A vehicle-machine cooperative emergency material delivery planning method, system and device

Abstract

The present application relates to a kind of vehicle machine coordination emergency material delivery planning method, system and equipment.The method includes: according to the demand task of emergency material, the total transport capacity of vehicle and unmanned aerial vehicle formation is constructed resource delivery planning model.Through resource delivery planning model, delivery completion time is obtained, according to delivery completion time and preset material recycling mechanism, the total distribution time of unmanned aerial vehicle formation executing demand task is optimized, and delivery planning scheme is generated.This method breaks through the static limitation of traditional single planning, can make quick, effective dynamic response to the changing demand, significantly improves the efficiency and accuracy of emergency material delivery.

Description

Technical Field

[0001] This invention relates to the field of cross-disciplinary technology of logistics scheduling and emergency management, and in particular to a vehicle-machine collaborative emergency material delivery planning method, system and equipment. Background Technology

[0002] With the continuous advancement of technologies such as wireless communication, automatic control, and artificial intelligence, drones are widely used in various civilian and military delivery scenarios, including on-demand delivery, emergency delivery, and delivery to remote areas, due to their lack of traffic and terrain limitations and lower operating costs. However, the current development of drone logistics delivery still faces many obstacles. For example, the flight time of most mainstream logistics drones is less than half an hour, limiting their delivery range significantly. In response, a new logistics model has emerged in recent years: drone-ground vehicle collaborative delivery, or vehicle-drone collaborative delivery for short. In this model, ground vehicles carry drones to collaboratively complete logistics delivery services. The drone is launched from the ground vehicle or warehouse, provides service to a specific customer, and then returns to the vehicle, while the ground vehicle is responsible for serving the remaining customers. Existing research has made some progress, but most of it is based on deterministic information assumptions and still has significant shortcomings in emergency material delivery applications, as detailed below:

[0003] Information sensitivity deficiency: Existing drone-based emergency supply delivery technology relies heavily on accurate demand data, but in the critical 72 hours after a disaster, demand information can often only be estimated within a range. For example, the demand for medicines in a disaster-stricken area may only be determined to be within the range of "500-800 boxes". In this situation, traditional route planning models cannot function effectively, making it difficult to formulate a reasonable delivery plan.

[0004] The rigidity of resource allocation is a flaw: existing single-phase planning schemes typically allocate resources to various disaster-stricken areas all at once. However, if actual needs deviate significantly from initial forecasts, some areas will have large amounts of idle resources, while other areas will face severe shortages, failing to achieve efficient resource utilization.

[0005] Lack of coordination mechanisms: Currently, most drone systems operate independently in different regions, lacking cross-regional material allocation channels. This results in significant duplication of transport capacity during material delivery. Post-disaster relief data analysis shows that traditional drone-based emergency material delivery methods suffer from a 35% waste rate of transport capacity due to redundant deliveries, causing substantial resource waste. Summary of the Invention

[0006] Therefore, it is necessary to provide a vehicle-machine collaborative emergency material delivery planning method, system, and equipment that can improve the efficiency and collaborative energy efficiency of material delivery in response to the above-mentioned technical problems.

[0007] A vehicle-machine collaborative emergency supplies delivery planning method, the method comprising:

[0008] A resource delivery planning model is constructed based on the emergency supplies requirements and the total transport capacity of vehicle and drone fleets.

[0009] The delivery completion time is obtained through a resource delivery planning model. Based on the delivery completion time and the preset material recycling mechanism, the total delivery time for the drone formation to perform the required tasks is optimized, and a delivery planning scheme is generated.

[0010] A vehicle-machine collaborative emergency supplies delivery planning system, the system comprising:

[0011] The pre-planning module is used to build a resource delivery planning model based on the emergency supplies needs and the total transport capacity of vehicle and drone fleets.

[0012] The dynamic delivery planning module is used to obtain the delivery completion time through the resource delivery planning model. Based on the delivery completion time and the preset material recycling mechanism, it uses an improved heuristic algorithm to optimize the total delivery time of the drone formation to perform the required tasks and generate a delivery planning scheme.

[0013] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program performing the following steps:

[0014] A resource delivery planning model is constructed based on the emergency supplies requirements and the total transport capacity of vehicle and drone fleets.

[0015] The delivery completion time is obtained through a resource delivery planning model. Based on the delivery completion time and the preset material recycling mechanism, the total delivery time for the drone formation to perform the required tasks is optimized, and a delivery planning scheme is generated.

[0016] The aforementioned vehicle-machine collaborative emergency material delivery planning method, system, and equipment, at the resource coordination level, focuses on constructing a resource delivery planning model based on emergency material demand tasks and the total transport capacity of vehicle and drone fleets. This model breaks away from the traditional extensive "allocation on demand" model of delivery, achieving precise matching of resources and needs by quantitatively analyzing the urgency, material type, and quantity of needs in each region, combined with the transport capacity characteristics of vehicle-machine collaboration (such as the large capacity and long-distance advantage of vehicles and the flexible short-distance advantage of drones). The model avoids "blind delivery" caused by information asymmetry—it prevents material idleness due to overemphasis on a certain region, and it can fill demand gaps through reasonable allocation of transport capacity, ensuring that resources flow to areas that are truly in urgent need from the planning source, laying the foundation for efficient utilization. At the dynamic optimization level, the model calculates the delivery completion time and optimizes the total delivery time by combining it with a preset material recycling mechanism. Material demand in emergency scenarios is dynamic and changing; some areas may have surplus materials after consumption, while new shortage areas may emerge. The recycling mechanism allows already delivered idle materials to re-enter the dispatch system, enabling rapid transfer to shortage areas via drone convoys, reducing the cost and time of repeated warehouse relocation. Simultaneously, using delivery completion time as an optimization anchor, the rhythm of vehicle-drone collaboration can be dynamically adjusted. For example, vehicles can focus on core trunk line transportation, while drones are dedicated to short-distance connections and cyclical allocation, forming a highly efficient "trunk line + branch line" collaborative network. This not only improves the efficiency of a single delivery but also maximizes resource utilization through material recycling, ultimately achieving the goal of "dual improvement in delivery efficiency and collaborative efficiency." Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating a vehicle-machine collaborative emergency supplies delivery planning method in one embodiment;

[0018] Figure 2 A flowchart of a vehicle-machine collaborative emergency supplies delivery planning algorithm in one embodiment;

[0019] Figure 3 This is a structural block diagram of a vehicle-machine collaborative emergency material delivery planning system in one embodiment;

[0020] Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0022] In one embodiment, such as Figure 1As shown, a vehicle-machine collaborative emergency supplies delivery planning method is provided, including the following steps:

[0023] Step 102: Construct a resource delivery planning model based on the emergency supplies needs and the total transport capacity of the vehicle and drone fleet.

[0024] For each requirement By analyzing satellite imagery and integrating on-site reports, the material demand ranges for each disaster-stricken area are generated, and the material demand is defined as the range number. ,in Calculated based on disaster level, population size, and infrastructure damage rate. fuzzy coefficient The data is obtained through training with historical disaster data (typical value 0.3-0.5), providing accurate basic data for subsequent planning.

[0025] Specifically, the total carrying capacity of the vehicle and drone fleet is set at... C Establish the following resource delivery planning model:

[0026] ;

[0027] in, It is the delivery completion time of the vehicle and drone formation k.

[0028] The first-stage constraints are as follows:

[0029] 1) Total allocation requirements: Ensure that the total allocation of supplies meets the overall rescue needs. .

[0030] 2) The drone must be launched or recovered from a truck:

[0031] ;

[0032] This constraint states that if a drone is launched or recovered at a certain site, its truck must visit the same site. This indicates that the vehicles in vehicle formation k did not carry drones as they traversed the path arc. The value is 1 if it is true, and 0 otherwise. This indicates that the drone in vehicle formation k traverses the path arc alone. It is 1 if it is true, otherwise it is 0. A collection of nodes for drone launches or recoveries, including distribution centers; A group of customers served by vehicles. A collection of customers served by drones.

[0033] 3) Consider the range constraints of vehicles and drones to avoid supplies failing to reach their destination due to insufficient range:

[0034] ;

[0035] ;

[0036] It is a vehicle Maximum driving distance It is a drone Maximum range Whether it passes through the demand point To the point of demand The value is 1 if the path arc is passed through it, and 0 otherwise. To start from the demand point To the point of demand The flight distance of the drone To start from the demand point To the point of demand The distance the vehicle traveled.

[0037] This model achieves a balance in workload for different vehicle and drone formations while ensuring that basic needs are covered, thereby improving the overall efficiency of resource utilization.

[0038] Step 104: Obtain the delivery completion time through the resource delivery planning model, and optimize the total delivery time of the vehicle platoon to perform the required tasks based on the delivery completion time and the preset material recycling mechanism.

[0039] Specifically, based on the execution dynamics of the initial delivery plan, the closed-loop transfer mechanism achieves efficient circulation by responding to changes in supply and demand of materials in real time. When the delivery volume of the vehicle platoon cannot meet the needs of the disaster-stricken area, a delivery failure point is identified, and the transfer mechanism is activated. Unlike a single transfer, the closed-loop transfer in this study can circulate among multiple task nodes, realizing "task-execution-feedback-re-optimization".

[0040] Specifically as follows:

[0041] 1) When a failure point occurs, the failure point scheduling mechanism is triggered to perform rescheduling before the failure point. Based on the feedback of the failure point location and the information of surrounding served nodes, rescheduling is performed with the preceding successful served node of the failure point as the hub. At this time, the empty vehicle group can go to the remaining material placement point to pick up the goods and continue delivery if the truck and drone have sufficient power. If the power is insufficient to support subsequent delivery, the truck carries the drone back to the central warehouse. At the same time, the central warehouse is notified to schedule a new vehicle group or activate the remaining material sharing protocol of other idle vehicle groups to ensure that the replenishment of the failure point is completed.

[0042] 2) When vehicle train k has delivered supplies to all pre-planned disaster-stricken areas and still has remaining inventory, the surplus sharing protocol is triggered. Using real-time feedback on the location and demand data of each disaster-stricken area, priority is given to searching for nearby disaster-stricken areas with demand gaps, and only then is the remaining supplies considered for return to the central warehouse. Therefore, vehicle trains at disaster-stricken areas... A After unloading, if the trucks and drones have sufficient power, they can immediately load the remaining supplies and fly to disaster-stricken areas experiencing shortages. B Replenishment will be carried out; if the power is insufficient, the remaining supplies will be placed at the disaster site and reported back to the central warehouse, and then the drones will be returned to the central warehouse by truck.

[0043] 3) To address situations where demand is excessive at a single disaster-stricken location or the capacity of a single trainset is insufficient, a demand segmentation rule is established. By using real-time feedback on the total demand at the disaster-stricken location and the capacity data of each trainset, the demand at that location is broken down into multiple sub-tasks. Multiple trainsets are then dispatched from different hub nodes to collaboratively complete the service in a parallel closed-loop transfer manner. This ensures efficient demand coverage while further improving the fault tolerance and flexibility of the overall transfer system.

[0044] Furthermore, with the objective of minimizing the total delivery time, the following model is constructed:

[0045] The constraints for the second phase are as follows:

[0046] This ensures that every remaining task can be executed;

[0047] To constrain the payload of drones and ensure that the payload of drones does not exceed their carrying capacity;

[0048] This indicates a truck load constraint, ensuring that the truck's load does not exceed its carrying capacity;

[0049] This ensures that trucks and drones only depart after meeting unloading and loading time requirements.

[0050] This model effectively avoids situations where vehicle formations return empty, significantly increases the average daily delivery frequency per unit, and improves the efficiency of material delivery.

[0051] To solve the above problem, a hybrid optimization algorithm is proposed, which uses a population-based evolutionary algorithm and a local search algorithm to solve the model and generate a delivery planning scheme.

[0052] The algorithm consists of two phases, such as Figure 2 As shown:

[0053] Phase 1 involves using an improved NSGAII algorithm and an enhanced multi-objective optimization method to solve the robust allocation model, thus achieving resource pre-allocation in the first phase. Details are as follows:

[0054] (1) Using a dual-layer coding method of trucks and drones, considering constraints such as the load capacity, range, and time window of the disaster site of the vehicle group, an initial solution is generated.

[0055] (2) Design an evaluation function based on the objective function of the model.

[0056] (3) Perform selection, crossover, and mutation operations to generate new solutions as offspring, and return to step (2) for evaluation.

[0057] (4) An elite solution strategy is adopted to select non-dominated solutions and put them into the external archive, and a local search is performed on the solutions in the external archive.

[0058] (5) If the maximum number of iterations has been reached or the optimal solution has not improved for several consecutive generations, stop and output the optimal delivery scheme in the final non-dominated solution set; otherwise, continue iterating.

[0059] Phase 2 introduces a material transfer mechanism to achieve dynamic coordination in the second phase.

[0060] (1) Check whether the failure point or the margin sharing condition is triggered. When the condition is triggered, start the transfer mechanism, call the failure point response operator, etc. to generate the adjustment plan, and update the path and task allocation.

[0061] (2) Re-evaluate the revised plan.

[0062] (3) Repeat the above process until the needs of all disaster-stricken points are met, and output the final dynamically optimized delivery plan.

[0063] In the aforementioned vehicle-machine collaborative emergency material delivery planning method, at the resource coordination level, the core of the solution lies in constructing a resource delivery planning model based on the emergency material demand tasks and the total transport capacity of vehicle and drone fleets. This model breaks away from the traditional extensive "allocation on demand" model of delivery, achieving precise matching of resources and needs by quantitatively analyzing the urgency, material type, and quantity of needs in each region, combined with the transport capacity characteristics of vehicle-machine collaboration (such as the large capacity and long-distance advantage of vehicles and the flexible short-distance advantage of drones). The model avoids "blind delivery" caused by information asymmetry—it avoids material idleness due to overemphasis on a certain region, and it can also fill demand gaps through reasonable allocation of transport capacity, ensuring that resources flow to areas that are truly in urgent need from the planning source, laying the foundation for efficient utilization. At the dynamic optimization level, the model calculates the delivery completion time and optimizes the total delivery time by combining it with a preset material recycling mechanism. Material demand in emergency scenarios is dynamic and changing; some areas may have a surplus of materials after consumption, while new shortage areas may emerge. The recycling mechanism allows already delivered idle materials to re-enter the dispatch system, enabling rapid transfer to shortage areas via drone convoys, reducing the cost and time of repeated warehouse relocation. Simultaneously, using delivery completion time as an optimization anchor, the rhythm of vehicle-drone collaboration can be dynamically adjusted. For example, vehicles can focus on core trunk line transportation, while drones are dedicated to short-distance connections and cyclical allocation, forming a highly efficient "trunk line + branch line" collaborative network. This not only improves the efficiency of a single delivery but also maximizes resource utilization through material recycling, ultimately achieving the goal of "dual improvement in delivery efficiency and collaborative efficiency."

[0064] In one embodiment, a fuzzy demand setting task demand representation is adopted based on the demand points and material demand scope in the emergency material demand task. A resource delivery planning model is constructed based on the constraints of the task demand representation and the total transport capacity of the vehicle and drone formation.

[0065] ;

[0066] in, For preference coefficients, To minimize the demand for supplies, The total carrying capacity of the vehicle and drone convoy. For vehicle and drone swarm Delivery completion time, Assign numbers to the drones in the drone formation that will perform the required tasks. For demand points;

[0067] The constraints are as follows:

[0068] ;

[0069] ;

[0070] ;

[0071] ;

[0072] in, For a collection of customers who use drones for services, For a group of customers who are served by vehicles, A set of nodes for launching or recovering drones. To perform the required tasks in the vehicle formation Does the drone travel through the path arc alone? The judgment result, Does each vehicle in a platoon, performing the required task, traverse the path arc individually? The judgment result, The total number of drones in the drone formation. For vehicle platooning Did the vehicle carrying the drone pass through the path arc? , To start from the demand point To the point of demand The flight distance of the drone For drones Maximum range To start from the demand point To the point of demand The distance the vehicle traveled, For vehicles Maximum driving distance Indicates drone, It refers to a truck.

[0073] In one embodiment, the preset material recycling mechanism includes an operation mechanism and a recycling mechanism. The operation mechanism is as follows: when the train to which the vehicle belongs has delivered all the disaster-stricken points corresponding to the demand task and there is still inventory remaining, the inventory sharing protocol is triggered and the recycling mechanism is started; when the train to which the vehicle belongs cannot meet the demand task corresponding to any of the disaster-stricken points, the current disaster-stricken point is a failure point, and the failure point scheduling mechanism is triggered to start the failure point rescheduling.

[0074] In one embodiment, the loop mechanism is as follows: a closed-loop transfer path is set according to the required tasks and priority rules. On the closed-loop transfer path, after the drone unloads at the first disaster-stricken point, it loads the remaining supplies and delivers them to the second disaster-stricken point. The failure point scheduling mechanism is as follows: multiple vehicles and drones are grouped together to divide the required tasks, and services are provided to the disaster-stricken points of the failure points at the same time.

[0075] In one embodiment, the priority rule is: the delivery priority of the disaster-stricken area near the location of the vehicle and drone group is higher than the recovery priority of the central warehouse.

[0076] In one embodiment, the delivery completion time is obtained through a resource delivery planning model:

[0077] ;

[0078] in, For the first The delivery completion time of each vehicle platoon. Based on the delivery completion time and a pre-set material recycling mechanism, the total delivery time for the drone platoon to perform the required task is optimized.

[0079] ;

[0080] ;

[0081] ;

[0082] ;

[0083] in, For a set of client nodes, and These are the maximum capacities for drones and trucks, respectively. For vehicle platooning at nodes Departure time For drones at nodes Arrival time, For trucks at the node Arrival time, For nodes Service hours, For nodes The time window start time is determined. Based on the delivery completion time and the preset material recycling mechanism, the total delivery time for the drone formation to perform the required task is optimized, and a delivery planning scheme is generated.

[0084] In one embodiment, a flood relief scenario is used as an example for illustration:

[0085] 1. Initial configuration phase:

[0086] 1) The demand ranges for the 10 disaster-stricken areas are: [300, 450], [200, 320]... (unit: first aid kits);

[0087] 2) 20 vehicle groups will be deployed, with load capacities of 50kg and 100kg respectively;

[0088] 3) By solving the robust configuration model, the configuration amount of each region is obtained, such as 380 packages for customers in disaster-stricken area Z1 and 290 packages for disaster-stricken area Z2.

[0089] 2. Dynamic Adjustment Phase:

[0090] 1) Actual demand feedback shows that the Z1 disaster site only needs 300 packs, leaving a surplus of 80 packs; the Z5 disaster site needs 400 packs, leaving a shortage of 110 packs.

[0091] 2) Based on the material recycling mechanism and collaborative path optimization model, the system generates a transfer plan: vehicle group #07 flies from disaster point Z1 to disaster point Z5 to transport 80 packages (the remaining 30 packages will be supplemented by the warehouse); vehicle group #12 carries 30 packages to disaster point Z5 after performing the pre-planned task in Z3.

[0092] It should be understood that, although Figures 1-2 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figures 1-2 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0093] In one embodiment, such as Figure 3 As shown, a vehicle-machine collaborative emergency material delivery planning system is provided, including: a pre-planning module 302 and a dynamic delivery planning module 304, wherein:

[0094] The pre-planning module 302 is used to construct a resource delivery planning model based on the emergency supplies demand and the total transport capacity of vehicle and drone formations.

[0095] The dynamic delivery planning module 304 is used to obtain the delivery completion time through the resource delivery planning model, optimize the total delivery time of the drone formation to perform the required tasks based on the delivery completion time and the preset material recycling mechanism, and generate a delivery planning scheme.

[0096] For specific limitations regarding a vehicle-to-machine (V2M) collaborative emergency supplies delivery planning system, please refer to the limitations of a V2M collaborative emergency supplies delivery planning method described above, which will not be repeated here. Each module in the aforementioned V2M collaborative emergency supplies delivery planning system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0097] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, network interface, display screen, and input system connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a vehicle-machine collaborative emergency material delivery planning method. The display screen can be an LCD screen or an e-ink screen. The input system can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0098] Those skilled in the art will understand that Figures 3-4 The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the computer device to which the present invention is applied. A specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0099] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to perform the following steps:

[0100] A resource delivery planning model is constructed based on the emergency supplies requirements and the total transport capacity of vehicle and drone fleets.

[0101] The delivery completion time is obtained through a resource delivery planning model. Based on the delivery completion time and the preset material recycling mechanism, the total delivery time for the drone formation to perform the required tasks is optimized, and a delivery planning scheme is generated.

[0102] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0103] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0104] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the appended claims.

Claims

1. A vehicle-machine collaborative emergency material delivery planning method, characterized in that, The method includes: A resource delivery planning model is constructed based on the emergency supplies requirements and the total transport capacity of vehicle and drone fleets. Based on the demand points and scope of material demand in the emergency supplies task, a fuzzy demand setting task demand representation is adopted. Based on the constraints of the task demand representation and the total transport capacity of the vehicle and drone formation, a resource delivery planning model is constructed: in, For preference coefficients, To minimize the demand for supplies, The total carrying capacity of the vehicle and drone convoy. For vehicle and drone swarm Delivery completion time, Assign numbers to the drones in the drone formation that will perform the required tasks. For demand points; The constraints are as follows: in, Indicates drone, Indicates truck, For a collection of customers who use drones for services, For a group of customers who are served by vehicles, A set of nodes for launching or recovering drones. For vehicle platooning Does the drone in the image travel through the path arc alone? The judgment result, For vehicle platooning Did the vehicles in the route pass through the arc without carrying drones? The judgment result, This refers to the path arc traversed individually by a vehicle in a platoon. The judgment result, The total number of vehicles in the platoon. For vehicle platooning Did the vehicle carrying the drone pass through the path arc? , To start from the demand point To the point of demand The flight distance of the drone For drones Maximum range To start from the demand point To the point of demand The distance the vehicle traveled, For vehicles Maximum driving distance; The delivery completion time is obtained through the resource delivery planning model. Based on the delivery completion time and the preset material recycling mechanism, the total delivery time of the drone formation in performing the required task is optimized to generate a delivery planning scheme. The delivery completion time is obtained through the resource delivery planning model. in, For the first Delivery completion time for each vehicle convoy; The total delivery time for the drone swarm to perform the required task is optimized based on the delivery completion time and the preset material recycling mechanism. in, For a set of client nodes, and These are the maximum capacities for drones and trucks, respectively. For vehicle platooning at nodes Departure time For drones at nodes Arrival time, For trucks at the node Arrival time, For nodes Service hours, For nodes Start time of the time window; Based on the delivery completion time and the preset material recycling mechanism, optimize the total delivery time of the drone formation to perform the required task, and generate a delivery planning scheme; The pre-designed material recycling mechanism includes an operational mechanism and a recycling mechanism; The operating mechanism is as follows: when the train to which the vehicle belongs has delivered all the disaster-stricken points corresponding to the demand task and there is still inventory remaining, the inventory sharing protocol is triggered and the loop mechanism is started; when the train to which the vehicle belongs cannot meet the demand task corresponding to any disaster-stricken point, the current disaster-stricken point is a failure point, and the failure point scheduling mechanism is triggered and the failure point rescheduling is started.

2. The method according to claim 1, characterized in that, The loop mechanism is as follows: a closed-loop transfer path is set according to the required tasks and priority rules. On the closed-loop transfer path, after the drone unloads at the first disaster point, it loads the remaining materials and delivers them to the second disaster point. The failure point scheduling mechanism is as follows: multiple vehicles and drones are grouped together to divide the required tasks, and services are provided to the disaster-stricken points of the failure points at the same time.

3. The method according to claim 2, characterized in that, The priority rule is as follows: the delivery priority of the vehicle and drone group to the disaster-stricken area near the disaster-stricken area is higher than the recovery priority of the central warehouse.

4. A vehicle-machine collaborative emergency material delivery planning system, characterized in that, The system for implementing the method according to any one of claims 1 to 3 comprises: The pre-planning module is used to build a resource delivery planning model based on the emergency supplies demand and the total transport capacity of vehicle and drone fleets; The dynamic delivery planning module is used to obtain the delivery completion time through the resource delivery planning model, optimize the total delivery time of the drone formation to perform the required task based on the delivery completion time and the preset material recycling mechanism, and generate a delivery planning scheme.

5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 3.

Images