Parcel delivery method, device and equipment based on unmanned aerial vehicle logistics system and storage medium

Abstract

The invention discloses a parcel delivery method, device and equipment based on an unmanned aerial vehicle logistics system and a storage medium, the unmanned aerial vehicle logistics system comprises at least one group of heterogeneous unmanned aerial vehicles and a plurality of delivery sites, and the method comprises the following steps: constructing a task scheduling model; the task scheduling model takes minimization of the maximum completion time of all parcel delivery tasks as a target function, and constructs a multi-dimensional constraint condition set based on the isomerism, flight time limitation and loading capacity constraint of the unmanned aerial vehicle; solving the task scheduling model by adopting a genetic algorithm to generate a high-quality task scheduling scheme meeting the multi-dimensional constraint condition set; and controlling at least one group of heterogeneous unmanned aerial vehicles to execute package loading, path planning and site access according to the task scheduling scheme, and completing the distribution task. Therefore, through mutual cooperation of the task scheduling model and the genetic algorithm, a targeted high-quality task scheduling scheme is provided according to actual conditions, so that the resource utilization rate and the overall distribution efficiency are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicle control, and more particularly, to a package delivery method and device based on an unmanned aerial vehicle logistics system, equipment and a storage medium. BACKGROUND

[0002] With the rapid development of unmanned aerial vehicle technology, unmanned aerial vehicle logistics systems have shown high efficiency and flexibility in scenarios such as express delivery and emergency material delivery. However, in actual applications, how to efficiently schedule multiple heterogeneous unmanned aerial vehicles to quickly complete package delivery tasks remains a key problem to be solved.

[0003] In the prior art, the task scheduling method usually adopts static allocation or simple heuristic rules (such as the nearest neighbor method and the greedy algorithm), which often leads to uneven task allocation, with some unmanned aerial vehicles overloaded or flight time exceeding the limit, while other unmanned aerial vehicles return early, resulting in low resource utilization and limited overall delivery efficiency. SUMMARY

[0004] In view of the above problems, the present application provides a package delivery method and device based on an unmanned aerial vehicle logistics system, which can effectively solve the above problems.

[0005] In a first aspect, the embodiments of the present application provide a package delivery method based on an unmanned aerial vehicle logistics system, applied to an unmanned aerial vehicle logistics system, the unmanned aerial vehicle logistics system comprising at least one group of heterogeneous unmanned aerial vehicles and a plurality of delivery sites. The method comprises: constructing a task scheduling model; the task scheduling model takes minimizing the maximum completion time of all package delivery tasks as the objective function, and constructs a multi-dimensional constraint condition set based on the heterogeneity of the unmanned aerial vehicles, the flight time limit and the load capacity constraint; using a genetic algorithm to solve the task scheduling model to generate a high-quality task scheduling scheme that satisfies the multi-dimensional constraint condition set; and controlling the at least one group of heterogeneous unmanned aerial vehicles to perform package loading, path planning and site access according to the high-quality task scheduling scheme to complete the delivery task.

[0006] In a second aspect, the embodiments of the present application further provide a package delivery device based on a UAV logistics system, applied to the UAV logistics system, the UAV logistics system comprising at least one group of heterogeneous UAVs and a plurality of delivery sites, the device comprising: a construction module configured to construct a task scheduling model; the task scheduling model taking minimizing the maximum completion time of all package delivery tasks as an objective function, and constructing a multi-dimensional constraint condition set based on the heterogeneity, flight time limit and load capacity constraints of the UAVs; a generation module configured to solve the task scheduling model by using a genetic algorithm, and generate a high-quality task scheduling scheme satisfying the multi-dimensional constraint condition set; and a delivery module configured to control the at least one group of heterogeneous UAVs to perform package loading, path planning and site access according to the high-quality task scheduling scheme, and complete the delivery task.

[0007] In a third aspect, the embodiments of the present application further provide a package delivery device, comprising a processor, a memory and one or more application programs; the one or more application programs are stored in the memory and configured to be executed by the processor to implement the above-mentioned package delivery method based on the UAV logistics system.

[0008] In a fourth aspect, the embodiments of the present application further provide a computer-readable storage medium, the computer-readable storage medium storing program codes, wherein the program codes are executed by a processor to perform the above-mentioned package delivery method based on the UAV logistics system based on the UAV logistics system.

[0009] The technical scheme provided by the present application, the UAV logistics system comprises at least one group of heterogeneous UAVs and a plurality of delivery sites, and the package delivery method based on the UAV logistics system comprises: constructing a task scheduling model; the task scheduling model takes minimizing the maximum completion time of all package delivery tasks as an objective function, and constructs a multi-dimensional constraint condition set based on the heterogeneity, flight time limit and load capacity constraints of the UAVs; solving the task scheduling model by using a genetic algorithm, and generating a high-quality task scheduling scheme satisfying the multi-dimensional constraint condition set; and controlling the at least one group of heterogeneous UAVs to perform package loading, path planning and site access according to the task scheduling scheme, and completing the delivery task. Therefore, the task scheduling model and the genetic algorithm cooperate with each other to provide a high-quality task scheduling scheme according to the actual situation, so as to improve the resource utilization rate and the overall delivery efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0010] In order to more clearly illustrate the technical schemes in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, but not all the embodiments. Based on the embodiments of the present application, all other embodiments and drawings obtained by those skilled in the art without creative labor are within the scope of the present application.

[0011] Figure 1 A structural schematic diagram of a UAV logistics system is shown.

[0012] Figure 2 A flowchart of a package delivery method based on a UAV logistics system is shown.

[0013] Figure 3 A structural schematic diagram of a package delivery device based on a UAV logistics system is shown.

[0014] Figure 4 A structural schematic diagram of a package delivery device is shown.

[0015] Figure 5 A structural schematic diagram of a computer-readable storage medium is shown. DETAILED DESCRIPTION

[0016] In order to enable those skilled in the art to better understand the present application, the technical solutions in the present application will be described clearly and completely below with reference to the drawings in the present application.

[0017] With the rapid development of UAV technology, UAV logistics systems have shown high efficiency and flexibility in scenarios such as express delivery and emergency material delivery. However, in actual application, how to efficiently schedule multiple heterogeneous UAVs to quickly complete package delivery tasks is still a key problem to be solved.

[0018] In the prior art, the task scheduling method usually adopts static allocation or simple heuristic rules (such as nearest neighbor method, greedy algorithm), which often leads to uneven task allocation, some UAVs with excessive load or flight time exceeding the limit, and other UAVs returning early, resulting in low resource utilization and limited overall delivery efficiency.

[0019] In order to improve the above problems, the present application provides a package delivery method, device, equipment and storage medium based on a UAV logistics system. The method is applied to a UAV logistics system, which includes at least one group of heterogeneous UAVs and multiple delivery sites, and includes: constructing a task scheduling model; the task scheduling model takes minimizing the maximum completion time of all package delivery tasks as the objective function, and constructs a multi-dimensional constraint condition set based on the heterogeneity of the UAVs, the flight time limit and the load capacity constraint; a genetic algorithm is used to solve the task scheduling model to generate a high-quality task scheduling scheme that meets the multi-dimensional constraint condition set; and the at least one group of heterogeneous UAVs is controlled to perform package loading, path planning and site access according to the task scheduling scheme to complete the delivery task.

[0020] Thus, by the task scheduling model and the genetic algorithm cooperate with each other, a high-quality task scheduling scheme is provided according to the actual situation, so as to improve the resource utilization and the overall distribution efficiency.

[0021] The application provides a UAV logistics system, which comprises at least one set of heterogeneous UAVs and a plurality of distribution sites The heterogeneous UAVs are used to distribute different packages from the starting distribution sites to the corresponding destination sites, and the different heterogeneous UAVs in the UAV logistics system have different flight speeds, load capacities and maximum flight times.

[0022] Exemplarily, please refer to Figure 1 , Figure 1 a structural schematic diagram of a UAV logistics system related to an embodiment of the application is shown, as shown in Figure 1 the UAV logistics system comprises at least one set of heterogeneous UAVs, respectively UAV and UAV , a plurality of distribution sites, respectively starting distribution site , distribution site , distribution site , distribution site and distribution site , and a plurality of packages to be distributed, respectively package , package , package , package and package . UAV is responsible for distributing package from starting distribution site to distribution site , and distributing package from starting distribution site to distribution site ; UAV is responsible for distributing package , package and package from starting distribution site to distribution site , distribution site , distribution site and distribution site .

[0023] In the present application, for the scheduling problem of heterogeneous UAVs in the UAV logistics system, the maximum completion time of the package distribution task is minimized. The heterogeneous UAVs are located at the starting distribution sites a large number of packages in a transfer station (i.e., a transfer station) are distributed to destination stations in a nearby area.

[0024] In the process of path planning for heterogeneous UAVs to deliver packages, different UAVs have different flight speeds, load capacities (which limit the number of packages that can be delivered by a UAV in a single flight) and maximum flight times (which limit the distance of a single flight of a UAV), bringing great challenges to UAV scheduling, specifically: First, UAVs are heterogeneous; second, packages loaded on the same UAV can have different destination stations, so the stop sequence in flight must be determined; finally, because the number of packages at the starting distribution station is large, each UAV may need to perform multiple flights, and the flight sequence for each UAV must be determined.

[0025] In this application, the above problems are solved by using a classic genetic algorithm (GA) ), which can effectively solve the scheduling problem of UAVs in a UAV logistics system and has great advantages in global search capability. Specifically: Please refer to Figure 2 , Figure 2 Fig. 1 shows a flowchart of a package delivery method based on a UAV logistics system according to an embodiment of the present application, which can be applied to the above-mentioned UAV logistics system. As shown in Figure 2 , the package delivery method based on the UAV logistics system can include steps 110 to 130.

[0026] In step 110, a task scheduling model is constructed.

[0027] The task scheduling model takes minimizing the maximum completion time of all package delivery tasks as the objective function, and constructs a multi-dimensional constraint condition set based on the heterogeneity of UAVs, flight time limits and load capacity constraints.

[0028] The flight time limit and load capacity constraint can be determined by the state reporting data of the UAV. In some embodiments, the package delivery method based on the UAV logistics system can further include the following steps: (1) receiving periodic state reporting data from each UAV; (2) determining the flight time limit and load capacity constraint according to the state reporting data.

[0029] ​wherein the state reporting data at least includes one of current geographic position coordinate, flight height, flight speed, remaining power, current payload weight, list of on-board package identifiers, and executed task progress information. In embodiments of the present application, the state reporting data includes current position of the UAV, current payload weight, and maximum allowed payload.

[0030] The flight time limit of the UAV is determined based on real-time distance between the current position of the UAV and the target delivery station. The payload capacity constraint of the UAV is determined by comparing the current payload weight and the maximum allowed payload.

[0031] In the UAV logistics system, there is a station as the starting delivery station (i.e., the transfer station), and delivery stations as express cabinets distributed therein. Any delivery station and the delivery station The distance between any two delivery stations is denoted by .

[0032] Suppose all the packages that need to be delivered are placed at the starting delivery station . The set of packages can be denoted as: The weight and destination of any package in the set of packages are denoted by and , respectively, and . These packages will be delivered to the destinations by a set of UAVs: . All UAVs are initially available at the starting delivery station . The payload capacity, flight speed, and maximum flight time of a UAV are denoted by , and , respectively. The delivery of a package is considered as a delivery task. The UAV logistics system is responsible for generating a scheduling solution for these tasks. A solution that completes all the tasks can be denoted as a set of solutions for each UAV, i.e., . denotes the solution to be executed by a UAV , which consists of a set of flight tasks, i.e., .

[0033] In each flight, a UAV may stop at several delivery stations and drop off some packages at each delivery station. Therefore, a flight can also be denoted as a set of delivery stations, i.e., Drones of the first flight are represented as a triple where, is the time at which the drone arrives at the delivery site from which the package set is to be unloaded.

[0034] In one solution, each package should be assigned to a drone and have a certain completion time, which is determined by the delivery site from which it is loaded and the delivery site at which it is unloaded. The drone logistics system aims to find a feasible solution that minimizes the completion time of all tasks. Illustratively, assume four delivery sites, two drones, a load capacity of = 2 kg, = 5 kg for the two drones, an average speed of = 60 km / h, = 48 km / h, and a maximum flight time of = 0.5 h, = 0.67 h for the two drones, respectively. Initially, there are five packages = 1.5 kg, = 1.1 kg, = 0.7 kg, = 2 kg, = 2.5 kg at the starting delivery site , respectively. Their destinations are = 、 = 、 = 、 = 、 = . denotes the distance between the delivery sites and . Based on the above background, two feasible solutions and are generated. Assume that in the drone delivering packages by two flights and packages , the UAV delivering packages in sequence in one flight , packages and packages . In , the UAV delivering packages by two flights , packages and packages , the UAV delivering packages by one flight and packages . It takes 6 minutes to complete all tasks, the total completion time is 3.5 minutes. Therefore, is superior to , and is taken as a high-quality task scheduling scheme.

[0035] According to the above description and assumptions, it is constructed into a task scheduling model. In a specific embodiment, the objective function is: wherein, “ ” is the number of UAVs, “ ” is the number of flights of the UAV , “ ” is the number of sites visited by the UAV in the th flight, “ ” is the time for the UAV to visit the th delivery site in the th flight, “ ” is a binary variable, which is whether the package is unloaded in this flight.

[0036] In some embodiments, the multi-dimensional constraint condition set at least includes one or more of the flight time sequence constraint condition, the time constraint condition for returning to the starting delivery site, the initial time constraint condition, the initial position constraint condition, the package weight and the UAV load capacity matching constraint condition, the package destination and the UAV flight path matching constraint condition, the single flight load limit constraint condition, the single flight time limit constraint condition, the package allocation integrity constraint condition, and the definition domain constraint condition of the decision variable.

[0037] In one specific implementation, the multi-dimensional constraint set includes flight time sequence constraints, return time constraints to the originating delivery station constraints, initial time constraints, initial location constraints, package weight and drone payload capacity matching constraints, package destination and drone flight path matching constraints, single flight payload limit constraints, single flight time limit constraints, package allocation integrity constraints, and domain constraints for decision variables.

[0038] In one specific implementation, the flight time sequence constraint is as follows: .

[0039] in," "For drones" In the During the second flight, the visit to the The time at each delivery station, "For delivery stations" to delivery station distance, "For drones" Flight speed; In one specific implementation, the time constraint for returning to the originating delivery station is: .

[0040] in," "For drones" In the The start time of the next flight (i.e., the time of departure from the originating delivery station), "For drones" In the The last stop on the flight (i.e., the...) Arrival time at each stop), "For delivery stations" To the originating delivery station The distance; In one specific implementation, the initial time constraint is: ; in," "For drones" The start time of the first flight; In one specific implementation, the initial position constraint is: .

[0041] In one specific implementation, the constraint condition for matching the package weight with the drone's payload capacity is: .

[0042] in," "for the first" The weight of the package, "For drones" Maximum load capacity, "For all packages," There are one or more drones Its maximum load capacity meets the conditions. "For the package" weight No more than drones Maximum load capacity ; In one specific implementation, the constraint condition for matching the package destination with the drone flight path is: .

[0043] in," "For the package" The final delivery location, "For drones" In the The first flight The location of each stop; In one specific implementation, the single-flight payload limit constraint is as follows: .

[0044] In one specific implementation, the single flight time limitation constraint is as follows: .

[0045] in," "For drones" In the The start time of the next flight, "For drones" Maximum flight time.

[0046] In one specific implementation, the package allocation integrity constraint is as follows: .

[0047] In one specific implementation, the domain constraint condition for the decision variable is: .

[0048] In determining the drone flight number (i.e., the...) In the case of the second flight and the unloading dock for delivering packages, the first The objective function can be calculated by the UAV. The time-of-flight order constraint is a recursive formula for calculating the delivery time of the package. The start time of the flight can be recursively calculated by the formula returning the time constraint of the initial distribution site and the initial time constraint. The initial position constraint indicates that the last stop of the UAV flight is the transfer station, i.e. each UAV should return. The package weight and UAV load capacity matching constraint means that no package weight exceeds the load capacity of any UAV. The package destination and UAV flight path matching constraint ensures that the package is delivered to its destination. The single flight load limit constraint limits the total weight of the package loaded in one flight to the load capacity of the UAV. The single flight time limit constraint limits the total duration of one flight to the maximum flight duration of the corresponding UAV. The package allocation integrity constraint and the definition domain constraint of the decision variable ensure that each package can be delivered. Further: In step 120, a genetic algorithm is used to solve the task scheduling model to generate a high-quality task scheduling scheme that satisfies the multi-dimensional constraint set.

[0049] The genetic algorithm is composed of initial population generation, fitness evaluation and genetic operation. The genetic operation mainly includes selection operation, crossover operation and mutation operation.

[0050] The task scheduling model is solved by the genetic algorithm to minimize the completion time of all distribution tasks to obtain a high-quality task scheduling scheme. Specifically, in some embodiments, the step of "using a genetic algorithm to solve the task scheduling model to generate a high-quality task scheduling scheme that satisfies the multi-dimensional constraint set" can include the following steps: (1) encode the potential solution of the task scheduling problem into a chromosome; the chromosome adopts a one-dimensional arrangement form, representing the priority sequence of all tasks to be distributed or destination sites; (2) in the decoding process, according to the priority sequence in the chromosome, combined with the maximum load capacity and maximum flight time constraint of each UAV, a feasible task allocation scheme that satisfies the UAV load and flight time constraint is generated; (3) according to the feasible task allocation scheme, determine the complete flight path of the UAV and its corresponding task completion time; (4) based on the objective function, the maximum value of the task completion time is taken as the fitness value of the corresponding potential solution; (5) in the population evolution process, the selection operation is performed according to the fitness value, combined with the crossover and mutation operation, to generate a new generation of population; (6) after multiple iterations, a high-quality task scheduling scheme is obtained.

[0051] In the embodiments of this application, chromosomes are represented in a two-dimensional matrix form, and the chromosomes are composed of... The sequence consists of several queues, where each queue is a sequence of packages with the same destination. The matrix contains... Line, corresponding There are several destination stations. The size of any row in the two-dimensional matrix is ​​equal to the number of packages at the corresponding destination. To further simplify the representation, a chromosome can be represented by a series of queues, i.e. , ,…, Each queue is assigned a destination and a series of packages to that destination.

[0052] Each chromosome is represented as a series of package allocation queues. In reality, the order of the packages in the allocation queues is determined by the decoding method applied when decoding the chromosome (i.e., the decoding method determines the specific order of the packages in the allocation queues, i.e., the order in which drones should deliver packages to the various delivery stations). Therefore, a chromosome can be simply represented as a series of destination stations, each delivery station corresponding to one or more packages, and the order in which these delivery stations are accessed is determined by the decoding method.

[0053] For example, two chromosomes and Two chromosomes and Packages on the same line have the same destination site.

[0054] ; ; in," "This is the first package," "This is the second package," "For the third package,..." "This is the 9th package."

[0055] To generate a feasible task allocation scheme, a decoding method is used to allocate packages to drones based on the priorities given by the chromosome. Specifically, in some implementations, the step "during the decoding process, allocating packages to drones according to the priority sequence represented by the chromosome to generate a feasible task allocation scheme that satisfies the drone's payload and flight time constraints" may include the following steps: (1) Determine the priority of the UAV based on its return time and load capacity, and arrange the UAVs according to their priority to form a UAV priority queue; (2) converting the chromosomes in two-dimensional matrix form into a plurality of package distribution queues by rows; each row in the package distribution queue corresponds to a destination station, and the arrangement order of the packages in each row represents the delivery priority of the package at the station; (3) in each roulette selection strategy, selecting a target package distribution queue from the plurality of package distribution queues, and selecting the currently highest priority available UAV from the UAV priority queue to perform task allocation; (4) repeatedly executing the roulette selection strategy to dynamically allocate the tasks in the target package distribution queue to the selected UAV, and generating a feasible task allocation scheme.

[0056] The priority of the UAV is a two-element tuple composed of two values, i.e., the priority of the UAV is a two-element tuple composed of the return time and the load capacity. Among them, the return time refers to the time for the UAV to complete the currently allocated task and return to the starting distribution station (initially usually set to zero). If the load capacities of two UAVs are the same, the UAV with the earlier return time has a higher priority.

[0057] The roulette selection strategy is repeatedly executed until all the tasks in the package distribution queue are allocated. For example, in the first iteration, if the package distribution queue is not empty, the package distribution queue is selected as the target package distribution queue, and then part or all of the packages in the target package distribution queue are allocated to the UAV with the highest priority in the UAV priority queue. It is worth noting that if all the packages in the target package distribution queue are allocated to the UAV, if the current UAV still has remaining loading space after completing the loading of the packages in this iteration, the UAV continues to select packages from other non-empty package distribution queues for loading until the UAV cannot accommodate more packages. When the UAV completes the loading of a flight task and is full, its priority is updated according to its predicted return time, and it is reinserted into the UAV priority queue to participate in subsequent task allocation.

[0058] Based on the start and end times and path information of each flight task in the generated feasible task allocation scheme, the maximum completion time of all tasks is calculated, and the maximum completion time is returned as the fitness value of the individual. The fitness value is used to measure the overall execution efficiency of the feasible task allocation scheme, and the smaller the fitness value, the shorter the completion time of all tasks. The genetic algorithm selects, crosses and mutates the individuals in the population according to their fitness values, preferentially retains individuals with higher fitness values, thereby guiding the population to evolve in the direction of reducing the maximum completion time, and gradually approaching a high-quality task scheduling scheme.

[0059] After obtaining the feasible task allocation scheme, a task sequence for each UAV to visit is determined according to the feasible task allocation scheme, and a complete flight path and corresponding task completion time are calculated based on the distance matrix between sites and flight speed parameters. The goodness of each chromosome is measured by determining the fitness value. During the evolution of the population, selection operation is performed according to the fitness value, combined with crossover and mutation operations to generate a new generation of population. Specifically: Firstly, since the initial population is the starting point of the iterative optimization of the genetic algorithm, its diversity and solution quality affect the convergence speed of the genetic algorithm and the performance of the high-quality task scheduling scheme to some extent. Based on this, the application first provides a way to obtain an initial population with high diversity and high quality. Specifically, three generation methods are used to generate the initial population. Specifically, the three methods include: a method based on the traveling salesman problem (TSP) (used to generate a more reasonable path planning), a local search (LS) method (used to quickly find some better local optimal solutions), and a random method (used to randomly generate some chromosomes as part of the initial population to ensure the diversity of the population). Specifically: In one specific embodiment, the traveling salesman problem method, the local search method, and the random method contribute 20%, 40%, and 40% to the initial population, respectively. Specifically: The distance matrix (which is calculated according to the geographic coordinates between all sites, which represents the flight distance or time between any two sites), based on the distance matrix, a traveling salesman problem modeling method is used, and a simulated annealing (Simulated Annealing, SA) algorithm is used to optimize the randomly generated initial site visit sequence to find a feasible route that visits each site exactly once and has a shorter total path. The site arrangement order corresponding to the route is encoded as a chromosome, called a TSP chromosome, which is used to constitute 20% of the initial population of the genetic algorithm.

[0060] In the local search method, the TSP chromosome is used as the initial sequence, and a decoding method with weighted longest match (Weighted Longest Match, WLM) is performed to generate a specific task allocation scheme (i.e. initial solution) as the starting point of local search. Subsequently, a greedy strategy is used to iteratively improve the initial solution: in each step, select the neighborhood operation that can make the fitness value (such as the maximum completion time) decrease until no better solution can be found or the number of iterations exceeds a predetermined threshold.

[0061] The goal of local search is to improve the quality of the initial solution, making it as close as possible to the local optimum. This aligns with the overall goal of the genetic algorithm in optimizing task scheduling schemes—namely, minimizing the maximum completion time of all tasks. Each independent run of the local search yields a best solution corresponding to a sequence of site visits, called a local search chromosome. Through multiple runs, a set of high-quality local search chromosomes is generated, collectively forming 40% of the initial population of the genetic algorithm.

[0062] By combining the initial 40% individuals generated by random methods, a complete initial population with both diversity and initial quality is finally formed, which helps the genetic algorithm converge to a high-quality task scheduling scheme more quickly in the subsequent evolution process.

[0063] Thus, we can see that the initial population of the genetic algorithm is generated using a local search method. By selecting TSP chromosomes as the initial sequence, the WLM decoding method is used to generate initial solutions, and the algorithm is iteratively improved in a greedy manner. Finally, a series of high-quality local search chromosomes are obtained. These chromosomes will serve as the initial population members of the genetic algorithm, helping the algorithm converge to a high-quality task scheduling scheme more quickly.

[0064] In the process of population evolution, selection operations are performed based on individual fitness values. Combined with crossover and mutation, a new generation of the population is generated. Through multiple generations of iteration, the task scheduling scheme is gradually optimized, resulting in a high-quality task scheduling scheme. The selection operation is the first step in the genetic algorithm. It is used to select "excellent" individuals from the current population as parents to participate in subsequent crossover and mutation operations. Specifically, in the selection operation, two chromosomes are randomly selected from the current population. and The strategy employed is that the better the fitness, the higher the probability that the chromosome will be selected.

[0065] For example, suppose It is a chromosome. fitness It is a chromosome. The worst fitness value. Then the chromosome... The probability of being selected can be expressed as: ; in," "For from chromosomes" Randomly select a subsequence from the given information.

[0066] The selection operation randomly selects two chromosomes from the current population. and Then, the crossover operation is based on chromosomes. and Generate offspring, specifically: (1) From chromosomes randomly select a sub-sequence from the chromosome randomly select a sub-sequence from the chromosome randomly select a sub-sequence from the chromosome the sub-sequence is the same length as the sequence .

[0067] (2) replace the sub-sequence in the chromosome with the sub-sequence .

[0068] (3) replace the sub-sequence in the chromosome with the sub-sequence .

[0069] replace the sub-sequence in the chromosome with the sub-sequence , the replaced chromosome may have some duplicated genes. Therefore, it is necessary to remove duplicates from the chromosome and fill in the missing genes according to the original order of the chromosome to ensure that the replaced chromosome is a legal solution.

[0070] Similarly, replace the sub-sequence in the chromosome with the sub-sequence , the replaced chromosome may have some duplicated genes. Therefore, it is necessary to remove duplicates from the chromosome and fill in the missing genes according to the original order of the chromosome to ensure that the replaced chromosome is a legal solution.

[0071] After all the new offspring are generated, perform a mutation operation on the entire new population. In the mutation operation, each chromosome has a certain probability of mutating into a new chromosome, although the probability is very low. The probability is set to 1%. A chromosome is mutated by randomly swapping the positions of two genes.

[0072] Through the specific implementation method of the three core operations of selection, crossover and mutation in genetic algorithm, they jointly act on the iterative updating process of the population, gradually optimize the quality of the solution, and finally approach the high-quality task scheduling scheme.

[0073] In step 130, control at least one group of heterogeneous unmanned vehicles to perform package loading, path planning and site access according to the task scheduling scheme, and complete the delivery task.

[0074] The task sequence assigned to each UAV in the high-quality task scheduling scheme is parsed into structured task instructions containing target delivery station sequence, to-be-delivered package identification, estimated load and flight time constraints.

[0075] According to the package list in the task instructions, the automatic sorting system or manual operation terminal is controlled to load the corresponding packages into the cargo hold of the specified UAV, and the total weight of the load is monitored in real time through the built-in weighing sensor to ensure that it does not exceed the maximum load capacity of the UAV.

[0076] Based on the station access sequence in the task instructions, the current UAV position, electronic map data (including obstacles, no-fly zones), weather information (such as wind speed), and flight performance parameters (such as maximum speed, turning radius), a path planning algorithm is called to generate a three-dimensional safe flight path from the starting point, sequentially visiting each target station and finally returning.

[0077] The generated flight path is converted into a sequence of waypoints and sent to the flight control system of the corresponding UAV through a wireless communication link (such as 4G / 5G or a dedicated remote control link); after confirming that the UAV is in normal state, the autonomous flight mode is started, thereby completing the delivery task.

[0078] In some embodiments, the UAV autonomously flies according to the waypoint sequence, performs precise landing or hovering delivery operations when it arrives at each target station; after the delivery is completed, the task status is automatically updated and the "delivered" signal and the remaining power are returned to the central control system. When all UAVs complete their task sequences and safely return, the central control system marks the completion of this delivery task and records key indicators such as actual maximum completion time and energy consumption for subsequent scheduling model optimization.

[0079] Please refer to Figure 3 , Figure 3 A structural diagram of a package delivery device based on a UAV logistics system is shown, which is applied to a UAV logistics system, and the UAV logistics system includes at least one set of heterogeneous UAVs and a plurality of delivery stations. The package delivery device based on the UAV logistics system 200 includes a construction module 210, a generation module 220, and a delivery module 230, specifically: The construction module 210 is configured to construct a task scheduling model. The task scheduling model takes minimizing the maximum completion time of all package delivery tasks as an objective function, and constructs a multi-dimensional constraint condition set based on the heterogeneity of the UAVs, flight time limitations, and load capacity constraints. The generation module 220 is configured to solve the task scheduling model using a genetic algorithm to generate a high-quality task scheduling scheme that satisfies the multi-dimensional constraint condition set. The distribution module 230 is configured to control at least one group of heterogeneous unmanned aerial vehicles to perform package loading, path planning and site access according to the high-quality task scheduling scheme, and complete the distribution task.

[0080] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described device and module can refer to the corresponding process in the foregoing method embodiments, and will not be described here.

[0081] In several embodiments provided in the present application, the coupling or direct coupling or communication connection between the modules displayed or discussed can be indirect coupling or communication connection between some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0082] In addition, each functional module in each embodiment of the present application can be integrated in one processing module, or each module can exist physically independently, or two or more modules can be integrated in one module. The integrated module can be realized in the form of hardware or in the form of a software functional module.

[0083] Please refer to Figure 4 , Figure 4 A structure diagram of a package distribution device provided by an embodiment of the present application is shown, and the package distribution device 300 in the present application can include one or more of the following components: a processor 310, a memory 320, and one or more application programs, wherein the one or more application programs can be stored in the memory 320 and configured to be executed by the one or more processors 310, and the one or more programs are configured to perform the package distribution method based on the unmanned aerial logistics system as described in the foregoing method embodiments.

[0084] The processor 310 can include one or more processing cores. The processor 310 connects various parts within the package delivery device 300 by running or executing instructions, programs, code sets or instruction sets stored in the memory 320, and calling data stored in the memory 320, to perform various functions and process data of the package delivery device 300. Alternatively, the processor 310 can be implemented in at least one of a hardware form of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 310 can be integrated with a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU is mainly used to process operating systems, user interfaces, and application programs; the GPU is used to render and draw display content; and the modem is used to process wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 310, but can be implemented by a separate communication chip.

[0085] The memory 320 can include a random access memory (RAM) and can also include a read-only memory (ROM). The memory 320 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 320 can include a program storage area and a data storage area, wherein the program storage area can store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing each of the method embodiments described below, etc. The data storage area can also store data created by the package delivery device 300 in use.

[0086] Referring to Figure 5 , Figure 5 A structure diagram of a computer readable storage medium provided by an embodiment of the present application is shown, the computer readable storage medium 400 stores program codes, and the program codes can be called and executed by a processor to perform the package delivery method based on the unmanned aerial vehicle logistics system described in the above method embodiments.

[0087] The computer-readable storage medium 400 can be an electronic memory such as a flash memory, EEPROM (electrically erasable programmable read-only memory), EPROM, hard disk or ROM. Alternatively, the computer-readable storage medium 400 comprises a non-transitory computer-readable medium. The computer-readable storage medium 400 has storage space for program code 410 to perform any of the method steps described above. The program code can be read from or written to one or more computer program devices. The program code 410 can be compressed, for example, in a suitable form.

[0088] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than limit the technical solutions of the present application; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for part of the technical features; and these modifications or replacements do not drive the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A package delivery method based on a UAV logistics system, characterized in that, The unmanned logistics system comprises at least one set of heterogeneous unmanned aerial vehicles and a plurality of distribution sites, and the method comprises: constructing a task scheduling model; the task scheduling model takes minimizing the maximum completion time of all package distribution tasks as an objective function, and constructs a multi-dimensional constraint condition set based on the heterogeneity of the unmanned aerial vehicles, flight time limitations and load capacity constraints; solving the task scheduling model by using a genetic algorithm to generate a high-quality task scheduling scheme that satisfies the multi-dimensional constraint condition set; controlling the at least one set of heterogeneous unmanned aerial vehicles to perform package loading, path planning and site access according to the high-quality task scheduling scheme to complete the distribution tasks.

2. The package delivery method based on the unmanned aerial logistics system according to claim 1, wherein, The objective function is: in," "This refers to the number of drones," "For drones" Number of flights, "For drones" In the The number of sites visited during this flight. "For drones" In the During the second flight, the visit to the The time at each delivery station, " is a binary variable, which is a wrapper Whether it was unloaded during that flight. 3.The package delivery method based on the UAV logistics system of claim 1, wherein, The multi-dimensional constraint condition set at least comprises one of a flight time sequence constraint condition, a time constraint condition for returning to a starting distribution site, an initial time constraint condition, an initial position constraint condition, a package weight and unmanned aerial vehicle load capacity matching constraint condition, a package destination and unmanned aerial vehicle flight path matching constraint condition, a single flight load limit constraint condition, a single flight time limit constraint condition, a package distribution integrity constraint condition and a definition domain constraint condition of a decision variable. 4.The package delivery method based on the UAV logistics system of claim 1, wherein, The solving of the task scheduling model by using a genetic algorithm to generate a high-quality task scheduling scheme that satisfies the multi-dimensional constraint condition set comprises: encoding a potential solution of the task scheduling problem into a chromosome; the chromosome adopts a one-dimensional arrangement form and represents an access priority sequence of all to-be-distributed tasks or destination sites; in the decoding process, a feasible task allocation scheme that satisfies the load and flight time constraints of the unmanned aerial vehicles is generated according to the priority sequence in the chromosome, in combination with the maximum load capacity and maximum flight time constraints of each unmanned aerial vehicle; according to the feasible task allocation scheme, a complete flight path of the unmanned aerial vehicle and a corresponding task completion time are determined; based on the objective function, the maximum value in the task completion time is taken as the fitness value of the corresponding potential solution; in the population evolution process, a new generation population is generated by performing selection operation according to the fitness value, in combination with cross and mutation operations; after multiple iterations, the high-quality task scheduling scheme is obtained. 5.The package delivery method based on the UAV logistics system according to claim 4, wherein, The generating of the feasible task allocation scheme that satisfies the load and flight time constraints of the unmanned aerial vehicles in the decoding process according to the priority sequence in the chromosome, in combination with the maximum load capacity and maximum flight time constraints of each unmanned aerial vehicle, comprises: determining the priority of the unmanned aerial vehicle according to the return time and load capacity of the unmanned aerial vehicle, and arranging the unmanned aerial vehicles according to the priority to form an unmanned aerial vehicle priority queue; converting the chromosome in a two-dimensional matrix form into a plurality of package allocation queues by row; each row in the package allocation queue corresponds to a destination site, and the arrangement order of the packages in each row represents the distribution priority of the packages at the site; in each roulette selection strategy, a target package allocation queue is selected from the plurality of package allocation queues, and a currently highest-priority available unmanned aerial vehicle is selected from the unmanned aerial vehicle priority queue to perform task allocation. The roulette selection strategy is repeatedly executed to dynamically allocate tasks in the target package distribution queue to selected drones, thereby generating the feasible task allocation scheme. 6.The package delivery method based on the UAV logistics system according to claim 1, wherein, The method further comprises: receiving periodic state reporting data from each of the drones, the state reporting data including at least one of current geographic position coordinates, flight altitude, flight speed, remaining power, current load weight, onboard package identification list, and executed task progress information; determining the flight time limit and the load capacity constraint based on the state reporting data. 7.The package delivery method based on the UAV logistics system according to claim 3, wherein, The flight time sequence constraint condition is: ； wherein, is the UAV is the time to visit the th delivery site in the th flight, is the distance from the th delivery site to the th delivery site, is the flight speed of the UAV . The time constraint condition for returning to the starting distribution site is: in," "For drones" In the The start time of the next flight (i.e., the time of departure from the originating delivery station), "For drones" In the The last stop on the flight (i.e., the...) Arrival time at each stop), "For delivery stations" To the originating delivery station The distance; The initial time constraint condition is: ； Wherein, ” is a UAV The starting time in the first flight; The initial position constraint condition is: ； The package weight and drone load capacity matching constraint condition is: ； wherein, W is the weight of the nth package, Wmax is the maximum payload capacity of the UAV, W is the weight of the nth package, Wmax is the maximum payload capacity of the UAV, W is the weight of the nth package, Wmax is the maximum payload capacity of the UAV, W is the weight of the nth package, Wmax is the maximum payload capacity of the UAV, W is the weight of the nth package, Wmax is the maximum payload capacity of the UAV, W is the weight of the nth package, Wmax is the maximum payload capacity of the UAV, The package destination and drone flight path matching constraint condition is: ； in," "for the package" The final delivery location, "For drones" In the The first flight The location of each stop; The single flight load limit constraint condition is: ； The single flight time limit constraint condition is: ； Wherein, The maximum flight duration of the UAV The starting time of the first flight The starting time of the second flight The maximum flight duration of the UAV The maximum flight duration of the UAV The package distribution integrity constraint condition is: ； The decision variable definition domain constraint condition is: 。 8.A package delivery apparatus based on a UAV logistics system, characterized in that, The drone logistics system includes at least one set of heterogeneous drones and multiple distribution sites, and the device includes: a construction module for constructing a task scheduling model; the task scheduling model takes minimizing the maximum completion time of all package distribution tasks as an objective function, and constructs a multi-dimensional constraint condition set based on the heterogeneity of the drones, flight time limit, and load capacity constraint; a generation module for solving the task scheduling model using a genetic algorithm to generate a high-quality task scheduling scheme that satisfies the multi-dimensional constraint condition set; a distribution module for controlling the at least one set of heterogeneous drones to perform package loading, path planning, and site access according to the high-quality task scheduling scheme to complete the distribution task.

9. A package delivery apparatus, characterized by, comprise: one or more processors; memory; one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to perform the package distribution method based on the drone logistics system as claimed in any one of claims 1-7.

10. A computer readable storage medium, characterized in that, The computer-readable storage medium stores program code, which can be called and executed by the processor to perform the package distribution method based on the drone logistics system as claimed in any one of claims 1-7.

Images