Vehicle and drone collaborative delivery path planning method considering heterogeneous vehicle fleet

Abstract

The application discloses a kind of vehicle unmanned plane low-altitude collaborative distribution path planning method considering heterogeneous machine team.First, obtain low-altitude logistics distribution demand data, distribution joint body data of distribution vehicle-heterogeneous unmanned plane, and distribution joint body data of vehicle-heterogeneous unmanned plane for low-altitude logistics distribution, preliminary realize distribution resource allocation;Then, with the shortest total distribution time, total distribution cost is lower as target, establish vehicle-heterogeneous unmanned plane team low-altitude logistics collaborative distribution path optimization model, improve customer all demand distribution timeliness and optimize cost, using improved adaptive neighborhood search algorithm optimization vehicle and unmanned plane low-altitude logistics collaborative distribution path, obtain the overall distribution scheme of terminal logistics demand.The application can be compatible with different models unmanned plane collaborative transportation, so as to face different transportation demand configuration corresponding unmanned plane team combination, save transportation cost, while having good machine-vehicle collaborative path planning solution efficiency.

Description

Technical Field

[0001] This invention relates to the field of route planning and logistics distribution, and specifically to a method for collaborative delivery route planning of vehicles and heterogeneous drones considering heterogeneous fleets. Background Technology

[0002] With the rapid development of e-commerce, the contradiction between the limited logistics capacity of the existing short-distance freight system and the ever-increasing demand for logistics delivery is becoming increasingly prominent. While the traditional vehicle-based transportation mode has a large carrying capacity, it is costly, inefficient, and limited by terrain and transportation infrastructure. Currently, drone technology is gradually being applied to logistics delivery, enabling vehicle-drone collaborative delivery to improve delivery timeliness, reduce costs, and enhance customer satisfaction. Therefore, this invention proposes a multi-vehicle, multi-drone collaborative delivery path planning method considering heterogeneous fleets. Based on the existing logistics transportation network, it aims to achieve the shortest total delivery time and lowest total cost by pairing multiple vehicles and multiple heterogeneous drones for collaborative delivery. Compared with other existing air-ground logistics delivery methods based on vehicle-drone collaboration, the model constructed by this method is compatible with collaborative transportation of different drone models, thus configuring appropriate drone fleet combinations to meet different transportation needs, further saving transportation costs, and possessing good efficiency in solving vehicle-drone collaborative path planning and feasibility in path implementation. Summary of the Invention

[0003] This invention provides a multi-vehicle, multi-drone collaborative delivery route planning method that considers heterogeneous fleets, in order to achieve the goal of minimizing total delivery time and reducing total cost.

[0004] To achieve the above goals, it mainly includes two stages and four main steps:

[0005] A method for low-altitude collaborative delivery path planning between vehicles and drones considering heterogeneous fleets is characterized by comprising the following steps:

[0006] Phase 1: Allocation of Vehicle-Heterogeneous Unmanned Aerial Vehicle Transportation Resources to Meet Basic Transportation Needs

[0007] S1. Obtain the location and demand data of low-altitude logistics distribution center warehouses and customer demand nodes, as well as the data of the delivery consortium composed of vehicles and heterogeneous drones used for low-altitude logistics distribution;

[0008] S2. Based on the location and demand data of customer demand nodes and the delivery consortium data composed of vehicles and heterogeneous drones used for low-altitude logistics delivery, preliminary delivery resource allocation is achieved according to the location distribution and demand of customer demand nodes.

[0009] Phase Two: Vehicle-UAV Transportation Route Planning Based on Detailed Logistics Environment

[0010] S3. To meet all customer needs with the highest delivery timeliness, i.e., the shortest total delivery time and the lowest total cost, we establish a vehicle-heterogeneous drone fleet low-altitude logistics collaborative delivery path optimization model.

[0011] S4. An improved adaptive neighborhood search algorithm is used to solve the low-altitude logistics collaborative delivery path optimization model of vehicle-heterogeneous drone fleet.

[0012] As a further improvement of the present invention, the acquisition of data of the delivery consortium composed of low-altitude logistics delivery vehicles and heterogeneous drones in step S1 includes:

[0013] S101. Each vehicle is equipped with multiple drones for collaborative delivery. The drones are of different types and have different performance parameters such as load capacity and battery life.

[0014] S102. Obtain vehicle delivery data and drone delivery data; the vehicle delivery data includes: the time required for the vehicle to travel from delivery point m to delivery point n, and the time required for the vehicle to serve delivery point m; the drone delivery data includes: the time required for a g-type drone to travel from delivery point m to delivery point n, and the time required for a g-type drone to serve delivery point m.

[0015] As a further improvement of the present invention, the acquisition of delivery consortium data composed of vehicles and heterogeneous drones in step S1 includes: clustering the location information of customer demand nodes to initially determine the demand points served by each vehicle; and determining the type and number of drones loaded on each vehicle based on the logistics delivery needs of the demand points and the performance parameters of the drones, thereby achieving preliminary allocation of delivery resources.

[0016] As a further improvement of the present invention, the construction steps of the vehicle-heterogeneous drone fleet low-altitude logistics collaborative delivery path optimization model in step S3 are as follows:

[0017] S401. Based on the preliminary distribution resource allocation results, each drone departs from the central warehouse along with the vehicle, takes off from any distribution point, completes the delivery task of another customer demand node, and then meets up with the vehicle at other customer demand nodes. After completing all deliveries, the drone and the vehicle return to the central warehouse together, resulting in the shortest overall delivery time and the lowest total cost. The objective function of the vehicle-heterogeneous drone collaborative path problem model is the total delivery time mint and the total cost minr.

[0018] As a further improvement of the present invention, the constraints of the vehicle-heterogeneous drone fleet low-altitude logistics collaborative delivery path optimization model include: customer service attribute constraints, vehicle path constraints, and drone path constraints.

[0019] The constraints of the customer service attributes include:

[0020] use Formula, defining decision variables: Used to determine customers Whether the delivery is made by the drone in a drone trip k∈K of type g; Judge customers Whether to use vehicle number z for delivery, using two decision variables whose sum is 1, ensures that the set of customers served by vehicle or drone is served only once;

[0021] The path constraints of the vehicle include:

[0022] The constraints include: a vehicle departing from the distribution center once and returning to the distribution center once after delivery; each customer point being served by a vehicle at most once; eliminating the constraint of sub-loops in the vehicle's travel path; ensuring that there is exactly one vehicle delivering to customer point i, and that customer point i can only be delivered by one vehicle; that each customer point i is served once, and that the vehicle's departure time is greater than the sum of its arrival time and service time, thus guaranteeing that the vehicle leaves after fulfilling the customer point's service requirements; and that the drone's return time to the vehicle is earlier than the vehicle's departure time, ensuring the coordinated operation between the vehicle and the drone.

[0023] The UAV path constraints include:

[0024] Determine whether trip k∈K is flown along arc (m,n) by a drone of type g; determine whether customer point i is delivered by a drone of type g in trip k, and ensure that a drone of type g launches or returns only once at a given node; in a trip of a drone of type g, the total weight of packages at all customer points does not exceed the maximum payload of that type of drone; in a trip of a drone of type g, the drone's remaining battery power is sufficient to complete the entire trip and return to the vehicle; in a flight path of a drone of type g, at most one of the drone's landing point and takeoff point is within the set that the vehicle can reach / leave; in a flight path of a drone of type g, a path can only be served by a drone once.

[0025] As a further improvement of the present invention, the objective functions of the vehicle-heterogeneous drone fleet low-altitude logistics collaborative delivery path optimization model are formulated as follows: (The formulas for total delivery time mint and total cost minr are not provided in the original text.)

[0026]

[0027] Where i, j, b, f are the customer meeting point numbers, C is the set of customer meeting points; U is the set of drones, G is the set of drone types; and T is the set of vehicles. Let z be the time required for vehicle number z to travel from the warehouse to node b. Let z be the time required for vehicle number z to travel from node f to the warehouse; Let z be the time required for vehicle number z to travel from node i to node j. Let g be the time required for a drone of type g to travel from node i to node j. The time required to serve point i for vehicle number z; The time required to serve point i for a drone of type g; r T Fuel consumption per unit distance of a vehicle; v Tz The average speed of vehicle numbered z; u g r represents the number of drones of type g; Ug B represents the cost of a single drone of type g; B represents the fixed cost of a single vehicle.

[0028] As a further improvement of the present invention, step S4 employs an improved adaptive neighborhood search algorithm, which includes: solving the vehicle-heterogeneous drone fleet low-altitude logistics collaborative delivery path optimization model through a two-stage improved adaptive neighborhood search algorithm. In the first stage, an initial solution is generated through tabu search, and in the second stage, the locally optimal vehicle and drone low-altitude logistics collaborative delivery path is obtained through the genetic simulated annealing algorithm criterion.

[0029] As a further improvement of the present invention, the first stage of generating an initial solution through tabu search includes:

[0030] S601. Preprocess the relevant parameters of the vehicle-heterogeneous drone fleet low-altitude logistics collaborative delivery path optimization model based on the dataset;

[0031] S602, Add all customer requirement nodes to the set of unvisited nodes;

[0032] S603. Determine whether the customer requirement node has been traversed completely. If yes, proceed to S606; otherwise, proceed to the next step.

[0033] S604. Select a suitable unvisited customer demand node. Based on the node attributes, including the currently selected node, distance from other nodes, and whether it can be accessed by a drone, select a vehicle or drone for delivery.

[0034] S605. Based on the selection result of S604, if the conditions for drone service are met, add the customer demand node to the drone service path; if not, list it in the vehicle service path; mark the node as visited and return to S603.

[0035] S606. End preliminary processing and generate initial solution.

[0036] As a further improvement of the present invention, the second stage, which obtains the locally optimal path for low-altitude logistics collaborative delivery between vehicles and drones using a genetic simulated annealing algorithm criterion, includes:

[0037] S701. The ElimOperato neighborhood search algorithm is used to select the best solution from the initial solutions.

[0038] S702a. Randomly select a drone delivery scheme on a path from the initial solution as scheme p1;

[0039] S702b: Delete plan p1 and reselect the drone type for the delivery route plan;

[0040] S702c: Calculate the importance of customers on path p1 based on three factors: cargo demand, service time window, and distance, and then reorder them. Select drone types for customers on this path according to the customer order. Calculate the time and cost of this path to obtain the current solution. Determine whether to update the initial solution and the optimal solution based on the effect of the new solution.

[0041] S702d, Repeat steps 702a to 702c until the termination iteration condition is met.

[0042] The beneficial effects of this invention are as follows: It proposes an air-ground joint logistics transportation model based on vehicle-machine collaboration and a corresponding fast solution method. A collaborative delivery model is constructed by evaluating the transportation capacity and performance of various types of UAVs and ground vehicles, as well as logistics demand. Then, a domain search algorithm is designed to quickly solve for the vehicle-machine collaborative logistics delivery scheme. Compared with other existing air-ground logistics delivery methods based on vehicle-machine collaboration, the model constructed by this method is compatible with collaborative transportation of different types of UAVs, thus configuring appropriate UAV fleet combinations to meet different transportation needs, further saving transportation costs. It also possesses good efficiency in solving vehicle-machine collaborative path planning and feasibility in path implementation, and is expected to address the current problems of high time and economic costs in "last-mile" terminal logistics transportation. Attached Figure Description

[0043] Figure 1 This is a flowchart of the present invention.

[0044] Figure 2 The diagram shows a vehicle-drone collaborative delivery model.

[0045] Figure 3 A flowchart for improving the adaptive neighborhood search algorithm to solve collaborative delivery paths. Detailed Implementation

[0046] The present invention will be further illustrated below with reference to the accompanying drawings and specific embodiments. It should be understood that the following specific embodiments are for illustrative purposes only and are not intended to limit the scope of the invention.

[0047] As shown in the figure, this invention provides a method for low-altitude collaborative delivery path planning between vehicles and drones considering heterogeneous fleets, comprising the following steps:

[0048] Phase 1: Allocation of Vehicle-Heterogeneous Unmanned Aerial Vehicle Transportation Resources to Meet Basic Transportation Needs

[0049] S1. Obtain the location and demand data of low-altitude logistics distribution center warehouses and customer demand nodes, as well as the delivery consortium data composed of vehicles and heterogeneous drones used for low-altitude logistics distribution;

[0050] S2. Based on the location and demand data of customer demand nodes and the delivery consortium data composed of vehicles and heterogeneous drones used for low-altitude logistics delivery, preliminary delivery resource allocation is achieved according to the location distribution and demand of customer demand nodes.

[0051] Phase Two: Vehicle-UAV Transportation Route Planning Based on Detailed Logistics Environment

[0052] S3. To meet all customer needs with the highest delivery timeliness, i.e., the shortest total delivery time and the lowest total cost, we establish a vehicle-heterogeneous drone fleet low-altitude logistics collaborative delivery path optimization model.

[0053] S4. An improved adaptive neighborhood search algorithm is used to solve the low-altitude logistics collaborative delivery path optimization model of vehicle-heterogeneous drone fleet.

[0054] As a further improvement of the present invention, the acquisition of data of the delivery consortium composed of low-altitude logistics delivery vehicles and heterogeneous drones in step S1 includes:

[0055] S101. Each vehicle is equipped with multiple drones for collaborative delivery. The drones are of different types and have different performance parameters such as load capacity and battery life.

[0056] S102. Obtain vehicle delivery data and drone delivery data; the vehicle delivery data includes: the time required for the vehicle to travel from delivery point m to delivery point n, and the time required for the vehicle to serve delivery point m; the drone delivery data includes: the time required for a g-type drone to travel from delivery point m to delivery point n, and the time required for a g-type drone to serve delivery point m.

[0057] In this embodiment, the acquisition of delivery consortium data composed of low-altitude logistics delivery vehicles and heterogeneous drones in step S1 includes: clustering customer demand nodes by location information to initially determine the demand points served by each vehicle; and determining the type and number of drones loaded on each vehicle based on the logistics delivery needs of the demand points and the performance parameters of the drones, thereby achieving preliminary allocation of delivery resources.

[0058] In this embodiment, the construction steps of the vehicle-heterogeneous drone fleet low-altitude logistics collaborative delivery path optimization model in step S3 are as follows:

[0059] S401. Based on the preliminary distribution resource allocation results, each drone departs from the central warehouse along with the vehicle, takes off from any distribution point, completes the delivery task of another customer demand node, and then meets up with the vehicle at other customer demand nodes. After completing all deliveries, the drone and the vehicle return to the central warehouse together, resulting in the shortest overall delivery time and the lowest total cost. The objective function of the vehicle-heterogeneous drone collaborative path problem model is the total delivery time mint and the total cost minr.

[0060] In this embodiment, the constraints of the vehicle-heterogeneous drone fleet low-altitude logistics collaborative delivery path optimization model include: customer service attribute constraints, vehicle path constraints, and drone path constraints.

[0061] The constraints of the customer service attributes include:

[0062] use Formula, defining decision variables: Used to determine customers Whether the delivery is made by the drone in a drone trip k∈K of type g; Judge customers Whether to use vehicle number z for delivery, using two decision variables whose sum is 1, ensures that the set of customers served by vehicle or drone is served only once;

[0063] The path constraints of the vehicle include:

[0064] The constraints include: a vehicle departing from the distribution center once and returning to the distribution center once after delivery; each customer point being served by a vehicle at most once; eliminating the constraint of sub-loops in the vehicle's travel path; ensuring that there is exactly one vehicle delivering to customer point i, and that customer point i can only be delivered by one vehicle; that each customer point i is served once, and that the vehicle's departure time is greater than the sum of its arrival time and service time, thus guaranteeing that the vehicle leaves after fulfilling the customer point's service requirements; and that the drone's return time to the vehicle is earlier than the vehicle's departure time, ensuring the coordinated operation between the vehicle and the drone.

[0065] The UAV path constraints include:

[0066] Determine whether trip k∈K is flown along arc (m,n) by a drone of type g; determine whether customer point i is delivered by a drone of type g in trip k, and ensure that a drone of type g launches or returns only once at a given node; in a trip of a drone of type g, the total weight of packages at all customer points does not exceed the maximum payload of that type of drone; in a trip of a drone of type g, the drone's remaining battery power is sufficient to complete the entire trip and return to the vehicle; in a flight path of a drone of type g, at most one of the drone's landing point and takeoff point is within the set that the vehicle can reach / leave; in a flight path of a drone of type g, a path can only be served by a drone once.

[0067] In this embodiment, the objective functions of the vehicle-heterogeneous drone fleet low-altitude logistics collaborative delivery path optimization model, namely the total delivery time mint and the total cost minr, are defined as follows:

[0068]

[0069] Where i, j, b, f are the customer meeting point numbers, C is the set of customer meeting points; U is the set of drones, G is the set of drone types; and T is the set of vehicles. Let z be the time required for vehicle number z to travel from the warehouse to node b. Let z be the time required for vehicle number z to travel from node f to the warehouse; Let z be the time required for vehicle number z to travel from node i to node j. Let g be the time required for a drone of type g to travel from node i to node j. The time required to serve point i for vehicle number z; The time required to serve point i for a drone of type g; r T Fuel consumption per unit distance of a vehicle; v Tz The average speed of vehicle numbered z; u g r represents the number of drones of type g; Ug B represents the cost of a single drone of type g; B represents the fixed cost of a single vehicle.

[0070] In this embodiment, step S4 uses an improved adaptive neighborhood search algorithm to solve the problem, which includes: solving the vehicle-heterogeneous drone fleet low-altitude logistics collaborative delivery path optimization model through a two-stage improved adaptive neighborhood search algorithm. In the first stage, an initial solution is generated through tabu search, and in the second stage, the locally optimal vehicle and drone low-altitude logistics collaborative delivery path is obtained through the genetic simulated annealing algorithm criterion.

[0071] In this embodiment, the first stage of generating an initial solution through tabu search includes:

[0072] S601. Preprocess the relevant parameters of the vehicle and drone path model based on the dataset and format them into an acceptable format for algorithm input.

[0073] S602, Based on the network structure of available paths in the ground and airspace, add all customer demand nodes to the set of unvisited nodes, as well as the set of directed arcs between nodes;

[0074] S603. Based on the determined vehicle and heterogeneous drone fleet configuration information, generate an initial feasible solution as the initial path for vehicle-heterogeneous drone collaborative delivery.

[0075] S604. Configure the vehicle-road cooperative path planning cost function: minimize the transportation cost of the vehicle-heterogeneous drone fleet, mainly including time cost and energy consumption cost.

[0076] S605. Initialize the algorithm parameters as follows:

[0077] Initial temperature: The temperature parameter controls the probability of accepting different solutions, affecting the algorithm's ability to explore the search space. The choice of initial temperature affects the algorithm's convergence speed and search quality.

[0078] Cooling rate: The cooling rate determines how the temperature gradually decreases with increasing iterations. A higher cooling rate leads to a rapid decrease in temperature, but may cause the system to get stuck in a local optimum prematurely; a lower cooling rate causes the temperature to decrease slowly, increasing the likelihood of a global search.

[0079] Stopping condition: A maximum number of iterations or a satisfactory solution quality can be defined as the condition for stopping the search to ensure that the algorithm converges to a solution in a finite amount of time.

[0080] S606. Determine whether the customer demand node has been traversed completely. If yes, proceed to S609; otherwise, proceed to the next step.

[0081] S607. Select a suitable unvisited customer demand node. Based on node attributes, such as currently selected nodes, distance from other nodes, and whether it can be accessed by drones, select a vehicle or drone for delivery and calculate the transportation cost function:

[0082] Z = mint + minr

[0083]

[0084] S608. Select the current path node and make random modifications. Select a nearby node to replace the selected node. Based on the calculation results of S607, if the conditions for drone service are met, then decide to add the customer demand node to the drone service path based on the Metropolis criterion, as shown in the following formula; if not, then list it in the vehicle service path; mark the node as visited and return to S606.

[0085] A = e -ΔC / T

[0086] Where A is the probability that the node is accepted, ΔC is the difference between the cost function value of the new solution and the cost function value of the current solution, and T is the current temperature. As the temperature T decreases, the probability of accepting the inferior solution gradually decreases, and the algorithm tends to accept the superior solution, thus realizing the adaptive adjustment of the acceptance threshold of the neighborhood search algorithm.

[0087] S609. End preliminary processing and generate initial solution.

[0088] In this embodiment, the second stage, which uses a genetic simulated annealing algorithm to determine the locally optimal path for low-altitude logistics collaborative delivery between vehicles and drones, includes:

[0089] S701. The ElimOperato neighborhood search algorithm is used to select the best solution from the initial solutions.

[0090] S702a. Randomly select a drone delivery scheme on a path from the initial solution as scheme p1;

[0091] S702b: Delete plan p1 and reselect the drone type for the delivery route plan;

[0092] S702c: Calculate the importance of customers on path p1 based on three factors: cargo demand, service time window, and distance, and then reorder them. Select drone types for customers on this path according to the customer order. Calculate the time and cost of this path to obtain the current solution. Determine whether to update the initial solution and the optimal solution based on the effect of the new solution.

[0093] S702d, Repeat steps 702a to 702c until the termination iteration condition is met.

[0094] The technical means disclosed in this invention are not limited to those disclosed in the above embodiments, but also include technical solutions composed of any combination of the above technical features. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this invention, and these improvements and modifications are also considered within the scope of protection of this invention.

Claims

1. A method for low-altitude collaborative delivery path planning for vehicles and drones considering heterogeneous fleets, characterized in that: Includes the following steps: Phase 1: Allocation of Vehicle-Heterogeneous Unmanned Aerial Vehicle Transportation Resources to Meet Basic Transportation Needs S1. Obtain the location and demand data of low-altitude logistics distribution center warehouses and customer demand nodes, as well as the delivery consortium data composed of vehicles and heterogeneous drones used for low-altitude logistics distribution; S2. Based on the location and demand data of customer demand nodes and the delivery consortium data composed of vehicles and heterogeneous drones used for low-altitude logistics delivery, preliminary delivery resource allocation is achieved according to the location distribution and demand of customer demand nodes. Phase Two: Vehicle-UAV Transportation Route Planning Based on Detailed Logistics Environment S3. To meet all customer needs with the highest delivery timeliness, i.e., the shortest total delivery time and the lowest total cost, we establish a vehicle-heterogeneous drone fleet low-altitude logistics collaborative delivery path optimization model. S4. An improved adaptive neighborhood search algorithm is used to solve the low-altitude logistics collaborative delivery path optimization model of vehicle-heterogeneous drone fleet. The acquisition of data for the delivery consortium consisting of low-altitude logistics delivery vehicles and heterogeneous drones in step S1 includes: S101. Each vehicle is equipped with multiple drones for collaborative delivery. The drones are of different types and have different performance parameters such as load capacity and battery life. S102. Obtain vehicle delivery data and drone delivery data; the vehicle delivery data includes: the time required for the vehicle to travel from delivery point m to delivery point n, and the time required for the vehicle to serve delivery point m; the drone delivery data includes: the time required for a g-type drone to travel from delivery point m to delivery point n, and the time required for a g-type drone to serve delivery point m. The acquisition of data for the delivery consortium consisting of vehicles and heterogeneous drones in step S1 includes: clustering the location information of customer demand nodes to initially determine the demand points served by each vehicle; and determining the type and number of drones loaded on each vehicle based on the logistics delivery needs of the demand points and the performance parameters of the drones, thereby achieving preliminary allocation of delivery resources. The steps for constructing the vehicle-heterogeneous drone fleet low-altitude logistics collaborative delivery path optimization model in step S3 are as follows: S401. Based on the preliminary delivery resource allocation results, each drone departs from the central warehouse along with a vehicle, takes off from any delivery point, completes a delivery task at another customer demand node, and then rejoins the vehicle at other customer demand nodes. After completing all deliveries, the drones and vehicles return to the central warehouse together, minimizing the overall delivery time and reducing the total cost. The objective function of the vehicle-heterogeneous drone collaborative path problem model is the total delivery time. Total cost ; The constraints of the vehicle-heterogeneous drone fleet low-altitude logistics collaborative delivery path optimization model include: customer service attribute constraints, vehicle path constraints, and drone path constraints. The constraints of the customer service attributes include: use Formula, defining decision variables: Used to determine customers Is it in type Drone trip The delivery will be made by the drone. : Judging customers Is it by number The vehicles are used for delivery, using two decision variables and the sum of the results. Ensure that a customer group for a vehicle or drone service is served only once; The path constraints of the vehicle include: Constraints include: a vehicle departing from the distribution center once; a vehicle returning to the distribution center once after delivery; a vehicle serving each customer point at most once; eliminating constraints related to sub-loops in the vehicle's travel path; and ensuring that exactly one vehicle delivers to each customer point. And customer points The attribute is that delivery can only be made by vehicle, and each customer point The constraint that the vehicle leaves after being served once, and the time between the vehicle's arrival and the service time is greater than the sum of the vehicle's arrival and service times, ensures that the vehicle leaves after completing the customer's service request; the constraint that the drone returns to the vehicle before the vehicle leaves, ensures the coordinated operation between the vehicle and the drone. The UAV path constraints include: Determine the itinerary Is it of type The drone flies along the arc (m,n); the customer point is determined. Is it of type The drone will provide delivery service on route k, and ensure that the type is The drone is launched or retrieved only once at a given node; in type During a single trip of the drone, the total weight of packages from all customer points does not exceed the maximum payload capacity of that type of drone; During a particular trip, the drone's remaining battery power was sufficient to complete the entire trip and return to the vehicle; in type... In a given flight path of a drone, at most one of its landing and takeoff points falls within a set that can be reached / departed from by vehicles; in types... In the flight path of a drone, a path can only be served by the drone once; The objective function of the vehicle-heterogeneous drone fleet low-altitude logistics collaborative delivery path optimization model is the total delivery time. Total cost The formulas are divided into: in, The number of the customer meeting point. A collection of customer meeting points; For drones, A collection of drone types; For vehicle assembly; For the number Vehicles from warehouse to node The time required; For the number The vehicles from the node Time required to reach the warehouse; For the number The vehicles from the node To the node The time required; For type Drones from nodes To the node The time required; For the number vehicle service The time required for the point; For type Drone services The time required for the point; Fuel cost per unit distance for a vehicle; For the number The average speed of the vehicles; For type The number of drones; For type The cost of a single drone; The fixed cost per vehicle.

2. The vehicle-UAV low-altitude collaborative delivery path planning method considering heterogeneous fleets as described in claim 1, characterized in that, The improved adaptive neighborhood search algorithm is used in step S4 to solve the problem. It includes solving the vehicle-heterogeneous drone fleet low-altitude logistics collaborative delivery path optimization model through a two-stage improved adaptive neighborhood search algorithm. In the first stage, an initial solution is generated through tabu search. In the second stage, the locally optimal vehicle and drone low-altitude logistics collaborative delivery path is obtained through the genetic simulated annealing algorithm criterion.

3. The vehicle-UAV low-altitude collaborative delivery path planning method considering heterogeneous fleets as described in claim 2, characterized in that, The first stage, which generates an initial solution through tabu search, includes: S601. Preprocess the relevant parameters of the vehicle-heterogeneous drone fleet low-altitude logistics collaborative delivery path optimization model based on the dataset; S602, Add all customer requirement nodes to the set of unvisited nodes; S603. Determine whether the customer requirement node has been traversed completely. If yes, proceed to S606; otherwise, proceed to the next step. S604. Select a suitable unvisited customer demand node. Based on the node attributes, including the currently selected node, distance from other nodes, and whether it can be accessed by a drone, select a vehicle or drone for delivery. S605. Based on the selection result of S604, if the conditions for drone service are met, add the customer demand node to the drone service path; if not, list it in the vehicle service path; mark the node as visited and return to S603. S606. End preliminary processing and generate initial solution.

4. The vehicle-UAV low-altitude collaborative delivery path planning method considering heterogeneous fleets as described in claim 3, characterized in that, The second stage, which uses a genetic simulated annealing algorithm to determine the locally optimal path for collaborative low-altitude logistics delivery between vehicles and drones, includes: S701. The ElimOperator neighborhood search algorithm is used to select the best solution from the initial solutions. S702a. Randomly select a drone delivery scheme along a path from the initial solution as the solution. ; S702b, the solution Delete and reselect the drone type for this delivery route plan; S702c, Path The importance of customers on the path is calculated based on three factors: cargo demand, service time window, and distance. The drone type is then selected for the customers on this path according to the customer ranking. The time and cost of this path are calculated to obtain the current solution. The effect of the new solution is used to determine whether to update the initial solution and the optimal solution. S702d, Repeat steps 702a to 702c until the termination iteration condition is met.

Images