In ant colony optimization, pheromone concentration is the trace left by ants after they walk on a path. The higher the concentration, the more ants have walked on the path or the better it is considered. The pheromone concentration is dynamically updated as the ants choose their paths. Through the accumulation and volatilization mechanism of pheromones, the higher the value, the higher the probability of node selection, indicating that the path is more likely to be chosen by the ants.

[0089] Application of pheromone concentration: As explained in the probabilistic selection rule, when the ant colony algorithm selects nodes, it calculates the probability of going to the next node based on parameters such as pheromone concentration and heuristic factor. The higher the pheromone concentration, the higher the probability of the node being selected.

[0090] However, the route obtained by the traditional ant colony algorithm based solely on the node probability selection rule is not optimal. Since ants tend to choose paths that have been traversed by many ants and have a high pheromone concentration, if applied to AGV scenarios, when multiple AGVs are performing tasks simultaneously and choosing the same route, the probability of conflict will increase, leading to increased delivery time and reduced efficiency. Therefore, in this invention, a multi-objective weight optimization mechanism is introduced to solve problems such as conflict probability, thereby guiding ants to gradually obtain the optimal path.

[0091] In this embodiment of the invention, global optimization is achieved from multiple factors such as task path information, task priority information, and vehicle battery status information, and the weights are dynamically adjusted to improve the dynamic adaptability of transport vehicle scheduling.

[0092] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0093] Reference Figure 3 The diagram shows a structural schematic of an automated guided vehicle dynamic scheduling device according to an embodiment of the present invention, which may specifically include the following modules: The data acquisition module 301 is used to acquire task path information, task priority information, vehicle battery status information, and initial weight data of the automated guided vehicles for performing target tasks. The weight adjustment module 302 is used to adjust the initial weight data of each automated guided vehicle according to the task path information, the task priority information and the vehicle battery status information, so as to obtain the target weight data of each automated guided vehicle. The cost calculation module 303 is used to perform weighted calculations on the task path information, the task priority information and the vehicle battery status information according to the target weight data to obtain the task cost information of each automated guided vehicle. The scheduling module 304 is used to schedule the automated guided vehicle with the lowest task cost information to perform the target task.

[0094] In one embodiment of the present invention, the weight adjustment module 302 may include: The route conflict determination submodule is used to determine whether there is a route conflict based on the task path information; The conflict type determination submodule is used to determine the conflict type of the route conflict when it is determined that a route conflict exists; The weight data determination submodule is used to adjust the initial weight data of each automated guided vehicle according to the conflict type, the task priority information, and the vehicle battery status information, so as to obtain the target weight data of each automated guided vehicle.

[0095] In one embodiment of the present invention, the weight data determination submodule may include: The priority determination unit is used to determine whether the task priority information of the target automated guided vehicle is higher than that of other automated guided vehicles when the conflict type is a relative line conflict or a cross line conflict. The first weight adjustment unit is used to adjust the initial weight data corresponding to the task path information and the task priority information if the task priority information of the target automated guided vehicle is higher than that of other automated guided vehicles, so as to obtain the target weight data of each automated guided vehicle.

[0096] In one embodiment of the present invention, the weight data determination submodule may include: The battery status determination unit is used to determine whether the battery status information of the target automated guided vehicle is higher than that of other automated guided vehicles when the conflict type is a relative line conflict or a cross line conflict. The second weight adjustment unit is used to adjust the initial weight data corresponding to the task path information and the vehicle battery status information if the vehicle battery status information of the target automated guided vehicle is higher than that of other automated guided vehicles, so as to obtain the target weight data of each automated guided vehicle.

[0097] In one embodiment of the present invention, the weight data determination submodule may include: The third weight adjustment unit is used to adjust the initial weight data corresponding to the task path information when the conflict type is a same-direction route conflict, if the automated guided vehicle arrives at the conflict section and the waiting time exceeds a preset time, so as to obtain the target weight data of each automated guided vehicle.

[0098] In one embodiment of the present invention, the weight adjustment module 302 may include: The weight adjustment rule acquisition submodule is used to acquire preset weight adjustment rules; The adjustment submodule is used to adjust the initial weight data of each automated guided vehicle according to the conflict type, the task priority information, and the vehicle battery status information, and according to the weight adjustment rules, so as to obtain the target weight data of each automated guided vehicle.

[0099] In one embodiment of the present invention, the device further includes: The pheromone concentration acquisition module is used to acquire the pheromone concentration at the starting point of each automated guided vehicle's path; The shortest route determination module is used to determine the shortest route of the automated guided vehicle based on the task path information and the pheromone concentration.

[0100] In one embodiment of the present invention, the shortest route determination module may include: The distance and node set determination submodule is used to determine the distance information between each node and the set of neighboring nodes of the current node based on the task path information. The probability determination submodule is used to determine the probability of the next node based on the pheromone concentration, the distance information, and the set of neighboring nodes; The shortest route determination submodule is used to determine the shortest route of the automated guided vehicle based on the probability of the next node.

[0101] In one embodiment of the present invention, the device further includes: The pheromone concentration update submodule is used to update the pheromone concentration of the next node according to the pheromone concentration of the current node.

[0102] In this embodiment of the invention, task path information, task priority information, vehicle battery status information, and initial weight data of multiple automated guided vehicles (AGVs) used to execute a target task are obtained. The initial weight data of each AGV is adjusted based on the task path information, task priority information, and vehicle battery status information to obtain target weight data for each AGV. The task path information, task priority information, and vehicle battery status information are weighted and calculated according to the target weight data to obtain task cost information for each AGV. The AGV with the lowest task cost information is scheduled to execute the target task. This achieves global optimization from multiple factors including task path information, task priority information, and vehicle battery status information, dynamically adjusting weights and improving the dynamic adaptability of vehicle scheduling.

[0103] An embodiment of the present invention also provides an electronic device, which may include a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the above-described dynamic scheduling method for automated guided vehicles.

[0104] An embodiment of the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-described method for dynamic scheduling of automated guided vehicles.

[0105] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0106] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0107] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0108] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in one or more blocks of the flowchart illustrations and / or one or more blocks of the block diagrams.

[0109] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0110] These computer program instructions may also be loaded onto a computer or other programmable data processing terminal equipment to cause a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable terminal equipment, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0111] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0112] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0113] The above provides a detailed description of the automated guided vehicle (AGV) dynamic scheduling method and device, electronic equipment, and storage medium. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for dynamic scheduling of automated guided vehicles, characterized in that, The method comprises: obtaining task path information, task priority information, vehicle power state information of a plurality of automated guided vehicles for performing a target task, and initial weight data of the automated guided vehicles; adjusting the initial weight data of each automated guided vehicle according to the task path information, the task priority information, and the vehicle power state information to obtain target weight data of each automated guided vehicle; performing weighted calculation on the task path information, the task priority information, and the vehicle power state information according to the target weight data to obtain task cost information of each automated guided vehicle; scheduling an automated guided vehicle with the lowest task cost information to perform the target task.

2. The method of claim 1, wherein, The method comprises: determining whether there is a route conflict according to the task path information; when it is determined that there is a route conflict, determining a conflict type of the route conflict; adjusting the initial weight data of each automated guided vehicle according to the conflict type, the task priority information, and the vehicle power state information to obtain target weight data of each automated guided vehicle.

3. The method of claim 2, wherein, The method comprises: when the conflict type is a relative route conflict or a crossing route conflict, determining whether the task priority information of a target automated guided vehicle is higher than that of other automated guided vehicles; if the task priority information of the target automated guided vehicle is higher than that of other automated guided vehicles, adjusting the initial weight data corresponding to the task path information and the task priority information to obtain target weight data of each automated guided vehicle.

4. The method of claim 2, wherein, The method comprises: when the conflict type is a relative route conflict or a crossing route conflict, determining whether the vehicle power state information of a target automated guided vehicle is higher than that of other automated guided vehicles; if the vehicle power state information of the target automated guided vehicle is higher than that of other automated guided vehicles, adjusting the initial weight data corresponding to the task path information and the vehicle power state information to obtain target weight data of each automated guided vehicle.

5. The method of claim 2, wherein, The method comprises: When the conflict type is a same-direction line conflict, if the automated guided vehicle reaches the conflict road section and the waiting time exceeds a preset time, the initial weight data corresponding to the task path information is adjusted to obtain target weight data of each automated guided vehicle.

6. The method of claim 2, wherein, The adjusting of the initial weight data of each automated guided vehicle according to the conflict type, the task priority information and the vehicle power state information to obtain the target weight data of each automated guided vehicle comprises: obtaining a preset weight adjustment rule; adjusting the initial weight data of each automated guided vehicle according to the conflict type, the task priority information and the vehicle power state information according to the weight adjustment rule to obtain the target weight data of each automated guided vehicle.

7. The method of claim 1, wherein, Further comprising: obtaining the pheromone concentration of the path starting point of each automated guided vehicle; determining the shortest route of the automated guided vehicle according to the task path information and the pheromone concentration.

8. The method of claim 7, wherein, The determining of the shortest route of the automated guided vehicle according to the task path information and the pheromone concentration comprises: determining the distance information between each node and the adjacent node set of the current node according to the task path information; determining the probability of the next node based on the pheromone concentration, the distance information and the adjacent node set; determining the shortest route of the automated guided vehicle according to the probability of the next node.

9. The method of claim 7, wherein, Further comprising: updating the pheromone concentration of the next node according to the pheromone concentration of the current node.

10. An automated guided vehicle dynamic dispatching apparatus, characterized by, The device comprises: a data acquisition module configured to acquire task path information, task priority information, vehicle power state information of a plurality of automated guided vehicles for executing target tasks and initial weight data of the automated guided vehicles; a weight adjustment module configured to adjust the initial weight data of each automated guided vehicle according to the task path information, the task priority information and the vehicle power state information to obtain target weight data of each automated guided vehicle; a cost calculation module configured to perform weighted calculation on the task path information, the task priority information and the vehicle power state information according to the target weight data to obtain task cost information of each automated guided vehicle; a scheduling module configured to schedule the automated guided vehicle with the lowest task cost information to execute the target task.

11. An electronic device, comprising: The computer program is stored on the computer readable storage medium and is executed by the processor to implement the automated guided vehicle dynamic scheduling method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, The computer program is stored on the computer readable storage medium and is executed by the processor to implement the automated guided vehicle dynamic scheduling method according to any one of claims 1 to 9.

Images