WO2021142917A1

WO2021142917A1 - Multi-depot vehicle routing method, apparatus, computer device and storage medium

Info

Publication number: WO2021142917A1
Application number: PCT/CN2020/079881
Authority: WO
Inventors: 于琪嫄; 刘松柏; 林秋镇; 陈剑勇
Original assignee: 深圳大学
Priority date: 2020-01-15
Filing date: 2020-03-18
Publication date: 2021-07-22
Also published as: CN111260129A; CN111260129B

Abstract

A multi-depot vehicle routing method, comprising: determining whether a routing request sent by a client terminal is received (S110); if a routing request sent by a client terminal is received, acquiring input data and an end condition corresponding to the routing request, the input data corresponding to the routing request comprising a current number of users, a cargo capacity for each user corresponding to the current number of users, and current user position information of each user corresponding to the current number of users (S120); calling a pre-stored vehicle routing multi-objective optimization model, using the input data as input for the vehicle routing multi-objective optimization model, and performing many-objective evolutionary solving according to the end condition and the vehicle routing multi-objective optimization model, obtaining a route optimization solution set (S130); sending the route optimization solution set to the client terminal (S140). Also provided are a multi-depot vehicle routing apparatus, a computer device and a storage medium.

Description

Multi-depot vehicle path planning method, device, computer equipment and storage medium

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on January 15, 2020, the application number is 202010042242.2, and the application name is "Multi-yard vehicle path planning method, device, computer equipment and storage medium", and its entire content Incorporated in this application by reference.

Technical field

This application relates to the technical field of route planning, and in particular to a method, device, computer equipment, and storage medium for multi-yard vehicle route planning.

Background technique

With the vigorous development of e-commerce, the importance of the logistics industry has become more and more prominent. Modern logistics integrates various activities such as information, transportation, warehousing, inventory, and the use of computer technology to scientifically carry out logistics scheduling is still the key to the development of logistics and transportation industries.

For major logistics companies, one of the most important problems they face is how to formulate scientific transportation routes to efficiently meet the distribution needs of customers. Therefore, the planning of vehicle paths is extremely important to the transportation cost and efficiency of the entire logistics system. Impact. With the increasing scale of logistics transportation and the continuous improvement of distribution requirements, it is no longer possible to use the existing path planning methods to carry out optimal path planning in the case of multiple distribution centers.

Summary of the invention

The embodiments of the present application provide a method, device, computer equipment, and storage medium for vehicle path planning in multiple depots, aiming to solve the problem that the prior art cannot quickly and accurately perform optimization when multiple distribution centers are distributed in different areas. The problem of path planning.

In the first aspect, an embodiment of the present application provides a multi-park vehicle path planning method, which includes:

Determine whether the path planning request sent by the client is received;

If the path planning request sent by the client is received, the input data and constraint conditions corresponding to the path planning request are obtained; wherein, the input data corresponding to the path planning request includes the current number of users and each corresponding to the current number of users. The user’s cargo capacity and current user location information for each user corresponding to the current number of users;

Call a pre-stored vehicle path planning multi-objective optimization model, use the input data as the input of the vehicle path planning multi-objective optimization model, and perform a lot of operations on the vehicle path planning multi-objective optimization model according to the constraint conditions and The evolutionary solution of the goal, the optimal solution set of the path is obtained; and

Send the path optimal solution set to the client.

In a second aspect, an embodiment of the present application provides a multi-park vehicle path planning device, which includes a unit for executing the multi-park vehicle path planning method described in the first aspect.

In a third aspect, an embodiment of the present application provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and running on the processor, and the processor executes the computer The program implements the multi-depot vehicle path planning method described in the first aspect.

In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the above-mentioned first On the one hand, the multi-depot vehicle path planning method.

Description of the drawings

In order to explain the technical solutions of the embodiments of the present application more clearly, the following will briefly introduce the drawings used in the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present application. Ordinary technicians can obtain other drawings based on these drawings without creative work.

FIG. 1 is a schematic diagram of an application scenario of a multi-park vehicle path planning method provided by an embodiment of the application;

FIG. 2 is a schematic flowchart of a method for multi-parking vehicle path planning provided by an embodiment of the application;

FIG. 3 is a schematic diagram of a sub-process of a multi-park vehicle path planning method provided by an embodiment of the application;

FIG. 4 is a schematic diagram of another sub-flow of the method for multi-depot vehicle path planning provided by an embodiment of the application;

Fig. 5 is a schematic block diagram of a multi-park vehicle path planning device provided by an embodiment of the application;

Fig. 6 is a schematic block diagram of a computer device provided by an embodiment of the application.

Detailed ways

The technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of them. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

It should be understood that when used in this specification and appended claims, the terms "including" and "including" indicate the existence of the described features, wholes, steps, operations, elements and/or components, but do not exclude one or The existence or addition of multiple other features, wholes, steps, operations, elements, components, and/or collections thereof.

It should also be understood that the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in the specification of this application and the appended claims, unless the context clearly indicates other circumstances, the singular forms "a", "an" and "the" are intended to include plural forms.

It should be further understood that the term "and/or" used in the specification and appended claims of this application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations .

Please refer to FIGS. 1 and 2. FIG. 1 is a schematic diagram of an application scenario of a multi-park vehicle path planning method provided by an embodiment of the application; FIG. 2 is a schematic flowchart of a multi-park vehicle path planning method provided by an embodiment of the application. The vehicle path planning method is applied to the server, and the method is executed by application software installed in the server.

As shown in Figure 2, the method includes steps S110 to S140.

S110: Determine whether a path planning request sent by the client is received.

In order to understand the technical solution of the present application more clearly, the terminals involved are introduced below. This application describes the technical solution from the perspective of the server.

The first is the client. The client can be understood as a user terminal. The user terminal can be a smart phone, tablet computer, notebook computer, desktop computer, personal digital assistant, wearable device and other electronic devices with communication functions. The user terminal sends a path plan Request to the server.

The second is the server. The server receives the path planning request sent by the client, based on the input data and constraint conditions corresponding to the path planning request, and calls the pre-stored vehicle path planning multi-objective optimization model to perform the evolutionary solution of super multi-objectives. Obtain the path optimal solution set. The optimal solution set of the path is obtained from the server and sent to the client.

In this embodiment, the server detects whether the path planning request sent by the client is received, and when the server receives the path planning request sent by the client, the subsequent step S120 is executed. When the server does not receive the path planning request sent by the client Upon request, step S110 is executed again after waiting for the preset delay time.

S120. If the path planning request sent by the client is received, the input data and constraint conditions corresponding to the path planning request are obtained; wherein, the input data corresponding to the path planning request includes the current number of users and information corresponding to the current number of users. The current user location information of each user corresponding to the cargo capacity of each user and the number of current users.

In this embodiment, if the server receives the path planning request sent by the client, it obtains the input data and constraint conditions corresponding to the path planning request. Since the vehicle path planning multi-objective optimization model has been pre-stored in the server, it can be solved subsequently according to the input data and constraint conditions, so as to obtain the path optimal solution set.

S130. Invoke a pre-stored vehicle path planning multi-objective optimization model, use the input data as input to the vehicle path planning multi-objective optimization model, and perform processing on the vehicle path planning multi-objective optimization model according to the constraint conditions and The evolutionary solution of super-multi-objectives obtains the optimal solution set of the path.

In this embodiment, the vehicle path planning multi-objective optimization model stored in the server is a multi-depot multi-vehicle path planning multi-objective optimization model. By solving the vehicle path planning multi-objective optimization model, the optimization objectives are all Try to achieve a satisfactory path scheduling plan.

In an embodiment, the vehicle path planning multi-objective optimization model includes five optimization objective functions, which are respectively denoted as:

Dispatching the number of vehicles to optimize the objective function minf ₁ (x), the total delivery duration of all vehicles to optimize the objective function minf ₂ (x), the total driving distance of all vehicles to optimize the objective function minf ₃ (x), the maximum capacity difference of a single vehicle to optimize the objective function minf ₄ (x), customer waiting time optimization objective function min f ₅ (x);

Wherein, the vehicle path planning multi-objective optimization model is preset with R parking lots, each parking lot has K vehicles, the total cargo capacity of each vehicle is Q and the maximum total service time is T; R, S, K and The value of Q is a positive integer; the current number of users included in the input data corresponding to the path planning request is denoted as P; the P customer nodes corresponding to the current number of users P are denoted as node 1 to node P, and R parking lots The corresponding parking lot nodes are respectively marked as node P+1 to node P+R;

K _r represents the r-th actual number of yard vehicles; RK k represents a vehicle ID of the r-yard; d _ij represents the distance between node i to the j-th node,

Represents the travel time of the k numbered vehicle of the r-th parking lot from the i-th node to the j-th node, s _i represents the service time corresponding to the i-th node, s _j represents the service time corresponding to the j-th node, and p _i represents the i-th node The cargo capacity of the i-th customer corresponding to the node,

Represents the path access state of the k numbered vehicle of the rth parking lot moving from the ith node to the jth node,

It means that the k-numbered vehicle of the r-th parking lot moves from the i-th node to the customer of the j-th node and is served.

Among them, when the k-numbered vehicle of the r-th parking lot has visited the path from the i-th node to the j-th node, then

Is 1, otherwise

Is 0; in the same way, when the k-numbered vehicle in the r-th parking lot serves the i-th node (in this case, i is a customer), then

otherwise

Is 0.

That is, the multi-park vehicle path planning problem can be defined as: assuming that there are R parking lots, each parking lot has K vehicles with a total cargo capacity of Q and a maximum total service time (path travel time plus customer service time) of T, and there is P A customer needs delivery, the cargo capacity of the i-th customer p _i <Q, and the service time s _i <T of _{the customer p i.} Each customer can be served by any vehicle but can only be served once, each vehicle can serve multiple users and can be required to return to the departure depot when the service is over.

For a candidate solution x of the vehicle path planning multi-objective optimization model, it refers to satisfying the above 5 optimization objective functions (that is, satisfying minf ₁ (x), minf ₂ (x), minf ₃ (x), minf ₄ (x) ), _{a path of minf 5} (x)), X represents a set containing multiple candidate solutions, and the path optimal solution set X is _optimal composed of multiple path optimal solutions.

When the vehicle path planning multi-objective optimization model is used to obtain the path optimal solution set, the model is a high-dimensional optimization model that combines the above five objective functions, namely input data and constraint conditions, to obtain the path optimal solution set X _{When it is optimal} , the proposed optimization goals and constraints can be met to the greatest extent. More specifically, the most appropriate number of vehicle dispatches, the smaller the total delivery duration of vehicles and the total travel distance of vehicles, the appropriate maximum capacity difference of single vehicles, and the Smaller waiting time for customers.

In this embodiment, the constraint conditions corresponding to the path planning request are as follows:

Among them, "st" is called subject to and means to be restricted (the expression of general constraints starts with st), for each i∈{1,2,...,P}:

Indicates that the values of i in the set {1,2,……,P} are such that

Through the data and the constraint conditions, the vehicle path planning multi-objective optimization model can be solved.

In an embodiment, as shown in FIG. 3, the step S130 includes:

S1301. Randomly generate an initial multi-objective population according to the constraint conditions; wherein the initial multi-objective population includes multiple individuals, and each individual corresponds to a path output solution of the vehicle path planning multi-objective optimization model, and the initial The total number of multiple individuals in a multi-target population is recorded as the population size N;

S1302: Obtain the current iteration algebra, and determine whether the current iteration algebra reaches a preset maximum iteration algebra;

S1303. If the current iteration algebra does not reach the maximum iteration algebra, obtain the ideal individual and the worst individual in the initial multi-objective population; wherein the ideal individual is input to the vehicle path planning multi-objective optimization model to obtain The target value of is the smallest target value among the target values corresponding to each individual in the initial multi-objective population, and the worst individual is input to the vehicle path planning multi-objective optimization model to obtain the target value for each individual in the initial multi-objective population The largest target value among the corresponding target values;

S1304. Perform simulated binary crossover and polynomial mutation on the initial multi-target population to obtain a subpopulation with the same total number of individuals as the initial multi-target population;

S1305. Combine the initial multi-target population and the sub-population to obtain a mixed population;

S1306. Perform non-dominated sorting of individuals in the mixed population to obtain a non-dominated solution set and a multi-layer solution set; the non-dominated solution set is denoted as Q ₁ , and the multi-layer solution set includes multiple solution set subsets And respectively denoted as Q ₂ to Q _L , where the _{union of Q 1} to Q _L is the mixed population, the intersection of any two sets from _{Q 1} to Q _L _{is the empty set, Q 1} ≥Q ₂ ≥Q ₃ ≥ ……≥Q _L ;

S1307. In the non-dominated solution set and the multi-layer solution set, multiple solution set subsets are sequentially merged to obtain multiple sets until the total number of individuals exceeds the population size N to form an archive set;

S1308. Normalize each individual in the archive set according to the ideal individual and the worst individual to obtain a normalized archive set; wherein, in the normalized archive set and the non-dominated The normalized individual set corresponding to the solution set is recorded as the normalized non-dominated solution set;

S1309: Obtain the shape of the Pareto front and the hypersurface corresponding to the shape of the Pareto front according to the normalized non-dominated solution set estimation;

S1310. Map each individual in the normalized archive set to the hypersurface to obtain a mapping set; wherein each individual in the normalized archive set corresponds to a mapping on the hypersurface Points to form the mapping set, and the number of corresponding mapping points in the mapping set is denoted as L _max ;

S1311. Invoke a pre-stored target point fitness algorithm to obtain the fitness value corresponding to each mapping point in the mapping set;

S1312. Cluster the corresponding Euclidean distance in the hyperplane between the mapping points in the mapping set and the population size N to obtain a clustering result; wherein the clustering in the clustering result The total number of clusters is equal to the population size N;

S1313. Select a mapping point in each cluster cluster of the clustering result to form a target mapping point set;

S1314. Obtain an individual corresponding to each target mapping point in the target mapping point set to form a current multi-target population, and use the current multi-target population as an initial multi-target population;

S1315. Add one to the current iteration algebra as the current iteration algebra, and return to execute the step of judging whether the current iteration algebra reaches the preset maximum iteration algebra;

S1316: If the current iteration algebra reaches the maximum iteration algebra, output the current multi-target population as a path optimal solution set.

In this embodiment, an initial multi-target population is randomly generated under the restriction of constraint conditions. The initial multi-target population is the first-generation multi-target population. At this time, it is first judged whether the current iteration algebra reaches the preset maximum iteration algebra. Determine whether to continue to iteratively execute the next steps to obtain the optimal solution set of the path. Among them, the initial value of the current iteration algebra is set to 1. If the current iteration algebra reaches the maximum iteration algebra, the current multi-target population output is used as the path optimal solution set.

If the current iteration algebra does not reach the maximum iteration algebra, first find the ideal individual and the worst individual in the initial multi-target population in the initial multi-target population. Each target value of the ideal individual indicates that the initial multi-target population is in the corresponding objective function The minimum target value of the ideal individual, that is, the path output solution corresponding to the ideal individual is substituted into f ₁ (x) to f ₅ (x), and all correspond to the minimum target value; each target value of the worst individual represents the current population in the corresponding target function The maximum target value, that is, the path output solution corresponding to the worst individual corresponds to the maximum target value after substituting f ₁ (x) to f ₅ (x).

Afterwards, it is necessary to generate subpopulations based on the initial multi-target population. In this process, the initial multi-target population can be simulated binary crossover and polynomial mutation to obtain a subpopulation with the same total number of individuals as the initial multi-target population. (The generation of subpopulation is to randomly select two individuals from the current initial population to simulate binary crossover until N new individuals are crossed. Then, the N new individuals are mutated according to the mutation probability and polynomial mutation to get the updated N individuals, the updated N individuals form a subpopulation).

That is, two individuals are randomly selected from the initial multi-target population to perform binary crossover in sequence until N cross-processed new individuals are generated, and the N cross-processed new individuals are subjected to polynomial mutation, and the new individual after polynomial mutation Form subpopulations.

In this embodiment, after two individuals are randomly selected from the initial multi-target population to perform binary crossover processing, N new individuals after crossover processing are obtained. Here, the process of randomly selecting two individuals for binary crossover is similar to an iterative process. Until the number of new individuals reaches the population size N, the process of multiple binary crossovers is stopped. In addition, binary crossover and polynomial mutation are both conventional processing procedures, and will not be repeated here.

Then, the initial multi-target population and the sub-population are combined to obtain a mixed population, and the total number of individuals included in the mixed population is twice the population size N.

At this time, non-dominated sorting can be performed on the individuals in the mixed population, thereby obtaining non-dominated solution sets and multi-layer solution sets. When specifically performing non-dominated sorting of the entities in the mixed population, the non-dominated solution set corresponding to the mixed population can be obtained through a non-dominated solution (also called Pareto solution) acquisition method. Among them, the definition of Pareto solution is to assume that for any two solutions S1 and S2, S1 is better than or the same as S2 for all targets, and there is at least one target, and the corresponding target value of S1 on this target is better than S2. The corresponding target value on the target is called S1 dominates S2. If the solution of S1 is not dominated by other solutions, then S1 is called the non-dominated solution (undominated solution), also called the Pareto solution (ie Pareto solution). Specifically, when solving the non-dominated solution in the mixed population, the obtained non-dominated solution set is denoted as Q ₁ . After the individuals corresponding to the non-dominated solution set are removed from the mixed population, the multi-layer solution set is obtained. The multi-layer solution set includes multiple solution set subsets and is respectively denoted as Q ₂ to Q _L , where Q ₁ to The union of Q _L is the mixed population, and the intersection of any two sets from _{Q 1} to Q _L _{is an empty set, Q 1} ≥Q ₂ ≥Q ₃ ≥……≥Q _L ; where "≥" indicates a dominance relationship , Q _i ≥ _{Q j} means that Q _j is dominated by the solution in Q _i , and the relationship is transitive. Q ₁ ≥ _{Q 2} means that for f ₁ (x) to f ₅ (x), each of Q2 The solutions are all dominated by at least one solution in Q1, and the relationship is transitive, that is, each solution in Q3 is dominated by at least one solution in Q1 or Q2, and the others are in turn.

After the non-dominated solution set and the multi-layer solution set are obtained, solutions that exceed the population size N need to be selected at this time to form an archive set. At this time, the selection mode as follows: first of all individuals in the selected Q _1, determines whether the total number of individuals beyond the current population size N, if the current total number of individuals of the population size does not exceed N, continue Q ₂ in the selection of all of the individuals, the total number of individual current plus the number of Q ₂ in the subject to update the current as the total number of individuals, and then determines whether the total number of individuals beyond the current The population size N, until the _{total number of individuals in Q 1} to Q _{a obtained} exceeds the population size N (where a is a positive integer greater than 1 and not exceeding L) to form an archive set.

At this time, each individual in the archive set may be normalized according to the ideal individual and the worst individual to obtain a normalized archive set; wherein, the normalized archive set and the The normalized individual set corresponding to the non-dominated solution set is recorded as the normalized non-dominated solution set. That is, each individual in the archive set is normalized, and a normalized individual corresponding to each individual is obtained, thereby forming a normalized non-dominated solution set. The purpose of the above normalization processing is to eliminate the difference between different dimensions, so as to facilitate subsequent data processing.

In an embodiment, step S1308 includes:

according to

Perform normalization processing on each individual in the archive set to obtain a normalized individual corresponding to each individual in the archive set to form a normalized archive set; where NA _m represents in the archive set the individual over the individual normalization, a represents _{the worst} of the worst _individual subject, a represents _{the individual over the} individual m-th corresponding to a _m.

Through the above-mentioned normalized processing model, a normalized archive set can be obtained, thereby eliminating the difference between different dimensions.

After obtaining the normalized archive set, the shape of the Pareto front and the hypersurface corresponding to the shape of the Pareto front can be estimated according to the normalized individuals included therein. Estimate the shape of the population in the objective function space based on all non-dominated solutions, which will help to discover the characteristics of multi-objective optimization tasks. Multi-objective optimization is usually divided into three categories, convex optimization, concave optimization, and linear optimization. In this step, the curvature values of three types of hypersurfaces will be obtained.

In one embodiment, as shown in FIG. 4, step S1309 includes:

S13091. Remove the normalized non-dominated individuals that are not in the standardized target space among the normalized non-dominated individuals in the normalized non-dominated solution set to obtain the normalized non-dominated solution set after screening; where Each target value corresponding to each normalized non-dominated individual in the standardized target space does not exceed 1;

S13092. Obtain each non-dominated individual in the normalized non-dominated solution set after the screening, which is respectively recorded as B ₁ to B _n ; where the value of n is normalized to the normalized non-dominated solution set after the screening The total number of non-dominant individuals is the same;

_{S13093. Obtain the hyperplane distance D i} corresponding to the target hyperplane from the non-dominated individual B _i ; where the value range of i is [1,n], and the target hyperplane is f ₁ (x)+f ₂ (x)+ f ₃ (x)+f ₄ (x)+f ₅ (x)=1;

S13094, and obtaining a distance mean value hyperplane standard differential hyperplane distance from the hyperplane D ₁ to D _n corresponding to; wherein hyperplane distance from the hyperplane D ₁ to D _n corresponding to an average value referred to as D _avg, from the hyperplane The standard deviation of the hyperplane distance corresponding _{to D 1} to D _n _{is denoted as D std} ;

S13095. Perform a norm operation according to the quotient of the hyperplane distance average value and the hyperplane distance standard deviation to obtain a corresponding coefficient of variation; wherein the coefficient of variation is denoted as cv;

S13096. Obtain a first hypersurface corresponding to a curvature of 2 of the target hyperplane, and a second hypersurface corresponding to a curvature of 0.5 of the target hyperplane, according to the target hyperplane, the first hypersurface, and the second hypersurface And a preset curvature determination strategy to obtain the current curvature corresponding to the normalized non-dominated solution set; wherein, the curvature determination strategy is

d(2.0) represents the distance from the peak point of the first hypersurface to the target hyperplane, and d(0.5) represents the distance from the peak point of the second hypersurface to the target hyperplane;

S13097. Adjust the current curvature according to the coefficient of variation to obtain an adjusted curvature; wherein, if the coefficient of variation is less than 0.1, adjust the value of the current curvature to 1, so that the adjusted curvature value is 1; if the coefficient of variation is greater than or equal to 0.1, keep the value of the current curvature unchanged, so that the adjusted curvature is equal to the current curvature;

S13098: Obtain the shape of the Pareto front and the hypersurface corresponding to the shape of the Pareto front according to the adjusted curvature.

In this embodiment, since there may still be normalized non-dominated individuals in the normalized non-dominated solution set that are not in the standardized target space, at this time, each normalized non-dominated individual in the normalized non-dominated solution set Remove the normalized non-dominated individuals that are not in the standardized target space (the standardized target space is the target space formed by f ₁ (x) to f ₅ (x) equal to 1), and get the normalized non-dominated solution after screening set. After removing the normalized non-dominated individuals that are not in the standardized target space, the interference of these individuals is effectively eliminated, which is beneficial to the subsequent population evolution.

in,

The value of m in this application is 5. When p=2, the value of d(2.0) can be obtained, and when p=0.5, the value of d(0.5) can be obtained. Cur represents the current curvature corresponding to the normalized non-dominated solution set.

At this time, the shape of the Pareto front and the hypersurface corresponding to the shape of the Pareto front are obtained through the processing process of steps S13091-S13098, in order to facilitate the subsequent clustering operation, and the individuals used in the prediction process are all non-dominated individual.

_{Moreover, when calculating the distance D i} from the non-dominated individual B _i to the target hyperplane, a negative value of the distance D _i means that the individual is below the target hyperplane, a positive value means that the individual is above the target hyperplane, and the distance D _i is 0 Indicates that the individual is on the target hyperplane. By obtaining the _{hyperplane distance average value and the hyperplane distance standard deviation corresponding to the hyperplane distance D 1} to D _n , the coefficient of variation cv required for subsequent adjustment of the curvature can be obtained correspondingly.

The current curvature is adjusted according to the coefficient of variation cv to obtain the adjusted curvature. The shape of the Pareto front and the hypersurface corresponding to the shape of the Pareto front can be correspondingly obtained according to the adjusted curvature. The hypersurface corresponding to the shape of the Pareto front will help to discover the characteristics of the multi-objective optimization task.

Afterwards, each individual in the normalized archive set is mapped to the hypersurface to obtain a mapping set; wherein each individual in the normalized archive set corresponds to a mapping on the hypersurface Points to form the mapping set, and the number of corresponding mapping points in the mapping set is denoted as L _max . At this time, the fitness value of each mapping point needs to be obtained, specifically

Obtain the fitness value of each mapping point, f _i (x _l ) represents the i-th target value corresponding to the l-th mapping point in the mapping set, and the value range of l is [1, L _max ]. The fitness value of each mapping point represents the sum of all the target values of the individual corresponding mapping points. Since it tends to find a well-converged solution set, the fitness value is used as a measure of convergence.

At this time, in order to cluster each mapping point in the mapping set, and make the total number of cluster clusters in the clustering result equal to the population size N, it is possible to set the distance between each mapping point on the hyperplane The corresponding Euclidean distance in clustering. If the corresponding Euclidean distance between two mapping points in the hyperplane is smaller, it means that the individuals corresponding to the two mapping points are more similar.

After the clustering is completed, a mapping point is selected from each cluster cluster in the clustering result to form a target mapping point set, so that the number of mapping points in the target mapping point set is equal to the population size N, and the mapping The individual set corresponding to the point set is the population of this evolution, and it is also the parent population of the next generation. Through this selection strategy, it can ensure that the next generation population has good convergence and diversity. The current iteration algebra is iterated multiple times to reach the maximum iteration algebra, and the current multi-target population output is used as a path optimal solution set. Wherein, each individual in the path optimal solution set is the optimal solution corresponding to the vehicle path planning multi-objective optimization model obtained according to the input data and constraint conditions.

In specific implementation, the specific encoding method of each path optimal solution in the path optimal solution set (that is, the method that is finally displayed to the user) is a user-defined encoding format and saved in the server, which is not limited this time Specific encoding method.

S140. Send the path optimal solution set to the client.

In this embodiment, after obtaining the path optimal solution set in the server, it can be sent to the client. Therefore, the client can assist the delivery process after determining the delivery route according to the optimal solution set of the route.

This method realizes that the convergence and diversity of the population are fully considered in the process of solving super-multi-objective evolution, and the effective prediction of the shape of the population is realized, and the multi-objective of vehicle path planning is obtained quickly and accurately based on input data and constraints. The path optimal solution set of the optimization model.

The embodiment of the present application also provides a multi-park vehicle path planning device, which is used to execute any embodiment of the foregoing multi-park vehicle path planning method. Specifically, please refer to FIG. 5, which is a schematic block diagram of a multi-park vehicle path planning apparatus provided by an embodiment of the present application. The multi-parking vehicle path planning device 100 may be configured in a server.

As shown in FIG. 5, the multi-depot vehicle path planning device 100 includes a path planning request detection unit 110, a data condition acquisition unit 120, a path optimal solution set acquisition unit 130, and an optimal solution set transmission unit 140.

Wherein, the path planning request detection unit 110 is used to determine whether the path planning request sent by the client is received.

The data condition obtaining unit 120 is configured to, if a path planning request sent by the client is received, obtain input data and constraint conditions corresponding to the path planning request; wherein the input data corresponding to the path planning request includes the current number of users , The cargo capacity of each user corresponding to the current number of users, and the current user location information of each user corresponding to the current number of users.

The path optimal solution set acquisition unit 130 is configured to call a pre-stored vehicle path planning multi-objective optimization model, use the input data as the input of the vehicle path planning multi-objective optimization model, and according to the constraint conditions and the control The vehicle path planning multi-objective optimization model performs the evolutionary solution of super multi-objectives, and obtains the optimal solution set of the path.

The optimal solution set sending unit 140 is configured to send the path optimal solution set to the client.

In an embodiment, the path optimal solution set obtaining unit 130 includes:

The initial multi-objective population generating unit is used to randomly generate an initial multi-objective population according to the constraint conditions; wherein the initial multi-objective population includes multiple individuals, and each individual corresponds to one of the vehicle path planning multi-objective optimization models Path output solution, the total number of multiple individuals included in the initial multi-target population is recorded as the population size N;

The first judging unit of the current iteration algebra is used to obtain the current iteration algebra, and judge whether the current iteration algebra reaches the preset maximum iteration algebra;

A target individual obtaining unit, configured to obtain an ideal individual and a worst individual in the initial multi-target population if the current iteration algebra does not reach the maximum iteration algebra; wherein the ideal individual is input to the vehicle path planning The target value obtained by the multi-objective optimization model is the smallest target value among the target values corresponding to each individual in the initial multi-objective population, and the worst individual is input to the vehicle path planning multi-objective optimization model and the target value obtained is the initial multi-objective The largest target value among the target values corresponding to each individual in the population;

The individual crossover mutation unit is used to simulate binary crossover and polynomial mutation on the initial multi-target population to obtain a subpopulation with the same total number of individuals as the initial multi-target population;

A mixed population obtaining unit, configured to merge the initial multi-target population and the sub-population to obtain a mixed population;

The non-dominated solution set obtaining unit is used to perform non-dominated sorting of the individuals in the mixed population to obtain a non-dominated solution set and a multi-layer solution set; wherein the non-dominated solution set is denoted as Q ₁ , and the multi-layer The solution set includes multiple solution set subsets and are respectively denoted as Q ₂ to Q _L , where the _{union of Q 1} to Q _L is the mixed population, and the intersection of any two sets from _{Q 1} to Q _{L is an empty set,} Q ₁ ≥Q ₂ ≥Q ₃ ≥……≥Q _L ;

The archive set acquisition unit is used to sequentially merge multiple solution set subsets in the non-dominated solution set and the multi-layer solution set to obtain multiple sets until the total number of individuals exceeds the population size N to form an archive gather;

The normalization processing unit is configured to normalize each individual in the archive set according to the ideal individual and the worst individual to obtain a normalized archive set; wherein, the normalized archive set The set of normalized individuals corresponding to the non-dominated solution set is recorded as the normalized non-dominated solution set;

A hypersurface acquiring unit, configured to estimate and acquire the shape of the Pareto front and the hypersurface corresponding to the shape of the Pareto front according to the normalized non-dominated solution set;

The individual mapping unit is used to map each individual in the normalized archive set to the hypersurface to obtain a mapping set; wherein each individual in the normalized archive set corresponds to the hypersurface A mapping point above to form the mapping set, and the number of corresponding mapping points in the mapping set is denoted as L _max ;

The fitness value obtaining unit is used to call a pre-stored target point fitness value algorithm to obtain the fitness value corresponding to each mapping point in the mapping set;

The mapping point clustering unit is used to cluster the corresponding Euclidean distance in the hyperplane between each mapping point in the mapping set and the population size N to obtain a clustering result; wherein, the The total number of clusters in the clustering result is equal to the population size N;

The target mapping point set acquiring unit is configured to select a mapping point in each cluster cluster of the clustering result to form a target mapping point set;

The initial multi-target population update unit is used to obtain the individual corresponding to each target mapping point in the target mapping point set to form a current multi-target population, and use the current multi-target population as the initial multi-target population;

The current iteration algebra second judging unit, configured to add one to the current iteration algebra as the current iteration algebra, and return to execute the step of judging whether the current iteration algebra reaches the preset maximum iteration algebra;

The path optimal solution set output unit is configured to output the current multi-target population as the path optimal solution set if the current iteration algebra reaches the maximum iteration algebra.

In an embodiment, the individual cross mutation unit is also used for:

Randomly select two individuals in the initial multi-target population to perform binary crossover in sequence, until N cross-processed new individuals are generated, and the N cross-processed new individuals are subjected to polynomial mutation, and the new individuals after polynomial mutation are composed of subgroups. Population.

In an embodiment, the normalization processing unit is further used for:

according to

In an embodiment, the hypersurface acquiring unit includes:

The non-dominated individuals screening unit is used to remove the normalized non-dominated individuals that are not in the standardized target space among the normalized non-dominated individuals in the normalized non-dominated solution set to obtain the normalized non-dominated individuals after screening Solution set; wherein each target value corresponding to each normalized non-dominated individual located in the standardized target space does not exceed 1;

The non-dominated individual acquisition unit is used to acquire each non-dominated individual in the normalized non-dominated solution set after the screening, which is respectively recorded as B ₁ to B _n ; where the value of n is the same as the normalized non-dominated after screening. The total number of normalized non-dominated individuals in the dominating solution set is the same;

Hyperplane distance acquisition unit for acquiring the individual B _i to a non-dominant hyperplane hyperplane corresponding target distance D _i; where i is the range [1, n], the target hyperplane f ₁ (x) + f ₂ (x)+f ₃ (x)+f ₄ (x)+f ₅ (x)=1;

Hyperplane from the parameter acquisition unit, configured to obtain hyperplane distance D ₁ to D _n corresponding hyperplane distance from average and standard deviation hyperplane; wherein hyperplane distance D ₁ to D _n corresponding to the average distance referred hyperplane Is D _avg , the standard deviation of the hyperplane distance corresponding to the hyperplane distance D ₁ to D _n _{is denoted as D std} ;

The coefficient of variation obtaining unit is configured to perform a norm operation according to the quotient of the average value of the hyperplane distance and the standard deviation of the hyperplane distance to obtain the corresponding coefficient of variation; wherein the coefficient of variation is denoted as cv;

The current curvature acquisition unit is configured to acquire a first hypersurface corresponding to a curvature of 2 of the target hyperplane, and a second hypersurface corresponding to a curvature of 0.5 of the target hyperplane, according to the target hyperplane and the first hypersurface , The second hypersurface and the preset curvature determination strategy, to obtain the current curvature corresponding to the normalized non-dominated solution set; wherein, the curvature determination strategy is

The curvature adjustment unit is configured to adjust the current curvature according to the coefficient of variation to obtain an adjusted curvature; wherein, if the coefficient of variation is less than 0.1, adjust the value of the current curvature to 1, so that the adjusted curvature The value of the curvature is 1; if the coefficient of variation is greater than or equal to 0.1, the value of the current curvature is kept unchanged, so that the adjusted curvature is equal to the current curvature;

The hypersurface generating unit is used to obtain the shape of the Pareto front and the hypersurface corresponding to the shape of the Pareto front according to the adjusted curvature.

The device realizes that the convergence and diversity of the population are fully considered in the process of solving super-multi-objective evolution, and the effective prediction of the shape of the population is realized, and the multi-objective of vehicle path planning is obtained quickly and accurately based on input data and constraint conditions. The path optimal solution set of the optimization model.

The above-mentioned multi-yard vehicle path planning apparatus may be implemented in the form of a computer program, and the computer program may run on a computer device as shown in FIG. 6.

Please refer to FIG. 6, which is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device 500 is a server, and the server may be an independent server or a server cluster composed of multiple servers.

Referring to FIG. 6, the computer device 500 includes a processor 502, a memory, and a network interface 505 connected through a system bus 501, where the memory may include a non-volatile storage medium 503 and an internal memory 504.

The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, the processor 502 can execute the multi-park vehicle path planning method.

The processor 502 is used to provide calculation and control capabilities, and support the operation of the entire computer device 500.

The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can make the processor 502 execute the multi-park vehicle path planning method.

The network interface 505 is used for network communication, such as providing data information transmission. Those skilled in the art can understand that the structure shown in FIG. 6 is only a block diagram of part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device 500 to which the solution of the present application is applied. The specific computer device 500 may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

Wherein, the processor 502 is configured to run a computer program 5032 stored in a memory to implement the multi-park vehicle path planning method disclosed in the embodiment of the present application.

Those skilled in the art can understand that the embodiment of the computer device shown in FIG. 6 does not constitute a limitation on the specific configuration of the computer device. In other embodiments, the computer device may include more or less components than those shown in the figure. Or combine certain components, or different component arrangements. For example, in some embodiments, the computer device may only include a memory and a processor. In such an embodiment, the structure and function of the memory and the processor are consistent with the embodiment shown in FIG. 6 and will not be repeated here.

It should be understood that, in this embodiment of the application, the processor 502 may be a central processing unit (Central Processing Unit, CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (Digital Signal Processors, DSPs), Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor.

In another embodiment of the present application, a computer-readable storage medium is provided. The computer-readable storage medium may be a non-volatile computer-readable storage medium. The computer-readable storage medium stores a computer program, where the computer program is executed by a processor to implement the multi-parking vehicle path planning method disclosed in the embodiments of the present application.

The storage medium is a physical, non-transitory storage medium, such as a U disk, a mobile hard disk, a read-only memory (Read-Only Memory, ROM), a magnetic disk, or an optical disk, etc., which can store program codes. medium.

Those skilled in the art can clearly understand that, for the convenience and conciseness of description, the specific working process of the above-described equipment, device, and unit can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

The above are only specific implementations of this application, but the protection scope of this application is not limited to this. Anyone familiar with the technical field can easily think of various equivalents within the technical scope disclosed in this application. Modifications or replacements, these modifications or replacements shall be covered within the protection scope of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claims.

Claims

A method for multi-depot vehicle path planning includes:

Determine whether the path planning request sent by the client is received;

If a path planning request sent by the client is received, the input data and constraint conditions corresponding to the path planning request are obtained; wherein, the input data corresponding to the path planning request includes the current number of users and each corresponding to the current number of users. The user’s cargo capacity and current user location information for each user corresponding to the current number of users;

Call a pre-stored vehicle path planning multi-objective optimization model, use the input data as the input of the vehicle path planning multi-objective optimization model, and perform a lot of operations on the vehicle path planning multi-objective optimization model according to the constraint conditions and The evolutionary solution of the goal, the optimal solution set of the path is obtained; and

Send the path optimal solution set to the client.
The method of multi-depot vehicle path planning according to claim 1, wherein the vehicle path planning multi-objective optimization model includes five optimization objective functions, which are respectively recorded as the number of dispatch vehicles optimization objective function minf 1 (x), and the total number of all vehicles Delivery duration optimization objective function minf 2 (x), total travel distance optimization objective function of all vehicles minf 3 (x), single vehicle maximum capacity difference optimization objective function minf 4 (x), customer waiting time optimization objective function min f 5 ( x);

Wherein, the vehicle path planning multi-objective optimization model is preset with R parking lots, each parking lot has K vehicles, the total cargo capacity of each vehicle is Q and the maximum total service time is T; R, S, K and The value of Q is a positive integer; the current number of users included in the input data corresponding to the path planning request is denoted as P; the P customer nodes corresponding to the current number of users P are denoted as node 1 to node P, and R parking lots The corresponding parking lot nodes are respectively marked as node P+1 to node P+R;

K r represents the r-th actual number of yard vehicles; RK k represents a vehicle ID of the r-yard; d ij represents the distance between node i to the j-th node,
Represents the travel time of the k numbered vehicle of the r-th parking lot from the i-th node to the j-th node, s i represents the service time corresponding to the i-th node, s j represents the service time corresponding to the j-th node, and p i represents the i-th node The cargo capacity of the i-th customer corresponding to the node,
Represents the path access state of the k numbered vehicle of the rth parking lot moving from the ith node to the jth node,
It means that the k-numbered vehicle of the r-th parking lot moves from the i-th node to the customer of the j-th node and is served.
The method of multi-depot vehicle path planning according to claim 2, wherein the input data is used as the input of the vehicle path planning multi-objective optimization model, and the vehicle path planning is based on the constraint conditions and the multi-objective optimization model. The goal optimization model performs the evolutionary solution of super-multi-objectives, and obtains the path optimal solution set, which includes:

An initial multi-objective population is randomly generated according to the constraint conditions; wherein the initial multi-objective population includes a plurality of individuals, and each individual corresponds to a path output solution of the vehicle path planning multi-objective optimization model, and the initial multi-objective The total number of individuals in the population is recorded as the population size N;

Acquiring the current iteration algebra, and judging whether the current iteration algebra reaches the preset maximum iteration algebra;

If the current iteration algebra does not reach the maximum iteration algebra, obtain the ideal individual and the worst individual in the initial multi-objective population; wherein the ideal individual is input to the target obtained by the vehicle path planning multi-objective optimization model The value is the smallest target value among the target values corresponding to each individual in the initial multi-objective population, and the worst individual is input to the vehicle path planning multi-objective optimization model to obtain the target value corresponding to each individual in the initial multi-objective population The maximum target value among the target values;

Performing simulated binary crossover and polynomial mutation on the initial multi-target population to obtain a subpopulation with the same total number of individuals as the initial multi-target population;

Combining the initial multi-target population and the sub-population to obtain a mixed population;

The individuals in the mixed population are sorted in a non-dominated manner to obtain a non-dominated solution set and a multi-layer solution set; wherein the non-dominated solution set is denoted as Q 1 , and the multi-layer solution set includes a plurality of solution set subsets And respectively denoted as Q 2 to Q L , where the union of Q 1 to Q L is the mixed population, the intersection of any two sets from Q 1 to Q L is the empty set, Q 1 ≥Q 2 ≥Q 3 ≥ ……≥Q L ;

In the non-dominated solution set and the multi-layer solution set, multiple solution set subsets are sequentially merged to obtain multiple sets until the total number of individuals exceeds the population size N to form an archive set;

According to the ideal individual and the worst individual, each individual in the archive set is normalized to obtain a normalized archive set; wherein, the normalized archive set and the non-dominated solution set The corresponding normalized individual set is recorded as the normalized non-dominated solution set;

Obtaining the shape of the Pareto front and the hypersurface corresponding to the shape of the Pareto front according to the estimation of the normalized non-dominated solution set;

Mapping each individual in the normalized archive set to the hypersurface to obtain a mapping set; wherein each individual in the normalized archive set corresponds to a mapping point on the hypersurface, To form the mapping set, the number of corresponding mapping points in the mapping set is denoted as L max ;

Calling a pre-stored target point fitness algorithm to obtain the fitness value corresponding to each mapping point in the mapping set;

Clustering the corresponding Euclidean distance in the hyperplane between the mapping points in the mapping set and the population size N to obtain a clustering result; wherein, the clustering cluster in the clustering result The total number of is equal to the population size N;

Selecting a mapping point in each cluster of the clustering result to form a target mapping point set;

Acquiring an individual corresponding to each target mapping point in the target mapping point set to form a current multi-target population, and use the current multi-target population as an initial multi-target population;

Adding one to the current iterative algebra as the current iterative algebra, and return to execute the step of judging whether the current iterative algebra reaches the preset maximum iterative algebra;

If the current iteration algebra reaches the maximum iteration algebra, output the current multi-target population as a path optimal solution set.
The method of multi-depot vehicle path planning according to claim 3, wherein the simulated binary crossover and polynomial mutation are performed on the initial multi-target population to obtain a sub-population with the same total number of individuals as the initial multi-target population ,include:

Randomly select two individuals in the initial multi-target population to perform binary crossover in sequence, until N cross-processed new individuals are generated, and the N cross-processed new individuals are subjected to polynomial mutation, and the new individuals after polynomial mutation are composed of subgroups. Population.
The method of multi-depot vehicle path planning according to claim 3, wherein, according to the ideal individual and the worst individual, each individual in the archive set is normalized to obtain a normalized archive set ,include:

according to
Perform normalization processing on each individual in the archive set to obtain a normalized individual corresponding to each individual in the archive set to form a normalized archive set; where NA m represents in the archive set the individual over the individual normalization, a represents the worst of the worst individual subject, a represents the individual over the individual m-th corresponding to a m.
The method of multi-depot vehicle path planning according to claim 3, wherein the target point fitness algorithm is
f i (x l ) represents the i-th target value corresponding to the l-th mapping point in the mapping set, and the value range of l is [1, L max ].
The method of multi-depot vehicle path planning according to claim 3, wherein said obtaining the shape of the Pareto front and the hypersurface corresponding to the shape of the Pareto front according to the normalized non-dominated solution set estimation comprises :

Remove the normalized non-dominated individuals that are not in the standardized target space among the normalized non-dominated individuals in the normalized non-dominated solution set, and obtain the normalized non-dominated solution set after screening; wherein, located in the Each target value corresponding to each normalized non-dominated individual in the standardized target space does not exceed 1;

Obtain each non-dominated individual in the normalized non-dominated solution set after the screening, respectively denoted as B 1 to B n ; where the value of n is the same as the normalized non-dominated in the normalized non-dominated solution set after the screening The total number of individuals is the same;

Obtain the hyperplane distance D i corresponding to the target hyperplane from the non-dominated individual B i ; where the value range of i is [1,n], and the target hyperplane is f 1 (x)+f 2 (x)+f 3 (x)+f 4 (x)+f 5 (x)=1;

Get hyperplane distance D 1 to D n corresponding hyperplane distance from average and standard deviation hyperplane; wherein hyperplane distance from the hyperplane D 1 to D n corresponding to an average value referred to as D avg, the distance D 1 hyperplane The standard deviation of the hyperplane distance corresponding to D n is denoted as D std ;

Perform a norm operation according to the quotient of the average value of the hyperplane distance and the standard deviation of the hyperplane distance to obtain the corresponding coefficient of variation; wherein the coefficient of variation is denoted as cv;

Obtain a first hypersurface corresponding to a curvature of 2 of the target hyperplane, and a second hypersurface corresponding to a curvature of 0.5 of the target hyperplane, according to the target hyperplane, the first hypersurface, the second hypersurface, and the prediction Set the curvature determination strategy to obtain the current curvature corresponding to the normalized non-dominated solution set; wherein, the curvature determination strategy is
d(2.0) represents the distance from the peak point of the first hypersurface to the target hyperplane, and d(0.5) represents the distance from the peak point of the second hypersurface to the target hyperplane;

Adjust the current curvature according to the coefficient of variation to obtain an adjusted curvature; wherein, if the coefficient of variation is less than 0.1, adjust the value of the current curvature to 1, so that the adjusted curvature takes the value of 1; If the coefficient of variation is greater than or equal to 0.1, keeping the value of the current curvature unchanged, so that the adjusted curvature is equal to the current curvature;

According to the adjusted curvature, the shape of the Pareto front and the hypersurface corresponding to the shape of the Pareto front are correspondingly obtained.
A multi-parking vehicle path planning device, including:

The path planning request detection unit is used to determine whether the path planning request sent by the client is received;

The data condition obtaining unit is configured to obtain input data and constraint conditions corresponding to the path planning request if the path planning request sent by the client is received; wherein, the input data corresponding to the path planning request includes the current number of users, The cargo capacity of each user corresponding to the current number of users, and the current user location information of each user corresponding to the current number of users;

The path optimal solution set acquisition unit is used to call a pre-stored vehicle path planning multi-objective optimization model, use the input data as the input of the vehicle path planning multi-objective optimization model, and compare the constraints to the The multi-objective optimization model of vehicle path planning performs the evolutionary solution of super multi-objectives and obtains the optimal solution set of the path;

The optimal solution set sending unit is configured to send the path optimal solution set to the client.
A computer device includes a memory, a processor, and a computer program stored on the memory and capable of running on the processor, wherein the processor implements the following steps when the processor executes the computer program:

Determine whether the path planning request sent by the client is received;

If a path planning request sent by the client is received, the input data and constraint conditions corresponding to the path planning request are obtained; wherein, the input data corresponding to the path planning request includes the current number of users and each corresponding to the current number of users. The user’s cargo capacity and current user location information for each user corresponding to the current number of users;

Call a pre-stored vehicle path planning multi-objective optimization model, use the input data as the input of the vehicle path planning multi-objective optimization model, and perform a lot of operations on the vehicle path planning multi-objective optimization model according to the constraint conditions and The evolutionary solution of the goal, the optimal solution set of the path is obtained; and

Send the path optimal solution set to the client.
A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program that, when executed by a processor, causes the processor to perform the following operations:

Determine whether the path planning request sent by the client is received;

If the path planning request sent by the client is received, the input data and constraint conditions corresponding to the path planning request are obtained; wherein, the input data corresponding to the path planning request includes the current number of users and each corresponding to the current number of users. The user’s cargo capacity and current user location information for each user corresponding to the current number of users;

Call a pre-stored vehicle path planning multi-objective optimization model, use the input data as the input of the vehicle path planning multi-objective optimization model, and perform a lot of operations on the vehicle path planning multi-objective optimization model according to the constraint conditions and The evolutionary solution of the goal, the optimal solution set of the path is obtained; and

Send the path optimal solution set to the client.