A truck-unmanned aerial vehicle combined distribution path planning method and system for urban waterlogging scene emergency supplies

Abstract

The present application relates to the field of transportation engineering, and discloses a truck-unmanned aerial vehicle joint distribution path planning method and system for emergency supplies in an urban waterlogging scene, which divides demand points into type I demand points, type II demand points and type III demand points based on road interruption data, the quantity of supplies required by each demand point, the maximum load capacity of unmanned aerial vehicles and the maximum range of unmanned aerial vehicles; minimizes the latest time at which all demand points are serviced as an objective function, and constructs a truck-unmanned aerial vehicle joint distribution path planning model with demand point access, flow balance, path coordination, time, truck load capacity, unmanned aerial vehicle range, path access order and variable relationship as constraint conditions; the truck-unmanned aerial vehicle joint distribution path planning model is optimized and solved to obtain a joint distribution path scheme. The present application can provide an efficient and reliable joint distribution scheme for emergency decision-making in a waterlogging scene, thereby improving the overall efficiency and response speed of emergency supply distribution.

Description

Technical Field

[0001] This invention belongs to the field of transportation engineering technology and relates to a method and system for planning the joint delivery route of emergency supplies by trucks and drones in urban flooding scenarios. Background Technology

[0002] In a disaster emergency response system, the distribution of emergency supplies is a crucial link, and its efficiency directly determines the timeliness of relief for affected people and the speed of post-disaster recovery.

[0003] However, in the specific disaster scenario of urban flooding, the distribution of emergency supplies faces severe challenges. The main problem is that the water accumulation, damage, and traffic congestion caused by flooding often lead to large-scale disruption or paralysis of the ground transportation network.

[0004] Currently, existing emergency supply distribution technologies primarily rely on ground freight vehicles. The conventional emergency response method involves trucks departing from emergency distribution centers and delivering supplies to various points of need along the ground road network. The drawback of this method is its heavy dependence on the connectivity of the road network. If flooding causes critical road sections or bridges to be blocked, trucks will be unable to pass, creating "transportation islands" that prevent those in need from receiving timely assistance, severely restricting the overall timeliness and coverage of the emergency response.

[0005] To overcome ground obstacles, some technical solutions propose using drones for emergency supply delivery. Drones, with their aerial capabilities, can traverse flooded and damaged roads, offering high flexibility and accessibility. However, existing drone technology, especially small and medium-sized multi-rotor drones, generally suffers from inherent limitations such as small payload capacity and short flight range. Relying solely on drones to and from distribution centers is insufficient to meet the demands of short-term, multi-point, and large-volume supply delivery in emergency scenarios.

[0006] To combine the advantages of both, some research has revealed a truck-drone joint delivery model. In this model, trucks act as mobile platforms, carrying drones for collaborative operations. This overcomes the trucks' high dependence on road network connectivity while fully utilizing the drones' mobility, and also avoids the limitations of drones' short range and small payload. However, existing joint delivery methods are mostly applied to conventional logistics, with optimization goals typically focused on minimizing transportation costs or total travel distance. This doesn't align with the "time-first" and fairness-based requirements of emergency rescue scenarios. Furthermore, these methods often fail to adequately consider the specific constraints of emergency scenarios, such as road inaccessibility due to flooding or the necessary time for drones to launch and recover from trucks. This leads to discrepancies between the planned collaborative paths and actual operations, making it difficult to achieve optimal emergency efficiency. Summary of the Invention

[0007] The purpose of this invention is to provide a truck-drone joint delivery route planning method and system for emergency supplies in urban flooding scenarios, which can provide an efficient and reliable joint delivery solution for emergency decision-making in flooding scenarios, thereby improving the overall efficiency and response speed of emergency supplies delivery.

[0008] To solve the above-mentioned technical problems, the present invention is implemented using the following technical solution.

[0009] In a first aspect, this invention proposes a method for planning the joint delivery route of emergency supplies by trucks and drones in urban flooding scenarios, including:

[0010] Based on road interruption data, material demand at each demand point, maximum payload of drones, and maximum flight range of drones, the demand point set is divided into three categories: Category I, Category II, and Category III. Category I demand points represent those that can be delivered by drones only, Category II demand points represent those that can be delivered by trucks only, and Category III demand points represent those that can be delivered by both trucks and drones.

[0011] Input the road interruption data, the material demand at each demand point, the type of demand point, the maximum payload of the drone, and the maximum flight range of the drone into the pre-built truck-drone joint delivery route planning model;

[0012] For Category I demand points that can only be accessed by drones, construct drone sub-paths;

[0013] A hybrid genetic search algorithm is used to generate truck main routes that satisfy the truck load constraints for all Class II and Class III demand points. These routes are then combined with the obtained drone sub-routes to form an initial joint delivery route scheme, i.e., the initial solution.

[0014] Based on the initial joint delivery route plan, an adaptive large-scale neighborhood search algorithm is used to optimize and solve the truck-drone joint delivery route planning model, generating a new joint delivery route plan, i.e., generating a new solution.

[0015] Determine whether the generated new solution is better than the current solution. If the new solution is better than the current solution, accept the new solution. If the new solution is worse than the current solution, determine whether to accept the new solution according to the Metropolis criterion, and update the current solution and the optimal solution. Continue until the number of iterations reaches the maximum number of iterations or the temperature reaches the minimum temperature. Then output the optimal solution as the final joint delivery route solution. Otherwise, continue iterating.

[0016] The method for constructing the truck-drone joint delivery route planning model is as follows:

[0017] With the objective function of minimizing the latest time for all demand points to be served, and with constraints such as demand point access, traffic balancing, path coordination, time, truck load capacity, drone range, path access order, and variable relationships, a truck-drone joint delivery path planning model is constructed.

[0018] In conjunction with the first aspect, further, based on road interruption data, the material demand at each demand point, the maximum payload of the UAV, and the maximum range of the UAV, the demand points are divided into Category I, Category II, and Category III demand points, including:

[0019] The criteria for determining a Class I demand point is that the road at its location is interrupted; the criteria for determining a Class II demand point is that the road is passable but the demand for supplies exceeds the maximum payload of the drone or the low-altitude flight path distance to all other demand points that can serve as take-off and landing points for the drone exceeds the maximum range of the drone; the criteria for determining a Class III demand point is that the road is passable and the demand for supplies does not exceed the maximum payload of the drone, while the low-altitude flight path distance to at least one other demand point does not exceed the maximum range of the drone.

[0020] In conjunction with the first aspect, further, when constructing a truck-drone joint delivery route planning model for the time coordination of trucks and drones, in addition to considering the impact of truck travel time and drone flight time, the impact of drone launch time and recovery time must also be considered. Specifically, it can be described as follows: If a demand point is only a drone launch point, the point needs to satisfy: truck departure time = truck arrival time + drone launch duration; if a demand point is only a drone recovery point, the point needs to satisfy: truck departure time = max(vehicle arrival time, drone arrival time) + drone recovery duration; if a demand point is both a drone launch point and a drone recovery point, the demand point needs to satisfy: truck departure time = max(truck arrival time, drone arrival time) + drone recovery duration + drone launch duration.

[0021] In conjunction with the first aspect, further, the construction of drone sub-paths for Class I demand points that can only be accessed by drones includes: matching a demand point in the set of Class II and Class III demand points that has the minimum low-altitude track distance to a certain Class I demand point, and using it as the drone take-off point and recovery point for that Class I demand point, thereby obtaining a drone sub-path, and then obtaining all drone sub-paths for Class I demand points.

[0022] Building upon the first aspect, the method for obtaining all UAV sub-paths for Category I demand points is as follows:

[0023] Step S31: Generate a set of candidate nodes for drones from all Class I demand points, and generate a set of candidate nodes for trucks from all Class II and III demand points.

[0024] Step S32: Prioritize all demand points in the drone candidate set according to the order of material demand from largest to smallest. For the drone candidate node with the highest current priority, select the demand point closest to it in the truck candidate node set as the drone take-off point and recovery point, construct a drone sub-path between the two, and remove the drone candidate node from the drone candidate set after completing the demand point matching;

[0025] Step S33: Repeat step S32 until the drone candidate set is empty, and finally an independent drone sub-path is constructed for all Class I demand points.

[0026] Furthermore, the method of generating truck master paths that satisfy truck load constraints for all Class II and Class III demand points using a hybrid genetic search algorithm includes:

[0027] Step S41: Update the information of the II and III demand points that are matched with the I demand points, and update the demand of these demand points to the sum of their own demand and the demand of the matched I demand points. In addition, when the truck arrives at these demand points, the flight time of all the drone sub-paths connected to the demand point needs to be added to the truck's arrival time as the truck's departure time.

[0028] Step S42: Input the locations of all Class II and Class III demand points, the updated demand quantity, and the truck load capacity, and call the Hybrid Genetic Search Algorithm (HGS-CVRP) to generate an initial truck master path that satisfies the truck load capacity constraint.

[0029] In conjunction with the first aspect, furthermore, destruction and repair operators are executed on the current solution to generate a new solution. Specifically, this includes employing six neighborhood structures as the specific execution methods for the destruction and repair operators. These six neighborhood structures cover different delivery methods and node transformation operations. The six neighborhood structures include:

[0030] Swap two truck access demand points, remove a truck access demand point and insert it into a new location in the truck path, swap two drone access demand points, swap a drone access demand point with a truck access demand point, change a truck access demand point to be delivered by drone, and change a drone access demand point to be delivered by truck.

[0031] In conjunction with the first aspect, further, the determination of whether to accept the new solution (i.e., the new truck-drone joint delivery route scheme) based on the Metropolis criterion includes: the Metropolis criterion calculating the acceptance probability. The formula for determining whether to accept a new solution is as follows:

[0032] ;

[0033] ;

[0034] in, The current temperature; This is the current solution; This is a new interpretation; The objective function value of the current solution; The objective function value for the new solution; This is the cooling coefficient.

[0035] It should be noted that: the above solution refers to the truck-drone joint delivery route scheme; the objective function value refers to the latest time that all demand points are served under this delivery route scheme; temperature refers to the degradation tolerance parameter of the delivery scheme.

[0036] When outputting the final joint delivery route plan, it also includes the node access order of each truck main route, the take-off point, service point and collection point of each drone sub-route, and the latest time when all demand points are served.

[0037] In conjunction with the first aspect, the objective function of the truck-drone joint delivery route planning model is further expressed as:

[0038] ;

[0039] in, This represents the collection of all drones. , It is a constant; This indicates the collection of all trucks. , It is a constant; Indicates truck Reaching the demand point The moment; Indicates from truck Launched drone Reaching the demand point At that moment.

[0040] In conjunction with the first aspect, the constraints of the truck-drone joint delivery route planning model are specifically as follows:

[0041] The access constraints for emergency demand points are shown in equations (1) to (5):

[0042] (1);

[0043] (2);

[0044] (3);

[0045] (4);

[0046] (5);

[0047] in, Indicates when demand point By truck Delivery time Otherwise, it is 0; Indicates when demand point By truck The drones carried The value is 1 if delivery is required, otherwise it is 0. Represents the set of all demand points. , ; This represents the set of demand points for Class I services that are solely provided by drones. , ; This represents the set of demand points in category II that are served solely by freight trucks. , ; This represents the set of demand points for Category III services provided by trucks or drones. , ; Represents the final set. , Represents the final distribution center; Represents the starting set, 0 represents the starting distribution center; Indicates from truck UAV launched from above At the point of demand Takeoff, service demand points And at the point of demand The value is 1 when the item is recycled, and 0 otherwise.

[0048] The flow balance constraints are shown in equations (6) to (9):

[0049] (6);

[0050] (7);

[0051] (8);

[0052] (9);

[0053] in, Indicates when truck Moving from the origin distribution center to the demand point It is 1 if it is true, otherwise it is 0; Indicates when truck Both the origin and destination are distribution centers; Indicates when truck From the demand point Move to demand point The value is 1 if it is true, and 0 otherwise. This indicates the total number of trucks involved in the delivery mission. Indicates when truck From the demand point Move to the final delivery center The value is 1 if it is true, and 0 otherwise. Indicates when truck From the demand point Move to demand point The value is 1 if it is true, and 0 otherwise.

[0054] The path coordination constraints are shown in equations (10) to (12):

[0055] (10);

[0056] (11);

[0057] (12);

[0058] in, Indicates the starting point emergency delivery center; Indicates from truck UAV launched from above Take off from the originating distribution center, serving demand points And at the point of demand The value is 1 when the item is recycled, and 0 otherwise. This represents the total number of all nodes in the network, including the originating distribution center and the destination distribution center; Indicates when truck From the demand point Move to demand point The value is 1 if it is true, and 0 otherwise. Indicates when truck From the demand point Move to demand point The value is 1 if it is true, and 0 otherwise. Indicates when truck From the demand point Move to demand point The value is 1 if it is true, and 0 otherwise. Indicates truck Demand points in the path The sequence number; Indicates truck Demand points in the path The sequence number;

[0059] The time constraints are shown in equations (13) to (21):

[0060] (13);

[0061] (14);

[0062] (15);

[0063] (16);

[0064] (17);

[0065] (18);

[0066] (19);

[0067] (20);

[0068] (twenty one);

[0069] in, Indicates truck Reaching the demand point The moment; Indicates from truck Launched drone Reaching the demand point The moment; Indicates from truck Launched drone Reaching the demand point The moment; Indicates truck Leaving the point of demand The moment; Indicate demand points and demand points The weight of the road layer connections between them, i.e., the travel time of trucks between demand points; Represents a very large positive number; Indicates from truck Launched drone Leaving the point of demand The moment; Indicates the time required to launch the drone; Indicates from truck Launched drone Reaching the demand point The moment; Indicates the time required to recover the drone; Indicates truck Leaving the point of demand The moment; Indicates truck Reaching the demand point The moment; Indicates from truck UAV launched from above At the point of demand Takeoff, service demand points And at the point of demand i is 1 when it is recycled, otherwise it is 0; This indicates the weight of the inter-layer connections, i.e., the time of the drone's vertical takeoff and landing; Indicate demand points and demand points The weight of the low-altitude layer connections between them, i.e., the flight time of the drone between the demand points; Indicates from truck Launched drone Leaving the point of demand The moment; Indicate demand points and demand points Weights of low-altitude layer connections between them;

[0070] The cargo load capacity constraint is shown in Equation (23), and the UAV range constraint is shown in Equations (23) to (24):

[0071] (twenty two);

[0072] (twenty three);

[0073] (twenty four);

[0074] in, Indicate demand points Demand; Indicates when demand point By truck The drones carried The value is 1 if delivery is required, otherwise it is 0. Indicate demand points Demand; Indicates truck Maximum load capacity; Indicates when demand point By truck The drones carried The value is 1 if delivery is required, otherwise it is 0. Indicates drone Maximum load capacity; Indicates drone Maximum range; Indicates drone Level flight speed; Indicates drone Ascent / descent speed;

[0075] The path access order constraints are shown in equations (25) to (31):

[0076] (25);

[0077] (26);

[0078] (27);

[0079] (28);

[0080] (29);

[0081] (30);

[0082] (31);

[0083] in, Represents any demand point The access sequence number; Indicates when truck Traversing the required points in the path The value is 1 if the starting distribution center has been traversed, otherwise it is 0. Indicates when truck Traversing distribution centers in the path Previously, the requirements were traversed. The value is 1 if it is true, and 0 otherwise. Indicates when truck Traversing the required points in the path Previously, the requirements were traversed. The value is 1 if it is true, and 0 otherwise. When the truck Traversing the required points in the path Previously, the requirements were traversed. The value is 1 if it is true, and 0 otherwise.

[0084] The relationships between the variables are shown in equations (32) to (34):

[0085] (32);

[0086] (33);

[0087] (34);

[0088] in, Indicates when demand point By truck The drones carried The value is 1 if the item is delivered, otherwise it is 0.

[0089] Secondly, this invention proposes a truck-drone joint delivery route planning system for emergency supplies in urban flooding scenarios, comprising:

[0090] The demand point classification module is configured to divide the demand point set into three categories: Category I, Category II, and Category III, based on road interruption data, the material demand of each demand point, the maximum payload of the drone, and the maximum flight range of the drone. Category I demand points represent demand points that can only be delivered by drone, Category II demand points represent demand points that can only be delivered by truck, and Category III demand points represent demand points that can be delivered by both truck and drone.

[0091] The delivery route planning model module is configured to input road interruption data, material demand at each demand point, demand point type, maximum payload of the drone, and maximum range of the drone into a pre-built truck-drone joint delivery route planning model.

[0092] The drone sub-path construction module is configured to construct drone sub-paths for Class I demand points that can only be accessed by drones.

[0093] The initial joint delivery route scheme module is configured to use a hybrid genetic search algorithm to generate truck main routes that satisfy truck load constraints for all Class II and Class III demand points, and combine them with the obtained drone sub-routes to form an initial joint delivery route scheme, i.e., the initial solution.

[0094] The new solution generation module is configured to optimize and solve the truck-drone joint delivery route planning model based on the initial joint delivery route scheme using an adaptive large-scale neighborhood search algorithm, thereby generating a new joint delivery route scheme, i.e., generating a new solution.

[0095] The final joint delivery route solution module is configured to determine whether the generated new solution is better than the current solution. If the new solution is better than the current solution, it is accepted. If the new solution is worse than the current solution, it is determined whether to accept the new solution according to the Metropolis criterion, and the current solution and the optimal solution are updated until the number of iterations reaches the maximum number of iterations or the temperature reaches the minimum temperature. Then, the optimal solution is output as the final joint delivery route solution. Otherwise, the iteration continues.

[0096] Thirdly, the present invention proposes a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the above-mentioned truck-drone joint delivery route planning method for emergency supplies in urban flooding scenarios.

[0097] Fourthly, the present invention provides a computer device comprising:

[0098] Memory, used to store computer programs;

[0099] A processor is used to execute the computer program to implement the steps of the above-described method for truck-drone joint delivery route planning of emergency supplies in urban flooding scenarios.

[0100] Fifthly, the present invention proposes a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-mentioned truck-drone joint delivery route planning method for emergency supplies in urban flooding scenarios.

[0101] The joint delivery route planning method of the present invention adopts time-priority emergency needs, more refined rule means (i.e. constraints) and delivery strategies. Starting from the perspective of ensuring the latest delivery time is minimized, it takes into account the constraints under special scenarios, thereby improving the efficiency of the entire delivery process.

[0102] This invention automates the classification of emergency demand points based on road disruptions, material demand, and drone performance. It employs a two-stage strategy of "first constructing drone sub-paths, then constructing truck main paths" to generate an initial solution. With the optimization objective of minimizing the latest delivery time among all demand points, it iteratively optimizes the initial solution using an adaptive large-scale neighborhood search algorithm. This provides an efficient and reliable joint delivery solution for emergency decision-making in flood scenarios, thereby improving the overall efficiency and response speed of emergency material delivery.

[0103] Compared with the prior art, the beneficial effects achieved by the present invention are as follows:

[0104] (1) This invention can provide an efficient and reliable joint distribution route solution for emergency decision-making in the context of waterlogging, thereby improving the overall efficiency and response speed of emergency material distribution.

[0105] (2) This invention constructs a truck-drone joint delivery route planning model with the objective function of "minimizing the latest delivery time among all demand points". This makes up for the shortcomings of the current conventional logistics delivery model, which mainly focuses on total cost or total time and cannot meet the urgent needs of global timeliness and delivery fairness in emergency scenarios. At the same time, it proposes a two-stage initial solution construction strategy of "constructing the drone sub-path first and then constructing the truck main path" to solve the problem that the traditional "constructing the truck main path first" algorithm completely fails when the road is interrupted by waterlogging. Based on obtaining a feasible initial solution, this invention further designs an adaptive large neighborhood search algorithm containing six hybrid neighborhood structures. Through the coordinated destruction and repair of truck and drone paths, the overall delivery efficiency is significantly improved compared with the initial scheme. Finally, under the condition of satisfying complex constraints, the emergency response efficiency is maximized.

[0106] (3) This invention provides a truck-UAV joint delivery route planning method for emergency supplies in urban flooding scenarios. Considering the impact of urban flooding on the actual ground road traffic environment, the truck-UAV joint delivery route optimization method is used to solve the problem of high computational complexity and difficulty in meeting the emergency timeliness requirements caused by comprehensively considering and solving the complex environmental constraints and path combination problem in emergency scenarios. It overcomes the shortcomings of existing methods in terms of model precision and scheme feasibility. Attached Figure Description

[0107] Figure 1 This is a flowchart illustrating the joint delivery route planning method in Embodiment 1 of the present invention;

[0108] Figure 2 This is a simplified schematic diagram of the initial truck-drone joint delivery scheme in Embodiment 1 of the present invention;

[0109] Figure 3 The first embodiment of this invention is a schematic diagram of the actual road network for the initial truck-drone joint delivery scheme;

[0110] Figure 4 This is a flowchart illustrating the ALNS algorithm for solving the truck-drone joint delivery route planning model in Embodiment 1 of the present invention.

[0111] Figure 5 This is a simplified schematic diagram of the optimized truck-drone joint delivery scheme in Embodiment 1 of the present invention;

[0112] Figure 6 This is a schematic diagram of the actual road network for the optimized truck-drone joint delivery scheme in Embodiment 1 of the present invention. Detailed Implementation

[0113] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations thereof. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0114] The term "and / or" simply describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. Additionally, the character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0115] Example 1

[0116] like Figure 1 As shown in this embodiment, the steps of the truck-drone joint delivery route planning method for emergency supplies in urban flooding scenarios are as follows:

[0117] Step S1: Based on road interruption data, material demand at each demand point, maximum payload of the drone, and maximum flight range of the drone, the set of demand points is divided into Class I demand points, Class II demand points, and Class III demand points.

[0118] Step S2: With the objective function of minimizing the latest time when all demand points are served, and with the constraints of demand point access, traffic balance, path coordination, time, load capacity and range, path access order and variable relationships, construct a truck-drone joint delivery route planning model.

[0119] Step S3: In the set of demand points of type II and type III, match a demand point whose low-altitude flight path distance with the demand point of type I is the minimum value, and use it as the take-off point and recovery point of the UAV for the demand point of type I, thus forming a UAV subpath;

[0120] Step S4: Apply the Hybrid Genetic Search Algorithm (HGS-CVRP) to generate truck main routes that satisfy truck load constraints for all Class II and Class III demand points, and combine them with the drone sub-routes generated in Step S3 to form an initial delivery plan.

[0121] Step S5: Combining the initial delivery route scheme generated in step S4, the adaptive large-scale neighborhood search algorithm (ALNS) is applied to further optimize and solve the truck-drone joint delivery route planning model constructed in step S2. The destruction operator and repair operator are executed on the current solution to generate a new solution, continuously reducing the latest delivery time of the demand points in all routes, while ensuring that the truck capacity constraint is not violated throughout the entire optimization process.

[0122] Step S6: Determine whether the new solution generated in step S5 is better than the current solution. If the new solution is better than the current solution, accept the new solution. If the new solution is worse than the current solution, determine whether to accept the new solution according to the Metropolis criterion, and update the current solution and the optimal solution until the number of iterations reaches the maximum number of iterations or the temperature reaches the minimum temperature. Then output the optimal solution as the final joint delivery route scheme. Otherwise, continue iterating.

[0123] In one specific implementation of this embodiment, in step S1, the determination condition for a Class I demand point is that the road at its location is interrupted; the determination condition for a Class II demand point is that the road is passable but the demand for materials is greater than the maximum payload of the UAV or the low-altitude flight path distance to all other demand points that can be used as UAV take-off and landing points is greater than the maximum range of the UAV; the determination condition for a Class III demand point is that the road is passable and the demand for materials is not greater than the maximum payload of the UAV, and the low-altitude flight path distance to at least one other demand point is not greater than the maximum range of the UAV.

[0124] In one specific implementation of this embodiment, in step S2, when modeling the time coordination between trucks and drones, in addition to considering the impact of truck travel time and drone flight time, the impact of drone launch time and recovery time must also be considered. Specifically, it can be described as follows: if a certain demand point is only a drone launch point, the point needs to satisfy: truck departure time = truck arrival time + drone launch duration; if a certain demand point is only a drone recovery point, the point needs to satisfy: truck departure time = max(vehicle arrival time, drone arrival time) + drone recovery duration; if a certain demand point is both a drone launch point and a drone recovery point, the point needs to satisfy: truck departure time = max(truck arrival time, drone arrival time) + drone recovery duration + drone launch duration.

[0125] In one specific implementation of this embodiment, step S3 has the following specific features:

[0126] Step S31: Generate a set of candidate nodes for drones from all Class I demand points, and generate a set of candidate nodes for trucks from all Class II and III demand points.

[0127] Step S32: Prioritize all demand points in the drone candidate set according to the order of material demand from largest to smallest. For the drone candidate node with the highest current priority, select the demand point closest to it in the truck candidate node set as the drone take-off and landing point, construct a drone sub-path between the two, and remove the drone candidate node from the drone candidate set after completing the demand point matching;

[0128] Step S33: Repeat step S32 until the drone candidate set is empty, and finally an independent drone sub-path is constructed for all Class I demand points.

[0129] In one specific implementation of this embodiment, the specific process of step S4 is as follows:

[0130] Step S41: Update the information of the II and III demand points that were matched with the I demand points in step S3. Update the demand quantity of these demand points to the sum of their own demand quantity and the demand quantity of the matched I demand points. In addition, when the truck arrives at these demand points, the flight time of all the drone sub-paths connected to the demand point needs to be added to the truck's arrival time as the truck's departure time.

[0131] Step S42: Input the locations of all Class II and Class III demand points, the updated demand amount, and the truck load weight, and call the Hybrid Genetic Search Algorithm (HGS-CVRP) to generate an initial truck path that satisfies the truck load weight constraint.

[0132] In one specific implementation of this embodiment, in step S5, the combination of the destruction operator and the repair operator constitutes six neighborhood structures, including: swapping two truck access points, removing a truck access point and inserting it into a new position in the truck path, swapping two drone access points, swapping a drone access point with a truck access point, changing a truck access point to be delivered by a drone, and changing a drone access point to be delivered by a truck.

[0133] In one specific implementation of this embodiment, in step S6, the Metropolis criterion calculates the acceptance probability. The formula for determining whether to accept a new solution is as follows:

[0134]

[0135]

[0136] in, The current temperature; This is the current solution; This is a new interpretation; The objective function value of the current solution; The objective function value for the new solution; This is the cooling coefficient.

[0137] When outputting the final joint delivery route plan, it also includes the node access order of each truck main route, the take-off point, service point and collection point of each drone sub-route, and the latest time when all demand points are served.

[0138] Example 2

[0139] This embodiment further illustrates the road-low-altitude collaborative network trajectory planning method for urban flooding disasters using more specific data.

[0140] According to the road-low-altitude cooperative network trajectory planning method for urban flooding disasters proposed in this invention, the final joint delivery route scheme is obtained, and the specific steps are as follows:

[0141] Step 1: Based on road interruption data, demand point information in Table 1, and the maximum payload and maximum range of the UAV, the 40 demand points are automatically classified into three categories: Category I, Category II, and Category III. The classification results are as follows:

[0142] Table 1 Information on each demand point

[0143]

[0144] It should be noted that all demand points in this invention refer to emergency demand points.

[0145] Step 2: Using "minimizing the latest delivery completion time among all demand points" as the objective function, and with constraints such as emergency demand point access constraints, traffic balance constraints, path coordination constraints, time constraints, payload and range constraints, path access order constraints, and variable relationships as conditions, a truck-drone joint delivery route planning model is constructed. The objective function of the truck-drone joint delivery route planning model is specifically expressed as follows:

[0146] ;

[0147] in, This represents the collection of all drones. , It is a constant; This indicates the collection of all trucks. , It is a constant; Indicates truck Reaching the demand point The moment; Indicates from truck Launched drone Reaching the demand point At that moment.

[0148] The constraints are shown in equations (1) to (34):

[0149] The access constraints for emergency demand points are shown in equations (1) to (5):

[0150] (1);

[0151] (2);

[0152] (3);

[0153] (4);

[0154] (5);

[0155] in, Indicates when demand point By truck Delivery time Otherwise, it is 0; Indicates when demand point By truck The drones carried The value is 1 if delivery is required, otherwise it is 0. Represents the set of all demand points. , ; This represents the set of demand points for Class I services that are solely provided by drones. , ; This represents the set of demand points in category II that are served solely by freight trucks. , ; This represents the set of demand points for Category III services provided by trucks or drones. , ; Represents the final set. , Represents the final distribution center; Represents the starting set, 0 represents the starting distribution center; Indicates from truck UAV launched from above At the point of demand Takeoff, service demand points And at the point of demand It is 1 when it is recycled, and 0 otherwise.

[0156] Constraint (1) (i.e. Formula (1)) indicates that each emergency demand point needs to be served and can only be served once by a truck or drone; Constraint (2) indicates that drones cannot serve Class II emergency demand points that can only be served by trucks; Constraint (3) indicates that trucks cannot serve Class I emergency demand points that can only be served by drones; Constraint (4) indicates that if a drone takes off from an emergency demand point, it must serve only one emergency demand point and then return to the truck. If the drone does not take off from the emergency demand point, it will remain on the truck; Similarly, Constraint (5) indicates that if a drone lands at an emergency demand point, it must serve only one demand point before landing.

[0157] The flow balance constraints are shown in equations (6) to (9):

[0158] (6);

[0159] (7);

[0160] (8);

[0161] (9);

[0162] in, Indicates when truck Moving from the origin distribution center to the demand point It is 1 if it is true, otherwise it is 0; Indicates when truck Both the origin and destination are distribution centers; Indicates when truck From the demand point Move to demand point The value is 1 if it is true, and 0 otherwise. This indicates the total number of trucks involved in the delivery mission. Indicates when truck From the demand point Move to the final delivery center The value is 1 if it is true, and 0 otherwise. Indicates when truck From the demand point Move to demand point It is 1 if it is true, otherwise it is 0.

[0163] Constraint (6) indicates that the number of trucks leaving the emergency delivery center does not exceed the total number of trucks; Constraint (7) indicates that each truck departs from and returns from the emergency delivery center, and the number of trucks departing from the emergency delivery center is equal to the number of trucks returning; Constraint (8) indicates that after a truck leaves the delivery center, it must serve the emergency demand point and cannot return directly to the delivery center; Constraint (9) indicates that the flow of trucks entering and leaving the demand point is conserved, and the number of trucks entering a certain emergency demand point is equal to the number of trucks leaving the demand point.

[0164] The path coordination constraints are shown in equations (10) to (12):

[0165] (10);

[0166] (11);

[0167] (12);

[0168] in, Indicates the starting point emergency delivery center; Indicates from truck UAV launched from above Take off from the originating distribution center, serving demand points And at the point of demand The value is 1 when the item is recycled, and 0 otherwise. This represents the total number of all nodes in the network, including the originating distribution center and the destination distribution center; Indicates when truck From the demand point Move to demand point The value is 1 if it is true, and 0 otherwise. Indicates when truck From the demand point Move to demand point The value is 1 if it is true, and 0 otherwise. Indicates when truck From the demand point Move to demand point The value is 1 if it is true, and 0 otherwise. Indicates truck Demand points in the path The sequence number; Indicates truck Demand points in the path The sequence number;

[0169] Constraint (10) indicates that if the drone departs from the emergency demand point Take off, and If the vehicle is recycled, it must visit an emergency demand point in its route. and Constraint (11) indicates that if the drone takes off from the starting point and is at the emergency demand point... If it is recycled, it must be accessed in the truck route. Constraint (12) indicates that if the drone departs from the emergency demand point Take off and at the emergency demand point If it is recycled, the truck must be visited Previous visit .

[0170] The time constraints are shown in equations (13) to (21):

[0171] (13);

[0172] (14);

[0173] (15);

[0174] (16);

[0175] (17);

[0176] (18);

[0177] (19);

[0178] (20);

[0179] (twenty one);

[0180] in, Indicates truck Reaching the demand point The moment; Indicates from truck Launched drone Reaching the demand point The moment; Indicates from truck Launched drone Reaching the demand point The moment; Indicates truck Leaving the point of demand The moment; Indicate demand points and demand points The weight of the road layer connections between them, i.e., the travel time of trucks between demand points; Represents a very large positive number ( It is a common "large" in mathematical modeling The "Big-M method" constant is a sufficiently large positive constant whose value must be greater than the upper limit of all possible values ​​of the time variables in the model, used to relax the constraint when the decision variable is 0. Indicates from truck Launched drone Leaving the point of demand The moment; Indicates the time required to launch the drone; Indicates from truck Launched drone Reaching the demand point The moment; Indicates the time required to recover the drone; Indicates truck Leaving the point of demand The moment; Indicates truck Reaching the demand point The moment; Indicates from truck UAV launched from above At the point of demand Takeoff, service demand points And at the point of demand i is 1 when it is recycled, otherwise it is 0; This indicates the weight of the inter-layer connections, i.e., the time of the drone's vertical takeoff and landing; Indicate demand points and demand points The weight of the low-altitude layer connections between them, i.e., the flight time of the drone between the demand points; Indicates from truck Launched drone Leaving the point of demand The moment; Indicate demand points and demand points Weights of low-altitude layer connections between them.

[0181] Constraint (13) states that the initial time of all trucks departing from the emergency delivery center is 0; Constraint (14) states that the times when trucks and drones arrive at each emergency demand point and the emergency delivery center are greater than 0; Constraint (15) states that the departure time of a drone at any emergency demand point should not be earlier than its arrival time; Constraint (16) states that if a truck departs from an emergency demand point... Drive to So, at emergency demand points, trucks departure time and Between the arrival time of the drone, the travel time must be satisfied; constraint (17) means that at the drone launch point, the drone's takeoff time is no earlier than the time when the drone launch is completed after the truck arrives; constraint (18) means that at the drone recovery point, the truck's departure time is no earlier than the time when the drone is recovered after it arrives; constraint (19) means that the truck's departure time from a certain emergency demand point is no earlier than the time after arriving at that point and completing possible drone launch and recovery operations; constraint (20) means that between the drone's takeoff time at the launch point and the time it arrives at the service demand point, the travel time must be satisfied; constraint (21) means that between the time the drone leaves the service demand point and the time it arrives at the landing point, the travel time must be satisfied.

[0182] The payload and range constraints are shown in equations (22) to (24):

[0183] (twenty two);

[0184] (twenty three);

[0185] (twenty four);

[0186] in, Indicate demand points Demand; Indicates when demand point By truck The drones carried The value is 1 if delivery is required, otherwise it is 0. Indicate demand points Demand; Indicates truck Maximum load capacity; Indicates when demand point By truck The drones carried The value is 1 if delivery is required, otherwise it is 0. Indicates drone Maximum load capacity; Indicates drone Maximum range; Indicates drone Level flight speed; Indicates drone The rate of ascent / descent.

[0187] Constraint (22) states that the total demand at all emergency demand points on each truck route must be less than or equal to the maximum load capacity of the truck; Constraint (23) states that the demand at emergency demand points for drone services must be less than or equal to the maximum load capacity of the drone; Constraint (24) states that the demand at emergency demand points for drone services must be less than or equal to the maximum load capacity of the drone; Departure, serving emergency needs points And return to the landing point The total range must be less than or equal to the maximum flight range of the drone.

[0188] The path access order constraints are shown in equations (25) to (31):

[0189] (25);

[0190] (26);

[0191] (27);

[0192] (28);

[0193] (29);

[0194] (30);

[0195] (31);

[0196] in, Represents any demand point The access sequence number; Indicates when truck Traversing the required points in the path The value is 1 if the starting distribution center has been traversed, otherwise it is 0. Indicates when truck Traversing distribution centers in the path Previously, the requirements were traversed. The value is 1 if it is true, and 0 otherwise. Indicates when truck Traversing the required points in the path Previously, the requirements were traversed. The value is 1 if it is true, and 0 otherwise. Indicates when truck Traversing the required points in the path Previously, the requirements were traversed. The value is 1 if it is true, and 0 otherwise.

[0197] Constraints (25) and (26) ensure that the order in which trucks visit emergency demand points is correct; constraints (27) and (28) ensure that the order of visits to emergency demand points is correct and avoid vehicle backflow; constraint (29) specifies the range of sequence numbers of emergency demand points; constraints (30) and (31) indicate that the emergency delivery center needs to be the starting point and end point of each truck route.

[0198] The relationships between the variables are shown in equations (32) to (34):

[0199] (32);

[0200] (33);

[0201] (34);

[0202] in, Indicates when demand point By truck The drones carried The value is 1 if the item is delivered, otherwise it is 0.

[0203] Constraint (32) indicates that if the emergency demand point By truck Access, then there is the possibility of trucks from emergency demand points The starting path; constraint (33) indicates if the emergency demand point By truck If the visit occurs, there is a possibility that a truck will arrive at the emergency demand point. The path; constraint (34) indicates if the emergency demand point By truck Launched drone Access could allow drones to reach emergency demand points. The path.

[0204] Step 3: For the 7 Class I demand points identified in Step 1, match the demand point with the smallest low-altitude flight path distance from the Class II and Class III demand points, and use it as the takeoff and recovery point to construct the UAV subpath. The matched UAV subpath results are as follows: {33,5,33}, {7,14,7}, {16,28,16}, {23,39,23}, {15,17,15}, {22,29,22}, {36,25,36}, as shown below. Figure 2 As shown.

[0205] It should be noted that, taking the drone path {33,5,33} as an example, the first 33 in the drone path {33,5,33} represents the drone take-off point, the number 5 represents the drone service (access) demand point, and the second 33 represents the drone recovery point.

[0206] Step 4: Apply the Hybrid Genetic Search Algorithm (HGS-CVRP) to plan main truck routes that satisfy truck load constraints for the 33 Class II and Class III nodes defined in Step 1, as well as the distribution center. The resulting initial delivery scheme, i.e., the initial solution path scheme, is as follows: Figure 2 and Figure 3 As shown in Table 2, the initial solution path scheme is proposed.

[0207] Table 2 Initial Solution Path Scheme

[0208]

[0209] Step 5: Based on the set objective function and constraints, three strategies are adopted: node migration (removing a node from the longest path and inserting it into the shortest path, such as the two leftmost paths in Table 2, where Li Jing 2 takes longer and path 1 takes shorter, so a node is removed from path 2 and inserted into path 1), node swapping (swapping nodes between two paths to balance delivery time), and path reconstruction (reordering nodes on a single path). The algorithm iteratively executes six neighborhood structures, and the design of the six neighborhood structures is shown in Table 3.

[0210] Table 3 Neighborhood Structure Design

[0211]

[0212] Step 6: Apply the Adaptive Large-Scale Neighborhood Search (ALNS) algorithm to optimize the initial solution path, continuously reducing the latest delivery time of demand points in all paths, while ensuring that truck capacity constraints are not violated throughout the optimization process. The ALNS algorithm flowchart is shown below. Figure 4 As shown. The optimized delivery scheme generated using the six neighborhood structures in step 5 is as follows. Figure 5 and Figure 6 As shown in Table 4, the optimized solution path scheme is presented.

[0213] The ALNS algorithm in detail:

[0214] (1) Set the initial temperature Minimum temperature Cooling coefficient Maximum number of iterations and reaction parameters Initialize the current temperature Initialize the number of iterations The weights of the destruction and repair operators are initialized to the same value.

[0215] (2) Generate initial solution And calculate the initial solution objective function. Initialize the optimal solution and the current solution as follows: The initialization objective functions for both are also... .

[0216] (3) Select a pair of destruction and repair operators from the neighborhood set according to the operator pair weights, perform the destruction operation to generate a partial solution, and perform the repair operation to generate a new solution. Calculate the objective function of the new solution. .

[0217] (4) Compare the new solution with the current solution. If the new solution is better than the current solution, update the current solution to the new solution. Otherwise, use the Metropolis criterion to judge. Compare the updated current solution with the optimal solution. If the current solution is better than the optimal solution, update the optimal solution. Otherwise, the optimal solution remains unchanged.

[0218] (5) Each A scoring interval is defined, and after the scoring interval ends, the weights of the operator pairs are updated.

[0219] (6) Repeat steps (3)-(5) until the maximum number of iterations or the lowest temperature is reached, at which point the optimal solution is obtained.

[0220] Table 4 Optimized Solution Path Scheme

[0221]

[0222] As shown in the table above, the truck-drone joint delivery route planning method proposed in this invention can ensure the timeliness of material delivery in urban flooding emergency scenarios. In emergency scenarios where roads are blocked due to flooding and traditional trucks cannot pass, the two-stage strategy of "first constructing the drone sub-path, then constructing the truck main path" solves the problem of traditional algorithms failing due to the inability to access isolated demand points, thus generating a feasible initial delivery plan. Based on this, by establishing a truck-drone joint delivery route planning model and using the ALNS algorithm to iteratively optimize the initial solution, the efficiency of emergency response is maximized under complex constraints.

[0223] Example 3

[0224] Based on the same inventive concept as Embodiment 1, this embodiment introduces a truck-drone joint delivery route planning system for emergency supplies in urban flooding scenarios, including:

[0225] The demand point classification module is configured to divide the demand point set into three categories: Category I, Category II, and Category III, based on road interruption data, the material demand of each demand point, the maximum payload of the drone, and the maximum flight range of the drone. Category I demand points represent demand points that can only be delivered by drone, Category II demand points represent demand points that can only be delivered by truck, and Category III demand points represent demand points that can be delivered by both truck and drone.

[0226] The delivery route planning model module is configured to input road interruption data, material demand at each demand point, demand point type, maximum payload of the drone, and maximum range of the drone into a pre-built truck-drone joint delivery route planning model.

[0227] The drone sub-path construction module is configured to construct drone sub-paths for Class I demand points that can only be accessed by drones.

[0228] The initial joint delivery route scheme module is configured to use a hybrid genetic search algorithm to generate truck main routes that satisfy truck load constraints for all Class II and Class III demand points, and combine them with the obtained drone sub-routes to form an initial joint delivery route scheme, i.e., the initial solution.

[0229] The new solution generation module is configured to optimize and solve the truck-drone joint delivery route planning model based on the initial joint delivery route scheme using an adaptive large-scale neighborhood search algorithm, thereby generating a new joint delivery route scheme, i.e., generating a new solution.

[0230] The final joint delivery route solution module is configured to determine whether the generated new solution is better than the current solution. If the new solution is better than the current solution, it is accepted. If the new solution is worse than the current solution, it is determined whether to accept the new solution according to the Metropolis criterion, and the current solution and the optimal solution are updated until the number of iterations reaches the maximum number of iterations or the temperature reaches the minimum temperature. Then, the optimal solution is output as the final joint delivery route solution. Otherwise, the iteration continues.

[0231] Example 4

[0232] Based on the same inventive concept as other embodiments, this embodiment introduces a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described truck-drone joint delivery route planning method for emergency supplies in urban flooding scenarios.

[0233] Example 5

[0234] Based on the same inventive concept as other embodiments, this embodiment introduces a computer device, including: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of the above-described truck-drone joint delivery route planning method for emergency supplies in urban flooding scenarios.

[0235] Example 6

[0236] Based on the same inventive concept as other embodiments, this embodiment introduces a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described truck-drone joint delivery route planning method for emergency supplies in urban flooding scenarios.

[0237] This invention addresses the "traffic island" problem and slow delivery time caused by road interruptions in emergency scenarios by constructing a path planning model with the objective of minimizing the latest time for service completion at all demand points. It improves the overall efficiency and response speed of emergency material delivery while overcoming the limitations of conventional logistics models in meeting the "time-priority" requirements of emergencies. First, demand points are categorized based on road interruption data, material demand, and drone performance parameters. A truck-drone joint delivery path planning model is established, considering refined constraints such as drone launch and recovery times. A two-stage strategy of "constructing drone sub-paths first, then constructing truck main paths" is adopted, and an initial solution is generated using a hybrid genetic search algorithm (HGS-CVRP). Second, based on the constructed initial solution, an adaptive large-scale neighborhood search algorithm (ALNS) is applied to iteratively optimize the initial solution, with the optimization objective being to minimize the latest delivery time among all demand points. During the optimization process, when a new solution is inferior to the current solution, the Metropolis criterion is used to determine whether to accept the new solution until the iteration stops, maximizing emergency response efficiency while satisfying complex constraints.

[0238] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0239] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0240] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0241] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0242] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other modifications under the guidance of the present invention, and these modifications are all within the protection scope of the present invention.

Claims

1. A method for planning the joint delivery route of emergency supplies by trucks and drones in urban flooding scenarios, characterized in that, include: Based on road interruption data, material demand at each demand point, maximum payload of drones, and maximum flight range of drones, the demand point set is divided into three categories: Category I, Category II, and Category III. Category I demand points represent those that can be delivered by drones only, Category II demand points represent those that can be delivered by trucks only, and Category III demand points represent those that can be delivered by both trucks and drones. Input the road interruption data, the material demand at each demand point, the type of demand point, the maximum payload of the drone, and the maximum flight range of the drone into the pre-built truck-drone joint delivery route planning model; For Category I demand points that can only be accessed by drones, construct drone sub-paths; A hybrid genetic search algorithm is used to generate truck main routes that satisfy the truck load constraints for all Class II and Class III demand points. These routes are then combined with the obtained drone sub-routes to form an initial joint delivery route scheme, i.e., the initial solution. Based on the initial joint delivery route plan, an adaptive large-scale neighborhood search algorithm is used to optimize and solve the truck-drone joint delivery route planning model, generating a new joint delivery route plan, i.e., generating a new solution. Determine whether the generated new solution is better than the current solution. If the new solution is better than the current solution, accept the new solution. If the new solution is worse than the current solution, determine whether to accept the new solution according to the Metropolis criterion, and update the current solution and the optimal solution. Continue until the number of iterations reaches the maximum number of iterations or the temperature reaches the minimum temperature. Then output the optimal solution as the final joint delivery route scheme. Otherwise, continue iterating.

2. The truck-drone joint delivery route planning method for emergency supplies in urban flooding scenarios according to claim 1, characterized in that: Based on road interruption data, material demand at each demand point, maximum payload of UAVs, and maximum flight range of UAVs, the demand points are divided into three categories: Category I, Category II, and Category III, including: The criteria for determining a Class I demand point is that the road at its location is interrupted; the criteria for determining a Class II demand point is that the road is passable but the demand for supplies exceeds the maximum payload of the drone or the low-altitude flight path distance to all other demand points that can serve as take-off and landing points for the drone exceeds the maximum range of the drone; the criteria for determining a Class III demand point is that the road is passable and the demand for supplies does not exceed the maximum payload of the drone, while the low-altitude flight path distance to at least one other demand point does not exceed the maximum range of the drone.

3. The truck-drone joint delivery route planning method for emergency supplies in urban flooding scenarios according to claim 1, characterized in that: The process of constructing drone sub-paths for Class I demand points that can only be accessed by drones includes: matching a demand point in the sets of Class II and Class III demand points that has the minimum low-altitude track distance to a certain Class I demand point, and using it as the drone take-off and recovery point for that Class I demand point, thus obtaining a drone sub-path, and then obtaining all drone sub-paths for Class I demand points.

4. The truck-drone joint delivery route planning method for emergency supplies in urban flooding scenarios according to claim 1, characterized in that: The method for constructing the truck-drone joint delivery route planning model is as follows: With the objective function of minimizing the latest time for all demand points to be served, and with constraints such as demand point access, traffic balance, path coordination, time, truck load capacity, drone range, path access order, and variable relationships, a truck-drone joint delivery path planning model is constructed.

5. The truck-drone joint delivery route planning method for emergency supplies in urban flooding scenarios according to claim 4, characterized in that: The objective function of the truck-drone joint delivery route planning model is expressed as follows: ； in, This represents the collection of all drones. , It is a constant; This indicates the collection of all trucks. , It is a constant; Indicates truck Reaching the demand point The moment; Indicates from truck Launched drone Reaching the demand point At that moment.

6. The truck-drone joint delivery route planning method for emergency supplies in urban flooding scenarios according to claim 4, characterized in that: The specific constraints of the truck-drone joint delivery route planning model are as follows: The access constraints for emergency demand points are shown in equations (1) to (5): （1）； （2）； （3）； （4）； （5）； in, Indicates when demand point By truck When delivering Otherwise, it is 0; Indicates when demand point By truck The drones carried The value is 1 if delivery is made, otherwise it is 0. Represents the set of all demand points. , ; This represents the set of demand points for Class I services that are solely provided by drones. , ; This represents the set of demand points in category II that are served solely by freight trucks. , ; This represents the set of demand points for Category III services provided by trucks or drones. , ; Represents the final set. , Represents the final distribution center; Represents the starting set, 0 represents the starting distribution center; Indicates from truck UAV launched from above At the point of demand Takeoff, service demand points And at the point of demand The value is 1 when the item is recycled, and 0 otherwise. The flow balance constraints are shown in equations (6) to (9): （6）； （7）； （8）； （9）； in, Indicates when truck Moving from the origin distribution center to the demand point It is 1 if it is true, otherwise it is 0. Indicates when truck Both the origin and destination are distribution centers; Indicates when truck From the demand point Move to demand point The value is 1 if it is true, and 0 otherwise. This indicates the total number of trucks involved in the delivery mission. Indicates when truck From the demand point Move to the final delivery center The value is 1 if it is true, and 0 otherwise. Indicates when truck From the demand point Move to demand point The value is 1 if it is true, and 0 otherwise. The path coordination constraints are shown in equations (10) to (12): （10）； （11）； （12）； in, Indicates the originating distribution center; Indicates from truck UAV launched from above Take off from the originating distribution center, serving demand points And at the point of demand The value is 1 when the item is recycled, and 0 otherwise. This represents the total number of all nodes in the network, including the originating distribution center and the destination distribution center; Indicates when truck From the demand point Move to demand point The value is 1 if it is true, and 0 otherwise. Indicates when truck From the demand point Move to demand point The value is 1 if it is true, and 0 otherwise. Indicates when truck From the demand point Move to demand point The value is 1 if it is true, and 0 otherwise. Indicates truck Demand points in the path The sequence number; Indicates truck Demand points in the path The sequence number; The time constraints are shown in equations (13) to (21): （13）； （14）； （15）； （16）； （17）； （18）； （19）； （20）； （21）； in, Indicates truck Reaching the demand point The moment; Indicates from truck Launched drone Reaching the demand point The moment; Indicates from truck Launched drone Reaching the demand point The moment; Indicates truck Leaving the point of demand The moment; Indicate demand points and demand points The weight of the road layer connections between them, i.e., the travel time of trucks between demand points; Represents a very large positive number; Indicates from truck Launched drone Leaving the point of demand The moment; Indicates the time required to launch the drone; Indicates from truck Launched drone Reaching the demand point The moment; Indicates the time required to recover the drone; Indicates truck Leaving the point of demand The moment; Indicates truck Reaching the demand point The moment; Indicates from truck UAV launched from above At the point of demand Takeoff, service demand points And at the point of demand i is 1 when it is recycled, otherwise it is 0; This indicates the weight of the inter-layer connections, i.e., the time of the drone's vertical takeoff and landing; Indicate demand points and demand points The weight of the low-altitude layer connections between them, i.e., the flight time of the drone between the demand points; Indicates from truck Launched drone Leaving the point of demand The moment; Indicate demand points and demand points Weights of low-altitude layer connections between them; The cargo load capacity constraint is shown in Equation (23), and the UAV range constraint is shown in Equations (23) to (24): （22）； （23）； （24）； in, Indicate demand points Demand; Indicates when demand point By truck The drones carried The value is 1 if delivery is made, otherwise it is 0. Indicate demand points Demand; Indicates truck Maximum load capacity; Indicates when demand point By truck The drones carried The value is 1 if delivery is made, otherwise it is 0. Indicates drone Maximum load capacity; Indicates drone Maximum range; Indicates drone Level flight speed; Indicates drone Ascent / descent speed; The path access order constraints are shown in equations (25) to (31): （25）； （26）； （27）； （28）； （29）； （30）； （31）； in, Represents any demand point The access sequence number; Indicates when truck Traversing the required points in the path The value is 1 if the starting distribution center has been traversed, otherwise it is 0. Indicates when truck Traversing distribution centers in the path Previously, the requirements were traversed. The value is 1 if it is true, and 0 otherwise. Indicates when truck Traversing the required points in the path Previously, the requirements were traversed. The value is 1 if it is true, and 0 otherwise. Indicates when truck Traversing the required points in the path Previously, the requirements were traversed. The value is 1 if it is true, and 0 otherwise. The relationships between the variables are shown in equations (32) to (34): （32）； （33）； （34）； in, Indicates when demand point By truck The drones carried The value is 1 if the item is delivered, otherwise it is 0.

7. A truck-drone joint delivery route planning system for emergency supplies in urban flooding scenarios, characterized in that, include: The demand point classification module is configured to classify demand points into three categories based on road interruption data, the material demand of each demand point, the maximum payload of the drone, and the maximum range of the drone. Among them, the demand point of category I represents the demand point that can only be delivered by drone, the demand point of category II represents the demand point that can only be delivered by truck, and the demand point of category III represents the demand point that can be delivered by both truck and drone. The joint delivery route output module is configured to input road interruption data, material demand at each demand point, demand point type, maximum payload of the drone, and maximum range of the drone into a pre-built truck-drone joint delivery route planning model to obtain the final joint delivery route plan. The method for constructing the truck-drone joint delivery route planning model is as follows: With the objective function of minimizing the latest time for all demand points to be served, and with constraints such as demand point access, traffic balance, path coordination, time, truck load capacity, drone range, path access order, and variable relationships, a truck-drone joint delivery path planning model is constructed.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the truck-drone joint delivery route planning method for emergency supplies in urban flooding scenarios as described in any one of claims 1 to 6.

9. A computer device, characterized in that, include: Memory, used to store computer programs; A processor is used to execute the computer program to implement the steps of the truck-drone joint delivery route planning method for emergency supplies in urban flooding scenarios as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that: When the computer program is executed by the processor, it implements the steps of the truck-drone joint delivery route planning method for emergency supplies in urban flooding scenarios as described in any one of claims 1 to 6.

Images