Heterogeneous multi-vehicle-multi-unmanned aerial vehicle collaborative distribution scheduling method and system

Abstract

The invention provides a heterogeneous multi-vehicle-multi-unmanned aerial vehicle collaborative distribution scheduling method and system. The method comprises the following steps: obtaining distribution data; dividing customer points with strong relevance in spatial positions in the distribution data into the same cluster to obtain a clustering result; after the vehicle carries the unmanned aerial vehicle team to start from the warehouse according to a planned path and arrive at the clustering center point, if the current clustering center point only contains one client point, the vehicle directly executes a distribution task, and if the center point contains multiple client points, sub-distribution tasks are distributed to the carried unmanned aerial vehicle team according to a priority sequence; all the unmanned aerial vehicles return after completing the sub-distribution tasks, all the client points in the cluster complete distribution, the vehicle goes to the next center point to execute the distribution task according to the planned path, and if the vehicle is currently located at the last cluster center point in the path, the vehicle returns to the warehouse to perform state check and maintenance so as to complete the distribution process. According to the method, the resource utilization efficiency is improved while the overall operation cost is reduced.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle (UAV) air-ground collaborative logistics technology, and in particular to a heterogeneous multi-vehicle-multi-UAV collaborative distribution scheduling method and system. Background Art

[0002] With the rapid development of the e-commerce industry in recent years, the demand for terminal logistics and distribution has surged, and users have increasingly stringent requirements for stronger delivery timeliness and more accurate delivery time windows. The traditional logistics and distribution model is increasingly unable to meet the growing demand for terminal delivery. At the same time, the low-altitude economy industry has ushered in an explosive development momentum. The low-altitude economy is a strategic emerging industry with a long industrial chain, rich application scenarios, and extremely broad development space. In 2023, the number of registered drones in China will reach 1.267 million, a year-on-year increase of 32.2%; the flight time of drones will reach 23.11 million hours, a year-on-year increase of 11.8%. By the end of 2023, there will be about 2,000 drone design and manufacturing units and nearly 20,000 operating companies in China. With the increasing maturity of drone manufacturing technology and the gradual opening of low-altitude airspace control, as well as the in-depth promotion of my country's low-altitude airspace management reform, the innovative "last mile" delivery model based on drones has become an emerging research direction that has attracted much attention.

[0003] The advantages of using drones to deliver eligible packages from the terminal distribution center to customers include fast response, efficient delivery, strong flexibility, high cost-effectiveness, and no impact from traffic congestion and ground obstacles. However, drone delivery is currently still limited by its relatively limited load capacity and battery capacity, and cannot achieve long-distance, multi-customer delivery tasks without one-way replenishment. Therefore, the application scenarios of independent drone delivery are relatively narrow, and the objects of delivery are often special goods with light weight and strong timeliness requirements, such as fresh food and emergency rescue supplies, and they often rely on ground facilities for replenishment, thereby extending the delivery range of drones and improving the endurance of delivery services.

[0004] Therefore, the drone delivery method in the prior art has high delivery costs, low utilization efficiency of delivery resources and low delivery efficiency. Summary of the invention

[0005] In view of this, the present invention provides a heterogeneous multi-vehicle-multi-UAV collaborative delivery scheduling method and system to solve the above problems.

[0006] The present invention provides a heterogeneous multi-vehicle-multi-UAV collaborative delivery scheduling method, comprising: obtaining delivery data, the delivery data including the coordinate positions of customer points, cargo demand information corresponding to each customer point, performance parameters of each UAV and each vehicle, and other environmental data; grouping the customer points using a k-means algorithm with constraints, dividing customer points with strong spatial correlation into the same cluster, and obtaining clustering results; analyzing the delivery data, with the goal of minimizing the total delivery cost under the current state, establishing the delivery task and planning path for each vehicle; the vehicle carrying the UAV fleet departs from the warehouse according to the planned path, and the front To the cluster center point; after the vehicle arrives at the cluster center point, if the current cluster center point only contains one customer point, the vehicle directly performs the delivery task. If the center point contains multiple customer points, sub-delivery tasks are assigned to the drone team on board according to a certain priority order; after all drones complete the sub-delivery tasks and return, and all customer points in the cluster are delivered, the vehicle goes to the next cluster center point according to the planned path to continue to perform the delivery task. If it is currently at the last cluster center point in the path, it returns to the warehouse; after all vehicles and drones return to the warehouse, status inspection and maintenance are performed to complete the delivery process.

[0007] In another implementation of the present invention, it also includes: establishing a two-dimensional coordinate system with the location of the warehouse as the coordinate origin; and determining the coordinate position of the customer point based on the two-dimensional coordinate system.

[0008] In another implementation of the present invention, the constraints include: the warehouse and customer points that only support vehicle delivery are set as fixed cluster center points; the distance from a point in any cluster to the cluster center point cannot be greater than the maximum range of all drones.

[0009] In another implementation of the present invention, the vehicles are a heterogeneous fleet with different cost weights, load capacities and travel speeds.

[0010] In another implementation of the present invention, the drones are a heterogeneous drone fleet with different maximum ranges, payloads and flight speeds.

[0011] In another implementation of the present invention, the priority order includes: giving priority to selecting the farthest customer point for delivery, and selecting the fastest drone among drones with sufficient maximum range to perform the sub-delivery task.

[0012] In another implementation of the present invention, it also includes: the vehicle provides charging and replenishment services for the drone, and after the drone completes the sub-delivery task, it returns to the vehicle to perform replenishment operations.

[0013] Another aspect of the present invention provides a heterogeneous multi-vehicle-multi-UAV collaborative delivery scheduling system, including: a data acquisition module: acquiring delivery data, the delivery data including the coordinate position of the customer point, the cargo demand information corresponding to each customer point, the performance parameters of each UAV and each vehicle, and other environmental data; a data processing module: grouping the customer points using a k-means algorithm with constraints, dividing the customer points with strong spatial correlation into the same cluster, and obtaining clustering results; analyzing the delivery data, with the goal of minimizing the total delivery cost under the current state, establishing the delivery task and planning path for each vehicle; a delivery module: the vehicle carrying the UAV fleet according to The planned path starts from the warehouse and goes to the cluster center point; after the vehicle arrives at the cluster center point, if the current cluster center point only contains one customer point, the vehicle directly performs the delivery task; if the center point contains multiple customer points, sub-delivery tasks are assigned to the drone team on board according to a certain priority order; after all drones complete the sub-delivery tasks and return, and all customer points in the cluster are delivered, the vehicle goes to the next cluster center point according to the planned path to continue to perform the delivery task; if it is currently at the last cluster center point in the path, it returns to the warehouse; after all vehicles and drones return to the warehouse, status inspection and maintenance are performed to complete the delivery process.

[0014] In another aspect of the present invention, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the heterogeneous multi-vehicle-multi-UAV collaborative delivery scheduling method as described in any one of the above items are implemented.

[0015] Another aspect of the present invention provides a computer storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the heterogeneous multi-vehicle-multi-UAV collaborative delivery scheduling method as described in any one of the above items are implemented.

[0016] The heterogeneous multi-vehicle-multi-UAV collaborative delivery scheduling method of the present invention takes into account heterogeneous vehicles and UAV fleets with different parameter specifications. Compared with homogeneous vehicle-UAV collaborative delivery, it combines the advantages of heavy-loaded UAVs and large-capacity vehicles, and light, highly maneuverable UAVs and small vehicles. It can flexibly allocate resources according to the specific needs of the delivery task, optimize the resource allocation of the logistics system, and improve the delivery efficiency; while further reducing the overall operating cost, it significantly improves the resource utilization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. By reading the detailed description of the following implementations, the advantages and benefits of the solutions become clear to those skilled in the art. The drawings are only used to illustrate the preferred implementations and are not to be considered as limiting the present invention.

[0018] In the attached picture:

[0019] Figure 1 The present invention is a flowchart of a heterogeneous multi-vehicle-multi-UAV collaborative delivery scheduling method according to an embodiment of the present invention.

[0020] Figure 2 A schematic diagram of a heterogeneous multi-vehicle-multi-UAV scenario according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] For ease of understanding, before describing in detail the specific embodiments of the present invention, an exemplary description of the prior art of a heterogeneous multi-vehicle-multi-UAV collaborative delivery scheduling method of the present invention is first given.

[0022] Parallel delivery with vehicles is another idea to expand the delivery capabilities of drones. Vehicles and drones act as independent transport units in the scene, delivering to near and far customer points respectively, and performing their own delivery tasks without affecting each other.

[0023] In order to further improve the delivery efficiency and increase the utilization rate of drones, the delivery model based on the collaboration of vehicles and drones has attracted more and more attention. In the vehicle-drone collaborative delivery model, the vehicle carries one or more drones, and the two deliver goods to their respective customer points. The drone and the vehicle have a collaborative relationship, and the vehicle acts as a mobile warehouse and supply / charging station for the drone, thereby making up for the shortcomings of the drone itself in terms of load capacity and battery capacity. In the traffic congestion and narrow restricted areas in the urban road network, drones can replace vehicles to complete the delivery more quickly and flexibly.

[0024] Collaborative delivery of vehicles and drones integrates drones with traditional truck transportation systems, giving full play to the respective advantages of traditional truck delivery and drone low-altitude delivery, and making up for their respective disadvantages in non-collaborative modes. Compared with the independent drone delivery mode and the drone-vehicle parallel delivery mode, it has better overall performance and broader research prospects in terms of improving delivery timeliness, reducing delivery costs, and balancing delivery stability and flexibility.

[0025] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be described clearly and in detail below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in the field based on the embodiments in the embodiments of the present invention should fall within the scope of protection of the embodiments of the present invention.

[0026] Figure 1 A schematic diagram of a heterogeneous multi-vehicle-multi-UAV collaborative delivery scheduling method provided by an embodiment of the present invention is shown in FIG. Figure 1 As shown, this embodiment mainly includes:

[0027] S101. Obtaining distribution data, where the distribution data includes coordinate locations of customer points, cargo demand information corresponding to each customer point, performance parameters of each drone and each vehicle, and other environmental data.

[0028] Exemplarily, the distribution data needed to solve the distribution task allocation and scheduling problems are collected, including the coordinate positions of all customer points, the cargo demand information corresponding to each customer point (including the weight of the cargo, whether drone delivery is supported, etc.), the performance parameters of each drone and vehicle (load capacity, endurance time, flight speed, etc.), and other environmental data, to ensure the accuracy of the collected data and provide a basis for subsequent task allocation and scheduling planning.

[0029] S102, grouping the customer points using a k-means algorithm with constraints, dividing customer points with strong spatial correlation into the same cluster, and obtaining a clustering result.

[0030] Exemplarily, based on the geographical distribution and cargo demand of the collected customer points, the k-means algorithm with constraints is used to group the customer points, and the customer points with strong spatial correlation are divided into the same cluster. The cluster center will be used as the parking point for the vehicle, and the vehicle moves between the cluster center points.

[0031] Among them, the specific process of the k-means algorithm with constraints is:

[0032] enter:

[0033] Data point set X = {x1, x2, ..., xP}

[0034] Fixed cluster centers C_fixed = {c1, c2, ..., cN} # N customer points and warehouses that only support vehicle delivery

[0035] Maximum distance constraint M

[0036] Output:

[0037] The final cluster center C

[0038] The cluster assignment of each data point in X

[0039] Algorithm steps:

[0040] 1. Set the initial number of clusters:

[0041] Set the initial number of clusters to K = len(C_fixed) + 1

[0042] 2. Repeat the following steps until all constraints are met:

[0043] a. Initialize cluster centers:

[0044] Randomly generate C_adjustable

[0045] Set the initial cluster center to C = C_fixed ∪ C_adjustable

[0046] b. Repeat the following steps until the clustering results converge:

[0047] i. Cluster assignment:

[0048] For each data point xiin X:

[0049] Find the closest cluster center cj in set C

[0050] Assign xi to the nearest cluster center cj that satisfies the distance constraint

[0051] ii. Update the adjustable cluster center:

[0052] For each adjustable cluster center cj in C_adjustable:

[0053] If cj has data points assigned to it:

[0054] Update cj to the mean of all points assigned to the center

[0055] otherwise:

[0056] Keep cj in its previous position

[0057] iii. Check clustering convergence conditions:

[0058] -If no data point changes its cluster assignment and all cj in C_adjustable remain unchanged:

[0059] Exit the loop

[0060] c. Check clustering convergence conditions:

[0061] -If no data point changes its cluster assignment and all cj in C_adjustable remain unchanged:

[0062] Exit the loop

[0063] -otherwise:

[0064] The number of clusters K increases by 1

[0065] 3. Output the final cluster center C and the cluster assignment of all data points X

[0066] S103: Analyze the delivery data, establish the delivery task and plan the route for each vehicle with the goal of minimizing the total delivery cost under the current state.

[0067] For example, based on the clustering results, the task allocation and path planning of the vehicles are solved. The task allocation and path planning of heterogeneous multiple vehicles moving between cluster centers without duplication can be modeled as a VRP problem. Therefore, a heuristic algorithm based on the greedy strategy to optimize the total vehicle distribution cost is adopted. In each step of path generation, the choice that minimizes the total distribution cost under the current state is taken, so as to gradually establish the distribution task and planning path of each vehicle.

[0068] It should be understood that in order to deal with the significant increase in the complexity of solving the collaborative scheduling problem brought about by heterogeneous multi-vehicles and multi-UAVs, a two-stage heuristic scheduling algorithm based on unsupervised learning clustering and greedy strategy is provided. The joint optimization problem of task allocation and path planning is divided into two stages: clustering and path finding. While ensuring the real-time performance of the distribution system in handling large-scale distribution, a satisfactory solution for vehicle-UAV collaborative scheduling can be obtained.

[0069] The specific process is as follows:

[0070] enter:

[0071] Customer point set C = {c1,c2,...,cn}, each point contains demand information

[0072] Vehicle set V = {v1,v2,...,vm}

[0073] Warehouse Location W

[0074] The movement cost weight of vehicle vi, cost_weight[vi]

[0075] The maximum load constraint of vehicle vi max_load[vi]

[0076] Output:

[0077] The delivery path path[vi] of each vehicle minimizes the total cost

[0078] Algorithm steps:

[0079] 1. Initialization:

[0080] a. For each vehicle vi∈V, set the current path path[vi]=[W] (starting from the warehouse)

[0081] b. Set the remaining load of each vehicle remaining_load[vi] = max_load[vi]

[0082] c. Mark all customer points as unvisited

[0083] 2. Repeat the following steps until all customer points have been visited:

[0084] a. For each vehicle vi, try to find the next customer point cj to be visited:

[0085] - Calculate the moving cost of vehicle vi from the end of the current path to each unvisited customer point cj, defined as:

[0086] cost_vi_cj=cost_weight[vi]*distance(path[vi][-1],cj)

[0087] - If the demand of cj is greater than the remaining load remaining_load[vi], skip cj

[0088] -Select the customer point cj that minimizes cost_vi_cj as the next target point for vehicle vi

[0089] b. Assign the selected customer point cj to the corresponding vehicle vi:

[0090] - Add cj to the path path[vi]

[0091] -Update the remaining load of the vehicle remaining_load[vi]-=demand[cj]

[0092] -Mark customer point cj as visited

[0093] c. If all remaining customer points of a vehicle cannot meet the load constraint or there are no unvisited customer points, the vehicle returns to the warehouse:

[0094] -Add warehouse W to the end of path[vi], ending the delivery path of the vehicle

[0095] 3. When all customer points have been visited:

[0096] - For all vehicles vi still in the path, add warehouse W to the end of path path[vi] so that it returns to the warehouse

[0097] 4. Output the final path path[vi] and total cost of each vehicle

[0098] S104: The vehicle carrying the drone fleet departs from the warehouse and heads to the cluster center according to the planned path.

[0099] S105. After the vehicle arrives at the cluster center, if the current cluster center contains only one customer point, the vehicle directly performs the delivery task. If the center contains multiple customer points, sub-delivery tasks are assigned to the drone fleet on board according to a certain priority order.

[0100] For example, if the current cluster center point is a customer point, the vehicle performs a delivery service and places the goods at a designated location.

[0101] If there are multiple customer points at the center point, the drone takes off from the vehicle, loads the goods and goes to the assigned customer point for delivery. According to the mission requirements, after the drone arrives at the customer point, it delivers the goods to the designated location and records the delivery status (such as the delivery time, success or abnormal status, etc.).

[0102] After the delivery is completed, the drone returns to the vehicle for resupply. The vehicle provides charging and resupply services for the drone to ensure that the drone maintains its endurance to continue to perform subsequent tasks. If there are still undelivered customer points in the current cluster, the drone will continue to deliver; if all the current clusters have been delivered, the drone will return.

[0103] S106. After all drones have completed the sub-delivery mission and returned, and all customer points in the cluster have completed delivery, the vehicle goes to the next cluster center point according to the planned path to continue to perform the delivery mission. If it is currently at the last cluster center point in the path, it returns to the warehouse.

[0104] S107. After all vehicles and drones return to the warehouse, status inspection and maintenance are performed to complete the delivery process.

[0105] The heterogeneous multi-vehicle-multi-UAV collaborative delivery scheduling method of the present invention takes into account heterogeneous vehicles and UAV fleets with different parameter specifications. Compared with homogeneous vehicle-UAV collaborative delivery, it combines the advantages of heavy-loaded UAVs and large-capacity vehicles, and light, highly maneuverable UAVs and small vehicles. It can flexibly allocate resources according to the specific needs of the delivery task, optimize the resource allocation of the logistics system, and improve the delivery efficiency; while further reducing the overall operating cost, it significantly improves the resource utilization efficiency.

[0106] In another implementation of the present invention, it also includes: establishing a two-dimensional coordinate system with the location of the warehouse as the coordinate origin; and determining the coordinate position of the customer point based on the two-dimensional coordinate system.

[0107] In another implementation of the present invention, the constraints include: the warehouse and customer points that only support vehicle delivery are set as fixed cluster center points; the distance from a point in any cluster to the cluster center point cannot be greater than the maximum range of all drones.

[0108] In another implementation of the present invention, the vehicles are a heterogeneous fleet with different cost weights, load capacities and travel speeds.

[0109] In another implementation of the present invention, the drones are a heterogeneous drone fleet with different maximum ranges, payloads and flight speeds.

[0110] It should be understood that different types of equipment have their own advantages in energy consumption, cost and delivery capabilities. By selecting more suitable equipment in appropriate scenarios, the complexity of solving the scheduling problem is increased while also improving the flexibility of the overall planning, which can further reduce the overall operating costs, avoid unnecessary resource consumption, and significantly improve resource utilization efficiency.

[0111] In another implementation of the present invention, the priority order includes: giving priority to selecting the farthest customer point for delivery, and selecting the fastest drone among drones with sufficient maximum range to perform the sub-delivery task.

[0112] like Figure 2 As shown, in the collaborative delivery scenario modeled by the present invention, a team of heterogeneous vehicles, each loaded with a group of drones of different models (different models of drones have different load capacities, endurances, and flight speeds, such as low-speed and high-load cargo drones and high-speed and small cargo drones), departs from the warehouse with the goods and goes to the customer points in sequence along the planned path. The drone loads the goods from the vehicle and departs, goes to the customer point to complete the delivery, and then returns to the vehicle to charge and replenish the goods. In addition to serving as a temporary warehouse and a mobile base station for drone delivery, the vehicle itself will also go to the customer point to complete the delivery task. After completing the delivery tasks for all customer points and all vehicles and drones have returned to the warehouse, the delivery task is completed.

[0113] Specifically, in order to ensure the practical significance of the research scenario and the solvability of the scheduling problem, the following necessary assumptions are made for the scenario:

[0114] There is only one warehouse in the area. Initially, a fleet of heterogeneous vehicles and their fleet of heterogeneous drones depart from the warehouse and return to the warehouse after completing the delivery to all customer points.

[0115] Movement constraints: Trucks need to travel along the road at a constant speed between different nodes in the scene, while drones travel at a constant speed regardless of road conditions. That is, the distance between the vehicle and a point in the scene is calculated using Manhattan distance, while the distance between the drone and a point in the scene is calculated using straight-line distance.

[0116] Load constraints: UAVs and vehicles have load limits, and the weight of the cargo carried cannot exceed their maximum load.

[0117] Cargo constraints: There is a one-to-one correspondence between customer points and drones or trucks. The cargo of a single customer point cannot be split and can only be delivered independently by a single drone or truck. A drone can only deliver to one customer point at a time, and the distance of a single delivery cannot exceed its maximum endurance.

[0118] Distance constraint: There is a maximum distance between the drone and the corresponding vehicle, which means that the distance between the drone and the corresponding vehicle cannot exceed this maximum distance.

[0119] Customer point classification: In the scenario, some customer points are delivered by vehicles, while other customer points can be delivered by drones and trucks. For example, some customer points may require signatures for delivery, or the surrounding areas are not suitable for drone landing or flying, so drones cannot be used for delivery.

[0120] The time it takes for a drone to load cargo, replace batteries, and complete delivery services at the customer point accounts for a very small proportion of the overall delivery time and is therefore negligible.

[0121] In another implementation of the present invention, it also includes: the vehicle provides charging and replenishment services for the drone, and after the drone completes the sub-delivery task, it returns to the vehicle to perform replenishment operations.

[0122] Another aspect of the present invention provides a heterogeneous multi-vehicle-multi-UAV collaborative delivery scheduling system, comprising:

[0123] Data acquisition module: acquires delivery data, which includes the coordinate positions of customer points, cargo demand information corresponding to each customer point, performance parameters of each drone and each vehicle, and other environmental data.

[0124] Data processing module: Use the k-means algorithm with constraints to group the customer points, divide the customer points with strong spatial correlation into the same cluster, and obtain clustering results; analyze the distribution data, with the goal of minimizing the total distribution cost under the current state, establish the distribution task and plan the route for each vehicle.

[0125] Distribution module: The vehicle carrying the drone team departs from the warehouse according to the planned path and goes to the cluster center point; after the vehicle arrives at the cluster center point, if the current cluster center point only contains one customer point, the vehicle directly performs the distribution task; if the center point contains multiple customer points, sub-distribution tasks are assigned to the drone team on board according to a certain priority order; after all drones complete the sub-distribution tasks and return, and all customer points in the cluster are delivered, the vehicle goes to the next cluster center point according to the planned path to continue to perform the distribution task; if it is currently at the last cluster center point in the path, it returns to the warehouse; after all vehicles and drones return to the warehouse, status inspection and maintenance are carried out to complete the distribution process.

[0126] The heterogeneous multi-vehicle-multi-UAV collaborative delivery scheduling system of the present invention takes into account heterogeneous vehicles and UAV fleets with different parameter specifications. Compared with homogeneous vehicle-UAV collaborative delivery, it combines the advantages of heavy-load UAVs and large-capacity vehicles, and light, highly maneuverable UAVs and small vehicles. It can flexibly allocate resources according to the specific needs of the delivery tasks, optimize the resource allocation of the logistics system, and improve the delivery efficiency; while further reducing the overall operating costs, it significantly improves the resource utilization efficiency.

[0127] In another aspect of the present invention, an electronic device includes: a processor, a memory, a communication bus, and a communication interface.

[0128] in:

[0129] The processor, memory and communication interface communicate with each other through a communication bus.

[0130] Communication interface, used to communicate with other electronic devices or servers.

[0131] The processor is used to execute the program, and specifically can execute the steps of any one of the heterogeneous multi-vehicle-multi-UAV collaborative delivery scheduling methods in the above-mentioned embodiments.

[0132] Specifically, the program may include program codes including computer operation instructions.

[0133] The processor may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the smart device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0134] The memory is used to store programs. The memory may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory.

[0135] The program can be specifically used to enable the processor to execute to implement the steps of any heterogeneous multi-vehicle-multi-drone collaborative delivery scheduling method described in the embodiment. The specific implementation of each step in the program can refer to the corresponding description in the steps and units executed by any heterogeneous multi-vehicle-multi-drone collaborative delivery scheduling method in the above steps, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described devices and modules can refer to the corresponding process description in the aforementioned method embodiment.

[0136] The exemplary embodiments of the present application also provide a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the methods of the various embodiments of the present application.

[0137] The above-described method according to an embodiment of the present invention may be implemented in hardware, firmware, or as software or computer code that may be stored in a recording medium (such as a CD ROM, RAM, floppy disk, hard disk, or magneto-optical disk), or as computer code that is originally stored in a remote recording medium or a non-temporary machine-readable medium downloaded over a network and will be stored in a local recording medium, so that the method described herein may be stored in such software processing on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware (such as an ASIC or FPGA). It is understood that a computer, processor, microprocessor controller, or programmable hardware includes a storage component (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code, and when the software or computer code is accessed and executed by a computer, processor, or hardware, the method described herein is implemented. In addition, when a general-purpose computer accesses the code for implementing the method shown herein, the execution of the code converts the general-purpose computer into a dedicated computer for executing the method shown herein.

[0138] Thus far, specific embodiments of the present invention have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve the desired results. Additionally, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing may be advantageous.

[0139] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0140] In the description of the present invention, the terms "first" and "second" are only used to facilitate the description of different components or names, and cannot be understood as indicating or implying a sequential relationship, relative importance, or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features.

[0141] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0142] It should be noted that although the specific embodiments of the present invention are described in detail in conjunction with the accompanying drawings, it should not be understood as limiting the scope of protection of the present invention. Within the scope described in the claims, various modifications and variations that can be made by those skilled in the art without creative work still belong to the scope of protection of the present invention.

[0143] The examples of the embodiments of the present invention are intended to concisely illustrate the technical features of the embodiments of the present invention so that those skilled in the art can intuitively understand the technical features of the embodiments of the present invention, and are not intended to be improper limitations of the embodiments of the present invention.

[0144] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A heterogeneous multi-vehicle-multi-UAV collaborative delivery scheduling method, characterized in that: include: Acquire delivery data, the delivery data including coordinate locations of customer points, cargo demand information corresponding to each customer point, performance parameters of each drone and each vehicle, and other environmental data; The customer points are grouped using a k-means algorithm with constraints, and customer points with strong spatial correlation are divided into the same cluster to obtain a clustering result; Analyze the delivery data to establish a delivery task and plan a route for each vehicle with the goal of minimizing the total delivery cost under the current state; The vehicle carrying the drone team departs from the warehouse and heads to the cluster center according to the planned path; After the vehicle arrives at the cluster center, if the current cluster center contains only one customer point, the vehicle will directly perform the delivery task. If the center contains multiple customer points, the sub-delivery tasks will be assigned to the drone fleet according to a certain priority order. After all drones have completed the sub-delivery mission and returned, and all customer points in the cluster have completed the delivery, the vehicle will go to the next cluster center point according to the planned path to continue to perform the delivery mission. If it is currently at the last cluster center point in the path, it will return to the warehouse; After all vehicles and drones return to the said warehouse, they undergo status inspection and maintenance to complete the delivery process.

2. The method according to claim 1, characterized in that Also includes: Establishing a two-dimensional coordinate system with the location of the warehouse as the coordinate origin; Based on the two-dimensional coordinate system, the coordinate position of the customer point is determined.

3. The method according to claim 1, characterized in that The constraints include: The warehouse and the customer points that only support vehicle delivery are set as fixed cluster centers; The distance from a point in any cluster to the center of the cluster cannot be greater than the maximum range of all drones.

4. The method according to claim 1, characterized in that: The vehicles are a heterogeneous fleet with different cost weights, load capacities and travel speeds.

5. The method according to claim 4, characterized in that The drones are a heterogeneous drone fleet with different maximum ranges, payloads and flight speeds.

6. The method according to claim 5, characterized in that The order of priority includes: Priority is given to selecting the farthest customer point for delivery, and the fastest drone is selected from among the drones with sufficient maximum range to perform the sub-delivery task.

7. The method according to claim 1, characterized in that Also includes: The vehicle provides charging, battery replacement and replenishment services for the drone. After the drone completes the sub-delivery mission, it returns to the vehicle for replenishment operations.

8. A heterogeneous multi-vehicle-multi-UAV collaborative delivery dispatching system, characterized in that: include: Data acquisition module: acquires delivery data, including the coordinates of customer points, cargo demand information corresponding to each customer point, performance parameters of each drone and each vehicle, and other environmental data; Data processing module: using the k-means algorithm with constraints to group the customer points, dividing the customer points with strong spatial correlation into the same cluster, and obtaining the clustering results; Analyze the delivery data to establish a delivery task and plan a route for each vehicle with the goal of minimizing the total delivery cost under the current state; Distribution module: The vehicle carrying the drone team departs from the warehouse according to the planned path and goes to the cluster center point; after the vehicle arrives at the cluster center point, if the current cluster center point only contains one customer point, the vehicle directly performs the distribution task; if the center point contains multiple customer points, sub-distribution tasks are assigned to the drone team on board according to a certain priority order; after all drones complete the sub-distribution tasks and return, and all customer points in the cluster are delivered, the vehicle goes to the next cluster center point according to the planned path to continue to perform the distribution task; if it is currently at the last cluster center point in the path, it returns to the warehouse; after all vehicles and drones return to the warehouse, status inspection and maintenance are carried out to complete the distribution process.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the heterogeneous multi-vehicle-multi-UAV collaborative delivery scheduling method as described in any one of claims 1 to 7 are implemented.

10. A computer storage medium, characterized in that: The computer storage medium stores a computer program, which, when executed by a processor, implements the steps in the heterogeneous multi-vehicle-multi-UAV collaborative delivery scheduling method as described in any one of claims 1 to 7.

Images