Task scheduling method and device for steel grabbing machine
Through genetic algorithms, the task scheduling of steel grab machines is solved, and the inefficiency and safety risks of multiple machines in the scrap steel yard are solved. Intelligent scheduling and efficient task execution are realized, providing unmanned scrap steel yards Technical support.
Patent Information
- Application Number
- CN202411007677.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-25
- Publication Date
- 2024-11-15
AI Technical Summary
In scrap steel yard, when multiple steel grab machines perform tasks in concert, the coupling relationship between task scheduling and path planning leads to inefficiency, safety risks, and increased labor costs.
Using genetic algorithms, by obtaining multiple task scheduling schemes, using task scheduling schemes as chromosomes, determining the fitness according to the path length required by the target steel grafting machine to complete the service task, perform selection, crossover and mutation operations, and generate optimized task paths to Realize intelligent scheduling of steel grab machines.
It realizes the intelligent scheduling of multi-machine clusters of scrap steel yards, reduces the risk of collaborative operations, improves the scheduling efficiency of steel yards, and provides support for the reduction and unmanned scrap steel yards.
Smart Images

Figure CN118966651A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of steel grabbers, and in particular to a task scheduling method and device for steel grabbers. Background Art
[0002] In recent years, with the acceleration of industrialization and the continuous increase in urbanization, the demand for steel has continued to expand. As an important downstream base for steel processing, the internal operating burden of the scrap steel yard has continued to increase. As a special equipment, the steel grabber is mainly used for steel loading and unloading, shearing feeding, steel packaging and other operations. It is a core operating tool in the scrap steel yard. At present, when manually operating the steel grabber to handle large orders, the following problems may occur: 1. Manual operation of the steel grabber and other equipment may lead to inefficiency; 2. Operating the steel grabber to handle scrap steel may involve safety risks such as scrap steel falling, and the stability and safety of the operation may be affected due to operator fatigue or inconsistent skills; 3. Long-term manual operation may result in expensive labor costs.
[0003] The steady development of the steel industry has made unmanned, intelligent, and environmentally friendly an inevitable trend in the transformation of the steel industry. In the future, unmanned steel grabbers will also be the general trend. Unmanned technology can improve operational efficiency and safety, reduce human errors, and achieve more precise operational control. Unmanned steel grabbers can achieve more efficient and safe scrap steel processing through advanced sensors and control systems. However, the scheduling and coordination of multiple steel grabbers is also an important factor affecting efficiency. Considering the scheduling of steel grabbers and ensuring the coordinated scheduling of steel grabbers is the key to improving the operating efficiency of the entire scrap steel yard.
[0004] In the process of multiple grabbers cooperating to perform tasks in a scrap steel yard, the number of tasks performed by the grabbers and their time sequence relationship will affect the planning results of the grabber's driving path, and sometimes even a feasible driving path cannot be generated; conversely, the different driving paths selected by the grabber will have an important impact on the efficiency of its task execution. Therefore, the task allocation and path planning of multiple vehicles and machines in the scrap steel yard are mutually coupled, and simple separation processing often reduces the final execution efficiency of the task. Therefore, a new task scheduling method for grabbers is urgently needed to realize the intelligent scheduling of multiple machines in the scrap steel yard cluster collaboration, reduce the risk of collaborative operation, and improve the scheduling efficiency of grabbers in the scrap steel yard, providing strong support for the realization of less-managed and unmanned operations in the scrap steel yard.
[0005] It should be noted that the above content only provides background technical information related to the present application and does not necessarily constitute prior art. Summary of the invention
[0006] In view of the shortcomings of the prior art mentioned above, the present application provides a task scheduling method and device for a steel grabber to realize cluster collaborative multi-machine intelligent scheduling in a scrap steel yard, reduce the risk of collaborative operations and improve the scheduling efficiency of steel grabbers in scrap steel yards, and provide strong support for realizing the less-manned or unmanned operation of scrap steel yards.
[0007] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.
[0008] According to one aspect of an embodiment of the present application, a task scheduling method for a steel grabber is provided, comprising: obtaining a plurality of task scheduling schemes, wherein the task scheduling schemes include service tasks corresponding to one or more target steel grabbers; using each of the task scheduling schemes as a chromosome in a population, and determining the fitness corresponding to each of the chromosomes according to the path length required for the target steel grabber to complete the service task; using a genetic algorithm to update each of the task scheduling schemes according to the fitness, wherein the genetic algorithm includes at least one of a selection operation, a crossover operation, and a mutation operation; determining a target scheduling scheme from the updated task scheduling schemes, and scheduling the target steel grabber through the task path in the target scheduling scheme.
[0009] In one embodiment of the present application, based on the aforementioned scheme, multiple groups of task scheduling schemes are obtained, including: obtaining a service task for the current scene, wherein the current scene includes a pile of materials to be collected and / or an area to be stacked, and the service task includes collecting materials from the pile of materials to be collected, and / or placing the materials in the area to be stacked; generating a plurality of task scheduling schemes according to scheme generation rules, wherein the scheme generation rules include randomly allocating at least a part of the service tasks to at least a part of the target steel grabber, so as to generate a task scheduling scheme according to the correspondence between the service tasks and the target steel grabber.
[0010] In one embodiment of the present application, based on the aforementioned scheme, at least a part of the service tasks is randomly assigned to at least a part of the target steel grabbers to generate a task scheduling scheme according to the correspondence between the service tasks and the target steel grabbers, including: obtaining the number of steel grabbers and the number of service tasks; if the number of steel grabbers is greater than the number of service tasks, randomly assigning all the service tasks to at least a part of the target steel grabbers to generate a task scheduling scheme according to the correspondence between the service tasks and the target steel grabbers; if the number of steel grabbers is less than or equal to the number of service tasks, randomly assigning at least a part of the service tasks to all the target steel grabbers to generate a task scheduling scheme according to the correspondence between the service tasks and the target steel grabbers.
[0011] In one embodiment of the present application, based on the aforementioned scheme, the fitness corresponding to each of the chromosomes is determined according to the path length required for the target steel grabber to complete the service task, including: constructing a discrete point network according to the current scene, wherein the discrete point network is used to characterize target elements and obstacle elements, and the target elements include the target steel grabber, the pile of materials to be collected and / or the area to be stacked; planning element edges between each of the target elements in the discrete point network, wherein the element edges do not pass through the obstacle elements; establishing a task path corresponding to the target steel grabber performing the service task from the element edges according to a preset path algorithm, and calculating the path length of the task path; calculating according to the path length corresponding to the same task scheduling scheme, and obtaining the fitness of the chromosome corresponding to the task scheduling scheme.
[0012] In one embodiment of the present application, based on the above scheme, the fitness is calculated by the following formula: In the formula, f(i) is the fitness, m is the number of steel grabbers, and D ij represents the travel time of the j-th steel grabber in the i-th chromosome, P ij is the priority weight of the task executed by the j-th steel grabber in the i-th chromosome, T ij The task execution time of the j-th steel grabber in the i-th chromosome to perform the service task.
[0013] In one embodiment of the present application, based on the aforementioned scheme, the selection operation is performed in the following manner: the fitness ratio of each chromosome to the total fitness of the population is calculated, and the fitness ratio is used as the selection probability of each chromosome being inherited to the next generation population, wherein the total fitness of the population is calculated based on the fitness of each chromosome; the cumulative probability of each chromosome is calculated based on the selection probability; a first random number within a preset range is randomly generated, and if the first random number is less than the cumulative probability, the chromosome corresponding to the cumulative probability is selected to the next generation population until the number of selected chromosomes is greater than or equal to the preset selection number.
[0014] In one embodiment of the present application, based on the above-mentioned scheme, a crossover operation is performed in the following manner: randomly select a first parent chromosome and a second parent chromosome, and randomly determine two crossover points; inherit the gene fragment between the two crossover points in the first parent chromosome to the corresponding position of the first daughter chromosome, use the genes outside the two crossover points in the first parent chromosome as first complementary genes, and inherit the corresponding first complementary genes in the second parent chromosome in sequence to the remaining positions of the first daughter chromosome; inherit the gene fragment between the two crossover points in the second parent chromosome to the corresponding position of the second daughter chromosome, use the genes outside the two crossover points in the second parent chromosome as second complementary genes, and inherit the corresponding second complementary genes in the first parent chromosome in sequence to the remaining positions of the second daughter chromosome.
[0015] In one embodiment of the present application, based on the aforementioned scheme, a mutation operation is performed in at least one of the following ways: randomly selecting a chromosome in the population according to a first preset probability, and randomly selecting two random points, and rewriting the genes between the two random points in reverse order; randomly selecting a chromosome in the population according to a second preset probability, and randomly selecting a first random point and a second random point, and exchanging the positions corresponding to the first random point and the second random point.
[0016] In one embodiment of the present application, based on the aforementioned scheme, the target steel grabber is scheduled through the task path in the target scheduling scheme, including: classifying the service tasks according to the task priorities corresponding to the service tasks, and determining the currently executed task according to the classification results; if it is determined that the first task path and the second task path have an intersection, calculating the time difference between the first steel grabber arriving at the intersection and the second steel grabber arriving at the intersection, wherein the first task path is the task path for the first steel grabber to perform the currently executed task, and the second task path is the task path for the second steel grabber to perform the second executed task; if the time difference is less than a preset time threshold, the target scheduling scheme is updated based on a preset adjustment method, and the target steel grabber is scheduled through the task path in the target scheduling scheme, wherein the preset adjustment method includes adjusting one or more of the departure time, driving speed and task path of the target steel grabber.
[0017] According to one aspect of an embodiment of the present application, a task scheduling device for a steel grabber is provided, comprising: an acquisition module, for acquiring a plurality of task scheduling schemes, wherein the task scheduling schemes include service tasks corresponding to one or more target steel grabbers; a determination module, for treating each of the task scheduling schemes as a chromosome in a population, and determining the fitness corresponding to each of the chromosomes according to the path length required for the target steel grabber to complete the service task; an update module, for adopting a genetic algorithm to update each of the task scheduling schemes according to the fitness, wherein the genetic algorithm includes at least one of a selection operation, a crossover operation and a mutation operation; a scheduling module, for determining a target scheduling scheme from the updated task scheduling schemes, and scheduling the target steel grabber through the task path in the target scheduling scheme.
[0018] Beneficial effects of the present application: The present application obtains a variety of task scheduling schemes, wherein the task scheduling schemes include service tasks corresponding to one or more target steel grabbers, and each task scheduling scheme is used as a chromosome in the population. The fitness corresponding to each chromosome is determined according to the path length required for the target steel grabber to complete the service task. A genetic algorithm is used to update each task scheduling scheme according to the fitness, wherein the genetic algorithm includes at least one of selection operation, crossover operation and mutation operation. The target scheduling scheme is determined from the updated task scheduling scheme, and the target steel grabber is scheduled through the task path in the target scheduling scheme, thereby realizing cluster collaborative multi-machine intelligent scheduling in the scrap steel yard, reducing the risk of collaborative operation, and improving the scheduling efficiency of the steel grabbers in the scrap steel yard, providing strong support for realizing the less-manned and unmanned operation of the scrap steel yard.
[0019] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:
[0021] Figure 1 is a schematic diagram of an exemplary system architecture shown in an exemplary embodiment of the present application;
[0022] Figure 2 is a flow chart of a task scheduling method for a steel grabber shown in an exemplary embodiment of the present application;
[0023] Figure 3is a schematic diagram of an example of a coding chromosome of a task scheduling method for a steel grabber shown in an exemplary embodiment of the present application;
[0024] Figure 4 is a schematic diagram of a chromosome sequence crossover example of a task scheduling method for a steel grabber shown in an exemplary embodiment of the present application;
[0025] Figure 5 is a schematic diagram of a chromosome sequence crossover example of a task scheduling method for a steel grabber shown in another exemplary embodiment of the present application;
[0026] Figure 6 is a schematic diagram of an example of chromosome inversion mutation of a task scheduling method for a steel grabber shown in an exemplary embodiment of the present application;
[0027] Figure 7 is a schematic diagram of a chromosome exchange variation example of a task scheduling method for a steel grabber shown in an exemplary embodiment of the present application;
[0028] Figure 8 It is a schematic diagram of an algorithm test scenario and calculation results of a task scheduling method for a steel grabber shown in an exemplary embodiment of the present application;
[0029] Fig. 9 is a flow chart of a task scheduling method for a steel grabber shown in another exemplary embodiment of the present application;
[0030] Fig.10 is a block diagram of a task scheduling device for a steel grabber shown in an exemplary embodiment of the present application;
[0031] Fig.11 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION
[0032] The following will describe the implementation methods of the present application with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for illustrating the present application, not for limiting the scope of protection of the present application.
[0033] It should be noted that the illustrations provided in the following embodiments are only used to illustrate the basic concept of the present application in a schematic manner, and therefore the illustrations only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.
[0034] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present application. However, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present application difficult to understand.
[0035] First of all, it should be explained that the genetic algorithm (GA) is a computational model of the biological evolution process that simulates the natural selection and genetic mechanisms of Darwin's theory of biological evolution. It uses mathematical methods and computer simulation operations to convert the problem-solving process into a process similar to the crossover and mutation of chromosome genes in biological evolution. Compared with some conventional optimization algorithms, genetic algorithms can usually obtain better optimization results faster when solving more complex combinatorial optimization problems.
[0036] Centralized solution algorithm,In the centralized optimization algorithm, all calculations and decisions are performed on a central node, and all information (such as objective function, constraints, etc.) must be concentrated together for processing.
[0037] Dijkstra's algorithm is an algorithm for finding the shortest path from a single source point to all other points in a graph. This algorithm is applicable to graphs with non-negative weights. Dijkstra's algorithm is based on a greedy strategy and gradually builds a shortest path tree until it contains all vertices.
[0038] In optimization algorithms such as genetic algorithms, Roulette Wheel Selection is a commonly used selection strategy. Its basic idea is to calculate the probability of each individual appearing in the offspring based on the individual's fitness value, and randomly select individuals to form the offspring population according to this probability. This method is also called the fitness proportional method or proportional selection method. In genetic algorithms, each individual (chromosome) is regarded as a sector on the roulette wheel, and the area of the sector is proportional to its fitness value. Therefore, the higher the fitness value of an individual, the larger its sector area, and the greater the possibility of being selected into the next generation.
[0039] Figure 1 It is a schematic diagram of an exemplary system architecture shown in an exemplary embodiment of the present application.
[0040] Reference Figure 1 As shown, the system architecture may include a data acquisition device 101 and a computer device 102. Among them, the computer device 102 may be at least one of a desktop graphics processing unit (GPU) computer, a GPU computing cluster, a neural network computer, etc. The data acquisition device 101 is used to collect the current scene and service tasks. In this embodiment, the data acquisition device 101 obtains the above data and provides it to the computer device 102 for processing. Relevant technicians can use the computer device 102 to generate a variety of task scheduling schemes according to the scheme generation rules, respectively, and use each task scheduling scheme as a chromosome in the population, and determine the fitness corresponding to each chromosome according to the path length required for the target steel grabber to complete the service task, and use a genetic algorithm to update each task scheduling scheme according to the fitness, determine the target scheduling scheme from the updated task scheduling scheme, and schedule the target steel grabber through the task path in the target scheduling scheme. It should be noted that the data acquisition device 101 and the computer device 102 provided in this embodiment are only an example, and should not bring any restrictions to the functions and scope of use of the embodiments of the present application.
[0041] It should be noted that the task scheduling method for the steel grabber provided in the embodiment of the present application is generally executed by the computer device 102 , and accordingly, the task scheduling device for the steel grabber is generally arranged in the computer device 102 .
[0042] Figure 2 is a flowchart of a task scheduling method for a steel grabber shown in an exemplary embodiment of the present application. The task scheduling method for a steel grabber can be executed by a computing and processing device, which can be Figure 1 The computer device 102 shown in FIG. Figure 2 As shown, the task scheduling method for the steel grabber includes at least steps S210 to S240, which are described in detail as follows:
[0043] In step S210, multiple task scheduling schemes are obtained.
[0044] Among them, the task scheduling plan includes service tasks corresponding to one or more target steel grabbers.
[0045] In one embodiment of the present application, a service task for the current scene is obtained, wherein the current scene includes a pile of materials to be collected and / or an area to be stacked, and the service task includes collecting materials from the pile of materials to be collected, and / or placing the materials in the area to be stacked; a plurality of task scheduling schemes are generated respectively according to scheme generation rules, wherein the scheme generation rules include randomly allocating at least a part of the service tasks to at least a part of the target steel grabber, so as to generate a task scheduling scheme according to the correspondence between the service tasks and the target steel grabber.
[0046] In one embodiment of the present application, the number of steel grabbers and the number of service tasks are obtained; if the number of steel grabbers is greater than the number of service tasks, all service tasks are randomly assigned to at least a part of the target steel grabbers to generate a task scheduling plan based on the correspondence between the service tasks and the target steel grabbers; if the number of steel grabbers is less than or equal to the number of service tasks, at least a part of the service tasks are randomly assigned to all target steel grabbers to generate a task scheduling plan based on the correspondence between the service tasks and the target steel grabbers.
[0047] In this embodiment, the initial population is very important to the genetic algorithm, which directly affects the convergence speed of the fitness value and the quality of the solution. The steps for generating the initial population in this application are as follows:
[0048] ① Determine the relationship between the number of steel grabbers and the number of service tasks;
[0049] ② If the number of steel grabbers m is greater than the number of service tasks n, randomly generate a non-repeating sequence of length m, including all service task numbers and several 0s, where the number of 0s is determined by the difference between the number of steel grabbers and the number of service tasks. If the number of steel grabbers m is less than or equal to the number of service tasks n, randomly generate a non-repeating sequence of length m with a coding value range of [1,n]. Add the generated sequence as an initialized chromosome to the population.
[0050] ③ Determine whether the preset end conditions are met. The preset end conditions include that the number of initialized chromosomes reaches the preset population size, that is, the number of initialized chromosomes is greater than or equal to the preset number of chromosomes. If the preset end conditions are met, the current operation ends and the loop is exited. If not, go to ②.
[0051] In step S220, each task scheduling scheme is used as a chromosome in the population, and the fitness corresponding to each chromosome is determined according to the path length required for the target steel grabber to complete the service task.
[0052] In one embodiment of the present application, the correspondence between the target steel grabber and the service task is characterized in the following manner: a steel grabber quantity field, used to carry the total number of target steel grabbers; a steel grabber code field, used to carry the steel grabber code corresponding to the target steel grabber; and a task code field, used to carry the task code corresponding to the service task.
[0053] In this embodiment, each chromosome represents a solution to the problem, where the length of the chromosome is the number of steel grabbers, the position of the node in the chromosome represents the number of the steel grabber, and the code value of the node represents the number of the service task. In particular, when the code value of the node is 0, it means that the steel grabber is not assigned any service task. Figure 3 As shown, Figure 3 : is a schematic diagram of an example of a coding chromosome of a task scheduling method for a steel grabber shown in an exemplary embodiment of the present application. Figure 3 The encoding value of the 4th node is 3, indicating that the service task corresponding to the 4th steel grabber is task No. 3; the encoding value of the 7th node is 0, indicating that the 7th steel grabber does not serve any task.
[0054] In one embodiment of the present application, a discrete point network is constructed according to the current scene, wherein the discrete point network is used to characterize target elements and obstacle elements, the target elements include a target steel grabber, a pile of materials to be collected and / or an area to be stacked, and the obstacle elements include obstacles and pile areas; element edges between target elements are planned in the discrete point network, wherein the element edges do not pass through obstacle elements; a task path corresponding to the target steel grabber performing the service task is established from the element edges according to a preset path algorithm, and the path length of the task path is calculated; the fitness of the chromosome corresponding to the task scheduling scheme is obtained by calculation according to the path length corresponding to the same task scheduling scheme.
[0055] In this embodiment, the shortest path Dijkstra algorithm is called to calculate the path length of the task path corresponding to the service task performed by the target steel grabber.
[0056] In this embodiment, a discrete point network is generated according to the scene information. A discrete point network graph G is constructed according to the scene information and the layout point interval, and then the layout point V is set as an infeasible element, i.e., an obstacle element, based on the obstacle information and the stockpile information. Finally, the information of all element edges E in the discrete point network graph G is obtained, where an element edge is a line connecting any two layout points, and an element edge does not pass through an obstacle element.
[0057] In one embodiment of the present application, the fitness is calculated by the following formula:
[0058]
[0059] In formula (1), f(i) is the fitness, m is the number of steel grabbers, that is, the total number of steel grabbers, and D ij represents the travel time of the j-th steel grabber in the i-th chromosome, P ij is the task priority weight of the service task performed by the j-th steel grabber in the i-th chromosome, T ij is the task execution time of the j-th steel grabber in the i-th chromosome to perform the service task. If the service task is to grab scrap steel, then T ij is the time required for the j-th steel grabber in the i-th chromosome to grab the scrap steel. The travel time of the steel grabber is calculated by calculating the distance between the target steel grabber and the service task.
[0060] In this embodiment, the inverse of the optimized objective function value is used as the fitness function of the genetic algorithm, where the fitness function is the inverse of the total service time corresponding to the task scheduling scheme converted by the chromosome, refer to formula (1). The better the scheduling allocation scheme, the smaller the total travel distance of the steel grabber, the smaller the objective function value, and the better the fitness function value. If the steel grabber does not arrange any tasks, its corresponding fitness value is 0. The larger the fitness function value of the chromosome, the better the allocation scheme, that is, the task scheduling scheme.
[0061] In step S230, a genetic algorithm is used to update each task scheduling scheme according to the fitness.
[0062] The genetic algorithm includes at least one of a selection operation, a crossover operation and a mutation operation. The general iterative steps of the genetic algorithm include a selection operation, a crossover operation and a mutation operation.
[0063] In one embodiment of the present application, the selection operation is performed in the following manner: the fitness ratio of each chromosome to the total fitness of the population is calculated, and the fitness ratio is used as the selection probability of each chromosome inherited to the next generation population, wherein the total fitness of the population is calculated based on the fitness of each chromosome; the cumulative probability of each chromosome is calculated based on the selection probability; a first random number within a preset range is randomly generated, and if the first random number is less than the cumulative probability, the chromosome corresponding to the cumulative probability is selected to the next generation population until the number of selected chromosomes is greater than or equal to the preset selection number.
[0064] In this embodiment, the genetic algorithm needs to select excellent chromosomes from the parent generation before performing operations such as crossover and mutation, so that their excellent genes can be inherited. Common selection operators include random sampling, tournament selection, and roulette selection. In this embodiment, the roulette selection method is used to select the operator. Corresponding to the selection operation, it can be understood that the chromosome with a larger fitness value has more chances to be selected, and its excellent genes are more likely to be inherited to the next generation, which reflects the survival of the fittest mechanism of the genetic algorithm.
[0065] In this embodiment, the specific process of roulette selection is as follows:
[0066] Step 1: Calculate the fitness value f of each chromosome in the population i (chromosome number i∈{1,2,...,G}), G is the population size.
[0067] Step 2: Calculate the ratio of the fitness value of each chromosome in the population to the sum of the fitness values of the population, as the selection probability r of each chromosome being inherited to the next generation population. i , where the calculation method of the selection probability refers to formula (2):
[0068]
[0069] In formula (2), r i is the selection probability, f(i) is the fitness, and G is the population size.
[0070] Step 3: Calculate the cumulative probability a of each chromosome based on the selection probability i , where the calculation method of the selection probability refers to formula (3):
[0071]
[0072] In formula (3), a i is the cumulative probability, r j is the selection probability, i is the current chromosome number.
[0073] Step 4: Randomly generate a uniformly distributed number q between [0,1]. If q is less than a i , then the i-th chromosome is selected to enter the next generation population. Repeat the above step 4 until the number of selected chromosomes is greater than or equal to the preset number of selections.
[0074] In one embodiment of the present application, the crossover operation is performed in the following manner: randomly selecting a first parent chromosome and a second parent chromosome, and randomly determining two crossover points; inheriting the gene fragment between the two crossover points in the first parent chromosome to the corresponding position of the first daughter chromosome, using the genes outside the two crossover points in the first parent chromosome as first complementary genes, and inheriting the corresponding first complementary genes in the second parent chromosome in sequence to the remaining positions of the first daughter chromosome; inheriting the gene fragment between the two crossover points in the second parent chromosome to the corresponding position of the second daughter chromosome, using the genes outside the two crossover points in the second parent chromosome as second complementary genes, and inheriting the corresponding second complementary genes in the first parent chromosome in sequence to the remaining positions of the second daughter chromosome.
[0075] In this embodiment, crossover is a key step of the genetic algorithm, which obtains improvements from parent chromosomes to produce better offspring chromosomes. This embodiment adopts sequential crossover, and the crossover process is described as follows: select any two parent chromosomes Chro parent 1 and Chro parent 2, and randomly inherit a continuous gene fragment in Chro parent 1 to the same position in the offspring chromosome Chro offspring 1. The genes not inherited by Chro offspring 1 are sequentially obtained from another parent chromosome Chro parent 2. Figure 4 As shown, Figure 4 is a schematic diagram of a chromosome sequence crossover example of a task scheduling method for a steel grabber shown in an exemplary embodiment of the present application. A similar method is used to obtain Chro offspring 2. Figure 5 As shown, Figure 5 It is a schematic diagram of a chromosome sequence crossover example of a task scheduling method for a steel grabber shown in another exemplary embodiment of the present application.
[0076] In one embodiment of the present application, the mutation operation is performed in at least one of the following ways: randomly selecting a chromosome in the population according to a first preset probability, and randomly selecting two random points, and rewriting the genes between the two random points in reverse order; randomly selecting a chromosome in the population according to a second preset probability, and randomly selecting a first random point and a second random point, and exchanging the positions corresponding to the first random point and the second random point.
[0077] In this embodiment, the mutation operator plays a key role in the genetic algorithm. It randomly selects a chromosome in the population with a certain probability, and mutates one or several gene positions in the chromosome, that is, changes its value to generate a new chromosome. The essence of this mutation operator can be regarded as a local random search strategy, which, combined with the selection operator and the crossover algorithm, jointly guarantees the effectiveness and global search capability of the genetic algorithm. This operation simulates the gene mutation phenomenon in biological inheritance, that is, randomly introducing small changes in genetic information. The present application adopts inversion mutation and exchange mutation. Inversion mutation is to rewrite the selected gene fragments in the parent chromosome in reverse order, and place the rewritten gene fragments in the corresponding position of the daughter chromosome, refer to Figure 6 As shown, Figure 6 1 is a schematic diagram of an exemplary embodiment of the present application showing a chromosome inversion mutation example of a task scheduling method for a steel grabber. The exchange mutation is to exchange the positions of two genes selected in the parent chromosome and place the exchanged genes in the corresponding positions of the daughter chromosome. Figure 7 As shown, Figure 7It is a schematic diagram of an example of chromosome exchange variation of a task scheduling method for a steel grabber shown in an exemplary embodiment of the present application.
[0078] In step S240, a target scheduling scheme is determined from the updated task scheduling scheme, and the target steel grabber is scheduled through the task path in the target scheduling scheme.
[0079] In one embodiment of the present application, a target scheduling scheme is determined from the updated task scheduling schemes according to the fitness of the updated task scheduling schemes. The specific method of determination is to sort the fitness of each updated task scheduling scheme, and determine the target scheduling scheme from the updated task scheduling scheme corresponding to the fitness ranked first.
[0080] In one embodiment of the present application, service tasks are classified according to the task priorities corresponding to the service tasks, and the currently executed task is determined according to the classification results; if it is determined that the first task path and the second task path have an intersection, the time difference between the first steel grabber arriving at the intersection and the second steel grabber arriving at the intersection is calculated, wherein the first task path is the task path for the first steel grabber to perform the currently executed task, and the second task path is the task path for the second steel grabber to perform the second executed task; if the time difference is less than a preset time threshold, the target scheduling plan is updated based on a preset adjustment method, and the target steel grabber is scheduled through the task path in the target scheduling plan, wherein the preset adjustment method includes but is not limited to adjusting one or more of the departure time, driving speed and task path of the target steel grabber.
[0081] In this embodiment, the driving path of each steel grabber will inevitably intersect and overlap. In order to avoid collisions between steel grabbers, the driving path and departure time of the steel grabbers in the final scheduling result need to be corrected. The priority of task execution needs to be considered during the correction to ensure that high-priority tasks are least affected. The collision judgment logic is: when the time difference between any two steel grabbers arriving at the intersection of the driving paths is less than the specified time, it is considered that the two steel grabbers will collide. For the overall allocation result, the collision detection and repair process is as follows:
[0082] Step 1: Categorize the tasks to be performed according to their priority.
[0083] Step 2: Select the currently executing task according to the task priority.
[0084] Step 3: Correct the path of the current steel grabber to perform the task. The correction logic is: call the shortest path algorithm to re-plan the current driving path of the steel grabber, mark the edges that have been visited in the undirected graph, and the subsequent planning of the driving path of the steel grabber cannot use the edges that have been visited.
[0085] Step 4: Calculate the intersection of the task path currently executed by the steel grabber and the existing path, and calculate the time difference T of each intersection.
[0086] Step 5: Determine whether the time difference T is less than the preset time threshold; if so, correct the departure time of the current steel grabber until the time difference of all intersections meets the requirements; otherwise, do not make any corrections.
[0087] Step 6: Determine whether the driving paths of the steel grabbers for all tasks have been corrected; if so, the algorithm ends, otherwise, go to step 2.
[0088] In one embodiment of the present application, the algorithm pseudo code corresponding to the above embodiment is shown in Table 1:
[0089] Table 1 Genetic algorithm pseudo code
[0090]
[0091] Refer to the pseudo code of the genetic algorithm in Table 1, where g_vServicePlatfortormSet is a set of steel grabbers, g_vTaskSet is a set of tasks to be served, g_tStockyardArea is a stockyard area, g_vStockpileAreas is a stockpile area, g_vObstacleAreas is an obstacle area, and g_vOptimalPlanResult is a task allocation result. The first line of code is used to build or update a network graph for path planning based on the input area and obstacles. The main loop of lines 2-15 continues until there are no idle steel grabbers, no tasks to be served, or the scheduling period is reached. The third line of code is used to initialize some necessary groups or data structures through InitGroup() in each loop. The fourth line of code is used to use GetDistanceMatrix() to calculate the distance matrix between all relevant points (such as steel grabbers, task points, stockpiles, etc.), which is crucial for subsequent path planning and task allocation. The fifth line of code is used to calculate the fitness of the current allocation scheme, that is, to evaluate the quality of the current scheme. Lines 6-12 of code use a loop (for i=0 in Gen) to execute a genetic algorithm to optimize the task allocation scheme. In each iteration, the optimal chromosome (i.e., the task allocation scheme) is saved. The mutation probability of the chromosome (dPMutation) is updated, which helps to increase the algorithm's search capability and avoid local optimal solutions. A selection operation (Select()) is performed to select the better chromosome to enter the next generation. Evolution operations (Evolution()) are performed, including crossover, mutation, etc., to generate new chromosomes. The fitness of the newly generated chromosomes (CalFitness()) is calculated again. Line 13 of code uses FixAllocationResult() to adjust and optimize the final task allocation result to ensure that there are no conflicts or unreasonableness. Line 14 of code is used to update the idle steel grabber set (vFreeServicePlatformSet) to reflect the current task allocation status. Line 16 of code is used to ReplanServicePlatformPath() to plan a specific movement path for each steel grabber to complete its assigned tasks after all tasks are allocated. Line 17 of code is used to return the optimal task allocation result (g_vOptimalPlanResult) as output.
[0092] Figure 8 1 is a schematic diagram of an algorithm test scenario and calculation results of a task scheduling method for a steel grabber shown in an exemplary embodiment of the present application. Figure 8As shown in the figure, in an exemplary embodiment, s represents the initial position of the steel grabber, t represents the initial position of the task, the red dots represent the steel grabbers that are not assigned to the task (busy), the yellow area represents obstacles, and the gray area is the stockpile. It can be seen that each idle steel grabber is only assigned to one task in each stage, and the driving path of each steel grabber will avoid the scrap steel area and obstacles in the stockpile, and the driving paths between steel grabbers do not overlap and are complete and continuous.
[0093] Fig. 9 FIG. 1 is a flow chart of a task scheduling method for a steel grabber according to another exemplary embodiment of the present application. Fig. 9 As shown, in an exemplary embodiment, the task scheduling method for a steel grabber includes at least steps S1 to S12.
[0094] In step S1, a discrete point network is generated according to the scene information. A graph G is constructed according to the scene information and the layout point interval, and then the layout point V is set as infeasible based on the obstacle information and the stockpile information, and finally the information of all edges E in the graph G is obtained. The graph G is a network graph for path planning, and an edge is a line between any two layout points.
[0095] In step S2, the population is initialized. Each chromosome represents a solution to the problem, where the length of the chromosome is the number of steel grabbers, the position of the node in the chromosome represents the number of the steel grabber, and the encoding value of the node represents the number of the task. In particular, when the encoding value of the node is 0, it means that the steel grabber is not assigned any task.
[0096] In step S3, the shortest path Dijkstra algorithm is called to calculate the distance between the steel grabber and the task target position.
[0097] In step S4, the fitness of the chromosome is calculated, wherein the fitness function is the inverse of the total service time corresponding to the task scheduling scheme converted by the chromosome.
[0098] In step S5, the roulette wheel method is used to select the population, that is, the higher the fitness value of the chromosome, the greater the probability that it will be selected to enter the next generation population, and the more likely it is to pass on high-quality genes.
[0099] In step S6, a sequential crossover operation is performed on the current population, and infeasible chromosomes are corrected, including deleting duplicate chromosomes.
[0100] In step S7, a mutation operation is performed on the current population, and infeasible chromosomes are corrected, including deleting duplicate chromosomes.
[0101] In step S8, the fitness of the chromosome is calculated.
[0102] In step S9, it is checked whether the population iteration reaches the specified number of times. If so, the iteration is completed and the process goes to step S10; if not, the process goes to step S5 and continues.
[0103] In step S10, the chromosome with the largest fitness value in the population is determined as the optimal chromosome, the allocation result corresponding to the optimal chromosome is corrected and the allocation result set is updated.
[0104] In step S11, it is determined whether the current scheduling is completed. If yes, it proceeds to the next step; if no, it proceeds to step S2. The judgment logic is mainly as follows: first determine whether the planned time reaches the specified value. If yes, it proceeds to the next step; if not, it is determined whether there are idle steel grabbers and idle trucks in the time period. If yes, it updates the planned time and proceeds to step S2; otherwise, it updates the planned time and proceeds to step S11.
[0105] In step S12, in order to avoid collision of the steel grabber during driving, the driving path of the steel grabber in the final allocation result is replanned.
[0106] The specific implementation of this embodiment has been described in detail in the above embodiments and will not be repeated here.
[0107] This application converts the problem of collaborative task scheduling of steel grabber clusters in scrap steel yards into a joint optimization problem of multi-machine task allocation and path planning, and considers multiple factors such as task attributes, steel grabber constraints, and external environment to jointly optimize multi-machine task allocation and paths. On this basis, a centralized solution algorithm based on genetic algorithms is further designed, taking into account the periodicity of task scheduling and the requirements for space-time collision avoidance of the steel grabber's driving path, and adding a genetic algorithm periodic startup mechanism and a path collision detection and repair module to the traditional genetic algorithm framework. The intelligent scheduling of multi-machines in the collaborative cluster of scrap steel yards is realized, which not only reduces the risk of collaborative operations, but also improves the scheduling efficiency of steel grabbers in scrap steel yards, providing strong support for the realization of less-manned and unmanned operations in scrap steel yards.
[0108] The technical effects that can be achieved by this application also include the following aspects:
[0109] 1. Autonomous collision avoidance. The driving path and departure time of the steel grabber generated by the genetic algorithm GA are corrected. The priority of task execution is taken into account during the correction to ensure that high-priority tasks are least affected, that is, the impact on the start execution time of important tasks is minimized. Compared with the randomness of traditional manual task assignment and the avoidance of collisions of steel grabbers through dynamic coordination, the results of algorithm planning greatly reduce labor costs and improve planning efficiency.
[0110] 2. Cycle adaptability. At present, the execution time and demand of the warehousing and outbound tasks in the scrap steel yard are uncertain. Traditional manual assignment often orders the steel grabber to perform a single task. In view of this, this patented algorithm introduces a periodic scheduling mechanism. The steel grabber can continuously perform multiple tasks within a scheduling cycle, making the algorithm more in line with actual needs and more flexible to call.
[0111] 3. Global optimality. Genetic algorithm is a centralized solution algorithm. It gives a scheduling plan for steel grabbers in scrap steel yards based on comprehensive consideration of various environmental constraints and task attributes. It has more advantages than traditional manual scheduling methods. This patent is based on a simulated manual scheduling method, which is compared with the results produced by the genetic algorithm. As shown in Table 2, there are a total of six groups of test data, and the test files are named as "number of tasks-number of steel grabbers-number of scene files in this group". For example, in the 10-15-1 test data, the number of tasks is 10, and the number of service platforms (steel grabbers) is 15, which is the first scene file in the second group of test data. Referring to the average solution value of GA solution and the simulated manual scheduling solution value in Table 2, or, GA improves efficiency, it can be seen from the comparison results that the solution effect of the genetic algorithm is significantly improved, which can better jump out of the local optimal solution and overcome the blindness of manual scheduling.
[0112] Table 2 Algorithm comparison results
[0113]
[0114] Fig.10 is a block diagram of a task scheduling device for a steel grabber shown in an exemplary embodiment of the present application. The device can be applied to Figure 1 The implementation environment shown in the figure is specifically configured in the computer device 102. The device can also be applied to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment to which the device is applied.
[0115] like Fig.10 As shown, the exemplary task scheduling device for a steel grabber includes: an acquisition module 1010 , a determination module 1020 , an update module 1030 and a scheduling module 1040 .
[0116] Among them, the acquisition module 1010 is used to obtain multiple task scheduling schemes, wherein the task scheduling schemes include service tasks corresponding to one or more target steel grabbers; the determination module 1020 is used to use each task scheduling scheme as a chromosome in the population, and determine the fitness corresponding to each chromosome according to the path length required for the target steel grabber to complete the service task; the update module 1030 is used to use a genetic algorithm to update each task scheduling scheme according to the fitness, wherein the genetic algorithm includes at least one of a selection operation, a crossover operation and a mutation operation; the scheduling module 1040 is used to determine the target scheduling scheme from the updated task scheduling scheme, and schedule the target steel grabber through the task path in the target scheduling scheme.
[0117] It should be noted that the task scheduling device for a steel grabber provided in the above embodiment and the task scheduling method for a steel grabber provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs the operation has been described in detail in the method embodiment and will not be repeated here. In actual applications, the task scheduling device for a steel grabber provided in the above embodiment can allocate the above functions to different functional modules as needed, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above, and this is not limited here.
[0118] An embodiment of the present application also provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by one or more processors, the electronic device implements the task scheduling method for a steel grabber provided in the above-mentioned embodiments.
[0119] Fig.11 The structure diagram of the computer system suitable for implementing the electronic device of the embodiment of the present application is shown. It should be noted that: Fig.11 The computer system 1100 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0120] like Fig.11As shown, the computer system 1100 includes a central processing unit (CPU) 1101, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1102 or the program loaded from the storage part 1108 to the random access memory (RAM) 1103, such as executing the methods provided in the above-mentioned various embodiments. In the RAM 1103, various programs and data required for system operation are also stored. The CPU 1101, the ROM 1102 and the RAM 1103 are connected to each other through the bus 1104. The input / output (I / O) interface 1105 is also connected to the bus 1104.
[0121] The following components are connected to the I / O interface 1105: an input section 1106 including a keyboard, a mouse, etc.; an output section 1107 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1108 including a hard disk, etc.; and a communication section 1109 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 1109 performs communication processing via a network such as the Internet. A drive 1110 is also connected to the I / O interface 1105 as needed. A removable medium 1111, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1110 as needed so that a computer program read therefrom is installed into the storage section 1108 as needed.
[0122] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 1109, and / or installed from a removable medium 1111. When the computer program is executed by a central processing unit (CPU) 1101, various functions defined in the system of the present application are executed.
[0123] It should be noted that the computer-readable medium shown in the embodiment of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can 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), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. This propagated data signal can take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. A computer program contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.
[0124] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, 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 box can also occur in a different order from the order marked in the accompanying drawings. For example, two 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 box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart 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.
[0125] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.
[0126] Another aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor of a computer, causes the computer to execute the task scheduling method for a steel grabber provided in the above-mentioned embodiments. The computer-readable storage medium may be included in the electronic device described in the above-mentioned embodiments, or may exist independently without being assembled into the electronic device.
[0127] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.
[0128] Another aspect of the present application also provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the task scheduling method for a steel grabber provided in each of the above embodiments.
[0129] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation methods of the present application.
[0130] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application.
[0131] The above embodiments are merely illustrative of the principles and effects of the present application, and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.
Claims
1. A task scheduling method for a steel grabber, characterized in that: include: Acquire multiple task scheduling schemes, wherein the task scheduling schemes include service tasks corresponding to one or more target steel grabbers; Each of the task scheduling schemes is used as a chromosome in the population, and the fitness corresponding to each of the chromosomes is determined according to the path length required for the target steel grabber to complete the service task; Adopting a genetic algorithm to update each of the task scheduling schemes according to the fitness, wherein the genetic algorithm includes at least one of a selection operation, a crossover operation, and a mutation operation; A target scheduling scheme is determined from the updated task scheduling scheme, and the target steel grabber is scheduled through the task path in the target scheduling scheme.
2. The task scheduling method for a steel grabber according to claim 1, characterized in that: Get multiple task scheduling plans, including: Obtaining a service task of a current scene, wherein the current scene includes a pile of materials to be collected and / or an area to be stacked, and the service task includes collecting materials from the pile of materials to be collected and / or placing materials in the area to be stacked; A plurality of task scheduling schemes are generated respectively according to scheme generation rules, wherein the scheme generation rules include randomly allocating at least a part of the service tasks to at least a part of the target steel grabber, so as to generate a task scheduling scheme according to the correspondence between the service tasks and the target steel grabber.
3. The task scheduling method for a steel grabber according to claim 2, characterized in that: Randomly assigning at least a portion of the service tasks to at least a portion of the target steel grabbers to generate a task scheduling scheme according to a corresponding relationship between the service tasks and the target steel grabbers, including: Get the number of steel grabbers and service tasks; If the number of the steel grabbers is greater than the number of the service tasks, all the service tasks are randomly assigned to at least a portion of the target steel grabbers, so as to generate a task scheduling scheme according to the corresponding relationship between the service tasks and the target steel grabbers; If the number of the steel grabbers is less than or equal to the number of the service tasks, at least a portion of the service tasks are randomly allocated to all target steel grabbers to generate a task scheduling plan based on the corresponding relationship between the service tasks and the target steel grabbers.
4. The task scheduling method for a steel grabber according to claim 2, characterized in that: The fitness corresponding to each of the chromosomes is determined according to the path length required for the target steel grabber to complete the service task, including: Constructing a discrete point network according to the current scene, wherein the discrete point network is used to characterize target elements and obstacle elements, wherein the target elements include the target steel grabber, the pile of materials to be collected and / or the area to be stacked; Planning element edges between the target elements in the discrete point network, wherein the element edges do not pass through the obstacle elements; Establishing a task path corresponding to the service task performed by the target steel grabber from the element edges according to a preset path algorithm, and calculating the path length of the task path; The fitness of the chromosome corresponding to the same task scheduling scheme is obtained by calculating the path length corresponding to the same task scheduling scheme.
5. The task scheduling method for a steel grabber according to any one of claims 1 to 4, characterized in that: The fitness is calculated by the following formula: In the formula, f(i) is the fitness, m is the number of steel grabbers, D ij represents the travel time of the j-th steel grabber in the i-th chromosome, P ij is the priority weight of the task executed by the j-th steel grabber in the i-th chromosome, T ij The task execution time of the j-th steel grabber in the i-th chromosome to perform the service task.
6. The task scheduling method for a steel grabber according to any one of claims 1 to 4, characterized in that: Select operations are performed in the following ways: Calculating the fitness ratio of each chromosome to the total fitness of the population, and using the fitness ratio as the selection probability of each chromosome being inherited to the next generation population, wherein the total fitness of the population is calculated based on the fitness of each chromosome; Calculating the cumulative probability of each of the chromosomes based on the selection probability; A first random number within a preset range is randomly generated. If the first random number is less than the cumulative probability, the chromosome corresponding to the cumulative probability is selected into the next generation population until the number of selected chromosomes is greater than or equal to the preset selection number.
7. The task scheduling method for a steel grabber according to any one of claims 1 to 4, characterized in that: The crossover operation is performed in the following way: Randomly select the first parent chromosome and the second parent chromosome, and randomly determine two crossover points; The gene fragment between the two intersection points in the first parent chromosome is inherited to the corresponding position of the first daughter chromosome, the gene outside the two intersection points in the first parent chromosome is used as the first supplementary gene, and the corresponding first supplementary gene in the second parent chromosome is inherited in sequence to the remaining position of the first daughter chromosome; The gene fragment between the two intersection points in the second parent chromosome is inherited to the corresponding position of the second daughter chromosome, the genes outside the two intersection points in the second parent chromosome are used as second complementary genes, and the corresponding second complementary genes in the first parent chromosome are inherited in sequence to the remaining positions of the second daughter chromosome.
8. The task scheduling method for a steel grabber according to any one of claims 1 to 4, characterized in that: Perform mutation operations in at least one of the following ways: A chromosome is randomly selected from the population according to a first preset probability, and two random points are randomly selected, and the genes between the two random points are rewritten in reverse order; A chromosome is randomly selected from the population according to a second preset probability, and a first random point and a second random point are randomly selected, and positions corresponding to the first random point and the second random point are exchanged.
9. The task scheduling method for a steel grabber according to any one of claims 1 to 4, characterized in that: Scheduling the target steel grabber through the task path in the target scheduling scheme includes: Classifying the service tasks according to the task priorities corresponding to the service tasks, and determining the currently executed task according to the classification results; If it is determined that the first task path and the second task path have an intersection, the time difference between when the first steel grabber reaches the intersection and when the second steel grabber reaches the intersection is calculated, wherein the first task path is the task path for the first steel grabber to perform the current execution task, and the second task path is the task path for the second steel grabber to perform the second execution task; If the time difference is less than a preset time threshold, the target scheduling plan is updated based on a preset adjustment method, and the target steel grabber is scheduled through the task path in the target scheduling plan, wherein the preset adjustment method includes adjusting one or more of the departure time, driving speed and task path of the target steel grabber.
10. A task scheduling device for a steel grabber, characterized in that: include: An acquisition module, used for acquiring a plurality of task scheduling schemes, wherein the task scheduling schemes include service tasks corresponding to one or more target steel grabbers; A determination module, used to take each of the task scheduling schemes as a chromosome in the population, and determine the fitness corresponding to each of the chromosomes according to the path length required for the target steel grabber to complete the service task; An updating module, configured to update each of the task scheduling schemes according to the fitness using a genetic algorithm, wherein the genetic algorithm includes at least one of a selection operation, a crossover operation, and a mutation operation; The scheduling module is used to determine the target scheduling plan from the updated task scheduling plan, and schedule the target steel grabber through the task path in the target scheduling plan.
