A Logistics UAV Urban Transportation Network Planning Method Based on Transshipment Point Location

Abstract

The present invention discloses a method for planning a logistics UAV urban transportation network based on transfer point location, belonging to the field of UAV transportation network planning. The steps include: based on the ground space layout and urban airspace characteristics, using the grid method to perform three-dimensional discretization modeling on the operation environment of logistics UAVs to identify potential airspace obstacles; designing a logistics UAV transportation network architecture containing one network, two layers, and three nodes; considering the number of transfer points and operation costs, and taking into account the balance of the service pressure of the distribution network, establishing a bi-level multi-objective planning model including transfer point location and network construction; building a bi-level solution framework based on the self-organizing mapping neural network and the hybrid simulated annealing algorithm, and outputting the topological structure of the logistics UAV three-dimensional transportation network. The present invention constructs a logistics UAV three-dimensional transportation network for the intensive distribution requirements in cities, which helps to guide the orderly flight of large-scale logistics UAVs in cities and realize the optimal allocation of low-altitude airspace resources.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle (UAV) transportation network planning, and particularly to a method for planning a logistics UAV urban transportation network based on transfer point location selection. Background Art

[0002] Problems such as traffic congestion and low efficiency caused by the traditional distribution method combining logistics vehicles and couriers are becoming increasingly prominent. This not only restricts the timeliness of logistics distribution but also increases the ground logistics distribution pressure, posing challenges to the sustainable development of cities. Due to the flexible and fast advantages of UAVs, it brings innovative development ideas to the logistics distribution industry. The continuous innovation of technology and the growing user demand indicate that UAV logistics is expected to achieve more extensive commercial applications. However, the large-scale flight of UAVs in future cities also poses challenges to urban air traffic management. The urban airspace is complex and distribution points are dense, and the contradiction between limited low-altitude resources and the huge UAV airspace demand is becoming increasingly prominent, restricting the development of the UAV logistics industry to a certain extent. Facing the multi-level urban spatial layout and high-density UAV operation requirements, it is particularly crucial to plan a suitable transportation network, which helps to guide the orderly and stable flight of UAVs. Existing related research mainly proposes a macro-structural planning scheme for the UAV transportation network based on the urban spatial layout, with problems such as a large network scale, dense airway intersection points, and uneven distribution of flight segment traffic. In addition, the network topology operation safety and user demand distribution characteristics are rarely considered in the transportation network design. Summary of the Invention

[0003] The purpose of the present invention is to provide a method for planning a logistics UAV urban transportation network based on transfer point location selection. In view of the intensive distribution requirements in cities and considering problems such as uneven distribution of distribution points and complex low-altitude airspace environment in the actual application of UAV logistics, based on the origin-destination cargo transportation information, the concept of transfer points is introduced into the transportation network, separating the process of departure from distribution points and reception at demand points, and constructing a safe, efficient, and standardized logistics UAV transportation network to accelerate the integration of UAVs into the urban airspace system.

[0004] To achieve the above purpose, the present invention provides a method for planning a logistics UAV urban transportation network based on transfer point location selection, including the following steps:

[0005] Step 1, based on the ground spatial layout and urban airspace characteristics, use the grid method to perform three-dimensional discretization modeling on the UAV operation environment and identify potential airspace obstacles;

[0006] Step 2, according to the distribution mode of UAVs from the supply end to the user end, design a logistics UAV transportation network architecture containing one network, two layers, and three nodes;

[0007] Step 3: Considering the number of transfer points and operating costs, and taking into account the balance of service pressure in the distribution network, a bi-level multi-objective programming model including transfer point location selection and network construction is established;

[0008] Step 4: Build a bi-level solution framework based on self-organizing mapping neural network and hybrid simulated annealing algorithm, and output the topological structure of the three-dimensional transportation network of logistics UAVs.

[0009] Preferably, in Step 1, the elevation data of buildings is obtained through remote sensing technology, and combined with information on no-fly zones, restricted zones, and dangerous zones in the air, a number of cubic grids are used to fill the three-dimensional geographical space. According to whether there are operation obstacles in the grids, the airspace grids are divided into free grids and obstacle grids. If there are no obstacles in the grid, it is a free grid; if there are obstacles in the grid, it is an obstacle grid. The free grids are the flight areas for logistics UAVs;

[0010] The center of each free grid is the potential location of the transfer point. Let the set of distribution points in the urban area be S, the set of demand points be R, and the set of potential locations of transfer points be T.

[0011] Preferably, in Step 2, the logistics UAV transportation network takes systematicness and hierarchy as the core of design, forming a structured logistics UAV transportation system. By integrating the transfer layer network and the distribution layer network, the connectivity among distribution points, transfer points, and demand points is realized, forming an overall architecture of one network - two layers - three nodes;

[0012] After loading goods at the distribution end, the logistics UAV takes off and flies along the planned route in the logistics UAV transportation network. After arriving at the destination user end, it lands and unloads the goods. According to the specific requirements of the distribution task, after completing a distribution task, the logistics UAV chooses to continue flying to the next user end for distribution, or directly returns to the starting distribution end for charging and maintenance.

[0013] Preferably, one network is the entire logistics UAV transportation network, covering the whole process from the starting point to the end point;

[0014] Two layers mean that the logistics UAV transportation network is a hierarchical structure, including a transfer layer network and a distribution layer network. The flight altitude layer where the transfer layer network is located is higher than the flight altitude layer where the distribution layer network is located. The transfer layer network is used to connect transfer points and distribution points, and the air routes of the transfer layer network are called transfer air routes. The distribution layer is used to connect transfer points and demand points, and the air routes of the distribution layer are called distribution air routes;

[0015] Three nodes are the nodes in the logistics UAV transportation network, including distribution points, transfer points, and demand points. The distribution point is the starting place of the goods, the transfer point is the hub in the transportation network, and the demand point is the end point of the logistics task.

[0016] Preferably, in step 3, based on the overall architecture of the logistics UAV transportation network, a two-layer programming model of the logistics UAV transportation network is established. The two-layer programming model of the logistics UAV transportation network includes an upper model and a lower model. The upper model is a transshipment point location model, and the objective function of the transshipment point location model includes two functions: the number of transshipment points N t and the distribution cost C;

[0017] For the potential location t (t ∈ T) of the transshipment point, a binary variable x is defined t to indicate whether it is enabled, which is expressed as:

[0018]

[0019] The number of transshipment points N of the transportation network t is expressed as:

[0020]

[0021] For the enabled transshipment point t, a binary variable x is defined tr to indicate whether it serves the demand point r (r ∈ R), which is expressed as:

[0022]

[0023] Regarding the quantity of goods as the demand weight of users, the distribution cost C of the distribution layer network is expressed as:

[0024]

[0025] In the formula, c tr is the quantity of goods delivered by the UAV from the transshipment point t to the demand point r, and d tr is the airway distance between the transshipment point t and the demand point r.

[0026] Preferably, during the transshipment point location process, combined with environmental restrictions and operation requirements, the airspace restriction constraint, the transshipment point quantity constraint, the distribution relationship constraint, the service scope constraint, and the transshipment point pressure constraint are used as the limiting conditions;

[0027] The airspace restriction constraint is expressed as:

[0028]

[0029] In the formula, g t is a binary variable, and g t = 1 indicates that there are obstacles at the potential location t of the transshipment point, and g t = 0 indicates that there are no obstacles at this location and the UAV can pass;

[0030] The transshipment point quantity constraint is expressed as:

[0031] N t≤N r ;

[0032] The number of transfer points N t is less than or equal to the number of demand points N r ;

[0033] The distribution relationship constraint is expressed as:

[0034]

[0035] Each demand point r is served by a transfer point;

[0036] The demand points covered by the transfer point are defined by the service range, and the service range constraint is expressed as:

[0037]

[0038] where r u is the service radius of the transfer point;

[0039] The pressure of the transfer point is defined as the total amount of goods that need to be delivered to the demand points at this point, which is less than the upper limit of the service pressure p max , and the transfer point pressure constraint is expressed as:

[0040]

[0041] Preferably, the lower-layer model is a network construction model, which incorporates the service pressure and length characteristics of the air route. The objective function of the network construction model includes the standard deviation of the service pressure of the air route δ, the characteristic path length L n , and the total length D of the transportation network n three functions;

[0042] Standard deviation of service pressure of air route δ:

[0043] According to the service relationship between the transfer point and the demand point obtained from the upper-layer model, the selected transfer point set is defined as T u (T u ∈T), the set of transfer layer network nodes V T =T u ∪S, the transfer air route is l ij (i,j∈V T ,i≠j), i and j represent the elements in the set of transfer layer network nodes, and the two nodes are not the same node. When the logistics drone transports goods, it is default to select the shortest path to execute the distribution task. The shortest path from the distribution point s (s∈S) to the demand point r (r∈R) for the drone is L sr , and the binary variable represents whether the air route l ij is within the shortest path L sr , which is expressed as:

[0044]

[0045] The difference in the service pressure of the transfer route is measured by the standard deviation of the service pressure of the route. The service pressure of route l ij is defined as the number of UAV flights f passing through this route after all delivery tasks are completed ij , expressed as:

[0046]

[0047] In the formula, p sr is the number of UAV flights required to transport the goods from the transportation and distribution point s to the demand point r, and c sr is the quantity of transported goods from the distribution point s to the demand point r, and w u is the maximum load of the UAV;

[0048] The average service pressure of the transfer route is expressed as:

[0049]

[0050] In the formula, N l is the number of transfer routes;

[0051] At this time, the standard deviation δ of the service pressure of all transfer routes is expressed as:

[0052]

[0053] In the formula, k ij is a binary variable. k ij = 1 indicates that route l ij is enabled, and k ij = 0 indicates that it is not enabled;

[0054] Characteristic path length L n :

[0055] In the UAV distribution network for logistics, the shortest path from the distribution point s to the demand point r is called the characteristic path. The characteristic path depends on the topological structure of the distribution network. The characteristic path length L of the distribution network n is defined as the average value of the characteristic path lengths from all distribution points to demand points, expressed as:

[0056]

[0057] In the formula, N s is the number of distribution points, and d ij is the length of the transfer route l ij ;

[0058] Total length D of the transportation network n :

[0059] The network construction model aims to minimize the total network length D n which is expressed as:

[0060]

[0061] Preferably, in the process of constructing the logistics UAV transportation network, considering the network topology and the performance limitations of UAVs, the constraints include no isolated point constraint, transfer times constraint, and UAV flight range constraint;

[0062] The logistics UAV transportation network connects all distribution points, transfer points and demand points to form a connected network without isolated points. The no isolated point constraint is expressed as:

[0063]

[0064] where, represents the continuous multiplication of the number of air routes connected to each transfer layer network node, represents the continuous multiplication of the number of transfer points serving each demand point;

[0065] The network is reasonably laid out by restricting the transfer times. The transfer times constraint is expressed as:

[0066]

[0067] In the formula, Q max is the maximum allowable transfer times of the logistics UAV;

[0068] The UAV flight range constraint is expressed as:

[0069]

[0070] In the formula, h is the height of the transfer layer network, and L u is the maximum flight range of the logistics UAV.

[0071] Preferably, in step four, in the two-layer planning model of the logistics UAV transportation network, the upper layer is a two-objective transfer point location model, and the lower layer is a three-objective network construction model. The decision variables are all discrete variables, and there is a coupling relationship between the objective functions of the upper and lower layer models. The upper layer model selects a set of suitable transfer points in the limited airspace grid to match the service relationship with the demand points, which is regarded as a node clustering problem. The self-organizing mapping neural network is used to solve it. Through the competitive learning strategy between neurons, the high-dimensional data is mapped into a low-dimensional topological space, and the demand point group in the airspace is clustered to obtain a set of transfer points that meet the constraint and objective conditions.

[0072] Preferably, the lower-layer model plans suitable air routes among nodes to form a transportation network, incorporates the non-dominated sorting idea, and uses a hybrid simulated annealing algorithm to solve. According to the cargo transportation information between the origin and destination, an air route library including transfer air routes and distribution air routes is constructed, encoded according to the characteristics of the air routes, and an initial population that meets the constraints is generated. Through roulette wheel selection, crossover, and mutation, offspring populations are produced. After combining with the parent population, a non-dominated sorting strategy is used to generate a new generation of population. Through a two-layer iterative strategy, the upper-layer transfer point location selection and the lower-layer network construction are continuously optimized until the entire system reaches an equilibrium state.

[0073] Therefore, the present invention adopts the above-mentioned method for planning a logistics UAV urban transportation network based on transfer point location selection, and has the following beneficial effects:

[0074] The present invention comprehensively considers the urban spatial layout, network topology structure and UAV flight performance, discretely models the UAV operation space using the grid method, designs a multi-level logistics UAV three-dimensional transportation network architecture, combines factors such as the number of transfer points and distribution costs, and takes into account the balance of the service pressure of the transportation network, constructs a two-layer multi-objective planning model for the logistics UAV transportation network, and designs an algorithm framework based on the self-organizing mapping neural network and the hybrid genetic algorithm to solve and obtain the UAV transportation network structure, promoting the structured and refined development of the logistics UAV transportation network, and providing an efficient and intelligent solution for future urban logistics distribution.

[0075] The technical solutions of the present invention will be further described in detail below through the accompanying drawings and embodiments. Description of the Drawings

[0076] Figure 1 It is a schematic flow chart of the method according to the embodiment of the present invention;

[0077] Figure 2 It is a schematic diagram of the logistics UAV urban transportation network architecture according to the embodiment of the present invention;

[0078] Figure 3 It is an operation scenario diagram of the logistics UAV urban transportation network according to the embodiment of the present invention. Detailed Embodiment

[0079] In order to make the objectives, technical solutions, and advantages of the embodiments of the present invention more clearly understood, the following further elaborates on the embodiments of the present invention in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely for explaining the embodiments of the present invention and are not used to limit the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts fall within the scope of protection of this application. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions throughout.

[0080] It should be noted that the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0081] Similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0082] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "upper", "lower", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship in which the product of this invention is customarily placed during use. It is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0083] In the description of the present invention, it should also be noted that unless otherwise clearly specified and limited, the terms "set", "install", and "connect" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0084] Embodiment

[0085] As Figures 1-3 shown, a method for planning a logistics UAV urban transportation network based on transfer point location selection according to the present invention includes the following steps:

[0086] Step 1: Based on the ground space layout and urban airspace characteristics, use the grid method to perform 3D discretization modeling on the operating environment of logistics UAVs and identify potential obstacles in the airspace.

[0087] Obtain building elevation data through remote sensing technology, and combine information such as no-fly zones, restricted zones, and dangerous zones in the air. Use a number of cubic grids to fill the 3D geographical space. According to whether there are operating obstacles in the grid, the airspace grids are divided into free grids and obstacle grids, and logistics UAVs can only fly in free grids;

[0088] The center of each free grid is the potential location of the transfer point. Let the set of distribution points in the urban area be S, the set of demand points be R, and the set of potential locations of transfer points be T.

[0089] Step 2: According to the distribution mode of logistics UAVs from the supply end to the user end, design a logistics UAV transportation network system architecture containing one network, two layers, and three nodes.

[0090] After loading goods at the distribution end, the logistics UAV takes off and flies according to the planned route in the transportation network. After arriving at the destination user end, it lands and unloads the goods. According to the specific requirements of the distribution task, after completing one distribution task, the logistics UAV can choose to continue flying to the next user end for distribution, or directly return to the starting distribution end for charging and maintenance;

[0091] The logistics UAV transportation network takes systematicness and hierarchy as the core of design, forming a structured logistics UAV transportation system. By integrating the transfer layer network and the distribution layer network, the connectivity between distribution points, transfer points, and demand points is realized, forming an overall architecture of one network - two layers - three nodes;

[0092] One network: refers to the entire logistics UAV transportation network, covering the whole process from the starting point to the end point, ensuring seamless connection throughout the distribution process of the logistics UAV;

[0093] Two layers: The logistics UAV transportation network is a hierarchical structure, including two levels: the transfer layer network and the distribution layer network. The transfer layer network is located at a higher flight altitude layer, connecting transfer points and distribution points. The air routes in this layer are called transfer air routes. The distribution layer network is located at a lower flight altitude layer, connecting transfer points and demand points. The air routes in this layer are called distribution air routes;

[0094] Three nodes: The nodes in the transportation network are divided into distribution points, transfer points, and demand points. The distribution point is the starting place of the goods. The transfer point is the hub in the transportation network and is the bridge between the distribution point and the demand point. The demand point is the end point of the logistics task, marking the final delivery of the goods.

[0095] Step 3: Considering the number of transfer points and operating costs, and taking into account the balance of the service pressure of the distribution network, a bi-level multi-objective programming model including transfer point location selection and network construction is established.

[0096] Based on the overall architecture of the logistics UAV transportation network, a bi-level programming model of the logistics UAV transportation network is established. The upper-level model is the transfer point location selection model, and the objective function includes two aspects:

[0097] (1) The number of transfer points N t

[0098] When constructing the logistics UAV transportation network, the number of transfer points is directly related to the operating cost and air traffic management efficiency. For the potential location t (t ∈ T) of the transfer point, a binary variable x is defined t to indicate whether it is enabled, which is expressed as:

[0099]

[0100] At this time, the number of transfer points N of the transportation network t can be expressed as:

[0101]

[0102] (2) The distribution cost C

[0103] The distance between the transfer point and the demand point is the key factor affecting the distribution cost. Usually, there is a direct proportional relationship between the two. For the enabled transfer point t, a binary variable x is defined tr to indicate whether it serves the demand point r (r ∈ R), which is expressed as:

[0104]

[0105] Considering that the cargo volume is also an important factor in the distribution cost, it can be regarded as the demand weight of users, which in turn affects the distribution strategy and cost calculation. Therefore, the distribution cost C of the distribution layer network can be expressed as:

[0106]

[0107] In the formula, c tr is the cargo volume of the UAV from the transfer point t to the demand point r, and d tr is the airway distance between the transfer point t and the demand point r;

[0108] During the transfer point location selection process, combined with environmental restrictions and operating requirements, the following constraint conditions also need to be considered:

[0109] (1) Airspace restriction constraint. There are various obstacles such as buildings and signal blind spots in the low-altitude airspace of the city. It is strictly prohibited for logistics UAVs to pass through, which also restricts the transfer point from being in these obstacle areas, which is expressed as:

[0110]

[0111] In the formula, g t is a binary variable, and g t = 1 indicates that there is an obstacle at the potential location t of the transfer point, and this location cannot be selected. g t = 0 indicates that there is no obstacle at this location and the UAV can pass through;

[0112] (2) Constraint on the number of transfer points. The setting of transfer points should ensure the rationality of the distribution service coverage range. At the same time, it is necessary to prevent the dispersion of resources due to excessive numbers. The number of transfer points generally shall not exceed the number N of demand points r , which is expressed as:

[0113] N t ≤ N r ;

[0114] (3) Distribution relationship constraint. To ensure the exclusivity of services, each demand point is served by one and only one transfer point, which is expressed as:

[0115]

[0116] (4) Service range constraint. To ensure the accessibility of distribution services, the demand points that a transfer point can cover are defined through the service range, which is expressed as:

[0117]

[0118] In the formula, r u is the service radius of the transfer point;

[0119] (5) Transfer point pressure constraint. A transfer point can serve more than one demand point. If the distribution tasks it undertakes are too many, it will lead to overloaded operation. The transfer point pressure is defined as the total amount of goods that need to be delivered from this point to the demand points, and it needs to be less than the service pressure upper limit p max , which is expressed as:

[0120]

[0121] According to the results of the transfer point location layout, the lower-layer model is a network construction model, which incorporates the airway service pressure and length characteristics in order to plan a convenient transportation network topology. The objective function includes three aspects:

[0122] (1) Standard deviation δ of airway service pressure

[0123] According to the upper-layer model, the service relationship between the transfer point and the demand point can be obtained. The selected transfer point set is defined as T u (T u∈T), at this time, the set of transfer layer network nodes V T = T u ∪S, and the transfer route is l ij (i, j ∈ V T , i ≠ j), where i and j represent elements in the set of transfer layer network nodes, and the two nodes are not the same node. When the logistics UAV transports goods, it is default to select the shortest path to execute the distribution task. The shortest path of the UAV from the distribution point s (s ∈ S) to the demand point r (r ∈ R) is L sr , define the binary variable indicating the route l ij whether it is within the shortest path L sr , which is expressed as:

[0124]

[0125] The transfer point can be connected to multiple transfer routes. If a transfer route undertakes too many distribution demands and the service pressure of the transfer route is unbalanced, it will affect the stability of the entire network. Therefore, the standard deviation of the service pressure of the transfer route is used to measure the gap in the service pressure of the transfer route. The service pressure of the route l ij is defined as the number of UAV flights f passing through this route after all distribution tasks are completed ij , which is expressed as:

[0126]

[0127] In the formula, p sr is the number of UAV flights required to transport the goods from the distribution point s to the demand point r, c sr is the quantity of transported goods from the distribution point s to the demand point r, and w u is the maximum load of the UAV;

[0128] The average service pressure of the transfer route can be expressed as:

[0129]

[0130] In the formula, N l is the number of transfer routes;

[0131] At this time, the standard deviation δ of the service pressure of all transfer routes can be expressed as:

[0132]

[0133] In the formula, k ij is a binary variable. k ij = 1 indicates that the route l ij is enabled, and k ij = 0 indicates that it is not enabled;

[0134] (2) Characteristic path length L n

[0135] In the logistics UAV delivery network, there may be more than one path from the delivery point s to the demand point r. The shortest path is also called the characteristic path, which depends on the topological structure of the delivery network. Its length is directly related to the flight efficiency and energy consumption of the UAV. The characteristic path length L of the delivery network n is defined as the average value of the characteristic path lengths from all delivery points to demand points, expressed as:

[0136]

[0137] In the formula, N s is the number of delivery points, and d ij is the length of the transfer route l ij .

[0138] (3) Total length D of the transportation network n

[0139] The total length of the transportation network directly affects the cost and pressure of network management. If the total network length is too large, it may lead to an extension of the transportation time and a reduction in service efficiency. At the same time, the complexity of the network structure will also increase, requiring more resources and more refined scheduling to ensure the stable operation of the network. Therefore, the network construction model aims to minimize the total network length D n , expressed as:

[0140]

[0141] During the network construction process, considering the network topological structure and UAV performance limitations, the following constraints also need to be considered:

[0142] (1) No isolated point constraint. The transportation network needs to connect all delivery points, transfer points and demand points to form a connected network, and there should be no isolated points in the network, expressed as:

[0143]

[0144] Among them, represents the continuous multiplication of the number of routes connected to each transfer layer network node, represents the continuous multiplication of the number of transfer points served by each demand point;

[0145] (2) Transfer times constraint. The characteristic path from the delivery point s to the demand point r may pass through multiple nodes for transfer. To avoid increasing the logistics cost due to frequent transfers, the network is reasonably laid out by restricting the transfer times, expressed as:

[0146]

[0147] In the formula, Q max is the maximum number of transfers allowed for the logistics UAV;

[0148] (3) UAV flight range constraint. The flight path of the logistics UAV from the distribution point s to the demand point r needs to strictly comply with its maximum flight range limit to ensure that the UAV can complete the distribution task safely and efficiently within its endurance range, which is expressed as:

[0149]

[0150] In the formula, h is the height of the transfer layer network, and L u is the maximum flight range of the logistics UAV.

[0151] Step 4: Build a two-layer solution framework based on the self-organizing mapping neural network and the hybrid simulated annealing algorithm, and output the topological structure of the logistics UAV three-dimensional transportation network.

[0152] In the two-layer planning model of the logistics UAV transportation network, the upper layer is a two-objective transfer point location model, and the lower layer is a three-objective network construction model. The decision variables are all discrete variables, and there is a coupling relationship between the objective functions of the upper and lower layer models, which belongs to the NP-hard problem. The essence of the upper layer model is to select a set of suitable transfer points in the limited airspace grid to match the service relationship with the demand points, which can be regarded as a node clustering problem. The self-organizing mapping neural network is used for solution. Through the competitive learning strategy between neurons, this algorithm maps high-dimensional data to a low-dimensional topological space, and can cluster the demand point groups in the airspace, so as to obtain a set of transfer points that meet the constraints and objective conditions;

[0153] In order to meet the objective function of the transfer point location model, calculate the distribution cost between neuron α and the input vector X, and define the neuron with the lowest distribution cost as the activated neuron. Centered on the activated neuron, update the weights of the activated neuron and the neurons in its neighborhood until the predetermined number of training times is reached. Since the model restricts that the number of transfer points cannot exceed the number of demand points, in order to find a set of transfer points that meet the dual objectives of minimizing the number of transfer points and the distribution cost, set the value range of the algorithm clustering number to [1, N r , for the transfer point location results under each clustering number, if they meet the model constraints, retain the solution. According to the dominance relationship between the feasible solutions, a set of Pareto optimal solutions can be obtained. There is no distinction between good and bad solutions in this solution set. Based on the objective function values, use the scoring method to select the solution with the highest score from them as the final solution of the upper layer model;

[0154] The lower-layer model aims to plan suitable air routes among nodes to form a transportation network. It incorporates the idea of non-dominated sorting and uses a hybrid simulated annealing algorithm to solve the problem. According to the cargo transportation information between the origin and destination, it constructs an air route library containing transfer air routes and distribution air routes, encodes according to the characteristics of the air routes, generates an initial population that meets the constraints, produces an offspring population through roulette wheel selection, crossover, and mutation, combines it with the parent population, and then uses the non-dominated sorting strategy to generate a new generation of population. Through a two-layer iterative strategy, it continuously optimizes the upper-layer transfer point location selection and the lower-layer network construction until the entire system reaches an equilibrium state.

[0155] Therefore, for the method for planning a logistics UAV urban transportation network based on transfer point location selection described in the present invention, aiming at the intensive distribution requirements in the city, it constructs a three-dimensional transportation network for logistics UAVs, which helps to guide the orderly flight of a large number of logistics UAVs in the city and realize the optimal allocation of low-altitude airspace resources.

[0156] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that they can still modify or equivalently replace the technical solutions of the present invention, and these modifications or equivalent replacements cannot make the modified technical solutions deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for planning a logistics UAV urban transportation network based on the location selection of transfer points, characterized in that: It includes the following steps: Step 1: Based on the ground space layout and urban airspace characteristics, use the grid method to conduct three-dimensional discretization modeling of the operating environment of logistics UAVs and identify potential obstacles in the airspace; Step 2: According to the distribution mode of logistics UAVs from the supply end to the user end, design a logistics UAV transportation network architecture containing one network, two layers, and three nodes; Step 3: Considering the number of transfer points and operating costs, and taking into account the balance of the service pressure of the distribution network, establish a two-layer multi-objective programming model including transfer point location selection and network construction; Step 4: Build a two-layer solution framework based on the self-organizing mapping neural network and the hybrid simulated annealing algorithm, and output the topological structure of the logistics UAV three-dimensional transportation network; In step 3, based on the overall architecture of the logistics UAV transportation network, a two-layer programming model of the logistics UAV transportation network is established. The two-layer programming model of the logistics UAV transportation network includes an upper-layer model and a lower-layer model. The upper-layer model is a transshipment point location model, and the objective function of the transshipment point location model includes two functions: the number of transshipment points N t and the distribution cost C; For a potential location \(t\) (\(t\in T\)) of the transfer point, define a binary variable \(x\) t to indicate whether it is enabled, expressed as: The number N of transfer points in the transportation network t It is expressed as: For the enabled transshipment point t, define the binary variable x tr indicating whether it serves the demand point r (r ∈ R), which is expressed as: Regarding the cargo volume as the demand weight of users, the distribution cost C of the distribution layer network is expressed as: Where c tr is the quantity of goods delivered by the UAV from the transfer point t to the demand point r, and d tr is the airway distance between the transfer point t and the demand point r; The lower-layer model is a network construction model that incorporates airway service pressure and length characteristics. The objective function of the network construction model includes the standard deviation of airway service pressure δ, the characteristic path length L n , and the total length D of the transportation network n These are three functions; Standard deviation δ of the airway service pressure: Based on the upper-layer model, the service relationship between the transfer points and the demand points is obtained, and the selected set of transfer points is defined as T u (T u ∈ T), the set of transfer layer network nodes V T = T u ∪ S, the transfer route is l ij (i, j ∈ V T , i ≠ j), i and j represent the elements in the set of transfer layer network nodes, and the two nodes are not the same node. When the logistics drone transports goods, it is default to select the shortest path to execute the distribution task. The shortest path of the drone from the distribution point s (s ∈ S) to the demand point r (r ∈ R) is L sr , define the binary variable indicating whether the route l ij is within the shortest path L sr as follows: The standard deviation of the airway service pressure is used to measure the gap in the transfer airway service pressure. The service pressure of airway l ij is defined as the number of drone flights f passing through this airway after all delivery tasks are completed ij , which is expressed as: Where p sr is the number of drone flights required to transport goods from the transportation and distribution point s to the demand point r, and c sr is the quantity of transported goods from the distribution point s to the demand point r, and w u is the maximum load of the drone; Average service pressure of the transfer route Expressed as: Where N l is the number of transfer routes; At this time, the standard deviation δ of the service pressure of all transfer airways is expressed as: where k ij is a binary variable, and k ij = 1 indicates that the route l ij is enabled, and k ij = 0 indicates that it is not enabled; Characteristic path length L n : In the logistics UAV delivery network, the shortest path from the delivery point s to the demand point r is called the characteristic path. The characteristic path depends on the topological structure of the delivery network. The length L of the characteristic path of the delivery network n is defined as the average value of the characteristic path lengths from all delivery points to demand points, and is expressed as: Where N s is the number of distribution points, and d ij is the length of the transfer route l ij . Total length D of the transportation network n : The network construction model aims to minimize the total network length D n which is expressed as:

2. The method for planning a logistics UAV urban transportation network based on the location selection of transfer points according to claim 1, wherein: In Step 1, obtain the building elevation data through remote sensing technology, and combine the information of no-fly zones, restricted zones, and dangerous zones in the air. Use a number of cube grids to fill the three-dimensional geographical space. According to whether there are operating obstacles in the grid, divide the airspace grids into free grids and obstacle grids. If there is no obstacle in the grid, it is a free grid; if there is an obstacle in the grid, it is an obstacle grid. The free grid is the flight area of the logistics UAV; The center of each free grid is the potential location of the transfer point. Let the set of distribution points in the urban area be S, the set of demand points be R, and the set of potential locations of transfer points be T.

3. The logistics UAV urban transportation network planning method based on transfer point location according to claim 2, characterized in that: In Step 2, the logistics UAV transportation network takes systematicness and hierarchy as the core of design, forms a structured logistics UAV transportation system, and realizes the connection between distribution points, transfer points, and demand points by integrating the transfer layer network and the distribution layer network, forming an overall architecture of one network - two layers - three nodes; After loading the goods at the distribution end, the logistics UAV takes off and flies along the planned route in the logistics UAV transportation network. After arriving at the destination user end, it lands and unloads the goods. According to the specific requirements of the distribution task, after completing a distribution task, the logistics UAV chooses to continue flying to the next user end for distribution, or directly returns to the starting distribution end for charging and maintenance.

4. The method for planning a logistics UAV urban transportation network based on transfer point location according to claim 3, wherein: One network is the entire logistics UAV transportation network, covering the whole process from the starting point to the end point; Two layers mean that the logistics UAV transportation network is a hierarchical structure. The two layers include the transfer layer network and the distribution layer network. The flight altitude layer where the transfer layer network is located is higher than the flight altitude layer where the distribution layer network is located. The transfer layer network is used to connect transfer points and distribution points. The airways of the transfer layer network are called transfer airways. The distribution layer is used to connect transfer points and demand points. The airways of the distribution layer are called distribution airways; Three nodes are the nodes in the logistics UAV transportation network. The three nodes include distribution points, transfer points, and demand points. The distribution point is the starting place of the goods. The transfer point is the hub in the transportation network. The demand point is the end point of the logistics task.

5. The method for planning a logistics UAV urban transportation network based on transfer point location according to claim 4, characterized in that: During the process of transfer point location selection, combined with environmental restrictions and operating requirements, use airspace restriction constraints, transfer point quantity constraints, distribution relationship constraints, service scope constraints, and transfer point pressure constraints as limiting conditions; The airspace restriction constraint is expressed as: where g t is a binary variable, and g t = 1 indicates that there is an obstacle at the potential location t of the transfer point, and g t = 0 indicates that there is no obstacle at this location and the UAV can pass through; The transfer point quantity constraint is expressed as: N t ≤N r ; The number of transfer points N t Less than or equal to the number of demand points N r ; The distribution relationship constraint is expressed as: Each demand point r is served by a transfer point; The demand points covered by the transfer point are defined by the service scope, and the service scope constraint is expressed as: where r u is the service radius of the transfer point; The transfer point pressure is defined as the total amount of goods that need to be delivered from this point to the demand points, which is less than the upper limit p of the service pressure. max , and the transfer point pressure constraint is expressed as:

6. The method for planning a logistics UAV urban transportation network based on the location selection of transfer points according to claim 5, characterized in that: During the construction of the logistics UAV transportation network, considering the network topology structure and UAV performance limitations, the constraints include no isolated point constraint, transfer times constraint, and UAV flight range constraint; The logistics UAV transportation network connects all distribution points, transfer points, and demand points to form a connected network without isolated points. The no isolated point constraint is expressed as: Among them, represents the continuous multiplication of the number of air routes connected to each transfer layer network node, represents the continuous multiplication of the number of transfer points served by each demand point; The network is reasonably laid out by restricting the transfer times. The transfer times constraint is expressed as: Where Q max is the maximum number of transfers allowed for the logistics UAV; The UAV flight range constraint is expressed as: where h is the height of the transfer layer network and L u is the maximum flight range of the logistics UAV.

7. The method for planning a logistics UAV urban transportation network based on transfer point location according to claim 6, wherein: In step 4, in the two-layer programming model of the logistics UAV transportation network, the upper layer is a two-objective transfer point location model, and the lower layer is a three-objective network construction model. The decision variables are all discrete variables, and there is a coupling relationship between the objective functions of the upper and lower layer models. The upper layer model selects a set of suitable transfer points in the limited airspace grid to match the service relationship with the demand points, regarded as a node clustering problem, and is solved by the self-organizing mapping neural network. Through the competitive learning strategy between neurons, the high-dimensional data is mapped into a low-dimensional topological space to cluster the demand point groups in the airspace, so as to obtain a set of transfer points that meet the constraint and objective conditions.

8. The method for planning a logistics UAV urban transportation network based on transfer point location according to claim 7, wherein: The lower layer model plans suitable air routes between nodes to form a transportation network, incorporates the non-dominated sorting idea, and is solved by the hybrid simulated annealing algorithm. According to the cargo transportation information between the starting and ending points, an air route library containing transfer air routes and distribution air routes is constructed, encoded according to the air route characteristics, and an initial population that meets the constraints is generated. Through roulette wheel selection, crossover, and mutation, the offspring population is generated. After combining with the parent population, the non-dominated sorting strategy is used to generate a new generation population. Through the two-layer iterative strategy, the upper layer transfer point location and the lower layer network construction are continuously optimized until the entire system reaches an equilibrium state.

Images