Urban logistics unmanned aerial vehicle navigation station network optimization method and device

Abstract

The invention discloses an urban logistics unmanned aerial vehicle navigation station network optimization method and device, and relates to the technical field of civil engineering computer algorithms. The method comprises the following steps: establishing an unmanned aerial vehicle route topology based on Delaunay triangulation; performing sample expansion calculation based on the urban travel data to obtain an outdoor exposed population model; performing unmanned aerial vehicle failure probability and head injury criterion-simple injury grading coupling operation on the outdoor exposed population model, and constructing a risk cost spatial distribution map; executing space weighted Gini coefficient operation to obtain the equality of service population distribution; constructing an energy consumption model; and constructing a Boolean mask matrix based on a gridding outdoor exposed population model, and executing a non-dominated sorting genetic algorithm under the constraint of a Boolean mask by taking a risk cost spatial distribution map, the equality of service population distribution and an energy consumption model as three targets to obtain an optimal navigation station spatial layout with a minimum mean square error. According to the invention, the performance of the urban logistics unmanned aerial vehicle navigation station network can be effectively optimized.

Description

Technical Field

[0001] This invention relates to the field of computer algorithm technology in civil engineering, and in particular to a method and apparatus for optimizing urban logistics drone station networks. Background Technology

[0002] As a critical infrastructure node in the logistics network, the spatial configuration of logistics drone air stations directly affects the overall network performance. Specifically, air station location can be used as an important optimization variable to reduce the risk costs, social inequality, and energy consumption of the drone logistics network.

[0003] Improving the network performance of drone logistics terminals mainly involves two parts: evaluation and optimization. Correspondingly, three major challenges need to be addressed. First, how to accurately predict the future urban drone logistics network and the number of people exposed outdoors. Second, accurately evaluating the performance of the drone logistics network is essential, requiring the development of a universally applicable evaluation model. Finally, for the proposed evaluation model, it is necessary to consider how to efficiently optimize the distribution of terminals at the urban scale to improve network performance.

[0004] On the one hand, risk cost, social equality and energy consumption are considered key factors in the performance of UAV networks. Existing research is mostly based on community-scale pilots and simulations (KOH CH, LOW KH, LI L, et.al. Weightthreshold estimation of falling UAVs (Unmanned Aerial Vehicles) based on impact energy[J]. Transportation Research Part C: Emerging Technologies,2018, 93: 228-255.; STOLAROFF JK, SAMARAS C, O'NEILL ER, et.al. Energy use and life cycle greenhouse gas emissions of drones for commercial package delivery[J]. Nature Communications, 2018, 9(1): 409.; Wu Jingqiong, Dian Ran, Zi Taisheng, et al. Research on UAV delivery: A systematic review on technology, benefits and applications[J]. Transportation Systems Engineering and Information, 1-21; [1] Zhou Yingjiang, Xie Minghui, Jiang Guoping, et al. Based on a new greedy algorithm The article "UAV Full Coverage Path Planning [J]. Journal of Nanjing University of Posts and Telecommunications (Natural Science Edition), 1-12" shows that collaboration with ground networks can improve timeliness stability, reduce waiting time, and lower marginal energy consumption, but these conclusions are difficult to extrapolate to complex and heterogeneous urban systems. On the other hand, finding the optimal value among the three assessment models of risk cost, end-point accessibility, and energy consumption is extremely difficult. Current research uses multi-objective optimization algorithms to calculate the optimal solution of the model under multi-objective constraints and attempts to extend traditional multi-objective optimization algorithms to the spatiotemporal domain (BRAIK AM, GUPTA HS, KOLIOU M, et al. Multi-hazard probabilisticrisk assessment and equitable multi-objective optimization of building retrofit strategies in hurricane-vulnerable communities[J]. Computer-Aided Civil and Infrastructure Engineering, 2025, n / a(n / a).; FAN Q, JIANG M, HUANGW, et al. Considering spatiotemporal evolutionary information in dynamic multi-objective optimization[J]. CAAI Transactions on Intelligence Technology, 2023, n / a(n / a).). However, the problem of lacking location assessment and optimization for logistics drone terminals still exists. Therefore, it is necessary to propose a spatiotemporal multi-objective optimization algorithm that addresses the time-varying characteristics of urban population distribution. Summary of the Invention

[0005] To address the technical problems of insufficient location assessment and optimization for logistics drone terminals in existing technologies, this invention provides a method and apparatus for optimizing urban logistics drone terminal networks. The technical solution is as follows:

[0006] On the one hand, a method for optimizing urban logistics drone terminal networks is provided. This method is implemented by an urban logistics drone terminal network optimization device and includes:

[0007] S1. Based on urban point of interest data, establish the topology of UAV flight routes through Delaunay triangulation and extract the flight distance of the routes;

[0008] S2. Based on urban travel data, expand the sample calculation to obtain a gridded outdoor exposure population model;

[0009] S3. Using the outdoor exposed population model as the population weight, perform coupled calculations of UAV failure probability and head injury criterion - simplified injury classification to construct a spatial distribution map of risk cost.

[0010] S4. Using the census population model as the service population, and combining it with the flight distance of the air routes, perform spatial weighted Gini coefficient calculation to obtain the equality of the service population distribution;

[0011] S5. Construct an energy consumption model by using the flight distance of the route as the only independent variable;

[0012] S6. Based on the gridded outdoor exposed population model, spatial clustering and population change determination are performed to obtain the Boolean mask matrix. The spatial distribution map of risk cost, the equality of service population distribution, and the energy consumption model are taken as the three objectives. Under the Boolean mask constraint, the non-dominated sorting genetic algorithm is executed to obtain the optimal terminal spatial layout with the minimum mean square error.

[0013] On the other hand, an urban logistics drone terminal network optimization device is provided, which is applied to an urban logistics drone terminal network optimization method. The device includes:

[0014] The first building unit is used to establish the topology of UAV flight routes based on urban point of interest data through Delaunay triangulation and extract the flight distance of the routes.

[0015] The expansion unit is used to perform expansion calculations based on urban travel data to obtain a gridded outdoor exposure population model.

[0016] The second building unit is used to use the outdoor exposed population model as population weights to perform coupled calculations of drone failure probability and head injury criterion - concise injury classification to construct a risk cost spatial distribution map.

[0017] The calculation unit is used to use the census population model as the service population, combine the flight distance of the route, and perform spatial weighted Gini coefficient calculation to obtain the equality of the service population distribution;

[0018] The third building unit is used to construct an energy consumption model by taking the flight distance of the route as the only independent variable.

[0019] The optimal selection unit is used to perform spatial clustering and population change determination based on the gridded outdoor exposure population model to obtain the Boolean mask matrix. The risk cost spatial distribution map, the equality of service population distribution and energy consumption model are taken as three objectives. Under the Boolean mask constraint, the non-dominated sorting genetic algorithm is executed to obtain the optimal terminal spatial layout with the minimum mean square error.

[0020] On the other hand, an urban logistics drone terminal network optimization device is provided, the urban logistics drone terminal network optimization device comprising: a processor; a memory, the memory storing computer-readable instructions, which, when executed by the processor, implement any of the methods described above for urban logistics drone terminal network optimization.

[0021] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction is stored in the storage medium, the at least one instruction being loaded and executed by a processor to implement any of the methods in the above-described urban logistics drone station network optimization methods.

[0022] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following:

[0023] Based on urban point-of-interest (POI) data, a drone flight path topology was established using Delaunay triangulation, and flight distances were extracted. Urban travel data was used for expansion calculations to obtain a gridded outdoor exposed population model. Using this model as population weights, a coupled computation of drone failure probability and head injury criterion—a simplified injury classification—was performed to construct a spatial distribution map of risk costs. A census population model was used as the service population, and combined with flight distances, a spatially weighted Gini coefficient was calculated to determine the equality of service population distribution. Flight distances were used as the sole independent variable to construct an energy consumption model. Based on the gridded outdoor exposed population model, spatial clustering and population change determination were performed to obtain a Boolean mask matrix. The spatial distribution map of risk costs, the equality of service population distribution, and the energy consumption model were used as three objectives. Under Boolean mask constraints, a non-dominated sorting genetic algorithm was executed to obtain the optimal station spatial layout with the minimum mean square error. This invention can systematically improve the performance and security of drone logistics networks through an "evaluation-optimization" collaborative decision-making framework. It can effectively optimize the performance of urban logistics drone terminal networks, enabling them to achieve the optimal solution under multiple constraints. It can be used for drone terminal site selection and planning, providing reference opinions for urban logistics drone terminal planning. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0025] Figure 1 This is a flowchart of a method for optimizing urban logistics drone terminal networks provided by an embodiment of the present invention;

[0026] Figure 2 This is a schematic diagram of an initial network topology constructed according to an embodiment of the present invention;

[0027] Figure 3 This is a schematic diagram of a clustering result provided in an embodiment of the present invention;

[0028] Figure 4 This is a schematic diagram illustrating the principle of a spatiotemporal crossover operator provided in an embodiment of the present invention;

[0029] Figure 5 This is a schematic diagram illustrating the principle of a mutation operator provided in an embodiment of the present invention;

[0030] Figure 6 This is a block diagram of an urban logistics drone terminal network optimization device provided in an embodiment of the present invention;

[0031] Figure 7 This is a schematic diagram of the structure of an urban logistics drone station network optimization device provided in an embodiment of the present invention. Detailed Implementation

[0032] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0033] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0034] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0035] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0036] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0037] This invention provides a method for optimizing urban logistics drone terminal networks. This method can be implemented using urban logistics drone terminal network optimization equipment, which can be a terminal or a server. Figure 1 The flowchart shown is for the optimization method of urban logistics drone terminal network. The processing flow of this method may include the following S1-S6:

[0038] S1. Based on urban point of interest data, establish the topology of UAV flight routes through Delaunay triangulation and extract the flight distance of the routes.

[0039] One feasible implementation involves establishing an urban logistics drone network and population model using multi-source data, thereby achieving digital twin modeling.

[0040] Optionally, S1, based on city point of interest data, establishes the UAV flight path topology through Delaunay triangulation and extracts the flight path distance, including:

[0041] S11. Extract the coordinates of logistics distribution centers and logistics delivery points in the city from the city's point of interest data, and establish the hub layer and node layer of the UAV flight path topology respectively.

[0042] S12. Use Delaunay triangulation technology to establish the connection layer of the UAV flight path topology, thereby completing the establishment of the UAV flight path topology and calculating the flight distance of each edge.

[0043] In one feasible implementation, the specific method for establishing the connection layer of the UAV flight path topology using Delaunay triangulation technology can be:

[0044] By treating logistics distribution centers and delivery nodes as discrete vertices, and connecting each distribution center to its nearest delivery node with straight lines, an initial connection layer with optimal spatial adjacency is generated. Calculating the distances between the straight lines in this initial connection layer determines the flight path distances for each edge. Figure 2 The diagram shows the structure of the initial network topology.

[0045] S2. Based on urban travel data, expand the sample calculation to obtain a gridded outdoor exposure population model.

[0046] Optionally, S2 expands its calculations based on urban travel data to obtain a gridded population model of outdoor exposure, including:

[0047] S21. Obtain spatiotemporal travel data for the city.

[0048] In one feasible implementation, urban spatiotemporal travel data can be obtained from publicly available datasets on the internet.

[0049] S22. Crawl the city's total daily travel intensity using the map software's open interface. and total urban population .

[0050] S23. Based on the total travel intensity and the total urban population, the spatiotemporal travel data is expanded to obtain a gridded outdoor exposure population model.

[0051] One feasible implementation method is to analyze spatiotemporal travel data based on the city's total travel intensity. Expanding the sample size yields a spatiotemporal exposure population model. The specific calculation formula is as follows:

[0052]

[0053] Where i represents the grid number and t represents the time.

[0054] By expanding the sample size, the total intensity of urban travel can be obtained, which can be approximated as the intensity of the exposed population in the city at different times.

[0055] S3. Using the outdoor exposed population model as the population weight, perform coupled calculations of UAV failure probability and head injury criterion - simplified injury classification to construct a spatial distribution map of risk cost.

[0056] In one feasible implementation, the UAV failure probability model is mapped across scales to the HIC-AIS damage criterion, unifying the probability of flight failure and the severity of human injury into the same evaluation framework.

[0057] Optionally, S3 uses a gridded outdoor exposure population model as population weights to perform coupled computations of UAV failure probability and head injury criterion-simplified injury grading, constructing a spatial distribution map of risk cost, including:

[0058] S31. Based on the head injury criteria and injury severity grading standards, construct a human injury probability model.

[0059] In one feasible implementation, the acceleration response of the human head is calculated based on the impulse data of the impact of the object. and collision start and end time , Then, the Head Injury Criterion (HIC) value is calculated. The specific calculation formula is as follows:

[0060]

[0061] Based on the nonlinear mapping function between the head injury criterion value and the injury level given in the simplified injury grading standard, the quantitative probability of human injury is calculated and output. The specific calculation method is as follows:

[0062]

[0063] S32. Set the failure probability of the unmanned aerial vehicle system. The value is 10 -4 For each flight hour, the risk cost is calculated by multiplying the probability of injury or death, the probability of drone system failure, the area of ​​the risk zone, and the gridded outdoor exposed population model.

[0064] In one feasible implementation, the failure probability of the unmanned aerial vehicle system is... Set to a conservative value of 10 -4 The risk cost calculation formula is as follows, based on the potential risks covered by typical low-altitude flight scenarios per flight hour:

[0065]

[0066] in, Indicates risk cost, This represents a population model of outdoor exposure. Indicates the area of ​​the risk zone.

[0067] S33. Using spatial association technology in geographic information processing software, the risk cost is mapped onto the outdoor exposure population model to construct a spatial distribution map of the risk cost.

[0068] In one feasible implementation, the calculated risk cost is superimposed with the corresponding outdoor population density data using geospatial coordinates as an index to obtain a regional comprehensive risk assessment value.

[0069] S4. Using the census population model as the service population, and combining it with the flight distance of the flight route, perform spatial weighted Gini coefficient calculation to obtain the equality of the service population distribution.

[0070] In one feasible implementation, under the premise of comprehensively considering the constraints of building accessibility and population accessibility, a spatially weighted Gini coefficient is introduced to quantify the accessibility of the "last mile" of logistics service coverage, so as to characterize the degree of balance of services among different spatial units.

[0071] Optionally, S4 uses a census population model as the service population, combines it with flight distances, and performs spatially weighted Gini coefficient calculation to obtain the equality of the service population distribution, including:

[0072] S41. Obtain the coordinates of urban logistics delivery points through publicly available urban point of interest datasets. Based on the coordinates of the delivery points and the latitude and longitude coordinates of the census population grid, use Euclidean distance to determine the spatial proximity of each delivery point.

[0073] In one feasible implementation, the latitude and longitude coordinates of the census population grid can be obtained from publicly available datasets on the internet. Specifically, determining the spatial proximity of each delivery point using Euclidean distance can involve dividing the population grid served by each delivery point into Thiessen polygons and calculating the Euclidean distance between the coordinates of each delivery point and the grid it serves.

[0074] S42. Use the census population model to extract spatial population density data and count the total service population covered by each logistics delivery point.

[0075] In one feasible implementation, a service coverage area is defined based on the geographical location of each logistics delivery point. This service coverage area is then spatially overlaid and numerically summed with population density data to calculate the total service population for each delivery point. .

[0076] S43. Determine the service cost of each delivery point based on the ratio of the total service population covered by each delivery point to its spatial proximity.

[0077] In one feasible implementation, the service cost of each delivery point is calculated using the following formula:

[0078]

[0079] in, This indicates the total service population covered by each delivery point. It represents spatial proximity, i.e., Euclidean distance.

[0080] S44. Perform spatially weighted Gini coefficient calculations on the total service population covered by each delivery point, spatial proximity, and service cost of each delivery point to determine the equality of service population distribution in the census population model.

[0081] In one feasible implementation, the equality of the service population distribution in grid N of the census population network is measured by the Gini coefficient, calculated as follows:

[0082]

[0083] S5. Construct an energy consumption model by using the flight distance of the flight route as the only independent variable.

[0084] In one feasible implementation, the energy requirements of UAVs in complex environments are quantified by establishing a multi-parameter coupled function model.

[0085] Optionally, S5 uses the flight distance of the route as the sole independent variable to construct an energy consumption model, including:

[0086] S51. Determine the energy consumption calculation model based on the UAV's acceleration, cruise speed, flight altitude, and cruise distance, where the UAV's acceleration, cruise speed, and flight altitude are set as constants.

[0087] In one feasible implementation, based on the dynamic characteristics of the UAV, energy consumption is mainly affected by the UAV's acceleration. cruising speed Flight altitude and cruising distance The impact of [the airport's] layout. At the terminal operation level, acceleration, speed, and altitude are typically limited by the external environment or technical specifications, while flight distance can be actively optimized through terminal layout. Therefore, the energy consumption calculation method simplifies to:

[0088]

[0089] in, The comprehensive influence factor characterizing dynamic flight parameters is set as a constant in this embodiment of the invention.

[0090] An energy consumption prediction model with flight distance as the single independent variable is established and driven and corrected by dynamic flight parameters to achieve continuous assessment of energy consumption under different flight ranges.

[0091] S6. Based on the gridded outdoor exposed population model, spatial clustering and population change determination are performed to obtain the Boolean mask matrix. The spatial distribution map of risk cost, the equality of service population distribution, and the energy consumption model are taken as the three objectives. Under the Boolean mask constraint, the non-dominated sorting genetic algorithm is executed to obtain the optimal terminal spatial layout with the minimum mean square error.

[0092] Optionally, the specific operation steps of S6 may include S61-S65:

[0093] S61. Based on a gridded outdoor exposed population model, calculate the population change and spatial gradient change of each grid per unit time.

[0094] In one feasible implementation, to improve the temporal continuity of the multi-objective optimization process, dynamic threshold constraints and spatial clustering are used to enhance temporal relevance, ensuring that the optimization is synchronized with time-varying population fluctuations. For each grid... Calculated in Population change within the region:

[0095]

[0096] in, Indicates in At time t, the grid of the outdoor exposure population model The number of people exposed to outdoor conditions.

[0097] S62. When the population change of a certain grid and its spatial neighboring grids is less than a first preset threshold in a series of consecutive units, and the spatial gradient change of the neighboring grids is less than a second preset threshold, then the grid is determined to be a population stable region.

[0098] In one possible implementation, the grid and spatial neighborhood grid in continuous Population change within a unit time series is less than a threshold And the neighborhood grid Spatial gradient change less than threshold If the clustering results are as follows, it is marked as a population-stable region. Figure 3 As shown. The specific determination formula is:

[0099]

[0100] S63. Generate a Boolean mask matrix based on the grid set of population-stable regions.

[0101] Stable population areas are marked as True, while unstable population areas are marked as False.

[0102] S64. Perform 3-D connected component clustering on the solution of the first time period of the Boolean mask matrix to form the steady-state boundary of the population. Define crossover and mutation rules based on the mask matrix and perform crossover and mutation on the basis of the steady-state boundary of the population.

[0103] In one feasible implementation, crossover and mutation rules are defined based on the mask matrix: for two parent solutions and Crossover operations are performed only on decision variables outside the mask, while those inside the mask remain fixed, such as... Figure 4 As shown; random perturbations are applied only to variables outside the mask to avoid disrupting spatiotemporal stability, such as Figure 5 As shown.

[0104] In the process of spatiotemporal multi-objective optimization, the logistics delivery point within the steady-state boundary only participates in the global optimization in the first time period and does not enter the iteration in subsequent time periods.

[0105] S65. Using the spatial distribution map of risk cost, the equality of the distribution of the service population, and the energy consumption model as constraints, the frontier solution set for each time period is obtained through spatiotemporal multi-objective optimization. The sum of the risk values ​​of all grids in the spatial distribution map of risk cost is defined as the total risk. The mean square error of the total risk of each frontier solution in each time period is calculated. The frontier solution with the smallest mean square error is taken as the global optimal solution. The station distribution corresponding to the optimal solution is determined as the optimized optimal performance distribution.

[0106] In this embodiment of the invention, based on urban point of interest data, a UAV flight path topology is established through Delaunay triangulation, and the flight path distance is extracted. Based on urban travel data, a gridded outdoor exposed population model is obtained through expansion calculation. Using the outdoor exposed population model as population weights, a coupled operation of UAV failure probability and head injury criterion-simplified injury classification is performed to construct a risk cost spatial distribution map. Using a census population model as the service population, combined with flight path distances, a spatially weighted Gini coefficient calculation is performed to obtain the equality of the service population distribution. Using flight path distances as the sole independent variable, an energy consumption model is constructed. Based on the gridded outdoor exposed population model, spatial clustering and population change determination are performed to obtain a Boolean mask matrix. The risk cost spatial distribution map, the equality of the service population distribution, and the energy consumption model are taken as three objectives. Under Boolean mask constraints, a non-dominated sorting genetic algorithm is executed to obtain the optimal station spatial layout with the minimum mean square error. This invention can systematically improve the performance and security of drone logistics networks through an "evaluation-optimization" collaborative decision-making framework. It can effectively optimize the performance of urban logistics drone terminal networks, enabling them to achieve the optimal solution under multiple constraints. It can be used for drone terminal site selection and planning, providing reference opinions for urban logistics drone terminal planning.

[0107] Figure 6 This is a block diagram of an urban logistics drone terminal network optimization device provided in an embodiment of the present invention. This device is used in an urban logistics drone terminal network optimization method. (Refer to...) Figure 6 The device includes a first construction unit 610, a sample expansion unit 620, a second construction unit 630, a calculation unit 640, a third construction unit 650, and an optimal selection unit 660. Wherein:

[0108] The first building unit 610 is used to establish the topology of UAV flight routes based on urban point of interest data through Delaunay triangulation and extract the flight distance of the flight routes.

[0109] The expansion unit 620 is used to perform expansion calculations based on urban travel data to obtain a gridded outdoor exposure population model.

[0110] The second building unit 630 is used to use the outdoor exposed population model as population weights to perform coupled calculations of UAV failure probability and head injury criteria - simplified injury classification to construct a risk cost spatial distribution map.

[0111] The calculation unit 640 is used to use the census population model as the service population, combine the flight distance of the route, perform spatial weighted Gini coefficient calculation, and obtain the equality of the service population distribution.

[0112] The third building unit 650 is used to construct an energy consumption model with the flight distance of the route as the only independent variable.

[0113] The optimal selection unit 660 is used to perform spatial clustering and population change determination based on the gridded outdoor exposed population model to obtain the Boolean mask matrix. Taking the spatial distribution map of risk cost, the equality of service population distribution and energy consumption model as three objectives, the non-dominated sorting genetic algorithm is executed under the Boolean mask constraint to obtain the optimal terminal spatial layout with the minimum mean square error.

[0114] In this embodiment of the invention, based on urban point of interest data, a UAV flight path topology is established through Delaunay triangulation, and the flight path distance is extracted. Based on urban travel data, a gridded outdoor exposed population model is obtained through expansion calculation. Using the outdoor exposed population model as population weights, a coupled operation of UAV failure probability and head injury criterion-simplified injury classification is performed to construct a risk cost spatial distribution map. Using a census population model as the service population, combined with flight path distances, a spatially weighted Gini coefficient calculation is performed to obtain the equality of the service population distribution. Using flight path distances as the sole independent variable, an energy consumption model is constructed. Based on the gridded outdoor exposed population model, spatial clustering and population change determination are performed to obtain a Boolean mask matrix. The risk cost spatial distribution map, the equality of the service population distribution, and the energy consumption model are taken as three objectives. Under Boolean mask constraints, a non-dominated sorting genetic algorithm is executed to obtain the optimal station spatial layout with the minimum mean square error. This invention can systematically improve the performance and security of drone logistics networks through an "evaluation-optimization" collaborative decision-making framework. It can effectively optimize the performance of urban logistics drone terminal networks, enabling them to achieve the optimal solution under multiple constraints. It can be used for drone terminal site selection and planning, providing reference opinions for urban logistics drone terminal planning.

[0115] Figure 7 This is a schematic diagram of the structure of an urban logistics drone terminal network optimization device provided in an embodiment of the present invention, as shown below. Figure 7 As shown, the urban logistics drone terminal network optimization equipment may include the above-mentioned Figure 6 The illustrated urban logistics drone terminal network optimization device. Optionally, the urban logistics drone terminal network optimization device 710 may include a first processor 2001.

[0116] Optionally, the urban logistics drone station network optimization device 710 may also include a memory 2002 and a transceiver 2003.

[0117] The first processor 2001, memory 2002, and transceiver 2003 can be connected via a communication bus.

[0118] The following is combined Figure 7 A detailed introduction to each component of the 710 urban logistics drone station network optimization equipment:

[0119] The first processor 2001 is the control center of the urban logistics UAV terminal network optimization equipment 710. It can be a single processor or a collective term for multiple processing elements. For example, the first processor 2001 can be one or more central processing units (CPUs), application-specific integrated circuits (ASICs), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0120] Optionally, the first processor 2001 can perform various functions of the urban logistics UAV station network optimization device 710 by running or executing software programs stored in the memory 2002 and calling data stored in the memory 2002.

[0121] In a specific implementation, as one example, the first processor 2001 may include one or more CPUs, for example... Figure 7 CPU0 and CPU1 are shown in the diagram.

[0122] In a specific implementation, as one example, the urban logistics drone station network optimization device 710 may also include multiple processors, for example... Figure 7 The first processor 2001 and the second processor 2004 are shown in the diagram. Each of these processors can be a single-core processor or a multi-core processor. Here, a processor can refer to one or more devices, circuits, and / or processing cores used to process data (such as computer program instructions).

[0123] The memory 2002 is used to store the software program that executes the present invention, and is controlled by the first processor 2001 to execute it. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0124] Optionally, the memory 2002 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 2002 may be integrated with the first processor 2001 or may exist independently, and may be connected via the interface circuit of the urban logistics UAV station network optimization device 710. Figure 7 (Not shown in the image) is coupled to the first processor 2001, and this embodiment of the invention does not specifically limit this.

[0125] The transceiver 2003 is used to communicate with network devices or with terminal devices.

[0126] Alternatively, transceiver 2003 may include a receiver and a transmitter. Figure 7 (Not shown separately). The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function.

[0127] Optionally, the transceiver 2003 can be integrated with the first processor 2001, or it can exist independently and be connected to the interface circuit of the urban logistics drone station network optimization device 710. Figure 7 (Not shown in the image) is coupled to the first processor 2001, and this embodiment of the invention does not specifically limit this.

[0128] It should be noted that, Figure 7 The structure of the urban logistics drone station network optimization device 710 shown in the figure does not constitute a limitation on the router. The actual urban logistics drone station network optimization device may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0129] Furthermore, the technical effects of the urban logistics drone station network optimization equipment 710 can be referenced from the technical effects of the urban logistics drone station network optimization method described in the above method embodiments, and will not be repeated here.

[0130] It should be understood that the first processor 2001 in the embodiments of the present invention may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or it may be any conventional processor, etc.

[0131] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0132] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0133] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0134] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0135] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0136] Those skilled in the art will recognize that the units and algorithms S of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0137] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0138] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0139] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0140] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0141] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods S described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0142] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for optimizing urban logistics drone terminal networks, characterized in that, The method includes: S1. Based on urban point of interest data, establish the topology of UAV flight routes through Delaunay triangulation and extract the flight distance of the routes; S2. Based on urban travel data, expand the sample calculation to obtain a gridded outdoor exposure population model; S3. Using the outdoor exposed population model as the population weight, perform coupled calculations of UAV failure probability and head injury criterion - simplified injury classification to construct a spatial distribution map of risk cost. S4. Using the census population model as the service population, and combining it with the flight distance of the air routes, perform spatial weighted Gini coefficient calculation to obtain the equality of the service population distribution; S5. Construct an energy consumption model by using the flight distance of the route as the only independent variable; S6. Based on the gridded outdoor exposed population model, spatial clustering and population change determination are performed to obtain the Boolean mask matrix. The spatial distribution map of risk cost, the equality of service population distribution, and the energy consumption model are taken as the three objectives. Under the Boolean mask constraint, the non-dominated sorting genetic algorithm is executed to obtain the optimal terminal spatial layout with the minimum mean square error.

2. The method for optimizing urban logistics drone terminal networks according to claim 1, characterized in that, The S1 method, based on city point of interest data, establishes the UAV flight path topology through Delaunay triangulation and extracts the flight path distance, including: S11. Extract the coordinates of logistics distribution centers and logistics delivery points in the city from the city's point of interest data, and establish the hub layer and node layer of the UAV flight path topology respectively. S12. Use Delaunay triangulation technology to establish the connection layer of the UAV flight path topology, thereby completing the establishment of the UAV flight path topology and calculating the flight distance of each edge.

3. The method for optimizing urban logistics drone terminal networks according to claim 1, characterized in that, The S2 method, based on urban travel data, expands the data to obtain a gridded outdoor exposure population model, including: S21. Obtain spatiotemporal travel data for the city; S22. Crawl the city's total daily travel intensity and total population through the open interface of the map software; S23. Based on the total travel intensity and the total urban population, the spatiotemporal travel data is expanded to obtain a gridded outdoor exposure population model.

4. The method for optimizing urban logistics drone terminal networks according to claim 1, characterized in that, The S3 method uses a gridded outdoor exposure population model as population weights to perform coupled calculations of UAV failure probability and head injury criteria—a simplified injury classification—to construct a spatial distribution map of risk cost, including: S31. Construct a human injury probability model based on head injury criteria and injury severity grading standards; S32. Set the failure probability of the unmanned aerial vehicle system to 10. -4 For each flight hour, the risk cost is calculated based on the product of the probability of injury or death, the probability of drone system failure, the area of ​​the risk zone, and the gridded outdoor exposed population model. S33. Using spatial association technology in geographic information processing software, the risk cost is mapped onto the outdoor exposure population model to construct a spatial distribution map of the risk cost.

5. The method for optimizing urban logistics drone terminal networks according to claim 1, characterized in that, S4 uses a census population model as the service population, combines it with flight distance, and performs spatially weighted Gini coefficient calculation to obtain the equality of the service population distribution, including: S41. Obtain the coordinates of urban logistics delivery points through publicly available urban point of interest datasets. Based on the coordinates of the delivery points and the latitude and longitude coordinates of the census population grid, use Euclidean distance to determine the spatial proximity of each delivery point. S42. Use the census population model to extract spatial population density data and count the total service population covered by each logistics delivery point; S43. Determine the service cost of each delivery point based on the ratio of the total service population covered by each delivery point to its spatial proximity. S44. Perform spatially weighted Gini coefficient calculations on the total service population covered by each delivery point, spatial proximity, and service cost of each delivery point to determine the equality of service population distribution in the census population model.

6. The method for optimizing urban logistics drone terminal networks according to claim 1, characterized in that, The S5 model uses the flight distance of the flight route as the sole independent variable to construct an energy consumption model, including: S51. Determine the energy consumption calculation model based on the UAV's acceleration, cruise speed, flight altitude, and cruise distance, where the UAV's acceleration, cruise speed, and flight altitude are set as constants.

7. The method for optimizing urban logistics drone terminal networks according to claim 1, characterized in that, The S6-based gridded outdoor exposure population model performs spatial clustering and population change determination to obtain a Boolean mask matrix. It uses the spatial distribution map of risk cost, the equality of service population distribution, and the energy consumption model as three objectives. Under Boolean mask constraints, it executes a non-dominated sorting genetic algorithm to obtain the optimal terminal spatial layout with the minimum mean square error, including: S61. Based on a gridded outdoor exposed population model, calculate the population change and spatial gradient change of each grid per unit time. S62. When the population change of a certain grid and its spatial neighboring grids is less than a first preset threshold in a series of consecutive units, and the spatial gradient change of the neighboring grids is less than a second preset threshold, then the grid is determined to be a population stable region. S63. Generate a Boolean mask matrix based on the grid set of stable population regions; in the Boolean mask matrix, stable population regions are marked as True, and unstable regions are marked as False. S64. Perform 3-D connected component clustering on the solution of the first time period of the Boolean mask matrix to form the steady-state boundary of the population. Define the crossover and mutation rules based on the mask matrix and perform crossover and mutation on the basis of the steady-state boundary of the population. S65. Using the spatial distribution map of risk cost, the equality of the distribution of the service population, and the energy consumption model as constraints, the frontier solution set for each time period is obtained through spatiotemporal multi-objective optimization. The sum of the risk values ​​of all grids in the spatial distribution map of risk cost is defined as the total risk. The mean square error of the total risk of each frontier solution in each time period is calculated. The frontier solution with the smallest mean square error is taken as the global optimal solution. The station distribution corresponding to the optimal solution is determined as the optimized optimal performance distribution.

8. A device for optimizing urban logistics drone terminal networks, wherein the device is used to implement the urban logistics drone terminal network optimization method as described in any one of claims 1-7, characterized in that, The device includes: The first building unit is used to establish the topology of UAV flight routes based on urban point of interest data through Delaunay triangulation and extract the flight distance of the routes. The expansion unit is used to perform expansion calculations based on urban travel data to obtain a gridded outdoor exposure population model. The second building unit is used to use the outdoor exposed population model as population weights to perform coupled calculations of drone failure probability and head injury criterion - concise injury classification to construct a risk cost spatial distribution map. The calculation unit is used to use the census population model as the service population, combine the flight distance of the route, and perform spatial weighted Gini coefficient calculation to obtain the equality of the service population distribution; The third building unit is used to construct an energy consumption model by taking the flight distance of the route as the only independent variable. The optimal selection unit is used to perform spatial clustering and population change determination based on the gridded outdoor exposure population model to obtain the Boolean mask matrix. The risk cost spatial distribution map, the equality of service population distribution and energy consumption model are taken as three objectives. Under the Boolean mask constraint, the non-dominated sorting genetic algorithm is executed to obtain the optimal terminal spatial layout with the minimum mean square error.

9. A device for optimizing urban logistics drone terminal networks, characterized in that, The urban logistics drone terminal network optimization equipment includes: processor; A memory storing computer-readable instructions that, when executed by the processor, implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains program code that can be invoked by a processor to execute the method as described in any one of claims 1 to 7.

Images