Path planning method and device, equipment, storage medium and product

Abstract

The invention discloses a path planning method and device, equipment, a storage medium and a product, and relates to the technical field of unmanned transportation, and the method comprises the steps: obtaining an initial path population, taking the initial path population as the first input, and carrying out the loop iteration through employing a differential evolution algorithm, a squirrel search algorithm and a large neighborhood search algorithm. According to the method, the scale factor and the crossover operator which adaptively change based on the number of iterations are introduced, so that the mutation and crossover probability of the differential evolution algorithm is adjusted, the differential evolution algorithm is prevented from falling into a local optimal solution along with the increase of iterations, and the diversity of a population is kept; a squirrel search algorithm is introduced to optimize a population solved by a differential evolution algorithm, a large neighborhood search algorithm is combined, a local optimal solution created by the differential evolution algorithm can be effectively evaded, and based on continuous iteration, a logistics planning scheme with lower output energy consumption and higher efficiency is achieved.

Description

Technical Field

[0001] The present application relates to the field of unmanned transportation technology, and in particular to a path planning method, device, equipment, storage medium and product. Background Art

[0002] Among related technologies, Automated Guided Vehicles (AGVs) have been widely used in material transportation and other tasks, which can significantly improve the production flexibility of enterprises. For smart workshops, rationally arranging the task routes of AGVs can greatly improve production efficiency, thereby achieving higher benefits for enterprises.

[0003] However, currently, when planning the path of AGV, most of them give priority to distance, time, quantity and penalty cost, and focus on optimizing these aspects. However, for AGV, since most of them are powered by electricity, there are still problems such as insufficient power during the task.

[0004] Therefore, how to improve the overall efficiency of logistics and transportation tasks while reducing energy consumption is an urgent problem that needs to be solved. Summary of the invention

[0005] The main purpose of this application is to provide a path planning method, device, equipment, storage medium and product, aiming to solve the technical problem of how to improve the overall efficiency of logistics transportation tasks while reducing energy consumption.

[0006] To achieve the above purpose, the present application proposes a path planning method, which includes: Obtaining a vehicle energy consumption calculation function, and establishing a path constraint model based on the energy consumption calculation function; Based on the path constraint model, generating an initial path population; The initial path population is used as the first input to perform loop iterations, wherein the loop iterations include performing mutation operations and crossover operations on the input based on a scaling factor and a crossover operator to obtain an intermediate path population, wherein the scaling factor is related to the current number of iterations and a preset scaling factor value, and the crossover operator is related to the current number of iterations and a preset crossover operator value; the intermediate path population is optimized and screened by a squirrel search algorithm to obtain a set of optimal solutions for the current iteration round; a large neighborhood search is performed on each individual in the set of optimal solutions to obtain a descendant population for the current iteration round; when the current number of iterations does not reach the set number, the descendant population is used as input, and the execution of the mutation operation and crossover operation based on the scaling factor and the crossover operator is returned to obtain an intermediate path population; when the current number of iterations reaches the set number, the descendant population is output as the best solution, and the loop iterations are terminated.

[0007] In some embodiments, the step of obtaining a vehicle energy consumption calculation function includes: Calculate the vehicle's transportation energy consumption and standby energy consumption based on the vehicle's attribute information and the load requirements of the current task; The sum of the transportation energy consumption and the standby energy consumption is used as the energy consumption calculation function of the vehicle.

[0008] In some embodiments, the establishing a path constraint model based on the energy consumption calculation function includes: Establish a path constraint model with the goal of minimizing vehicle energy consumption; Construct constraints, including: access constraints, path direction constraints, available vehicle quantity constraints, service time constraints, vehicle load constraints, pickup demand constraints, balance constraints, and decision variable constraints.

[0009] In some embodiments, the scaling factor is represented by the following expression:

[0010] in, is the preset scale factor value of the scale factor, It can be expressed by the following expression:

[0011] in, is the set number of iterations of the loop, is the current iteration number.

[0012] In some embodiments, the crossover operator is represented by the following expression:

[0013] in, is the crossover operator, is the preset crossover operator value, It can be expressed by the following expression: .

[0014] In some embodiments, the step S02 uses the squirrel search algorithm to optimize and screen the intermediate path population to obtain a set of optimal solutions for the current iteration round, including: For each individual in the intermediate path population, calculating the corresponding first fitness; Based on the first fitness, the multiple individuals are classified into optimal solutions, suboptimal solutions and common solutions; Cross the individuals of the optimal solution type with the individuals of the suboptimal solution type, and cross the individuals of the suboptimal solution type with the individuals of the common solution type to obtain multiple offspring individuals to be screened; Calculating the second fitness of each of the offspring individuals to be screened; Based on the second fitness, a set of better solutions for the current iteration round is screened and obtained.

[0015] In addition, to achieve the above purpose, the present application also proposes a path planning device, the path planning device comprising: A parameter predefinition module, used to obtain a vehicle energy consumption calculation function and establish a path constraint model based on the energy consumption calculation function; A population initialization module, used to generate an initial path population based on the path constraint model; A loop iteration module is used to perform loop iteration with the initial path population as the first input, wherein the loop iteration includes performing mutation operations and crossover operations on the input based on a proportional factor and a crossover operator to obtain an intermediate path population, wherein the proportional factor is related to the current number of iterations and a preset proportional factor value, and the crossover operator is related to the current number of iterations and a preset crossover operator value; optimizing and screening the intermediate path population through a squirrel search algorithm to obtain a set of optimal solutions for the current iteration round; performing a large neighborhood search on each individual in the set of optimal solutions to obtain a descendant population for the current iteration round; when the current number of iterations does not reach the set number, taking the descendant population as input, returning to execute the mutation operations and crossover operations on the input based on the proportional factor and the crossover operator to obtain an intermediate path population; when the current number of iterations reaches the set number, outputting the descendant population as the best solution, and terminating the loop iteration.

[0016] In addition, to achieve the above objectives, the present application also proposes a path planning device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the path planning method described above.

[0017] In addition, to achieve the above objectives, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the path planning method described above are implemented.

[0018] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the path planning method described above are implemented.

[0019] One or more technical solutions proposed in this application have at least the following technical effects: By introducing a proportional factor and crossover operator that adaptively changes based on the number of iterations, the mutation and crossover probabilities of the differential evolution algorithm are adjusted, so that the differential evolution algorithm can avoid falling into the local optimal solution as the iterations increase, which is beneficial to maintaining the diversity of the population; the squirrel search algorithm is introduced to optimize the population solved by the differential evolution algorithm, and combined with the large neighborhood search algorithm, it can effectively escape the local optimal solution created by the differential evolution algorithm, and based on continuous iterations, a logistics planning solution with lower output energy consumption and higher efficiency can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 A schematic diagram of a process flow of a path planning method provided by an embodiment of the present application is shown; Figure 2 A schematic diagram of a loop iteration process provided by an embodiment of the present application is shown; Figure 3 A schematic diagram of the structure of a path planning device provided in an embodiment of the present application is shown; Figure 4 A schematic diagram of the structure of a path planning device provided in an embodiment of the present application is shown.

[0023] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0024] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0025] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0026] The main solution of the embodiment of the present application is: obtaining a vehicle energy consumption calculation function, and establishing a path constraint model based on the energy consumption calculation function; generating an initial path population based on the path constraint model; using the initial path population as the first input, and performing a loop iteration, wherein the loop iteration includes performing mutation operations and crossover operations on the input based on a proportional factor and a crossover operator to obtain an intermediate path population, wherein the proportional factor is related to the current number of iterations and a preset proportional factor value, and the crossover operator is related to the current number of iterations and a preset crossover operator value; optimizing and screening the intermediate path population through the squirrel search algorithm to obtain a set of optimal solutions for the current iteration round; performing a large neighborhood search on each individual in the set of optimal solutions to obtain a descendant population for the current iteration round; when the current number of iterations does not reach the set number, taking the descendant population as input, returning to execute the mutation operation and crossover operation on the input based on the proportional factor and the crossover operator to obtain an intermediate path population; when the current number of iterations reaches the set number, outputting the descendant population as the best solution, and ending the loop iteration.

[0027] In related technologies, with the rapid development of Industry 4.0, traditional industrial work forms are facing unprecedented challenges. The construction of smart workshops has become an important starting point and technical approach for the manufacturing industry to promote digital transformation. Its core content is to improve the overall level of product production. As an important auxiliary link in the workshop, material distribution accounts for a large proportion of operating costs. As one of the important carriers of workshop logistics, the material handling system composed of AGV can greatly improve the production flexibility and competitiveness of enterprises.

[0028] When the AGV performs a processing task, it is powered by its own battery, and generally needs to be recharged after running for 8-10 hours. Therefore, the execution of the AGV's task may be interrupted due to insufficient power, which will lead to the interruption of the production plan and affect production efficiency. Therefore, it is very important for the smart workshop to reasonably arrange and plan the path for AGV to reduce energy consumption. It can not only save costs for enterprises and achieve the development goals of energy conservation and emission reduction, but also improve the stability of the material handling system of the smart workshop.

[0029] In summary, how to improve the overall efficiency of logistics and transportation tasks while reducing energy consumption is an urgent problem that needs to be solved.

[0030] Based on this, the present application provides a solution that enables AGV to maximize energy consumption while ensuring stable material transportation, thereby ensuring production efficiency.

[0031] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or a path planning device capable of realizing the above functions, etc. The following takes the path planning device as an example to illustrate this embodiment and the following embodiments.

[0032] Reference Figure 1 , Figure 1 The schematic diagram of the flow chart of the path planning method provided by an embodiment of the present application is shown. The path planning method can be applied to a path planning device, and includes the following steps S110 to S130: Step S110, obtaining a vehicle energy consumption calculation function, and establishing a path constraint model based on the energy consumption calculation function.

[0033] Among them, when AGV vehicles perform logistics tasks, the general scene will include multiple workstations. The layout of the workstations is not uniform and may be irregular. The workstation generally includes a buffer zone and a CNC zone. The buffer zone is used to store materials (that is, the materials transported by the AGV), and the CNC zone is used to perform production work. It is understandable that the CNC zone generally works continuously, that is, a certain amount of materials will be consumed every once in a while.

[0034] The production scheduling center is the scheduling starting point for all AGV vehicles. The production scheduling center can set the relevant parameters of the production work performed by the CNC area, such as production speed, material requirements, etc., by formulating production plans and scheduling plans. The scheduling plan controls the vehicles in the AGV vehicle group to move materials from the buffer zone and transport the materials to the CNC area. Since multiple AGV vehicles and multiple workstations are designed, in order to ensure the operation of the entire production task, it is necessary to make a preliminary plan for the flow of each vehicle in the AGV vehicle group, that is, the logistics path.

[0035] Based on the above scenario, this embodiment divides step S110 into two parts ① and ② for description.

[0036] ① In some implementations, the transport energy consumption and standby energy consumption of the vehicle can be calculated based on the vehicle's attribute information and the load requirement of the current task; the sum of the transport energy consumption and the standby energy consumption is used as the vehicle's energy consumption calculation function.

[0037] It is understandable that the vehicle does not always arrive at the workstation on time. In this embodiment, the vehicle is not allowed to arrive at the workstation late, but the vehicle is allowed to arrive at the workstation in advance to wait. Therefore, the energy consumption of the vehicle includes not only transportation energy consumption, but also standby energy consumption.

[0038] When calculating the transportation energy consumption, we can first define an undirected graph G according to the actual scenario, where G = (W, B), W refers to the nodes in the undirected graph, and the nodes can include the production scheduling center 0 and each workstation ,Right now , assuming there are n working points, then . B refers to the set of all edges in an undirected graph, that is, .

[0039] Based on the geodetic coordinate system, assuming that the AGV travels from node i to node j, the coordinates of position i are ,by represents the distance between nodes i and j, then:

[0040] Assuming that the AGV vehicle's speed is a preset fixed value v, the time required for the trip is That is:

[0041] In some implementations, if there is an obstacle between the i node and the j node, the Dijkstra algorithm may be used to calculate the distance between the two nodes. The specific implementation of the Dijkstra algorithm to calculate the distance between the two nodes is not described in detail in this embodiment.

[0042] It is understandable that after the AGV vehicle arrives at the workstation, there are still operations such as loading / unloading, which also takes a certain amount of time. Therefore, assuming represents the time to reach workstation i (from i's previous workstation), represents the usage time of workstation i, then the time for the AGV vehicle to arrive at node j is:

[0043] In some embodiments, since AGV vehicles generally run on flat ground in working scenarios, the energy consumption of the vehicle at this time is mainly affected by three forces, namely traction, friction and air resistance. Since the speed of AGV vehicles is generally not set very fast in logistics transportation scenarios, air resistance can be ignored. When the vehicle is moving, the reaction force on the vehicle is defined as ,but

[0044] in, Indicates the motor power of the AGV vehicle, usually a preset fixed value.

[0045] The friction force on the vehicle is defined as ,but

[0046] Among them, m refers to the weight of the AGV vehicle, g is the acceleration due to gravity, Refers to the rolling friction coefficient.

[0047] In order to solve the energy consumption changes caused by load changes, this embodiment defines an energy consumption function to calculate the energy consumption of AGV vehicles under different loads, where it is assumed that is the unladen weight of the vehicle, is the capacity of the vehicle, a is the energy consumption coefficient of the vehicle, then the energy consumption of the vehicle under full load can be expressed as:

[0048] The energy consumption of a vehicle under no-load conditions can be expressed as:

[0049] Then the parameter It can be calculated by the following expression:

[0050] Assume that the current vehicle load is , the energy consumption of the current vehicle can be expressed as:

[0051] In some implementations, a mixed integer programming expression may be constructed where: is the cost per unit of energy, n represents the total number of workstations, m represents the total number of AGV vehicles, K represents the set of all AGV vehicles, and k represents any AGV vehicle in the AGV set K. Then:

[0052] in, is the unit energy cost, represents the delivery demand of workstation i, and is the total demand for deliveries and pickups along an arc, It can be calculated by the following formula:

[0053] In summary, the total energy consumption of the AGV vehicle transportation process can be expressed as:

[0054] The AGV vehicle group has a total of m vehicles, and k is any vehicle in the AGV vehicle group.

[0055] As mentioned above, during the working process of the AGV vehicle, in this embodiment, the vehicle is allowed to arrive at the workstation in advance, but the AGV vehicle is not allowed to arrive at the workstation late.

[0056] In some implementations, the standby energy consumption of the vehicle is defined as:

[0057] in, Indicates the time when the AGV is expected to leave. Indicates the time when the AGV vehicle is expected to enter the site. is the service time length of workstation i, is the time when the kth AGV vehicle arrives at the i workstation.

[0058] Based on the above steps, the energy consumption calculation function of the vehicle can be obtained:

[0059] ② The purpose of this embodiment is to reduce the energy consumption of the entire logistics operation by changing the logistics path of the AGV vehicle. Therefore, based on the energy consumption calculation function, a path constraint model can be established with the goal of minimizing vehicle energy consumption. When constructing a path constraint model, the constraint conditions can be constructed first.

[0060] Specifically, the constraints are as follows: (1) (2) (3) (4) (5) (6) (7) (8) (9) (10) (11) (12) (13) In the above path constraint model, H represents the ordered node set of the path. represents the pickup demand of the workstation. Constraint (1) ensures that each workstation can only be visited by one AGV and can only be visited once. Constraint (2) stipulates that reverse paths and possible loops are not allowed. Constraint (3) stipulates that each AGV starts from the production scheduling center and returns to the production scheduling center. Constraint (4) limits the number of AGVs used. Constraint (5) ensures that the service time of the AGV to the workstation does not exceed the point, that is, the time window constraint. Constraint (6) ensures that the load of any workstation on the AGV transportation route does not exceed the maximum load of the vehicle body. Constraints (7)-(10) determine the upper and lower limits of pickup. Constraints (11) and (12) deal with the pickup and delivery needs on the route and the balance of the load on the arc. Constraint (13) is a decision variable constraint.

[0061] Step S120: generating an initial path population based on the path constraint model.

[0062] Based on the path constraint model constructed in step S110, the staff can determine the input of the path constraint model based on the actual task requirements. For example, based on the task requirements, the pickup requirements of different workstations, the number of AGV vehicles, the weight and load of AGV vehicles, etc. can be determined.

[0063] Through the path constraint model, the initial path population can be output eventually. Specifically, according to the characteristics of GVRPSDPTW, a natural number encoding mechanism can be used for chromosome encoding. Among them, the total number of genes on each chromosome in the population is n+m. Assuming that the workstations are numbered (1,2,3,...,n) and the AGV vehicles are numbered (n+1,n+2,n+3,...,n+m), the chromosome genes can be divided into multiple gene fragments, each of which represents a path of the AGV fleet in the logistics transportation task.

[0064] Step S130, taking the initial path population as the first input, optimizing the initial path population through loop iteration to obtain the best solution.

[0065] As mentioned above, the initial path population is only a feasible solution given by a mathematical model and is not necessarily the optimal solution pursued by this embodiment. Therefore, the embodiment of the present application is designed to continuously iterate and optimize the initial path population through step S130 in order to obtain the best solution.

[0066] Specifically, in this embodiment, Figure 2 As shown, the loop iteration for optimization is designed as the following steps S01 to S05: Step S01, based on the scale factor and the crossover operator, perform mutation operation and crossover operation on the input to obtain the intermediate path population.

[0067] In some embodiments, a differential evolution (DE) algorithm may be used to optimize the input. Specifically, DE is an optimization algorithm based on swarm intelligence theory, which generally includes at least three steps: initialization, mutation, and crossover. It can be understood that initialization is to obtain input, and through step S120, the input of the first loop iteration, i.e., the initial path population, has been obtained.

[0068] Mutation operation Mutation is to obtain a new solution different from the current population. Taking the first cycle iteration as an example, in this embodiment, for the target individual in the initial path population, two other individuals can be randomly selected in the initial path population and mutated using the following expression:

[0069] in, For the target individual, is the scale factor, and are the two random individuals mentioned above.

[0070] In the mutation strategy, the value of the proportional factor is highly correlated with the result. When the value of F is large, it is easy to get the optimal solution, but the convergence speed of the algorithm will decrease. On the contrary, the convergence speed of the algorithm becomes faster, but it is easy to stagnate.

[0071] To solve this problem, the present application designs a variable adaptive scaling factor, which changes continuously based on the number of iterations, to achieve the effect of "larger in the early stage of iteration and gradually smaller as the number of iterations increases".

[0072] In some embodiments, the scaling factor It can be obtained by the following expression:

[0073] in, is the preset scale factor value of the scale factor, It can be expressed by the following expression:

[0074] in, is the set number of iterations (i.e. the pre-set maximum number of iterations), is the current iteration number.

[0075] Through the above formula, in the early stage of iteration, the proportional factor can take a larger value, thereby maintaining the diversity of the population; during the iteration process, the proportional factor gradually decreases, and the convergence speed and local optimization ability gradually improve.

[0076] In addition, during the iteration process, There may be illegal values, such as negative numbers and duplicate values. Therefore, we will Through legalization. Define g as the value of the gene in the chromosome, P as the pre-defined maximum value of the gene, then if the gene g of the mutant individual is greater than P, then g=gP; if g is less than 0, then g=g+P; if there are multiple genes with the same value of g, only one gene with the value of g is retained. Finally, the missing gene fragments are corrected and screened.

[0077] In this embodiment, if some genes are deleted through the aforementioned correction and screening operations, the chromosome can be improved by adding the missing genes at the end of the chromosome to make up the number of genes.

[0078] Crossover operation is to increase the diversity of the population. In the crossover operation, a smaller crossover operator can avoid destroying mutant individuals; a larger crossover operator can prevent the algorithm from falling into the local optimum in the late stage of evolution and increase the diversity of the population. Therefore, in this embodiment, similar to the scale factor, the accuracy of the iterative process is guaranteed by setting an adaptively changing crossover operator.

[0079] Specifically, the crossover operator can be obtained by the following expression:

[0080] in, is the crossover operator, is the preset crossover operator value, It can be expressed by the following expression:

[0081] In order to ensure the comprehensiveness of the crossover operator during the iteration process, Can be set to 0.9.

[0082] Through the above mutation and crossover operations, the intermediate path population after the initial optimization is obtained.

[0083] Step S02: Optimize and screen the intermediate path population through the squirrel search algorithm to obtain a set of optimal solutions for the current iteration round.

[0084] The Squirrel Search Algorithm (SSA) searches for optimal solutions by simulating squirrels gliding between different types of trees (such as common trees, oak trees, and hickory trees) to find food and avoid the threat of predators.

[0085] In this embodiment, the squirrel search algorithm may include the following steps: ①For each individual in the intermediate path population, calculate the corresponding first fitness.

[0086] Since the purpose of this application is to find a solution with minimum energy consumption, the calculation method of the first fitness can be defined as the inverse of the total energy consumption E corresponding to the individual. The larger the first fitness, the lower the energy consumption.

[0087] ② Based on the first fitness, multiple individuals are classified into optimal solutions, suboptimal solutions and ordinary solutions.

[0088] The first fitness of multiple individuals can be sorted in order of size to form a queue. In the queue, the optimal solution, the suboptimal solution and the common solution are determined in sequence based on the set ratio (or quantity) according to the order of the first fitness from small to large.

[0089] The number (or proportion in the entire population) of the optimal solution (i.e., the hickory tree), the suboptimal solution (i.e., the oak tree), and the common solution (i.e., the common tree) can be preset by the staff. For example, in this embodiment, the number of optimal solutions can be set to x, the proportion of suboptimal solutions can be set to 10%, and the remaining individuals are all common solutions.

[0090] ③ Cross the individuals of the optimal solution type with the individuals of the suboptimal solution type, and cross the individuals of the suboptimal solution type with the individuals of the ordinary solution type to obtain multiple offspring individuals to be screened.

[0091] In this embodiment, in order to enhance the diversity and global search capability of SSA, an OX (Order-based Crossover) crossover operation may be introduced into the algorithm.

[0092] Specifically, for individuals in the suboptimal solution type, a random individual in the optimal solution type can be selected, and an OX crossover operation can be performed between them. For individuals in the common solution, a random individual in the suboptimal solution type can be selected, and an OX crossover operation can be performed between them.

[0093] By hybridizing different individuals through the above-mentioned OX crossover operation, more diversity can be introduced, preventing the obtained offspring individuals to be screened from falling into the local optimum too early.

[0094] ④ Calculate the second fitness of each offspring individual to be screened.

[0095] As mentioned above, the second fitness is similar to the first fitness, and the inverse of the total energy consumption E corresponding to the offspring individuals to be screened can be used as the second fitness, that is, the larger the second fitness, the smaller the energy consumption.

[0096] ⑤ Based on the second fitness, filter out the set of better solutions for the current iteration round.

[0097] In some implementations, the set of individuals with the target ratio of the second lowest fitness can be used as the set of better solutions. Specifically, in this embodiment, the target ratio can be 25%.

[0098] Step S03, performing a large neighborhood search on each individual in the set of better solutions to obtain the offspring population of the current iteration round.

[0099] The differential evolution algorithm is prone to fall into a local optimal solution during the solution process. To solve this problem, this embodiment designs a large neighborhood search algorithm to perform a local search on the excellent individuals in the set of better solutions, thereby improving the quality of the solution generated in this round of iteration.

[0100] It is understandable that the large neighborhood search algorithm includes two parts: destruction and repair, the purpose of which is to remove some parts of the current set in order to find a new feasible and better solution.

[0101] ①Destruction operation In this embodiment, the Shaw removal (SR) method is used. The general idea of ​​the SR operator is to remove multiple groups of points. The similarity between two workstations i and j is determined by the association weight To define, it includes two items: distance item and related projects . Using the distance between workstations i and j To define their relevance . The lower the value, the greater the relationship between the two workstations. Used to describe whether workstations i and j are on the same path. The determination method is the same as The same, because the relationship between two workstations i and j on the same transmission path is greater than the relationship on different transmission paths. The expression is as follows:

[0102] in, ,Right now is a value in the interval [0,1]; if i and j are on the same path, then is 0, otherwise is 1.

[0103] In this embodiment, the first node to be removed is randomly selected, and starting from the second node to be removed, the selection of the nodes to be removed subsequently is based on the relevance of the previously removed node (i.e., the above-mentioned relevance weight ), that is, the next node to be removed has the highest correlation with the current node.

[0104] ②Repair operation The greedy repair operator is the most commonly used insertion operator method. In this embodiment, let represents the change in the objective function value caused by inserting the best position of n into workstation i. hour, .

[0105] In the embodiment of the present application, a regret-regret-2 operator is set up to loop the nodes (workstations) to be inserted into all positions in the line in turn, and record the position that makes the objective function change best.

[0106] Among them, the objective function can be defined as:

[0107] Then the position that best changes the objective function can be expressed as follows:

[0108] In the above way, workstation i is continuously inserted at the optimal position until the number of workstations reaches the number before destruction in ①.

[0109] Through the large neighborhood search algorithm implemented by ① and ② above, the offspring population of the current iteration round can be calculated. It can be understood that the offspring population finally obtained after differential evolution, squirrel search algorithm and large neighborhood search algorithm is the optimal solution obtained in this round of iteration.

[0110] Step S04, when the current number of iterations does not reach the set number of iterations, the offspring population is used as input and the process returns to step S01.

[0111] Before the implementation of the loop iteration is started in step S130, the set number of iterations may be set in advance. It is understandable that the optimal solution obtained in the previous iteration round is used as input for the next iteration round, so that the solution can be continuously optimized.

[0112] Step S05, when the current number of iterations reaches the set number, the offspring population is output as the best solution, and the loop iteration ends.

[0113] This embodiment provides a path planning method, which introduces a proportional factor and a crossover operator that adaptively change based on the number of iterations, thereby adjusting the mutation and crossover probabilities of the differential evolution algorithm, so that the differential evolution algorithm avoids falling into a local optimal solution as the iterations increase, which is beneficial to maintaining the diversity of the population; the squirrel search algorithm is introduced to optimize the population solved by the differential evolution algorithm, and combined with the large neighborhood search algorithm, the local optimal solution created by the differential evolution algorithm can be effectively avoided, and based on continuous iterations, a logistics planning solution with lower output energy consumption and higher efficiency can be achieved.

[0114] This application also provides a path planning device, please refer to Figure 3 , the path planning device 100 includes: A parameter predefinition module 110 is used to obtain a vehicle energy consumption calculation function and establish a path constraint model based on the energy consumption calculation function; A population initialization module 120 is used to generate an initial path population based on a path constraint model; The loop iteration module 130 is used to perform loop iteration with the initial path population as the first input, wherein the loop iteration includes performing mutation operations and crossover operations on the input based on a proportional factor and a crossover operator to obtain an intermediate path population, wherein the proportional factor is related to the current number of iterations and a preset proportional factor value, and the crossover operator is related to the current number of iterations and a preset crossover operator value; optimizing and screening the intermediate path population through the squirrel search algorithm to obtain a set of better solutions for the current iteration round; performing a large neighborhood search on each individual in the set of better solutions to obtain a descendant population for the current iteration round; when the current number of iterations does not reach the set number, using the descendant population as input, returning to execute mutation operations and crossover operations on the input based on the proportional factor and the crossover operator to obtain an intermediate path population; when the current number of iterations reaches the set number, outputting the descendant population as the best solution, and terminating the loop iteration.

[0115] The path planning device 100 provided in the present application adopts the path planning method in the above embodiment, which can solve the technical problem of how to improve the overall efficiency of logistics transportation tasks while reducing energy consumption. Compared with the prior art, the beneficial effects of the path planning device 100 provided in the present application are the same as the beneficial effects of the path planning method provided in the above embodiment, and the other technical features in the path planning device 100 are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0116] The present application provides a path planning device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the path planning method in the above-mentioned embodiment one.

[0117] Reference below Figure 4, which shows a schematic diagram of the structure of a path planning device suitable for implementing the embodiment of the present application. The path planning device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The path planning device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0118] like Figure 4 As shown, the path planning device 200 may include a processing device 210 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 220 or a program loaded from a storage device 230 to a random access memory (RAM: Random Access Memory) 240. In RAM240, various programs and data required for the operation of the path planning device are also stored. The processing device 210, ROM220 and RAM240 are connected to each other through a bus 250. An input / output (I / O) interface 260 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 260: an input device 270 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 280 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 230 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 290. The communication device 290 can allow the path planning device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a path planning device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0119] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through a communication device, or installed from the storage device 230, or installed from the ROM 220. When the computer program is executed by the processing device 210, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0120] The path planning device provided by the present application adopts the path planning method in the above embodiment, which can solve the technical problem of how to improve the overall efficiency of logistics transportation tasks while reducing energy consumption. Compared with the prior art, the beneficial effects of the path planning device provided by the present application are the same as the beneficial effects of the path planning method provided by the above embodiment, and the other technical features in the path planning device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0121] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0122] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0123] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the path planning method in the above-mentioned embodiment.

[0124] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0125] The computer-readable storage medium may be included in the path planning device; or may exist independently without being assembled into the path planning device.

[0126] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the path planning device, the path planning device can write computer program codes for performing the operations of the present application in one or more programming languages ​​or a combination thereof. The programming languages ​​include object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0127] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0128] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0129] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned path planning method, and can solve the technical problem of how to improve the overall efficiency of logistics transportation tasks while reducing energy consumption. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the path planning method provided by the above-mentioned embodiment, and will not be repeated here.

[0130] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned path planning method when executed by a processor.

[0131] The computer program product provided by this application can solve the technical problem of how to improve the overall efficiency of logistics transportation tasks while reducing energy consumption. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the path planning method provided by the above embodiment, which will not be repeated here.

[0132] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A path planning method, characterized in that: The path planning method comprises: Obtaining a vehicle energy consumption calculation function, and establishing a path constraint model based on the energy consumption calculation function; Based on the path constraint model, generating an initial path population; The initial path population is used as the first input to perform loop iterations, wherein the loop iterations include performing mutation operations and crossover operations on the input based on a scaling factor and a crossover operator to obtain an intermediate path population, wherein the scaling factor is related to the current number of iterations and a preset scaling factor value, and the crossover operator is related to the current number of iterations and a preset crossover operator value; the intermediate path population is optimized and screened by a squirrel search algorithm to obtain a set of optimal solutions for the current iteration round; a large neighborhood search is performed on each individual in the set of optimal solutions to obtain a descendant population for the current iteration round; when the current number of iterations does not reach the set number, the descendant population is used as input, and the execution of the mutation operation and crossover operation based on the scaling factor and the crossover operator is returned to obtain an intermediate path population; when the current number of iterations reaches the set number, the descendant population is output as the best solution, and the loop iterations are terminated.

2. The path planning method according to claim 1, characterized in that: The obtaining of the vehicle energy consumption calculation function comprises: Calculate the vehicle's transportation energy consumption and standby energy consumption based on the vehicle's attribute information and the load requirements of the current task; The sum of the transportation energy consumption and the standby energy consumption is used as the energy consumption calculation function of the vehicle.

3. The path planning method according to claim 2, characterized in that: The establishing of a path constraint model based on the energy consumption calculation function comprises: Establish a path constraint model with the goal of minimizing vehicle energy consumption; Construct constraints, including: access constraints, path direction constraints, available vehicle quantity constraints, service time constraints, vehicle load constraints, pickup demand constraints, balance constraints, and decision variable constraints.

4. The path planning method according to claim 2, characterized in that: The scaling factor is expressed by the following expression: in, is the preset scale factor value of the scale factor, It can be expressed by the following expression: in, is the set number of iterations of the loop, is the current iteration number.

5. The path planning method according to claim 4, characterized in that: The crossover operator is expressed by the following expression: in, is the crossover operator, is the preset crossover operator value, It can be expressed by the following expression: 。 6. The path planning method according to claim 1, characterized in that: The squirrel search algorithm is used to optimize and screen the intermediate path population to obtain a set of optimal solutions for the current iteration round, including: For each individual in the intermediate path population, calculating the corresponding first fitness; Based on the first fitness, the multiple individuals are classified into optimal solutions, suboptimal solutions and common solutions; Cross the individuals of the optimal solution type with the individuals of the suboptimal solution type, and cross the individuals of the suboptimal solution type with the individuals of the common solution type to obtain multiple offspring individuals to be screened; Calculating the second fitness of each of the offspring individuals to be screened; Based on the second fitness, a set of better solutions for the current iteration round is screened and obtained.

7. A path planning device, characterized in that: The path planning device comprises: A parameter predefinition module, used to obtain a vehicle energy consumption calculation function and establish a path constraint model based on the energy consumption calculation function; A population initialization module, used to generate an initial path population based on the path constraint model; A loop iteration module is used to perform loop iteration with the initial path population as the first input, wherein the loop iteration includes performing mutation operation and crossover operation on the input based on a proportional factor and a crossover operator to obtain an intermediate path population, wherein the proportional factor is related to the current number of iterations and a preset proportional factor value, and the crossover operator is related to the current number of iterations and a preset crossover operator value; optimizing and screening the intermediate path population through a squirrel search algorithm to obtain a set of optimal solutions for the current iteration round; performing a large neighborhood search on each individual in the set of optimal solutions to obtain a descendant population for the current iteration round; when the current number of iterations does not reach the set number, taking the descendant population as input, returning to execute the mutation operation and crossover operation on the input based on the proportional factor and the crossover operator to obtain an intermediate path population; when the current number of iterations reaches the set number, outputting the descendant population as the best solution, and terminating the loop iteration.

8. A path planning device, characterized in that: The path planning device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the path planning method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the path planning method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the path planning method according to any one of claims 1 to 6 are implemented.

Images