An air-ground collaborative logistics planning method, system and device under a road network constraint

Abstract

This invention discloses a method, system, and device for air-ground cooperative logistics planning under road network constraints, relating to the field of logistics and distribution technology. The method includes: acquiring a real map of the target area; randomly sampling on the real map to generate drone delivery points and unmanned vehicle delivery points; clustering the drone delivery points using an improved K-Means algorithm to obtain multiple cluster centers; determining a distance matrix based on the cluster centers; calculating the initial delivery path of the unmanned vehicle using a heuristic algorithm based on the distance matrix; and using a local cooperative delivery planning algorithm to plan the cooperative delivery of drones and unmanned vehicles based on the initial delivery path of the unmanned vehicles. This invention, considering the cooperative work of drones and unmanned vehicles and their respective constraints, enables ground vehicles and flying vehicles to work continuously and collaboratively without long waiting times for each other, thereby improving delivery efficiency.

Description

Technical Field

[0001] This invention relates to the field of logistics and distribution technology, and in particular to a method, system and equipment for air-ground collaborative logistics planning under road network constraints. Background Technology

[0002] In recent years, the logistics and delivery industry has faced increasing demand and challenges. To improve delivery efficiency and meet customer expectations, the industry has begun exploring new delivery methods. Among these, the combination of drones and traditional unmanned vehicles has received widespread attention.

[0003] The application of drones in logistics and delivery has revolutionized the entire delivery process. Compared to traditional driverless vehicle delivery, drones can move freely in three-dimensional space, unrestricted by roads and traffic conditions. This freedom makes drone delivery routes more direct and efficient. However, drones have limited payload and flight range, meaning they cannot completely replace driverless vehicles but need to work in conjunction with them.

[0004] Air-to-ground collaborative logistics delivery, which combines the advantages of drones and unmanned vehicles, enables rapid delivery to residential areas and high-rise buildings, while unmanned vehicles can conduct large-scale deliveries within cities. However, this collaborative work also brings new challenges, such as how to effectively plan routes, how to ensure smooth cooperation between the two, and how to address the battery and payload limitations of drones.

[0005] Many current algorithms treat single-vehicle and single-machine as a heuristic to solve problems. However, heuristic algorithms often suffer from excessive computational scale and merely abstract delivery points, ignoring not only the road network limitations in the delivery process but also the possibility of drone delivery planning between delivery points. Summary of the Invention

[0006] The purpose of this invention is to provide a method, system, and equipment for air-ground collaborative logistics planning under road network constraints, which enables ground vehicles and flying vehicles to work continuously and collaboratively without having to wait for each other for a long time, thereby improving delivery efficiency, based on consideration of the collaborative work of drones and unmanned vehicles and their respective constraints.

[0007] To achieve the above objectives, this invention provides an air-ground collaborative logistics planning method under road network constraints, comprising:

[0008] Obtain a real map of the target area; the real map includes building information and road network information.

[0009] Random sampling is performed on the real map to generate drone delivery points and unmanned vehicle delivery points;

[0010] The improved K-Means algorithm is used to cluster the drone delivery points to obtain multiple cluster centers; the cluster centers represent the drone delivery tasks.

[0011] Determine the distance matrix based on the cluster centers;

[0012] Based on the distance matrix, the initial delivery path of the unmanned vehicle is calculated using a heuristic algorithm;

[0013] Based on the initial delivery path of the unmanned vehicle, a local collaborative delivery planning algorithm is used to plan the collaborative delivery between the drone and the unmanned vehicle.

[0014] To achieve the above objectives, the present invention also provides an air-ground collaborative logistics planning system under road network constraints, comprising:

[0015] The real map acquisition module is used to acquire a real map of the target area; the real map includes building information and road network information.

[0016] The random sampling module is used to perform random sampling on the real map to generate drone delivery points and unmanned vehicle delivery points;

[0017] The clustering module is used to cluster the drone delivery points using the improved K-Means algorithm to obtain multiple cluster centers; the cluster centers represent the drone delivery tasks.

[0018] A distance matrix determination module is used to determine a distance matrix based on the cluster centers;

[0019] The unmanned vehicle initial path calculation module is used to calculate the initial delivery path of the unmanned vehicle based on the distance matrix using a heuristic algorithm.

[0020] The collaborative delivery module is used to plan the collaborative delivery between the drone and the unmanned vehicle based on the initial delivery path of the unmanned vehicle and using a local collaborative delivery planning algorithm.

[0021] To achieve the above objectives, the present invention also provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to perform the above-described air-ground collaborative logistics planning method under road network constraints.

[0022] To achieve the above objectives, the present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described air-ground collaborative logistics planning method under road network constraints.

[0023] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0024] This invention first extracts a real-world map using OSM (Optical System Mapping). Based on this map, it randomly samples and generates drone and unmanned vehicle (UAV) delivery points. Then, it calculates cluster centers for the drone delivery points using an improved K-Means algorithm. These cluster centers are then merged with UAV delivery points, and heuristics are used to calculate the initial delivery path for the UAVs. Finally, a designed collaborative delivery algorithm is used to perform collaborative calculations based on the initial UAV path, resulting in the final delivery paths for both drones and UAVs. This invention considers the collaborative work of drones and UAVs, as well as their respective limitations, such as the drone's battery and payload constraints. This method enables UAVs and UAVs to work more continuously without long waiting times for each other, thereby improving delivery efficiency. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 A flowchart of the air-ground collaborative logistics planning method under road network constraints provided in Embodiment 1 of the present invention;

[0027] Figure 2 This is a schematic diagram of building information;

[0028] Figure 3 This is a schematic diagram of the road network information;

[0029] Figure 4 This is a schematic diagram illustrating the results of random sampling on a real map.

[0030] Figure 5 A diagram illustrating four scenarios encountered in human-machine and autonomous vehicle collaborative computing;

[0031] Figure 6 A rendering of the trajectory for final delivery by drones and unmanned vehicles. Detailed Implementation

[0032] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0033] The purpose of this invention is to provide a method, system, and equipment for air-ground collaborative logistics planning under road network constraints, and to improve delivery efficiency through a designed collaborative delivery algorithm.

[0034] 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.

[0035] Example 1

[0036] like Figure 1 As shown, the air-ground collaborative logistics planning method under road network constraints provided in this embodiment includes the following steps:

[0037] Step 10: Obtain a real map of the target area; the real map includes building information and road network information.

[0038] To facilitate algorithm description and improve its robustness in real-world scenarios, we utilize the OSM (OpenStreetMap) database to obtain real-world map information of the target area and plan air-ground collaborative logistics delivery within a real-world map context. The data obtained from the real-world map includes two categories: building information (B) and road network information (R).

[0039] This embodiment selects a typical urban area as the experimental scenario, specifically Siping Street in Yangpu District, Shanghai. This area contains numerous buildings and a complex road network. The OSM (OpenStreetMap) database is used to obtain real-world map information for this area. The data obtained from the real map includes two categories: building information (B) and road network information (R), such as... Figure 2 and Figure 3 As shown

[0040] Step 20: Perform random sampling on the real map to generate drone delivery points and unmanned vehicle delivery points. The sampling results are as follows: Figure 4 As shown.

[0041] To ensure these delivery points are located in accessible areas and to consider actual logistics needs, drone delivery points are randomly sampled from building information, and unmanned vehicle delivery points are randomly sampled from road network information. Drone delivery points can only be completed by drones, with each drone delivering a minimum of one point and a maximum of three points, regardless of the demand at each delivery point.

[0042] The drone delivery point sampling is D B =sample(B), where Each Each represents a specific drone delivery point, and 1 ≤ i ≤ m, where m represents the number of drone delivery points. The coordinates of the geometric center point of the building are used.

[0043] The unmanned vehicle delivery point sampling is D R =sample(R), where Each Each represents a specific unmanned vehicle delivery point, and 1 ≤ i ≤ n, where n represents the number of unmanned vehicle delivery points. Use the latitude and longitude coordinates of the path points.

[0044] Step 30: Use the improved K-Means algorithm to cluster the drone delivery points to obtain multiple cluster centers; the cluster centers represent the drone delivery tasks.

[0045] In this embodiment, the delivery radius of the drone is set to 350 meters, and the K-Means algorithm with radius threshold limitation is used to determine the delivery point D of the drone. B Perform clustering to obtain the corresponding cluster centers K. B ,like Figure 4 Points indicated by the rhombus. Among them... Each cluster center Let represent a delivery task by a drone, where 1 ≤ k ≤ m. The K-Means algorithm with radius threshold constraint is calculated as follows:

[0046] set up It is a drone delivery point. To identify cluster centers, we need to minimize the following objective function:

[0047]

[0048] in,

[0049]

[0050] The radius-threshold-limited K-Means algorithm employs an iterative process to ensure that the selected drone delivery points and their corresponding cluster centers satisfy specific conditions. To describe this process, the following parameters and conditions are defined:

[0051] Representative drone delivery point Its corresponding cluster centers The distance between them. R 无人机 It is the specified detection radius range for drones.

[0052] Initially, k is initialized to 1, representing the number of points selected from the drone delivery point set. Then, we proceed with an iterative process until any drone delivery point... Its corresponding cluster center The distance between them shall not exceed the prescribed drone detection radius R. 无人机 ,in Where ||·||2 represents the L2 norm, i.e., the Euclidean norm.

[0053] In each iteration, perform the following: Calculate cluster centers based on n drone delivery points using the K-Means algorithm:

[0054]

[0055] Then the value of k is increased by 1 until both conditions are met. This iterative process ensures that the selected drone delivery points and cluster centers reach a balance, guaranteeing both the delivery efficiency of the drones and meeting their flight distance limitations.

[0056] Step 40: Determine the distance matrix based on the cluster centers.

[0057] Put K B Mapped to the nearest point in the road network information R, i.e., the POI (Point of Interest), the coordinates of the cluster center are from K. B Become K' B , K' B This represents the delivery points that the autonomous vehicle needs to make deliveries to in the road network information R, such as... Figure 4 The point indicated by the cross.

[0058] To obtain the exact distance matrix, it is necessary to first calculate the distance for each cluster center. (from K') B (obtained from the middle) and each unmanned vehicle delivery point (from D) R The distance matrix M between each pair of Euclidean distances is obtained from the above. The calculation process is as follows:

[0059] 1) Initialize a (k+n)×(k+n) matrix M to store all distance values.

[0060] 2) Use the Euclidean distance formula to calculate the Euclidean distance between any two points.

[0061] 3) Calculate the distance m ij Store it in the corresponding position in matrix M.

[0062] 4) After this process, a complete distance matrix will be obtained, where each element m ij This matrix M represents the distance between the corresponding delivery points. This matrix M can provide important information for subsequent steps, such as route planning.

[0063] Step 50: Based on the distance matrix, calculate the initial delivery route of the unmanned vehicle using a heuristic algorithm.

[0064] After obtaining the distance matrix M, the 2-opt algorithm is used to optimize the initial delivery route of the autonomous vehicle. 2-opt is a heuristic method that aims to improve the initial solution of the Traveling Salesman Problem (TSP) by swapping two cities along the route. The calculation process is as follows:

[0065] 1) Initialization: Use a random initialization method to generate an initial delivery route for the driverless vehicle.

[0066] 2) Basic 2-opt: Traverse each pair of points i and j on the delivery path; swap the route between these two points to obtain a new path. Calculate the total distance of the new path. If the distance of the new path is shorter than the original path, use the new path.

[0067] 3) Iterative optimization: Repeat the above 2-opt process until no further improved path swaps can be found.

[0068] 4) Output: Output the initial delivery route of the unmanned vehicle after 2-opt optimization.

[0069] Step 60: Based on the initial delivery path of the unmanned vehicle, a local collaborative delivery planning algorithm is used to plan the collaborative delivery between the drone and the unmanned vehicle. For example... Figure 6 A rendering of the trajectory for final delivery by drones and unmanned vehicles.

[0070] Considering the collaborative work of drones and unmanned vehicles and their respective limitations, drones need to be released at appropriate times without affecting the delivery work of unmanned vehicles, and drones need to return to unmanned vehicles after completing deliveries to a maximum of three drone delivery points.

[0071] When the driverless car carries the drone into K B After a circular area with a specified radius threshold centered at a given point, the drone and the unmanned vehicle separate to perform the delivery task. The drone uses a greedy algorithm for delivery, so its trajectory can be considered a straight line. The unmanned vehicle continues along its initial delivery path during the drone's separation. The unmanned vehicle can leave the designated circular area during the drone's delivery task and return if necessary. If the unmanned vehicle does not enter the circular delivery area, it does not leave the vehicle. Figure 5 As shown, there are four scenarios encountered during this period of collaborative computing between drones and unmanned vehicles:

[0072] (a) There are no unfinished delivery tasks for either drones or unmanned vehicles within the circular area.

[0073] (b) There are still undelivered drones within the circular area, but no undelivered unmanned vehicles within the circle.

[0074] (c) There are no unfinished deliveries of drones within the circular area, but there are still unfinished deliveries of unmanned vehicles within the circle.

[0075] (d) There are unfinished deliveries of both drones and unmanned vehicles within the circular area.

[0076] In practice, the collaborative delivery planning algorithm doesn't need to care what the drone and the unmanned vehicle do during the delivery task after separation; it only needs to know the location of the unmanned vehicle when the drone completes the delivery. Therefore, after separation, the unmanned vehicle doesn't need to remain within the circle; it can leave the central area and then return. The collaborative delivery planning algorithm only needs to know that the drone must be within the central area when it wants to return. If the unmanned vehicle leaves the circle during the drone's delivery time and doesn't return in time, it will wait outside the circle. The following discusses each of the four delivery scenarios for drones and unmanned vehicles within the circle:

[0077] a) Neither the drone nor the unmanned vehicle has any outstanding deliveries within the circular area. This is the ideal scenario, where both the drone and the unmanned vehicle have completed their respective delivery tasks and remain within the circle. Since the drone has completed its final delivery, its movement is no longer restricted, and it will dynamically merge with the unmanned vehicle.

[0078] b) The drones within the circular area still have unfinished deliveries, while the unmanned vehicles within the circle have no unfinished deliveries. In this case, the collaborative delivery planning algorithm determines that once the unmanned vehicle leaves the circle, it will not return. There are two scenarios:

[0079] The drone performs the last delivery task within the circle. The collaborative delivery planning algorithm does not restrict the movement of the unmanned vehicle. The unmanned vehicle will continue to perform the delivery task, and the drone will dynamically merge with the unmanned vehicle.

[0080] The drone did not complete its final delivery within the circle, so the unmanned vehicle should stop outside the circle and wait for the drone to rendezvous. Once the drone and unmanned vehicle rendezvous, the unmanned vehicle's status will be reset, and the delivery schedule will be reassessed.

[0081] c) Within the circular area, there are no unfinished deliveries by the drone, but there are still unfinished deliveries by the unmanned vehicle within the circle. AGCD-CF does not restrict the movement of the unmanned vehicle; the drone will dynamically merge with the unmanned vehicle and then re-determine which delivery category the delivery task belongs to.

[0082] d) Both drones and unmanned vehicles have unfinished deliveries within the circular area. Drones will dynamically merge with unmanned vehicles to reassess the delivery status of the tasks.

[0083] Example 2

[0084] In order to implement the method corresponding to Embodiment 1 above and achieve the corresponding functions and technical effects, an air-ground collaborative logistics planning system under road network constraints is provided below.

[0085] The system includes:

[0086] The real map acquisition module is used to acquire a real map of the target area; the real map includes building information and road network information.

[0087] The random sampling module is used to perform random sampling on the real map to generate drone delivery points and unmanned vehicle delivery points.

[0088] The clustering module is used to cluster the drone delivery points using the improved K-Means algorithm to obtain multiple cluster centers; the cluster centers represent the drone delivery tasks.

[0089] The distance matrix determination module is used to determine the distance matrix based on the cluster centers.

[0090] The unmanned vehicle initial path calculation module is used to calculate the initial delivery path of the unmanned vehicle using a heuristic algorithm based on the distance matrix.

[0091] The collaborative delivery module is used to plan the collaborative delivery between the drone and the unmanned vehicle based on the initial delivery path of the unmanned vehicle and using a local collaborative delivery planning algorithm.

[0092] Example 3

[0093] This embodiment provides an electronic device, including a memory and a processor. The memory stores a computer program, and the processor runs the computer program to enable the electronic device to execute the air-ground collaborative logistics planning method under road network constraints provided in Embodiment 1.

[0094] In practical applications, the aforementioned electronic devices can be servers.

[0095] In practical applications, electronic devices include: at least one processor, memory, bus, and communication interface.

[0096] The processor, communication interface, and memory communicate with each other via a communication bus.

[0097] A communication interface is used to communicate with other devices.

[0098] The processor is used to execute programs, specifically the methods described in the above embodiments.

[0099] Specifically, the program may include program code, which includes computer operation instructions.

[0100] The processor may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The electronic device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or they may be processors of different types, such as one or more CPUs and one or more ASICs.

[0101] Memory is used to store programs. Memory may include high-speed RAM, and may also include non-volatile memory, such as at least one disk drive.

[0102] Example 4

[0103] Based on the description of Embodiment 3, this embodiment provides a storage medium on which a computer program is stored. The computer program can be executed by a processor to implement the air-ground collaborative logistics planning method under road network constraints of Embodiment 1.

[0104] The air-ground collaborative logistics planning system under road network constraints provided in Embodiment 2 of this invention exists in various forms, including but not limited to:

[0105] (1) Mobile communication devices: These devices are characterized by their mobile communication capabilities and primarily aim to provide voice and data communication. These terminals include: smartphones (e.g., iPhones), multimedia phones, feature phones, and low-end phones, etc.

[0106] (2) Ultra-mobile personal computer devices: These devices fall under the category of personal computers, possessing computing and processing capabilities, and generally also have mobile internet access capabilities. These terminals include PDAs, MIDs, and UMPCs, such as the iPad.

[0107] (3) Portable entertainment devices: These devices can display and play multimedia content. This category includes: audio and video players (such as iPods), handheld game consoles, e-books, as well as smart toys and portable car navigation devices.

[0108] (4) Other electronic devices with data interaction functions.

[0109] Specific embodiments of the subject matter have now been described. Other embodiments are within the scope of the appended claims. In some cases, the actions described in the claims can be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing can be advantageous.

[0110] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0111] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, in implementing this invention, the functions of each unit can be implemented in one or more software and / or hardware components. Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product 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.

[0112] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (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 apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0113] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing 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, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0114] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0115] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0116] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0117] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined in this invention, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0118] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus 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 apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0119] This invention can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules.

[0120] Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific transactions or implement specific abstract data types. This invention can also be practiced in distributed computing environments where transactions are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0121] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to the method section.

[0122] This document uses specific examples 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. Furthermore, 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 air-ground collaborative logistics planning under road network constraints, characterized in that, include: Obtain a real map of the target area; The real map includes building information and road network information; Random sampling is performed on the real map to generate drone delivery points and unmanned vehicle delivery points; The improved K-Means algorithm was used to cluster the drone delivery points, resulting in multiple cluster centers. The cluster centers represent the delivery tasks of the drones; Determine the distance matrix based on the cluster centers; Specifically, this includes: mapping each of the cluster centers to the road network information to obtain multiple mapped cluster centers; calculating the Euclidean distance between each mapped cluster center and each unmanned vehicle delivery point; and determining a distance matrix based on the Euclidean distance. Based on the distance matrix, the initial delivery path of the unmanned vehicle is calculated using a heuristic algorithm; Based on the initial delivery path of the unmanned vehicle, a local collaborative delivery planning algorithm is used to plan the collaborative delivery between the drone and the unmanned vehicle; specifically, when the unmanned vehicle carrying the drone enters a circular area with a specified radius threshold centered on the cluster center, the drone and the unmanned vehicle separate to perform the delivery task, and the drone uses a greedy algorithm to perform the delivery; during the separation of the drone, the unmanned vehicle continues to travel on the initial delivery path of the unmanned vehicle. There are four delivery scenarios when drones and unmanned vehicles are used for collaborative delivery: Within the circular area, neither the drones nor the unmanned vehicles had any outstanding delivery tasks. Within the circular area, the drone has unfinished delivery tasks, while the unmanned vehicle has no unfinished delivery tasks. Within the circular area, the drones have no outstanding delivery tasks, but the unmanned vehicles have outstanding delivery tasks. Both drones and drones within the circular area have unfinished delivery tasks. When neither the drone nor the unmanned vehicle has any unfinished delivery tasks within the circular area, the movement of humans and machines is unrestricted, and the drone will dynamically merge with the unmanned vehicle. When the drone has unfinished delivery tasks within the circular area, but the unmanned vehicle does not, and the drone is performing its last delivery task within the circular area, the unmanned vehicle's movement is unrestricted, and the unmanned vehicle will continue to perform its delivery tasks. The drone will then dynamically merge with the unmanned vehicle. If the drone has unfinished delivery tasks within the circular area, the unmanned vehicle does not have unfinished delivery tasks, and the drone has not performed its last delivery task within the circular area, the unmanned vehicle stops outside the circular area and waits for the drone to rendezvous; after the drone and the unmanned vehicle rendezvous, the unmanned vehicle's status is reset, and the delivery situation is re-determined. When the drone has no unfinished delivery tasks within the circular area, but the unmanned vehicle has unfinished delivery tasks, the unmanned vehicle's movement is unrestricted, the drone dynamically merges with the unmanned vehicle, and the delivery tasks are redefined. When both drones and unfinished delivery tasks are within the circular area, the drones will dynamically merge with the unmanned vehicles to redetermine the delivery tasks.

2. The air-ground collaborative logistics planning method under road network constraints according to claim 1, characterized in that, Random sampling is performed on the real map to generate drone delivery points and unmanned vehicle delivery points, specifically including: The drone delivery points are obtained by randomly sampling from the building information and the unmanned vehicle delivery points are obtained by randomly sampling from the road network information; the drone delivery points can only be completed by drone delivery, and each drone delivers at least one point and at most three points.

3. A road network-constrained air-ground collaborative logistics planning system, characterized in that, The system is used to execute the air-ground collaborative logistics planning method under road network constraints as described in any one of claims 1-2, and the system includes: The real map acquisition module is used to acquire a real map of the target area; the real map includes building information and road network information. The random sampling module is used to perform random sampling on the real map to generate drone delivery points and unmanned vehicle delivery points; The clustering module is used to cluster the drone delivery points using the improved K-Means algorithm to obtain multiple cluster centers; the cluster centers represent the drone delivery tasks. A distance matrix determination module is used to determine a distance matrix based on the cluster centers; The unmanned vehicle initial path calculation module is used to calculate the initial delivery path of the unmanned vehicle based on the distance matrix using a heuristic algorithm. The collaborative delivery module is used to plan the collaborative delivery between the drone and the unmanned vehicle based on the initial delivery path of the unmanned vehicle and using a local collaborative delivery planning algorithm.

4. An electronic device, characterized in that, The device includes a memory and a processor, wherein the memory stores a computer program and the processor runs the computer program to enable the electronic device to perform the air-ground collaborative logistics planning method under road network constraints as described in any one of claims 1-2.

5. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the air-ground collaborative logistics planning method under road network constraints as described in any one of claims 1-2.

Images