Method and system for optimizing path of vehicle and drone cooperative delivery

Abstract

The application provides a vehicle and unmanned aerial vehicle cooperative distribution path optimization method and system, and relates to the technical field of path planning.The vehicle information, the unmanned aerial vehicle information, the demand node information and the vehicle restricted area information are acquired; based on the vehicle information, the unmanned aerial vehicle information, the demand node information and the vehicle restricted area information, a vehicle and unmanned aerial vehicle cooperative distribution model is constructed with the shortest operation time of all vehicles returning to the warehouse as the target; the vehicle and unmanned aerial vehicle cooperative distribution model is solved to acquire the optimal vehicle and unmanned aerial vehicle cooperative distribution path.The application provides a vehicle and unmanned aerial vehicle cooperative distribution path optimization method considering the vehicle restricted area, solves the technical problem that the optimized path obtained by the prior art cannot meet the actual demand, realizes specific vehicle and unmanned aerial vehicle cooperative distribution path design for different regional division, meets different distribution demands, and improves the accuracy and feasibility of distribution.

Description

Technical Field

[0001] This invention relates to the field of route planning technology, specifically to a route optimization method and system for collaborative delivery by vehicles and drones. Background Technology

[0002] In recent years, drones have seen significant applications in the delivery of epidemic prevention materials both domestically and internationally. JD.com used drones to deliver supplies to locked-down towns, and SF Express successfully delivered epidemic prevention materials to hospitals using drones, demonstrating the effective application of drones in tiered delivery. Utilizing vehicles equipped with drones can effectively reduce delivery costs, and the ability to reduce delivery time through route planning has attracted increasing attention. Considering the tiered delivery of epidemic prevention materials and the different regional epidemic prevention strategies implemented in affected areas, the collaborative transportation method of vehicles and drones can not only effectively reduce delivery costs but also provide relevant departments with contingency plans for material delivery within areas with different control levels, which has strong practical significance.

[0003] However, existing technologies do not include specific vehicle-machine collaborative delivery route designs for implementing epidemic prevention and control strategies such as different regional divisions, resulting in optimized routes that cannot meet actual needs. Summary of the Invention

[0004] (a) Technical problems to be solved

[0005] To address the shortcomings of existing technologies, this invention provides a method and system for route optimization in collaborative delivery using vehicles and drones, solving the technical problem that the optimized routes derived from existing technologies cannot meet actual needs.

[0006] (II) Technical Solution

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] In a first aspect, the present invention provides a route optimization method for collaborative delivery by vehicles and drones, comprising:

[0009] S1. Obtain vehicle information, drone information, demand node information, and vehicle restricted area information;

[0010] S2. Based on vehicle information, drone information, demand node information, and vehicle restricted area information, a vehicle-machine collaborative delivery model is constructed with the goal of minimizing the running time of all vehicles returning to the warehouse.

[0011] S3. Solve the vehicle-machine collaborative delivery model to obtain the optimal collaborative delivery route between vehicles and drones.

[0012] Preferably, the vehicle-machine collaborative delivery model includes an objective function and constraints; wherein,

[0013] The objective function is to minimize the running time of all vehicles returning to the warehouse, and the expression is as follows:

[0014]

[0015] The constraints include:

[0016]

[0017] Constraint (1) Ensure that every demand point must be accessible by a vehicle or drone;

[0018]

[0019] Constraint (2) ensures the flow constraints of vehicles at the warehouse node;

[0020]

[0021] Constraint (3) ensures traffic balance at demand points;

[0022]

[0023]

[0024] Constraints (4) and (5) respectively ensure the flow balance of the UAV at the take-off node and the landing node;

[0025]

[0026]

[0027] Constraints (6) and (7) ensure that the drones maintain a balance of traffic at the points of demand for providing services;

[0028]

[0029] Constraint (8) is a vehicle capacity constraint, in which there is a one-to-one correspondence between UAVs and vehicles, and k represents the vehicle and UAV with the same sequence number k;

[0030]

[0031] Constraint (9) is a UAV sortie capacity constraint;

[0032]

[0033] Constraint (10) is the flight endurance constraint for UAV flights;

[0034]

[0035]

[0036] Constraints (11) and (12) will align the times of the vehicle and the drone at the takeoff and landing nodes;

[0037]

[0038]

[0039] Constraints (13) and (14) represent the inequalities in the running time of the vehicle and the drone;

[0040]

[0041] Constraint (15) means that the vehicle cannot restrict points within the area;

[0042]

[0043]

[0044] Constraints (16) and (17) indicate that sub-loops are not allowed at customer nodes for vehicle and drone paths;

[0045]

[0046]

[0047] Constraints (18) and (19) represent the value constraints for all variables;

[0048] Where V0 represents the set of warehouse nodes, including the starting point 0(s) and the returning point 0(r); V C K represents the set of customer nodes (in this embodiment of the invention, the customer nodes that require epidemic prevention materials); T K represents a set of vehicles; D V represents a collection of drones; T V represents the set of vehicle service nodes; D V represents the set of drone service nodes; L V represents the set of drone takeoff nodes; R Represents the set of drone landing nodes; R k' V represents the set of k' drone sorties; NT D represents the set of nodes within a restricted region; i Q represents the demand of service node i; M represents the maximum load capacity of the vehicle; q represents the maximum number of vehicles that can be called up; B represents the maximum load capacity of the drone; and q represents the maximum range of the drone. This represents the travel time of vehicle k as it traverses arc (i,j). T represents the time it takes for the drone k' to travel through arc (i,j); i kThis represents the cumulative travel time for vehicle k to reach node i; This represents the cumulative running time of drone k' to node i; This means that if vehicle k serves service point i, then the value is 1; otherwise, it is 0. This means that if drone k' serves point i, then the value is 1; otherwise, it is 0. This indicates that if vehicle k travels from point i to point j, the value is 1; otherwise, it is 0. The expression is 1 if the drone k' travels from point i to point j in its p-th flight, and 0 otherwise, where p∈Rk'.

[0049] Preferably, solving the vehicle-drone collaborative delivery model to obtain the optimal vehicle-drone collaborative delivery route includes:

[0050] The vehicle-drone collaborative delivery model is solved using a two-stage heuristic algorithm. In the first stage, an initial solution is generated using a greedy algorithm. In the second stage, the genetic algorithm is improved by using the tabu search algorithm to obtain the optimal collaborative delivery path between vehicles and drones.

[0051] Preferably, the first stage generates an initial solution using a greedy algorithm, including:

[0052] S301. Preprocess the relevant parameters in the vehicle-machine collaborative delivery model;

[0053] S302. Obtain the execution parameters of the greedy algorithm, including the maximum number of vehicles M and the current number of vehicles m;

[0054] S303, Add all client nodes to the set of inaccessible nodes;

[0055] S304. Find the unvisited node closest to the origin as the drone's first takeoff point;

[0056] S305. Determine whether the customer point has been traversed completely. If yes, execute S315; otherwise, proceed to the next step.

[0057] S306. Find the node closest to the drone from the customers to be served and add it to the drone's path;

[0058] S307. Determine if the drone capacity exceeds the constraint or the drone flight time exceeds the constraint. If so, proceed to the next step; otherwise, add the customer to the drone's service path and mark it as visited, then return to step S305.

[0059] S308. Move the last node of the drone path back to the set of customers to be served to obtain the initial drone path;

[0060] S309. Remove all nodes except the first and last nodes from the vehicle's list of nodes to be visited in the initial drone path.

[0061] S310. Determine whether the customer point has been traversed completely. If yes, proceed to S315; otherwise, proceed to the next step.

[0062] S311. Find the node closest to the vehicle from the customers waiting to be served and add it to the vehicle's path;

[0063] S312. Determine whether the vehicle's capacity exceeds the constraint. If so, proceed to the next step; otherwise, return to S310.

[0064] S313. Move the last node of the vehicle path back to the set of customers to be served to obtain the initial vehicle path.

[0065] S314. The number of vehicles m = m + 1. Determine whether m ≥ M is true. If yes, execute S315. Otherwise, return to S304 and re-plan the path.

[0066] S315. End the greedy algorithm and output the set of initial vehicle paths and initial drone paths as the initial solution.

[0067] Preferably, the second stage uses a tabu search algorithm to improve the genetic algorithm to obtain the optimal vehicle and drone collaborative delivery route, including:

[0068] Before executing the second phase, set the execution parameters of the genetic algorithm, including the maximum number of iterations N and the current number of iterations n;

[0069] S316. Use the initial solution generated in the first stage as the initial population of the genetic algorithm, and initialize the tabu list according to the initial population. The tabu list is used to record the solutions that have been visited.

[0070] S317, n = n + 1, determine whether n ≥ N is true. If yes, execute S326; otherwise, proceed to the next step.

[0071] S318. Through a roulette wheel selection operation, the parent population is selected from the current solution in a random manner according to the fitness value of the solution; where the fitness value is the reciprocal of the objective function in the vehicle-machine collaborative delivery model.

[0072] S319. Perform crossover operations on the parent population to generate a new offspring population by exchanging some genes of the parent population.

[0073] S320. Perform mutation operations on the offspring population to increase the diversity of the population by changing some genes, and obtain the mutated offspring population.

[0074] S321. Compare the fitness values ​​of the mutated offspring population and select the best individual as a candidate solution.

[0075] S322. Determine whether the candidate solution satisfies the contempt criterion. If yes, execute S323; otherwise, execute S324.

[0076] S323. Replace the current optimal solution with a candidate solution, update the tabu list, and return to S317.

[0077] S324. Check if the candidate solution exists in the tabu list. If it does, return to S317; otherwise, proceed to the next step.

[0078] S325. Take the candidate solution as the new current solution, update the tabu list, and return to S317;

[0079] S326. Output the current solution as the optimal solution, and output the total delivery time of the optimal solution.

[0080] Secondly, the present invention provides a route optimization system for collaborative delivery by vehicles and drones, comprising:

[0081] The information acquisition module is used to acquire vehicle information, drone information, demand node information, and vehicle restricted area information.

[0082] The model building module is used to build a vehicle-machine collaborative delivery model based on vehicle information, drone information, demand node information, and vehicle restricted area information, with the goal of minimizing the running time of all vehicles returning to the warehouse.

[0083] The solution module is used to solve the vehicle-drone collaborative delivery model and obtain the optimal collaborative delivery route between vehicles and drones.

[0084] Preferably, the vehicle-machine collaborative delivery model includes an objective function and constraints; wherein,

[0085] The objective function is to minimize the running time of all vehicles returning to the warehouse, and the expression is as follows:

[0086]

[0087] The constraints include:

[0088]

[0089] Constraint (1) Ensure that every demand point must be accessible by a vehicle or drone;

[0090]

[0091] Constraint (2) ensures the flow constraints of vehicles at the warehouse node;

[0092]

[0093] Constraint (3) ensures traffic balance at demand points;

[0094]

[0095]

[0096] Constraints (4) and (5) respectively ensure the flow balance of the UAV at the take-off node and the landing node;

[0097]

[0098]

[0099] Constraints (6) and (7) ensure that the drones maintain a balance of traffic at the points of demand for providing services;

[0100]

[0101] Constraint (8) is a vehicle capacity constraint, in which there is a one-to-one correspondence between UAVs and vehicles, and k represents the vehicle and UAV with the same sequence number k;

[0102]

[0103] Constraint (9) is a UAV sortie capacity constraint;

[0104]

[0105] Constraint (10) is the flight endurance constraint for UAV flights;

[0106]

[0107]

[0108] Constraints (11) and (12) will align the times of the vehicle and the drone at the takeoff and landing nodes;

[0109]

[0110]

[0111] Constraints (13) and (14) represent the inequalities in the running time of the vehicle and the drone;

[0112]

[0113] Constraint (15) means that the vehicle cannot restrict points within the area;

[0114]

[0115]

[0116] Constraints (16) and (17) indicate that sub-loops are not allowed at customer nodes for vehicle and drone paths;

[0117]

[0118]

[0119] Constraints (18) and (19) represent the value constraints for all variables;

[0120] Where V0 represents the set of warehouse nodes, including the starting point 0(s) and the returning point 0(r); V C K represents the set of customer nodes (in this embodiment of the invention, the customer nodes that require epidemic prevention materials); T K represents a set of vehicles; D V represents a collection of drones; T V represents the set of vehicle service nodes; D V represents the set of drone service nodes; L V represents the set of drone takeoff nodes; R Represents the set of drone landing nodes; R k ' represents the set of k drone sorties; V NT D represents the set of nodes within a restricted region; i Q represents the demand of service node i; M represents the maximum load capacity of the vehicle; q represents the maximum number of vehicles that can be called up; B represents the maximum load capacity of the drone; and q represents the maximum range of the drone. This represents the travel time of vehicle k as it traverses arc (i,j). T represents the time it takes for the drone k' to travel through arc (i,j); i k This represents the cumulative travel time for vehicle k to reach node i; This represents the cumulative running time of drone k' to node i; This means that if vehicle k serves service point i, then the value is 1; otherwise, it is 0. This means that if drone k' serves point i, then the value is 1; otherwise, it is 0. This indicates that if vehicle k travels from point i to point j, the value is 1; otherwise, it is 0. The expression is 1 if the drone k' travels from point i to point j in its p-th flight, and 0 otherwise, where p∈Rk'.

[0121] Preferably, solving the vehicle-drone collaborative delivery model to obtain the optimal vehicle-drone collaborative delivery route includes:

[0122] The vehicle-drone collaborative delivery model is solved using a two-stage heuristic algorithm. In the first stage, an initial solution is generated using a greedy algorithm. In the second stage, the genetic algorithm is improved by using the tabu search algorithm to obtain the optimal collaborative delivery path between vehicles and drones.

[0123] Thirdly, the present invention provides a computer-readable storage medium storing a computer program for route optimization in vehicle-drone collaborative delivery, wherein the computer program causes a computer to execute the route optimization method for vehicle-drone collaborative delivery as described above.

[0124] Fourthly, the present invention provides an electronic device, comprising:

[0125] One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs including a route optimization method for performing vehicle and drone collaborative delivery as described above.

[0126] (III) Beneficial Effects

[0127] This invention provides a method and apparatus for route optimization in collaborative delivery using vehicles and drones. Compared with existing technologies, it has the following advantages:

[0128] This invention acquires vehicle information, drone information, demand node information, and vehicle restricted area information. Based on this information, and with the goal of minimizing the return time of all vehicles to the warehouse, a vehicle-drone collaborative delivery model is constructed. The optimal vehicle-drone collaborative delivery route is obtained by solving this model. This invention proposes a route optimization method for vehicle-drone collaborative delivery that considers vehicle restricted areas. It solves the technical problem that optimized routes derived from existing technologies cannot meet actual needs, enabling the design of specific vehicle-drone collaborative delivery routes for different area divisions, satisfying diverse delivery requirements, and improving the accuracy and feasibility of delivery. Attached Figure Description

[0129] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0130] Figure 1 This is a block diagram of a route optimization method for collaborative delivery by vehicles and drones according to an embodiment of the present invention;

[0131] Figure 2 The flowchart shows a two-stage heuristic algorithm.

[0132] Figure 3 This is an example diagram of a collaborative delivery route using vehicles and drones. Detailed Implementation

[0133] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are described clearly and completely. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0134] This application provides a method and system for optimizing delivery routes using vehicles and drones, which solves the technical problem that optimized routes derived from existing technologies cannot meet actual needs. It enables the design of specific vehicle-drone collaborative delivery routes for different regional divisions, meeting different delivery requirements and improving the accuracy and feasibility of delivery.

[0135] The technical solution in this application is to solve the above-mentioned technical problems, and the general idea is as follows:

[0136] The embodiments of this invention propose vehicle delivery restrictions in different regions, which are in line with the process of vehicle-machine collaborative delivery of epidemic prevention materials, can meet different delivery needs, and improve the accuracy and feasibility of delivery.

[0137] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0138] This invention provides a route optimization method for collaborative delivery using vehicles and drones, such as... Figure 1 As shown, the method includes:

[0139] S1. Obtain vehicle information, drone information, demand node information, and vehicle restricted area information;

[0140] S2. Based on vehicle information, drone information, demand node information, and vehicle restricted area information, a vehicle-machine collaborative delivery model is constructed with the goal of minimizing the running time of all vehicles returning to the warehouse.

[0141] S3. Solve the vehicle-machine collaborative delivery model to obtain the optimal collaborative delivery route between vehicles and drones.

[0142] This invention proposes a route optimization method for vehicle-drone collaborative delivery considering vehicle-restricted areas. This method solves the technical problem that the optimized routes derived from existing technologies cannot meet actual needs. It enables the design of specific vehicle-drone collaborative delivery routes for different area divisions, meeting different delivery requirements and improving the accuracy and feasibility of delivery.

[0143] It should be noted that the route optimization method for vehicle and drone collaborative delivery in this embodiment of the invention is not only applicable to epidemic prevention materials, but can also be applied to other application scenarios, such as the delivery of materials in areas where vehicles cannot pass (these areas correspond to the vehicle-restricted areas in this embodiment of the invention).

[0144] The following is a detailed description of each step:

[0145] In step S1, vehicle information, drone information, demand node information, and vehicle restricted area information are obtained. The specific implementation process is as follows:

[0146] Vehicle information includes the number of vehicles, maximum load capacity, and other information.

[0147] The drone information includes the number of drones, drone takeoff points, drone landing points, maximum drone payload, and maximum drone range.

[0148] Demand node information includes the number of demand nodes, their location information, and the demand quantity.

[0149] Vehicle restricted area information includes a set of nodes within the restricted area, which refers to nodes that can only be delivered by drones.

[0150] In step S2, based on vehicle information, drone information, demand node information, and vehicle restricted area information, a vehicle-machine collaborative delivery model is constructed with the goal of minimizing the return time of all vehicles to the warehouse. The specific implementation process is as follows:

[0151] The vehicle-to-machine collaborative delivery model includes an objective function and constraints. Details are as follows:

[0152] The objective function is to minimize the running time of all vehicles returning to the warehouse, and the expression is as follows:

[0153]

[0154] The constraints include:

[0155]

[0156] Constraint (1) Ensure that every demand point must be accessible by a vehicle or drone;

[0157]

[0158] Constraint (2) ensures the flow constraints of vehicles at the warehouse node;

[0159]

[0160] Constraint (3) ensures traffic balance at demand points;

[0161]

[0162]

[0163] Constraints (4) and (5) respectively ensure the flow balance of the UAV at the take-off node and the landing node;

[0164]

[0165]

[0166] Constraints (6) and (7) ensure that the drones maintain a balance of traffic at the points of demand for providing services;

[0167]

[0168] Constraint (8) is a vehicle capacity constraint, in which there is a one-to-one correspondence between UAVs and vehicles, and k represents the vehicle and UAV with the same sequence number k;

[0169]

[0170] Constraint (9) is a UAV sortie capacity constraint;

[0171]

[0172] Constraint (10) is the flight endurance constraint for UAV flights;

[0173]

[0174]

[0175] Constraints (11) and (12) will align the times of the vehicle and the drone at the takeoff and landing nodes;

[0176]

[0177]

[0178] Constraints (13) and (14) represent the inequalities in the running time of the vehicle and the drone;

[0179]

[0180] Constraint (15) is an originality constraint, meaning that the vehicle cannot restrict points within the area;

[0181]

[0182]

[0183] Constraints (16) and (17) indicate that sub-loops are not allowed at customer nodes for vehicle and drone paths;

[0184]

[0185]

[0186] Constraints (18) and (19) represent the value constraints for all variables;

[0187] Where V0 represents the set of warehouse nodes, including the starting point 0(s) and the returning point 0(r); V C K represents the set of customer nodes (in this embodiment of the invention, the customer nodes that require epidemic prevention materials); T K represents a set of vehicles; D V represents a collection of drones; T V represents the set of vehicle service nodes; D V represents the set of drone service nodes; L V represents the set of drone takeoff nodes; R Represents the set of drone landing nodes; R k ' represents the set of k drone sorties; V NT D represents the set of nodes within a restricted region; i Q represents the demand of service node i; M represents the maximum load capacity of the vehicle; q represents the maximum number of vehicles that can be called up; B represents the maximum load capacity of the drone; and q represents the maximum range of the drone. This represents the travel time of vehicle k as it traverses arc (i,j). T represents the time it takes for the drone k' to travel through arc (i,j); i k This represents the cumulative travel time for vehicle k to reach node i; This represents the cumulative running time of drone k' to node i; This means that if vehicle k serves service point i, then the value is 1; otherwise, it is 0. This means that if drone k' serves point i, then the value is 1; otherwise, it is 0. This indicates that if vehicle k travels from point i to point j, the value is 1; otherwise, it is 0. The expression is 1 if the drone k' travels from point i to point j in its p-th flight, and 0 otherwise, where p∈Rk'.

[0188] In step S3, the vehicle-drone collaborative delivery model is solved to obtain the optimal collaborative delivery route between vehicles and drones. The specific implementation process is as follows:

[0189] It should be noted that, in the specific implementation process, the vehicle-machine collaborative delivery model can be solved using various methods. This embodiment of the invention uses a two-stage heuristic algorithm to solve the vehicle-machine collaborative delivery model. The first stage generates an initial solution using a greedy algorithm, and the second stage uses a tabu search algorithm to improve the genetic algorithm, generating collaborative delivery paths for vehicles and drones, ultimately obtaining an excellent vehicle and drone path scheme. For example... Figure 2 As shown, specifically:

[0190] The specific process of generating the initial solution using a greedy algorithm in the first stage includes:

[0191] S301. Preprocess the relevant parameters in the vehicle-machine collaborative delivery model. Preprocessing includes steps such as data conversion.

[0192] S302. Set the execution parameters for the genetic algorithm and obtain the execution parameters for the greedy algorithm. Specifically, this includes:

[0193] The execution parameters of a genetic algorithm include population size, maximum number of iterations N, current number of iterations n, and tabu list length.

[0194] The execution parameters of the greedy algorithm include the maximum number of vehicles M, the current number of vehicles m, and the coordinates of each point.

[0195] S303, Add all client nodes to the set of inaccessible nodes. Specifically, this includes:

[0196] Mark all customers as inaccessible to track which customers have been served and which have not.

[0197] S304. Find the unvisited node closest to the origin as the drone's initial takeoff point. Specifically:

[0198] Selecting the first customer to serve for the drone, choosing the nearest customer can reduce the drone's flight time.

[0199] S305. Determine whether the customer point has been traversed completely. If yes, execute S315; otherwise, proceed to the next step.

[0200] S306. Find the node closest to the drone from the customers to be served and add it to the drone's path;

[0201] S307. Determine if the drone capacity exceeds the constraint or the drone flight time exceeds the constraint. If so, proceed to the next step; otherwise, add the customer to the drone's service path and mark it as visited, then return to step S305.

[0202] S308. Move the last node of the drone path back to the set of customers to be served to obtain the initial drone path;

[0203] S309. Remove all nodes except the first and last nodes from the vehicle's list of nodes to be visited in the initial drone path.

[0204] S310. Determine whether the customer point has been traversed completely. If yes, proceed to S315; otherwise, proceed to the next step.

[0205] S311. Find the node closest to the vehicle from the customers waiting to be served and add it to the vehicle's path;

[0206] S312. Determine whether the vehicle's capacity exceeds the constraint. If so, proceed to the next step; otherwise, return to S310.

[0207] S313. Move the last node of the vehicle path back to the set of customers to be served to obtain the initial vehicle path.

[0208] S314. The number of vehicles m = m + 1. Determine whether m ≥ M is true. If yes, execute S315. Otherwise, return to S304 and re-plan the path.

[0209] S315. End the initial solution algorithm and output the set of initial vehicle paths and initial UAV paths as the initial population.

[0210] The second stage uses a tabu search algorithm to improve the genetic algorithm and generate vehicle-drone collaborative delivery routes. It should be noted that other heuristic algorithms can also be used to generate vehicle-drone collaborative delivery routes in practice; this embodiment uses the genetic algorithm as an example for detailed explanation.

[0211] S316. Initialize the tabu list based on the initial population. The tabu list is used to record solutions that have been visited to prevent the algorithm from getting stuck in local optima or repeatedly visiting the same solution during the search process, thereby improving search efficiency.

[0212] S317, n = n + 1, determine whether n ≥ N is true. If yes, execute S326; otherwise, proceed to the next step.

[0213] S318. Using a roulette wheel selection operation, parent populations are randomly selected from the current solutions based on their fitness values. It should be noted that in the first iteration, the current solution is the initial solution. In this embodiment, the fitness value is the reciprocal of the objective function; the higher the fitness value, the greater the selection probability. The roulette wheel selection operation, by randomly selecting parents based on the fitness values ​​of solutions, ensures that solutions with high fitness values ​​have a higher probability of being selected, while also ensuring that solutions with low fitness values ​​have a certain chance of survival, thereby maintaining population diversity.

[0214] S319. Perform crossover operations on the parent population to generate a new offspring population by exchanging some genes of the parent population.

[0215] S320. Perform mutation operations on the offspring population to increase population diversity by altering some genes, resulting in a mutated offspring population. Mutation operations are used to introduce new genes, breaking the local optima of the existing population, thereby increasing population diversity and search range.

[0216] S321. Compare the fitness values ​​of the mutated offspring population and select the best individual as a candidate solution. The candidate solution is selected from all generated solutions based on a certain evaluation criterion (e.g., fitness value). This ensures that a better solution may be found after each iteration.

[0217] S322. Determine whether the candidate solution satisfies the contempt criterion. If yes, execute S323; otherwise, execute S324.

[0218] S323. Replace the current optimal solution with a candidate solution, update the tabu list, and return to S317.

[0219] S324. Check if the candidate solution exists in the tabu list. If it does, return to S317; otherwise, proceed to the next step.

[0220] S325. Take the candidate solution as the new current solution, update the tabu list, and return to S317;

[0221] S326. Output the current solution as the optimal solution, and output the total delivery time of the optimal solution.

[0222] It should be noted that the optimal solution in the embodiments of the present invention corresponds to the collaborative delivery route of vehicles and drones, such as... Figure 3 As shown.

[0223] This invention also provides a route optimization system for collaborative delivery by vehicles and drones, comprising:

[0224] The information acquisition module is used to acquire vehicle information, drone information, demand node information, and vehicle restricted area information.

[0225] The model building module is used to build a vehicle-machine collaborative delivery model based on vehicle information, drone information, demand node information, and vehicle restricted area information, with the goal of minimizing the running time of all vehicles returning to the warehouse.

[0226] The solution module is used to solve the vehicle-drone collaborative delivery model and obtain the optimal collaborative delivery route between vehicles and drones.

[0227] It is understood that the route optimization device for vehicle and drone collaborative delivery provided in this embodiment of the invention corresponds to the route optimization method for vehicle and drone collaborative delivery described above. The explanation, examples, and beneficial effects of the relevant content can be referred to the corresponding content in the route optimization method for vehicle and drone collaborative delivery, and will not be repeated here.

[0228] This invention also provides a computer-readable storage medium storing a computer program for route optimization in vehicle-drone collaborative delivery, wherein the computer program causes a computer to execute the route optimization method for vehicle-drone collaborative delivery as described above.

[0229] This invention also provides an electronic device, comprising:

[0230] One or more processors;

[0231] Memory; and

[0232] One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs including a route optimization method for performing vehicle and drone collaborative delivery as described above.

[0233] In summary, compared with existing technologies, it has the following beneficial effects:

[0234] 1. This invention proposes a route optimization method for vehicle and drone collaborative delivery considering vehicle-restricted areas. This method solves the technical problem that the optimized routes derived from existing technologies cannot meet actual needs. It enables the design of specific vehicle-drone collaborative delivery routes for different area divisions, meeting different delivery needs and improving the accuracy and feasibility of delivery.

[0235] 2. The heuristic path planning algorithm of this invention can effectively plan the multiple take-off and landing paths of drones during vehicle-machine collaborative delivery, thereby improving the timeliness of delivering epidemic prevention materials.

[0236] 3. The embodiments of the present invention improve the genetic algorithm by using the tabu search algorithm to generate collaborative delivery routes between vehicles and drones. This can efficiently find the optimal solution when the search space is limited, thereby improving the efficiency and quality of route planning.

[0237] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0238] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A route optimization method for collaborative delivery using vehicles and drones, characterized in that, include: S1. Obtain vehicle information, drone information, demand node information, and vehicle restricted area information; S2. Based on vehicle information, drone information, demand node information, and vehicle restricted area information, a vehicle-machine collaborative delivery model is constructed with the goal of minimizing the running time of all vehicles returning to the warehouse. S3. Solve the vehicle-machine collaborative delivery model to obtain the optimal vehicle and drone collaborative delivery route; The vehicle-machine collaborative delivery model includes an objective function and constraints; wherein... The objective function is to minimize the running time of all vehicles returning to the warehouse, and the expression is as follows: The constraints include: （1） Constraint (1) Ensure that every demand point must be accessible by a vehicle or drone; （2） Constraint (2) ensures the flow constraints of vehicles at the warehouse node; （3） Constraint (3) ensures traffic balance at demand points; （4） （5） Constraints (4) and (5) respectively ensure the flow balance of the UAV at the take-off node and the landing node; （6） （7） Constraints (6) and (7) ensure that the drones maintain a balance of traffic at the points of demand for providing services; （8） Constraint (8) is a vehicle capacity constraint, in which there is a one-to-one correspondence between UAVs and vehicles, and k represents the vehicle and UAV with the same sequence number k; （9） Constraint (9) is a UAV sortie capacity constraint; （10） Constraint (10) is the flight endurance constraint for UAV flights; （11） （12） Constraints (11) and (12) will align the times of the vehicle and the drone at the takeoff and landing nodes; （13） （14） Constraints (13) and (14) represent the inequalities in the running time of the vehicle and the drone; （15） Constraint (15) means that the vehicle cannot restrict points within the area; （16） （17） Constraints (16) and (17) indicate that sub-loops are not allowed at customer nodes for vehicle and drone paths; （18） （19） Constraints (18) and (19) represent the value constraints for all variables; in, This represents the set of warehouse nodes, including the starting point 0(s) and the returning point 0(r); Represents a set of client nodes; Indicates a collection of vehicles; Indicates a collection of drones; Represents the set of vehicle service nodes; Represents the set of drone service nodes; This represents the set of drone takeoff nodes; This represents the set of drone landing nodes; Represents the set of drone sorties k'; Represents the set of nodes within a restricted region; Indicates service node i Demand; Indicates the vehicle's maximum load capacity; This indicates the maximum number of vehicles that can be called; Indicates the maximum payload of the drone; This indicates the drone's maximum flight time; This represents the travel time of vehicle k as it traverses arc (i,j). This represents the time it takes for the drone k' to travel through arc (i,j); This represents the cumulative travel time for vehicle k to reach node i; This represents the cumulative running time of drone k' to node i; This means that if vehicle k serves service point i, then the value is 1; otherwise, it is 0. This means that if drone k' serves point i, then the value is 1; otherwise, it is 0. This indicates that if vehicle k travels from point i to point j, the value is 1; otherwise, it is 0. This indicates that if the drone k' travels from point i to point j in its p-th sortie, then the value is 1; otherwise, it is 0, where p∈R. k' .

2. The route optimization method for collaborative delivery by vehicles and drones as described in claim 1, characterized in that, Solving the vehicle-drone collaborative delivery model to obtain the optimal vehicle-drone collaborative delivery route includes: The vehicle-drone collaborative delivery model is solved using a two-stage heuristic algorithm. In the first stage, an initial solution is generated using a greedy algorithm. In the second stage, the genetic algorithm is improved using the tabu search algorithm to obtain the optimal collaborative delivery path between vehicles and drones.

3. The route optimization method for collaborative delivery by vehicles and drones as described in claim 2, characterized in that, The first stage generates an initial solution using a greedy algorithm, including: S301. Preprocess the relevant parameters in the vehicle-machine collaborative delivery model; S302. Obtain the execution parameters of the greedy algorithm, including the maximum number of vehicles M and the current number of vehicles m; S303, Add all client nodes to the set of inaccessible nodes; S304. Find the unvisited node closest to the origin as the drone's first takeoff point; S305. Determine whether the customer point has been traversed completely. If yes, execute S315; otherwise, proceed to the next step. S306. Find the node closest to the drone from the customers to be served and add it to the drone's path; S307. Determine if the drone capacity exceeds the constraint or the drone flight time exceeds the constraint. If so, proceed to the next step; otherwise, add the customer to the drone's service path and mark it as visited, then return to step S305. S308. Move the last node of the drone path back to the set of customers to be served to obtain the initial drone path; S309. Remove all nodes except the first and last nodes from the vehicle's list of nodes to be visited in the initial drone path. S310. Determine whether the customer point has been traversed completely. If yes, proceed to S315; otherwise, proceed to the next step. S311. Find the node closest to the vehicle from the customers waiting to be served and add it to the vehicle's path; S312. Determine whether the vehicle's capacity exceeds the constraint. If so, proceed to the next step; otherwise, return to S310. S313. Move the last node of the vehicle path back to the set of customers to be served to obtain the initial vehicle path. S314. The number of vehicles m = m + 1. Determine whether m ≥ M is true. If yes, execute S315. Otherwise, return to S304 and re-plan the path. S315. End the greedy algorithm and output the set of initial vehicle paths and initial drone paths as the initial solution.

4. The route optimization method for vehicle and drone collaborative delivery as described in claim 2 or 3, characterized in that, The second stage improves the genetic algorithm using the tabu search algorithm to obtain the optimal vehicle and drone collaborative delivery route, including: Before executing the second phase, set the execution parameters of the genetic algorithm, including the maximum number of iterations N and the current number of iterations n; S316. Use the initial solution generated in the first stage as the initial population of the genetic algorithm, and initialize the tabu list according to the initial population. The tabu list is used to record the solutions that have been visited. S317, n=n+1, determine whether n≥N is true. If yes, execute S326; otherwise, proceed to the next step. S318. Through a roulette wheel selection operation, the parent population is selected from the current solution in a random manner according to the fitness value of the solution; where the fitness value is the reciprocal of the objective function in the vehicle-machine collaborative delivery model. S319. Perform crossover operations on the parent population to generate a new offspring population by exchanging some genes of the parent population. S320. Perform mutation operations on the offspring population to increase the diversity of the population by changing some genes, and obtain the mutated offspring population. S321. Compare the fitness values ​​of the mutated offspring population and select the best individual as a candidate solution. S322. Determine whether the candidate solution satisfies the contempt criterion. If yes, execute S323; otherwise, execute S324. S323. Replace the current optimal solution with a candidate solution, update the tabu list, and return to S317. S324. Check if the candidate solution exists in the tabu list. If it does, return to S317; otherwise, proceed to the next step. S325. Take the candidate solution as the new current solution, update the tabu list, and return to S317; S326. Output the current solution as the optimal solution, and output the total delivery time of the optimal solution.

5. A route optimization system for collaborative delivery by vehicles and drones, characterized in that, include: The information acquisition module is used to acquire vehicle information, drone information, demand node information, and vehicle restricted area information. The model building module is used to build a vehicle-machine collaborative delivery model based on vehicle information, drone information, demand node information, and vehicle restricted area information, with the goal of minimizing the running time of all vehicles returning to the warehouse. The solution module is used to solve the vehicle-machine collaborative delivery model and obtain the optimal vehicle and drone collaborative delivery route; The vehicle-machine collaborative delivery model includes an objective function and constraints; wherein... The objective function is to minimize the running time of all vehicles returning to the warehouse, and the expression is as follows: The constraints include: （1） Constraint (1) Ensure that every demand point must be accessible by a vehicle or drone; （2） Constraint (2) ensures the flow constraints of vehicles at the warehouse node; （3） Constraint (3) ensures traffic balance at demand points; （4） （5） Constraints (4) and (5) respectively ensure the flow balance of the UAV at the take-off node and the landing node; （6） （7） Constraints (6) and (7) ensure that the drones maintain a balance of traffic at the points of demand for providing services; （8） Constraint (8) is a vehicle capacity constraint, in which there is a one-to-one correspondence between UAVs and vehicles, and k represents the vehicle and UAV with the same sequence number k; （9） Constraint (9) is a UAV sortie capacity constraint; （10） Constraint (10) is the flight endurance constraint for UAV flights; （11） （12） Constraints (11) and (12) will align the times of the vehicle and the drone at the takeoff and landing nodes; （13） （14） Constraints (13) and (14) represent the inequalities in the running time of the vehicle and the drone; （15） Constraint (15) means that the vehicle cannot restrict points within the area; （16） （17） Constraints (16) and (17) indicate that sub-loops are not allowed at customer nodes for vehicle and drone paths; （18） （19） Constraints (18) and (19) represent the value constraints for all variables; in, This represents the set of warehouse nodes, including the starting point 0(s) and the returning point 0(r); Represents a set of client nodes; Indicates a collection of vehicles; Indicates a collection of drones; Represents the set of vehicle service nodes; Represents the set of drone service nodes; This represents the set of drone takeoff nodes; This represents the set of drone landing nodes; Represents the set of drone sorties k'; Represents the set of nodes within a restricted region; Indicates service node i Demand; Indicates the vehicle's maximum load capacity; This indicates the maximum number of vehicles that can be called; Indicates the maximum payload of the drone; This indicates the drone's maximum flight time; This represents the travel time of vehicle k as it traverses arc (i,j). This represents the time it takes for the drone k' to travel through arc (i,j); This represents the cumulative travel time for vehicle k to reach node i; This represents the cumulative running time of drone k' to node i; This means that if vehicle k serves service point i, then the value is 1; otherwise, it is 0. This means that if drone k' serves point i, then the value is 1; otherwise, it is 0. This indicates that if vehicle k travels from point i to point j, the value is 1; otherwise, it is 0. This indicates that if the drone k' travels from point i to point j in its p-th sortie, then the value is 1; otherwise, it is 0, where p∈R. k' .

6. The route optimization system for vehicle and drone collaborative delivery as described in claim 5, characterized in that, Solving the vehicle-drone collaborative delivery model to obtain the optimal vehicle-drone collaborative delivery route includes: The vehicle-drone collaborative delivery model is solved using a two-stage heuristic algorithm. In the first stage, an initial solution is generated using a greedy algorithm. In the second stage, the genetic algorithm is improved using the tabu search algorithm to obtain the optimal collaborative delivery path between vehicles and drones.

7. A computer-readable storage medium, characterized in that, It stores a computer program for route optimization in vehicle-drone collaborative delivery, wherein the computer program causes a computer to execute the route optimization method for vehicle-drone collaborative delivery as described in any one of claims 1 to 4.

8. An electronic device, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs including a route optimization method for vehicle and drone collaborative delivery as described in any one of claims 1 to 4.

Images