Multi-agricultural machinery cooperative scheduling path planning method, device, equipment and medium
The global optimal path planning scheme is determined in the coordinated scheduling of multi-agricultural machinery through the raccoon optimization algorithm, which solves the resource waste and high cost problems caused by inaccurate traditional solutions, and achieves more efficient agricultural machinery scheduling.
Patent Information
- Application Number
- CN202410945848.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-15
- Publication Date
- 2024-11-12
AI Technical Summary
The traditional multi-agricultural machinery collaborative scheduling path planning scheme is not accurate enough, resulting in waste of resources and high costs.
The raccoon population is initialized by using the raccoon optimization algorithm, and the location and fitness values of the raccoon individuals are updated iteratively, and the global optimal path planning scheme is determined, taking into account the cost of agricultural machinery transfer, waiting costs and dispatch costs.
A more accurate path planning scheme has been realized, which has significantly reduced the cost of coordinated scheduling of multiple agricultural machinery and reduced resource waste.
Smart Images

Figure CN118940788A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of agricultural technology, and in particular to a method, device, equipment and medium for planning a path for coordinated scheduling of multiple agricultural machines. Background Art
[0002] With the continuous development of science and technology and the modernization of agricultural production methods, the path planning problem of coordinated scheduling of multiple agricultural machinery has become increasingly important.
[0003] In traditional agricultural production, the path planning scheme for the coordinated scheduling of multiple agricultural machinery is not accurate enough, resulting in high scheduling costs when the agricultural machinery goes from the hangar to the farmland and then returns to the hangar from the farmland, which in turn makes the overall agricultural production cost high. The traditional coordinated scheduling of multiple agricultural machinery faces the problems of resource waste and high costs. Summary of the invention
[0004] The present invention provides a path planning method, device, equipment and medium for the coordinated scheduling of multiple agricultural machinery, which is used to solve the defects of the prior art that the path planning scheme is not accurate enough, resulting in waste of resources and high cost in the coordinated scheduling of multiple agricultural machinery, and to achieve a more accurate determined path planning scheme, and can reduce the cost of the coordinated scheduling of multiple agricultural machinery to a large extent and reduce waste of resources.
[0005] The present invention provides a multi-agricultural machinery coordinated scheduling path planning method, comprising the following steps.
[0006] Initializing a raccoon population of a raccoon optimization algorithm, determining a position of each raccoon individual in the raccoon population, wherein the position represents a path planning scheme corresponding to the coordinated scheduling of multiple agricultural machines; For each of the raccoon individuals, a fitness value of the raccoon individual is calculated based on the path planning scheme corresponding to the raccoon individual, wherein the fitness value is determined based on the agricultural machinery transfer cost, agricultural machinery waiting cost, and agricultural machinery dispatching cost corresponding to the path planning scheme; Determine whether an iteration termination condition of the raccoon optimization algorithm is met, and if the iteration termination condition is met, determine a target path planning scheme based on the fitness value of each raccoon individual in each iteration round; When the iteration termination condition is not met, the position of each raccoon individual is updated based on the fitness value of each raccoon individual; the fitness value of each raccoon individual is recalculated based on the updated position; the steps of updating the position and calculating the fitness value are continuously repeated until the iteration termination condition is met, and the target path planning scheme is determined based on the fitness value of each raccoon individual in each iteration round.
[0007] According to a multi-agricultural machinery coordinated scheduling path planning method provided by the present invention, the updating of the position of each raccoon individual based on the fitness value of each raccoon individual includes: In the current iteration round, the position of each raccoon individual is initially adjusted based on the fitness values of all the raccoon individuals to obtain the first position of each raccoon individual; for each raccoon individual, the reverse position of the raccoon individual is determined based on the first position of the raccoon individual through a reverse learning strategy; the position corresponding to the larger fitness value between the fitness value corresponding to the first position of the raccoon individual and the fitness value corresponding to the reverse position of the raccoon individual is determined as the updated position of the raccoon individual; Alternatively, in the current iteration round, the position of each raccoon individual is randomly adjusted for the first time to obtain the first position of each raccoon individual; for each raccoon individual, the reverse position of the raccoon individual is determined based on the first position of the raccoon individual through a reverse learning strategy; the position corresponding to the larger fitness value between the fitness value corresponding to the first position of the raccoon individual and the fitness value corresponding to the reverse position of the raccoon individual is determined as the updated position of the raccoon individual.
[0008] According to a multi-agricultural machinery coordinated scheduling path planning method provided by the present invention, the position of each raccoon individual is initially adjusted based on the fitness value of all the raccoon individuals to obtain the first position of each raccoon individual, including: Determine the position of the raccoon individual with the highest fitness value among all the raccoon individuals as the position of the prey, and randomly divide all the raccoon individuals into a first raccoon group and a second raccoon group; Initially adjusting the position of each raccoon in the first raccoon group based on the position of the prey; Adjusting the position of the prey according to a preset decision variable to obtain a random position of the prey; Initially adjusting the position of each raccoon individual in the second raccoon group based on the random position of the prey; For each raccoon individual in the raccoon population, when the fitness value corresponding to the adjusted position of the raccoon individual is less than the fitness value corresponding to the position of the raccoon individual before adjustment, the adjusted position of the raccoon individual is determined as the first position of the raccoon individual; when the fitness value corresponding to the adjusted position of the raccoon individual is greater than or equal to the fitness value corresponding to the position of the raccoon individual before adjustment, the adjusted position of the raccoon individual is adjusted again through the Levy flight strategy to determine the second position of the raccoon individual, and the second position of the raccoon individual is determined as the first position of the raccoon individual.
[0009] According to a multi-agricultural machinery coordinated scheduling path planning method provided by the present invention, the random initial adjustment of the position of each raccoon individual to obtain the first position of each raccoon individual includes: Randomly adjusting the position of each raccoon individual according to the number of rounds of the current iteration round and a preset decision variable; For each raccoon individual in the raccoon population, when the fitness value corresponding to the adjusted position of the raccoon individual is less than the fitness value corresponding to the position of the raccoon individual before adjustment, the adjusted position of the raccoon individual is determined as the first position of the raccoon individual; when the fitness value corresponding to the adjusted position of the raccoon individual is greater than or equal to the fitness value corresponding to the position of the raccoon individual before adjustment, the adjusted position of the raccoon individual is adjusted again through the Levy flight strategy to determine the second position of the raccoon individual, and the second position of the raccoon individual is determined as the first position of the raccoon individual.
[0010] According to a multi-agricultural machinery coordinated scheduling path planning method provided by the present invention, the determining the position of each raccoon individual in the raccoon population includes: Determine multiple path planning schemes corresponding to the coordinated dispatch of multiple agricultural machines through random functions; Based on the good point set initialization method, multiple path planning schemes are allocated one-to-one to multiple raccoon individuals to determine the position of each raccoon individual.
[0011] According to a multi-agricultural machinery coordinated scheduling path planning method provided by the present invention, the fitness value of the raccoon individual is calculated based on the path planning scheme corresponding to the raccoon individual, including: Determine the agricultural machinery transfer cost, the agricultural machinery waiting cost and the agricultural machinery dispatching cost corresponding to the path planning scheme based on the path planning scheme corresponding to the raccoon individual; The weighted sum of the agricultural machinery transfer cost, the agricultural machinery waiting cost and the agricultural machinery dispatching cost is determined as the fitness value of the individual raccoon.
[0012] According to a multi-agricultural machinery coordinated scheduling path planning method provided by the present invention, the target path planning scheme is determined based on the fitness value of each raccoon individual in each iteration round, including: Determine the raccoon individual with the highest fitness value in each iteration round as the global optimal raccoon individual; The path planning scheme represented by the position corresponding to the global optimal raccoon individual is determined as the target path planning scheme.
[0013] The present invention also provides a multi-agricultural machinery coordinated dispatching path planning device, comprising the following modules: An initialization module, used to initialize the raccoon population of the raccoon optimization algorithm, determine the position of each raccoon individual in the raccoon population, and the position represents the path planning scheme corresponding to the coordinated scheduling of multiple agricultural machinery; A calculation module, for calculating the fitness value of each raccoon individual based on the path planning scheme corresponding to the raccoon individual, wherein the fitness value is determined based on the agricultural machinery transfer cost, agricultural machinery waiting cost and agricultural machinery dispatching cost corresponding to the path planning scheme; A determination module, used to determine whether an iteration termination condition of the raccoon optimization algorithm is met, and when the iteration termination condition is met, determine a target path planning scheme based on the fitness value of each raccoon individual in each iteration round; An updating module is used to update the position of each raccoon individual based on the fitness value of each raccoon individual when the iteration termination condition is not met; recalculate the fitness value of each raccoon individual based on the updated position; and continuously repeat the steps of updating the position and calculating the fitness value until the iteration termination condition is met, and determine the target path planning scheme based on the fitness value of each raccoon individual in each iteration round.
[0014] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a multi-agricultural machinery coordinated scheduling path planning method as described in any one of the above-mentioned methods is implemented.
[0015] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described methods for collaborative scheduling of multiple agricultural machinery paths.
[0016] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for coordinated scheduling of multiple agricultural machinery paths.
[0017] The multi-agricultural machinery coordinated scheduling path planning method, device, equipment and medium provided by the present invention initialize the raccoon population of the raccoon optimization algorithm, determine the position of each raccoon individual in the raccoon population, and then calculate the fitness value of the raccoon individual based on the path planning scheme corresponding to the raccoon individual for each raccoon individual. When the iteration termination condition is met, the target path planning scheme is determined based on the fitness value of each raccoon individual in each iteration round. When the iteration termination condition is not met, the position of each raccoon individual is updated based on the fitness value of each raccoon individual, and the fitness value of each raccoon individual is recalculated based on the updated position, and the steps of updating the position and calculating the fitness value are continuously repeated until the iteration termination condition is met, and finally the target path planning scheme is determined based on the fitness value of each raccoon individual in each iteration round. The technical solution of the present invention can determine the global optimal and relatively accurate target path planning scheme through the raccoon optimization algorithm. Since the setting of the fitness value corresponding to the raccoon individual takes into account the agricultural machinery transfer cost, agricultural machinery waiting cost and agricultural machinery dispatch cost in the process of determining the target path planning scheme, the target path planning scheme finally determined can reduce the cost of coordinated scheduling of multiple agricultural machinery to a large extent and reduce resource waste. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0019] Figure 1 It is a flow chart of the multi-agricultural machinery coordinated scheduling path planning method provided by the present invention.
[0020] Figure 2 It is a schematic diagram of the farm operation area provided by the present invention.
[0021] Figure 3 It is a schematic diagram of the operation of the agricultural machine provided by the present invention.
[0022] Figure 4 This is one of the agricultural machinery path schematic diagrams of the operation area provided by the present invention.
[0023] Figure 5 This is the second schematic diagram of the agricultural machinery path in the operation area provided by the present invention.
[0024] Figure 6 This is the third schematic diagram of the agricultural machinery path in the operation area provided by the present invention.
[0025] Figure 7 It is a schematic diagram comparing the fitness values of the algorithm of the present invention and other algorithms in the iteration process.
[0026] Figure 8 It is a structural schematic diagram of the multi-agricultural machinery collaborative scheduling path planning device provided by the present invention.
[0027] Fig. 9 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION
[0028] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0029] In view of the above problems in the prior art, the present invention provides a multi-agricultural machinery coordinated scheduling path planning method. Figure 1 FIG. 1 is a flow chart of a multi-agricultural machinery coordinated dispatching path planning method provided by the present invention. Figure 1 As shown, the multi-agricultural machinery collaborative scheduling path planning method includes the following steps 110, 120, 130 and 140.
[0030] Step 110: Initialize the raccoon population of the raccoon optimization algorithm, determine the position of each raccoon individual in the raccoon population, and the position represents the path planning solution corresponding to the coordinated scheduling of multiple agricultural machines.
[0031] Specifically, the raccoon population of the raccoon optimization algorithm can be initialized, that is, the position of each raccoon individual in the raccoon population can be determined, and the position represents the path planning scheme corresponding to the coordinated scheduling of multiple agricultural machinery, wherein the number of raccoon individuals in the raccoon population can be predetermined, for example, the raccoon population can include 40 raccoon individuals.
[0032] In one embodiment, determining the location of each individual raccoon in the raccoon population includes: Determine multiple path planning schemes corresponding to the coordinated dispatch of multiple agricultural machines through random functions; Based on the good point set initialization method, multiple path planning schemes are allocated one-to-one to multiple raccoon individuals to determine the position of each raccoon individual.
[0033] Specifically, multiple path planning schemes for the coordinated scheduling of multiple agricultural machinery can be determined by random functions. Since the multiple path planning schemes are randomly determined, the multiple path planning schemes may be different or partially the same. Then, based on the optimal point set initialization method, the multiple path planning schemes can be assigned one-to-one to multiple raccoon individuals to determine the position of each raccoon individual. It is easy to understand that the position of the raccoon individual is the initial position of the raccoon individual.
[0034] For example, the longitude and latitude information of the boundaries of the fields in the example farm, the road information in the farm, and the obstacle information in the farm can be obtained in advance through Beidou satellites, and an environmental map corresponding to the example farm can be drawn accordingly. Figure 2 is a schematic diagram of the farm operation area provided by the present invention, such as Figure 2 As shown, the example farm includes a total of 38 working areas. Figure 3 The operation diagram of the agricultural machine provided by the present invention is as follows: Figure 3 Act as shown.
[0035] In the above embodiment, multiple path planning schemes corresponding to the coordinated scheduling of multiple agricultural machinery are determined by a random function, and then the multiple path planning schemes are assigned one-to-one to multiple raccoon individuals based on the best point set initialization method to determine the position of each raccoon individual, laying the foundation for the subsequent optimization of the position of the raccoon individual.
[0036] Optionally, the present invention aims to plan the path of the agricultural machinery from the garage to the farmland, from one working area in the farmland to another working area, and from the farmland back to the garage, and the working path of the agricultural machinery in the working area can be predetermined. For example, it can be determined in the following ways: 1) Based on the working width of the agricultural machinery and the minimum turning radius of agricultural machinery Determining the turning width for agricultural machinery operations and the number of unit operation rows, for example, the U-turn width can be determined by the following formula :
[0037] For example, the number of unit operation rows can also be determined by the following formula :
[0038] 2) For each operation area of agricultural machinery operation, determine the total number of agricultural machinery operation units corresponding to the operation area based on the number of unit operation rows and the total number of operation rows corresponding to the operation area. For example, the total number of units of agricultural machinery operation can be determined by the following formula :
[0039] in, Indicates the total number of job rows corresponding to the job area.
[0040] 3) Determine the agricultural machinery operation path in the operation area based on the number of unit operation rows and the total number of units in the operation area. The agricultural machinery operation path can be determined by the following formula:
[0041] in, and The same, both represent the total number of units of agricultural machinery operations, Indicates the job row number, Indicates the job sequence number, for example , In the case of , it means that the second operation row is operated for the fifth time, and mod represents the modulo operator.
[0042] For example, Figure 4 This is one of the schematic diagrams of agricultural machinery paths in the working area provided by the present invention. Figure 5 This is the second schematic diagram of the agricultural machinery path in the operation area provided by the present invention. Figure 6 This is the third schematic diagram of the agricultural machinery path in the operation area provided by the present invention. Figure 4 , Figure 5 and Figure 6 In the figure, the horizontal axis represents latitude and the vertical axis represents longitude. It is easy to understand that for operation area 1 (i.e. farmland No. 1), the operation path of the agricultural machinery in the operation area is as follows: Figure 4 As shown in the figure, for operation area 8 (i.e. farmland No. 8), the operation path of the agricultural machinery in the operation area is as follows: Figure 5 As shown in the figure, for operation area 17 (i.e. farmland No. 17), the operation path of the agricultural machinery in the operation area is as follows Figure 6 shown.
[0043] Step 120: For each raccoon individual, calculate the fitness value of the raccoon individual based on the path planning scheme corresponding to the raccoon individual, wherein the fitness value is determined based on the agricultural machinery transfer cost, agricultural machinery waiting cost and agricultural machinery dispatching cost corresponding to the path planning scheme.
[0044] Specifically, for each raccoon individual, the fitness value of the raccoon individual can be calculated based on the path planning scheme corresponding to the multi-agricultural machinery coordinated dispatching corresponding to the raccoon individual, and the fitness value can be determined based on the agricultural machinery transfer cost, agricultural machinery waiting cost, and agricultural machinery dispatching cost corresponding to the path planning scheme. Since the fitness value is determined based on the agricultural machinery transfer cost, agricultural machinery waiting cost, and agricultural machinery dispatching cost corresponding to the path planning scheme, the lower the fitness value, the lower the overall cost of the path planning scheme, and the better the path planning scheme.
[0045] In one embodiment, the calculating the fitness value of the raccoon individual based on the path planning scheme corresponding to the raccoon individual includes: Determine the agricultural machinery transfer cost, the agricultural machinery waiting cost and the agricultural machinery dispatching cost corresponding to the path planning scheme based on the path planning scheme corresponding to the raccoon individual; The weighted sum of the agricultural machinery transfer cost, the agricultural machinery waiting cost and the agricultural machinery dispatching cost is determined as the fitness value of the individual raccoon.
[0046] Specifically, the agricultural machinery transfer cost, agricultural machinery waiting cost and agricultural machinery dispatch cost corresponding to the path planning scheme can be determined based on the path planning scheme corresponding to the raccoon individual. The agricultural machinery transfer cost is the total cost of all agricultural machinery moving when transferring between work areas, such as the total transfer fuel consumption. The agricultural machinery waiting cost is the time cost of all agricultural machinery waiting in the work area. The dispatch cost is actually the cost of the agricultural machinery reaching the work area from the garage and returning to the garage from the agricultural area.
[0047] Agricultural machinery transfer costs It can be determined by the following formula:
[0048] in, Indicates the number of agricultural machinery hangars, Indicates agricultural machinery From the work area Transfer to the work area The decision variables, Indicates agricultural machinery Unit distance transfer cost, Indicates the working area To the work area distance.
[0049] Agricultural machinery waiting costs It can be determined by the following formula:
[0050] in, Indicates agricultural machinery The waiting cost per unit time, Indicates agricultural machinery In the working area waiting time.
[0051] Agricultural machinery dispatch costs It can be determined by the following formula:
[0052] in, Indicates agricultural machinery The single dispatch cost is actually the agricultural machinery The cost of getting from the garage to the working area, and returning from the agricultural area to the garage.
[0053] Furthermore, the weighted sum of the agricultural machinery transfer cost, the agricultural machinery waiting cost and the agricultural machinery dispatch cost can be determined as the fitness value of the individual raccoon.
[0054] Optionally, the fitness value of any raccoon individual can also be solved based on the path planning schemes corresponding to all raccoon individuals. In this case, the agricultural machinery transfer cost, agricultural machinery waiting cost and agricultural machinery dispatch cost are normalized respectively. The normalization can be performed by the following formula:
[0055] in, represents the normalized cost, represents the cost before normalization, represents the minimum cost among all path planning solutions, Represents the maximum cost among all path planning solutions. For example, the normalized agricultural machinery transfer cost can be determined by the following formula ,in represents the minimum agricultural machinery transfer cost among all path planning schemes, Represents the maximum agricultural machinery transfer cost among all path planning schemes.
[0056] After obtaining the normalized agricultural machinery transfer cost, agricultural machinery waiting cost, and agricultural machinery dispatch cost, the fitness value of the raccoon individual can be determined by the following formula: .
[0057]
[0058] in, represents the weight value corresponding to the agricultural machinery transfer cost, represents the weight value corresponding to the waiting cost of agricultural machinery, Indicates the weight value corresponding to the agricultural machinery dispatch cost, represents the normalized agricultural machinery transfer cost, represents the normalized waiting cost of agricultural machinery, Represents the normalized agricultural machinery dispatch cost.
[0059] In the above embodiment, the agricultural machinery transfer cost, agricultural machinery waiting cost and agricultural machinery dispatch cost corresponding to the path planning scheme are determined based on the path planning scheme corresponding to the raccoon individual, and the weighted sum of the agricultural machinery transfer cost, agricultural machinery waiting cost and agricultural machinery dispatch cost is determined as the fitness value of the raccoon individual, so that when optimizing the position of the raccoon individual, the cost of the path planning scheme corresponding to the position can be taken into account.
[0060] Step 130: Determine whether the iteration termination condition of the raccoon optimization algorithm is met. If the iteration termination condition is met, determine the target path planning scheme based on the fitness value of each raccoon individual in each iteration round.
[0061] Specifically, it can be determined whether the iteration termination condition of the raccoon optimization algorithm is reached. When the iteration termination condition is reached, the target path planning scheme can be determined based on the fitness value of each raccoon individual in each iteration round. For example, when the total number of iteration rounds of the raccoon optimization algorithm reaches a preset iteration round, it can be determined that the iteration termination condition of the raccoon optimization algorithm is reached. The preset iteration round can be set as needed, and the embodiment of the present invention is not specifically limited here. The preset iteration round can be, for example, 200.
[0062] In one embodiment, the determining of the target path planning scheme based on the fitness value of each raccoon individual in each iteration round includes: Determine the raccoon individual with the highest fitness value in each iteration round as the global optimal raccoon individual; The path planning scheme represented by the position corresponding to the global optimal raccoon individual is determined as the target path planning scheme.
[0063] Specifically, in each iteration round, the raccoon individual with the highest fitness value can be recorded, and the raccoon individual with the highest fitness value in each round can be determined as the global optimal raccoon individual, and then the path planning scheme represented by the position corresponding to the global optimal raccoon individual can be determined as the target path planning scheme.
[0064] In the above embodiment, the raccoon individual with the highest fitness value in each iteration round is determined as the global optimal raccoon individual, and the path planning scheme represented by the position corresponding to the global optimal raccoon individual is determined as the target path planning scheme, so that the fitness value corresponding to the target path planning scheme is the highest, that is, taking into account various costs, the optimal solution for the path planning of multi-agricultural machinery collaborative scheduling is obtained.
[0065] Step 140: When the iteration termination condition is not met, the position of each raccoon individual is updated based on the fitness value of each raccoon individual; the fitness value of each raccoon individual is recalculated based on the updated position; the steps of updating the position and calculating the fitness value are continuously repeated until the iteration termination condition is met, and the target path planning scheme is determined based on the fitness value of each raccoon individual in each iteration round.
[0066] Specifically, when the iteration termination condition is not reached, the position of each raccoon individual can be updated based on the fitness value of each raccoon individual, and then the fitness value of each raccoon individual can be recalculated based on the updated position. The method for calculating the fitness value of each raccoon individual here is the same as the method for calculating the fitness value of each raccoon individual in step 120. In order to obtain the target path planning scheme, it is necessary to continuously repeat the steps of updating the position and calculating the fitness value until the iteration termination condition is reached, and then the target path planning scheme can be determined based on the fitness value of each raccoon individual in each iteration round. Among them, the method for determining the target path planning scheme based on the fitness value of each raccoon individual in each iteration round is the same as the method for determining the target path planning scheme based on the fitness value of each raccoon individual in each iteration round in step 130.
[0067] In one embodiment, the updating of the position of each raccoon individual based on the fitness value of each raccoon individual includes: In the current iteration round, the position of each raccoon individual is initially adjusted based on the fitness values of all the raccoon individuals to obtain the first position of each raccoon individual; for each raccoon individual, the reverse position of the raccoon individual is determined based on the first position of the raccoon individual through a reverse learning strategy; the position corresponding to the larger fitness value between the fitness value corresponding to the first position of the raccoon individual and the fitness value corresponding to the reverse position of the raccoon individual is determined as the updated position of the raccoon individual; Alternatively, in the current iteration round, the position of each raccoon individual is randomly adjusted for the first time to obtain the first position of each raccoon individual; for each raccoon individual, the reverse position of the raccoon individual is determined based on the first position of the raccoon individual through a reverse learning strategy; the position corresponding to the larger fitness value between the fitness value corresponding to the first position of the raccoon individual and the fitness value corresponding to the reverse position of the raccoon individual is determined as the updated position of the raccoon individual.
[0068] Specifically, the method of updating the position of each raccoon individual based on the fitness value of each raccoon individual may include the following two methods. In an iteration round, the position of each raccoon individual may be updated by any method. In the first method: in the current iteration round, the position of each raccoon individual may be initially adjusted based on the fitness value of all raccoon individuals to obtain the first position of each raccoon individual. Then, for each raccoon individual, the reverse position of the raccoon individual may be determined based on the first position of the raccoon individual through a reverse learning strategy.
[0069] For example, a raccoon individual Reverse position It can be determined by the following formula:
[0070] in, Represents individual raccoons The first position, represents the lower limit value of the preset decision variable, represents the upper limit value of the preset decision variable, represents a random function, Represents the number of raccoon individuals in the raccoon population.
[0071] After determining the reverse position of the raccoon individual, the fitness value corresponding to the first position of the raccoon individual can be compared with the fitness value corresponding to the reverse position of the raccoon individual. When the fitness value corresponding to the first position is greater than the fitness value corresponding to the reverse position, the first position is determined as the updated position of the raccoon individual. When the fitness value corresponding to the reverse position is greater than the fitness value corresponding to the first position, the reverse position is determined as the updated position of the raccoon individual. It is easy to understand that when the fitness value corresponding to the first position is equal to the fitness value corresponding to the reverse position, the first position or the reverse position can be determined as the updated position of the raccoon individual.
[0072] In the second method, in the current iteration round, the position of each raccoon individual is randomly adjusted for the first time to obtain the first position of each raccoon individual. Then, for each raccoon individual, the reverse position of the raccoon individual can be determined based on the first position of the raccoon individual through a reverse learning strategy. Further, the position corresponding to the larger fitness value between the fitness value corresponding to the first position of the raccoon individual and the fitness value corresponding to the reverse position of the raccoon individual can be determined as the updated position of the raccoon individual.
[0073] In the above embodiment, in all iteration rounds, the position of each raccoon individual can be updated by one of two different methods based on the fitness value of each raccoon individual, which has high flexibility, and the use of the reverse learning strategy can ensure that the position of each raccoon individual will not fall into the local optimum to a certain extent.
[0074] In one embodiment, the first adjusting the position of each raccoon individual based on the fitness value of all the raccoon individuals to obtain the first position of each raccoon individual includes: Determine the position of the raccoon individual with the highest fitness value among all the raccoon individuals as the position of the prey, and randomly divide all the raccoon individuals into a first raccoon group and a second raccoon group; Initially adjusting the position of each raccoon in the first raccoon group based on the position of the prey; Adjusting the position of the prey according to a preset decision variable to obtain a random position of the prey; Initially adjusting the position of each raccoon individual in the second raccoon group based on the random position of the prey; For each raccoon individual in the raccoon population, when the fitness value corresponding to the adjusted position of the raccoon individual is less than the fitness value corresponding to the position of the raccoon individual before adjustment, the adjusted position of the raccoon individual is determined as the first position of the raccoon individual; when the fitness value corresponding to the adjusted position of the raccoon individual is greater than or equal to the fitness value corresponding to the position of the raccoon individual before adjustment, the adjusted position of the raccoon individual is adjusted again through the Levy flight strategy to determine the second position of the raccoon individual, and the second position of the raccoon individual is determined as the first position of the raccoon individual.
[0075] Specifically, the position of the raccoon individual with the highest fitness value among all raccoon individuals can be determined as the position of the prey, and all raccoon individuals can be randomly divided into a first raccoon group and a second raccoon group. The first raccoon group climbs up a tree to scare the prey, and the second raccoon group waits for the frightened prey under the tree. It should be noted that when the number of raccoon individuals in the raccoon population is an even number, the number of raccoon individuals in the first raccoon group and the second raccoon group is the same. When the number of raccoon individuals in the raccoon population is an odd number, the number of raccoon individuals in the first raccoon group and the second raccoon group differs by only one. For the raccoon individuals in the first raccoon group, the position of each raccoon individual can be initially adjusted based on the position of the prey. The following formula can be used to determine the number of raccoon individuals in the first raccoon group. Position after initial adjustment :
[0076] in, Represents individual raccoons Position before initial adjustment, represents the number of the individual raccoon in the first raccoon group, represents the number of all raccoon individuals in the raccoon population, Representation interval The random numbers in Indicates the location of the prey, Represents a set of integers The random number in .
[0077] For the raccoon individuals in the second raccoon group, the position of the prey can be adjusted according to the preset decision variables to obtain the random position of the prey. It can be determined by the following formula:
[0078] in, represents the lower limit value of the preset decision variable, Represents the upper limit value of the preset decision variable.
[0079] Furthermore, the positions of the raccoons in the second raccoon group can be adjusted based on the random positions of the prey. The positions of the raccoons in the second raccoon group can be determined by the following formula: Position after initial adjustment :
[0080] in, Represents individual raccoons Position before initial adjustment, represents the number of the individual raccoon in the second raccoon group, represents the fitness value corresponding to the random position of the prey, Represents individual raccoons The fitness value corresponding to the position before the initial adjustment.
[0081] Furthermore, for each raccoon individual in the raccoon population, when the fitness value corresponding to the adjusted position of the raccoon individual is less than the fitness value corresponding to the position of the raccoon individual before adjustment, the adjusted position of the raccoon individual is determined as the first position of the raccoon individual; when the fitness value corresponding to the adjusted position of the raccoon individual is greater than or equal to the fitness value corresponding to the position of the raccoon individual before adjustment, the adjusted position of the raccoon individual is adjusted again through the Levy flight strategy to determine the second position of the raccoon individual, and the second position of the raccoon individual is determined as the first position of the raccoon individual. The above process can be expressed by the following formula:
[0082] in, represents the first position of the raccoon individual, represents the adjusted position of the raccoon individual, represents the position of the raccoon individual before adjustment, It represents the fitness value of the raccoon individual before adjustment. It represents the fitness value corresponding to the adjusted position of the raccoon individual. represents the preset step size factor, The value range is , represents the Hadamard product, represents the Levy flight strategy, represents stability parameters, such as It can be 1.5. It can be determined by the following formula:
[0083] in, and represents a random number in the interval [0,1], represents the standard gamma function, Represents pi.
[0084] In the above embodiment, the raccoon population is divided into a first raccoon group and a second raccoon group, and different position adjustment methods are used for the first raccoon group and the second raccoon group. Finally, the first position of the raccoon individual is determined according to the fitness values corresponding to the adjusted position and the second position, respectively, so that each raccoon individual can approach the position with a higher fitness value more quickly, thereby improving the optimization speed of the raccoon optimization algorithm.
[0085] In one embodiment, the randomly initially adjusting the position of each raccoon individual to obtain the first position of each raccoon individual includes: Randomly adjusting the position of each raccoon individual according to the number of rounds of the current iteration round and a preset decision variable; For each raccoon individual in the raccoon population, when the fitness value corresponding to the adjusted position of the raccoon individual is less than the fitness value corresponding to the position of the raccoon individual before adjustment, the adjusted position of the raccoon individual is determined as the first position of the raccoon individual; when the fitness value corresponding to the adjusted position of the raccoon individual is greater than or equal to the fitness value corresponding to the position of the raccoon individual before adjustment, the adjusted position of the raccoon individual is adjusted again through the Levy flight strategy to determine the second position of the raccoon individual, and the second position of the raccoon individual is determined as the first position of the raccoon individual.
[0086] Specifically, the position of each raccoon individual can be randomly adjusted according to the number of rounds of the current iteration and the preset decision variables. Location It can be expressed by the following formula:
[0087] in, Represents the raccoon individual before random adjustment location, Indicates the round number of the current iteration round, Indicates the number of preset iteration rounds.
[0088] Furthermore, for each raccoon individual in the raccoon population, when the fitness value corresponding to the adjusted position of the raccoon individual is less than the fitness value corresponding to the position of the raccoon individual before adjustment, the adjusted position of the raccoon individual is determined as the first position of the raccoon individual; when the fitness value corresponding to the adjusted position of the raccoon individual is greater than or equal to the fitness value corresponding to the position of the raccoon individual before adjustment, the adjusted position of the raccoon individual is adjusted again through the Levy flight strategy to determine the second position of the raccoon individual, and the second position of the raccoon individual is determined as the first position of the raccoon individual. The above process can be expressed by the following formula:
[0089] in, represents the first position of the raccoon individual, represents the adjusted position of the raccoon individual, represents the position of the raccoon individual before adjustment, It represents the fitness value of the raccoon individual before adjustment. It represents the fitness value corresponding to the adjusted position of the raccoon individual. represents the preset step size factor, The value range is , represents the Hadamard product, represents the Levy flight strategy, represents stability parameters, such as It can be 1.5. It can be determined by the following formula:
[0090] in, and represents a random number in the interval [0,1], represents the standard gamma function, Represents pi.
[0091] In the above embodiment, the position of each raccoon individual is randomly adjusted according to the round number of the current iteration round and the preset decision variables, and then the first position of the raccoon individual is determined according to the fitness value corresponding to the adjusted position and the second position respectively, which can prevent the raccoon individual from falling into the local optimum during the optimization process to a certain extent.
[0092] For example, for 38 working areas, the agricultural machinery used is the Dongfanghong LF2204 tractor and the LEMKEN Juwel 8 hydraulic flip plow. Figure 7 FIG. 1 is a schematic diagram showing the comparison of fitness values of the algorithm of the present invention and other algorithms in the iteration process. Figure 7 As shown, the black curve represents the algorithm of the present invention, the green curve represents the improved genetic algorithm, and the pink curve represents the improved ant colony algorithm, wherein the number of raccoon individuals in the raccoon population is 40, and the preset iteration rounds are 200. For comparison, the population size of the improved genetic algorithm is 40, the preset iteration rounds are 200, the crossover probability is 0.75, and the mutation probability is 0.06. For comparison, the population size of the improved ant colony algorithm is 40, the preset iteration rounds are 200, the pheromone volatilization factor is 0.2, and the pheromone factor is 2. Figure 7 It can be seen that in the last iteration round, the fitness value corresponding to the algorithm of the present invention is 0.227, the fitness value corresponding to the improved genetic algorithm is 0.405, and the fitness value corresponding to the improved ant colony algorithm is 0.331. It can be concluded that the path planning scheme for coordinated scheduling of multiple agricultural machinery obtained by the algorithm of the present invention reduces the cost by 44% compared with the improved genetic algorithm, and reduces the cost by 31.4% compared with the improved ant colony algorithm.
[0093] The multi-agricultural machinery coordinated dispatching path planning method provided by the present invention determines the position of each raccoon individual in the raccoon population by initializing the raccoon population of the raccoon optimization algorithm, and then calculates the fitness value of the raccoon individual based on the path planning scheme corresponding to the raccoon individual for each raccoon individual. When the iteration termination condition is reached, the target path planning scheme is determined based on the fitness value of each raccoon individual in each iteration round. When the iteration termination condition is not reached, the position of each raccoon individual is updated based on the fitness value of each raccoon individual, and the fitness value of each raccoon individual is recalculated based on the updated position, and the steps of updating the position and calculating the fitness value are continuously repeated until the iteration termination condition is reached, and finally the target path planning scheme is determined based on the fitness value of each raccoon individual in each iteration round. The technical solution of the present invention can determine the global optimal and more accurate target path planning scheme through the raccoon optimization algorithm. Since the setting of the fitness value corresponding to the raccoon individual in the process of determining the target path planning scheme takes into account the agricultural machinery transfer cost, the agricultural machinery waiting cost and the agricultural machinery dispatch cost, the target path planning scheme finally determined can reduce the cost of multi-agricultural machinery coordinated dispatching to a large extent and reduce resource waste.
[0094] The multi-agricultural machinery collaborative scheduling path planning device provided by the present invention is described below. The multi-agricultural machinery collaborative scheduling path planning device described below and the multi-agricultural machinery collaborative scheduling path planning method described above can be referenced to each other.
[0095] Figure 8 Schematic diagram of the structure of the multi-agricultural machinery coordinated dispatching path planning device provided by the present invention. Figure 8 As shown, the multi-agricultural machinery collaborative scheduling path planning device 800 includes the following modules.
[0096] Initialization module 810, used to initialize the raccoon population of the raccoon optimization algorithm, determine the position of each raccoon individual in the raccoon population, and the position represents the path planning scheme corresponding to the coordinated scheduling of multiple agricultural machines; A calculation module 820 is used to calculate the fitness value of each raccoon individual based on the path planning scheme corresponding to the raccoon individual, wherein the fitness value is determined based on the agricultural machinery transfer cost, agricultural machinery waiting cost and agricultural machinery dispatching cost corresponding to the path planning scheme; A determination module 830 is used to determine whether an iteration termination condition of the raccoon optimization algorithm is met, and if the iteration termination condition is met, determine a target path planning scheme based on the fitness value of each raccoon individual in each iteration round; The updating module 840 is used to update the position of each raccoon individual based on the fitness value of each raccoon individual when the iteration termination condition is not met; recalculate the fitness value of each raccoon individual based on the updated position; and continuously repeat the steps of updating the position and calculating the fitness value until the iteration termination condition is met, and determine the target path planning scheme based on the fitness value of each raccoon individual in each iteration round.
[0097] In one embodiment, the update module 840 is specifically used to: In the current iteration round, the position of each raccoon individual is initially adjusted based on the fitness values of all the raccoon individuals to obtain the first position of each raccoon individual; for each raccoon individual, the reverse position of the raccoon individual is determined based on the first position of the raccoon individual through a reverse learning strategy; the position corresponding to the larger fitness value between the fitness value corresponding to the first position of the raccoon individual and the fitness value corresponding to the reverse position of the raccoon individual is determined as the updated position of the raccoon individual; Alternatively, in the current iteration round, the position of each raccoon individual is randomly adjusted for the first time to obtain the first position of each raccoon individual; for each raccoon individual, the reverse position of the raccoon individual is determined based on the first position of the raccoon individual through a reverse learning strategy; the position corresponding to the larger fitness value between the fitness value corresponding to the first position of the raccoon individual and the fitness value corresponding to the reverse position of the raccoon individual is determined as the updated position of the raccoon individual.
[0098] In one embodiment, the update module 840 is further configured to: Determine the position of the raccoon individual with the highest fitness value among all the raccoon individuals as the position of the prey, and randomly divide all the raccoon individuals into a first raccoon group and a second raccoon group; Initially adjusting the position of each raccoon in the first raccoon group based on the position of the prey; Adjusting the position of the prey according to a preset decision variable to obtain a random position of the prey; Initially adjusting the position of each raccoon individual in the second raccoon group based on the random position of the prey; For each raccoon individual in the raccoon population, when the fitness value corresponding to the adjusted position of the raccoon individual is less than the fitness value corresponding to the position of the raccoon individual before adjustment, the adjusted position of the raccoon individual is determined as the first position of the raccoon individual; when the fitness value corresponding to the adjusted position of the raccoon individual is greater than or equal to the fitness value corresponding to the position of the raccoon individual before adjustment, the adjusted position of the raccoon individual is adjusted again through the Levy flight strategy to determine the second position of the raccoon individual, and the second position of the raccoon individual is determined as the first position of the raccoon individual.
[0099] In one embodiment, the update module 840 is further configured to: Randomly adjusting the position of each raccoon individual according to the number of rounds of the current iteration round and a preset decision variable; For each raccoon individual in the raccoon population, when the fitness value corresponding to the adjusted position of the raccoon individual is less than the fitness value corresponding to the position of the raccoon individual before adjustment, the adjusted position of the raccoon individual is determined as the first position of the raccoon individual; when the fitness value corresponding to the adjusted position of the raccoon individual is greater than or equal to the fitness value corresponding to the position of the raccoon individual before adjustment, the adjusted position of the raccoon individual is adjusted again through the Levy flight strategy to determine the second position of the raccoon individual, and the second position of the raccoon individual is determined as the first position of the raccoon individual.
[0100] In one embodiment, the initialization module 810 is specifically used to: Determine multiple path planning schemes corresponding to the coordinated dispatch of multiple agricultural machines through random functions; Based on the good point set initialization method, multiple path planning schemes are allocated one-to-one to multiple raccoon individuals to determine the position of each raccoon individual.
[0101] In one embodiment, the calculation module 820 is specifically used for: Determine the agricultural machinery transfer cost, the agricultural machinery waiting cost and the agricultural machinery dispatching cost corresponding to the path planning scheme based on the path planning scheme corresponding to the raccoon individual; The weighted sum of the agricultural machinery transfer cost, the agricultural machinery waiting cost and the agricultural machinery dispatching cost is determined as the fitness value of the individual raccoon.
[0102] In one embodiment, the determination module 830 or the update module 840 is specifically configured to: Determine the raccoon individual with the highest fitness value in each iteration round as the global optimal raccoon individual; The path planning scheme represented by the position corresponding to the global optimal raccoon individual is determined as the target path planning scheme.
[0103] The multi-agricultural machinery coordinated dispatching path planning device provided by the present invention determines the position of each raccoon individual in the raccoon population by initializing the raccoon population of the raccoon optimization algorithm, and then calculates the fitness value of the raccoon individual based on the path planning scheme corresponding to the raccoon individual for each raccoon individual. When the iteration termination condition is reached, the target path planning scheme is determined based on the fitness value of each raccoon individual in each iteration round. When the iteration termination condition is not reached, the position of each raccoon individual is updated based on the fitness value of each raccoon individual, and the fitness value of each raccoon individual is recalculated based on the updated position, and the steps of updating the position and calculating the fitness value are continuously repeated until the iteration termination condition is reached, and finally the target path planning scheme is determined based on the fitness value of each raccoon individual in each iteration round. The technical solution of the present invention can determine the global optimal and more accurate target path planning scheme through the raccoon optimization algorithm. Since the setting of the fitness value corresponding to the raccoon individual in the process of determining the target path planning scheme takes into account the transfer cost of agricultural machinery, the waiting cost of agricultural machinery and the dispatch cost of agricultural machinery, the target path planning scheme finally determined can reduce the cost of multi-agricultural machinery coordinated dispatching to a large extent and reduce resource waste.
[0104] Fig. 9 An example of a physical structure diagram of an electronic device is shown in FIG. Fig. 9As shown, the electronic device may include: a processor 910, a communication interface 920, a memory 930 and a communication bus 940, wherein the processor 910, the communication interface 920 and the memory 930 communicate with each other through the communication bus 940. The processor 910 may call the logic instructions in the memory 930 to execute the multi-agricultural machinery coordinated scheduling path planning method, which includes: Initializing a raccoon population of a raccoon optimization algorithm, determining a position of each raccoon individual in the raccoon population, wherein the position represents a path planning scheme corresponding to the coordinated scheduling of multiple agricultural machines; For each of the raccoon individuals, a fitness value of the raccoon individual is calculated based on the path planning scheme corresponding to the raccoon individual, wherein the fitness value is determined based on the agricultural machinery transfer cost, agricultural machinery waiting cost, and agricultural machinery dispatching cost corresponding to the path planning scheme; Determine whether an iteration termination condition of the raccoon optimization algorithm is met, and if the iteration termination condition is met, determine a target path planning scheme based on the fitness value of each raccoon individual in each iteration round; When the iteration termination condition is not met, the position of each raccoon individual is updated based on the fitness value of each raccoon individual; the fitness value of each raccoon individual is recalculated based on the updated position; the steps of updating the position and calculating the fitness value are continuously repeated until the iteration termination condition is met, and the target path planning scheme is determined based on the fitness value of each raccoon individual in each iteration round.
[0105] In addition, the logic instructions in the above-mentioned memory 930 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.
[0106] On the other hand, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored on a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the multi-agricultural machinery coordinated scheduling path planning method provided by the above methods, the method includes: Initializing a raccoon population of a raccoon optimization algorithm, determining a position of each raccoon individual in the raccoon population, wherein the position represents a path planning scheme corresponding to the coordinated scheduling of multiple agricultural machines; For each of the raccoon individuals, a fitness value of the raccoon individual is calculated based on the path planning scheme corresponding to the raccoon individual, wherein the fitness value is determined based on the agricultural machinery transfer cost, agricultural machinery waiting cost, and agricultural machinery dispatching cost corresponding to the path planning scheme; Determine whether an iteration termination condition of the raccoon optimization algorithm is met, and if the iteration termination condition is met, determine a target path planning scheme based on the fitness value of each raccoon individual in each iteration round; When the iteration termination condition is not met, the position of each raccoon individual is updated based on the fitness value of each raccoon individual; the fitness value of each raccoon individual is recalculated based on the updated position; the steps of updating the position and calculating the fitness value are continuously repeated until the iteration termination condition is met, and the target path planning scheme is determined based on the fitness value of each raccoon individual in each iteration round.
[0107] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute the multi-agricultural machinery coordinated scheduling path planning method provided by the above methods, the method comprising: Initializing a raccoon population of a raccoon optimization algorithm, determining a position of each raccoon individual in the raccoon population, wherein the position represents a path planning scheme corresponding to the coordinated scheduling of multiple agricultural machines; For each of the raccoon individuals, a fitness value of the raccoon individual is calculated based on the path planning scheme corresponding to the raccoon individual, wherein the fitness value is determined based on the agricultural machinery transfer cost, agricultural machinery waiting cost, and agricultural machinery dispatching cost corresponding to the path planning scheme; Determine whether an iteration termination condition of the raccoon optimization algorithm is met, and if the iteration termination condition is met, determine a target path planning scheme based on the fitness value of each raccoon individual in each iteration round; When the iteration termination condition is not met, the position of each raccoon individual is updated based on the fitness value of each raccoon individual; the fitness value of each raccoon individual is recalculated based on the updated position; the steps of updating the position and calculating the fitness value are continuously repeated until the iteration termination condition is met, and the target path planning scheme is determined based on the fitness value of each raccoon individual in each iteration round.
[0108] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.
[0109] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for multi-agricultural machinery coordinated scheduling path planning, characterized in that: include: Initializing a raccoon population of a raccoon optimization algorithm, determining a position of each raccoon individual in the raccoon population, wherein the position represents a path planning scheme corresponding to the coordinated scheduling of multiple agricultural machines; For each of the raccoon individuals, a fitness value of the raccoon individual is calculated based on the path planning scheme corresponding to the raccoon individual, wherein the fitness value is determined based on the agricultural machinery transfer cost, agricultural machinery waiting cost and agricultural machinery dispatching cost corresponding to the path planning scheme; Determine whether an iteration termination condition of the raccoon optimization algorithm is met, and if the iteration termination condition is met, determine a target path planning scheme based on the fitness value of each raccoon individual in each iteration round; When the iteration termination condition is not met, the position of each raccoon individual is updated based on the fitness value of each raccoon individual; the fitness value of each raccoon individual is recalculated based on the updated position; the steps of updating the position and calculating the fitness value are continuously repeated until the iteration termination condition is met, and the target path planning scheme is determined based on the fitness value of each raccoon individual in each iteration round.
2. The method for multi-agricultural machinery coordinated scheduling path planning according to claim 1 is characterized in that: The updating of the position of each raccoon individual based on the fitness value of each raccoon individual comprises: In the current iteration round, the position of each raccoon individual is initially adjusted based on the fitness values of all the raccoon individuals to obtain the first position of each raccoon individual; for each raccoon individual, the reverse position of the raccoon individual is determined based on the first position of the raccoon individual through a reverse learning strategy; the position corresponding to the larger fitness value between the fitness value corresponding to the first position of the raccoon individual and the fitness value corresponding to the reverse position of the raccoon individual is determined as the updated position of the raccoon individual; Alternatively, in the current iteration round, the position of each raccoon individual is randomly adjusted for the first time to obtain the first position of each raccoon individual; for each raccoon individual, the reverse position of the raccoon individual is determined based on the first position of the raccoon individual through a reverse learning strategy; the position corresponding to the larger fitness value between the fitness value corresponding to the first position of the raccoon individual and the fitness value corresponding to the reverse position of the raccoon individual is determined as the updated position of the raccoon individual.
3. The method for multi-agricultural machinery coordinated scheduling path planning according to claim 2 is characterized in that: The step of initially adjusting the position of each raccoon individual based on the fitness value of all the raccoon individuals to obtain the first position of each raccoon individual includes: Determine the position of the raccoon individual with the highest fitness value among all the raccoon individuals as the position of the prey, and randomly divide all the raccoon individuals into a first raccoon group and a second raccoon group; Initially adjusting the position of each raccoon in the first raccoon group based on the position of the prey; Adjusting the position of the prey according to a preset decision variable to obtain a random position of the prey; Initially adjusting the position of each raccoon individual in the second raccoon group based on the random position of the prey; For each raccoon individual in the raccoon population, when the fitness value corresponding to the adjusted position of the raccoon individual is less than the fitness value corresponding to the position of the raccoon individual before adjustment, the adjusted position of the raccoon individual is determined as the first position of the raccoon individual; when the fitness value corresponding to the adjusted position of the raccoon individual is greater than or equal to the fitness value corresponding to the position of the raccoon individual before adjustment, the adjusted position of the raccoon individual is adjusted again through the Levy flight strategy to determine the second position of the raccoon individual, and the second position of the raccoon individual is determined as the first position of the raccoon individual.
4. The method for multi-agricultural machinery coordinated scheduling path planning according to claim 2 is characterized in that: The randomly adjusting the position of each raccoon individual for the first time to obtain the first position of each raccoon individual includes: Randomly adjusting the position of each raccoon individual according to the number of rounds of the current iteration round and a preset decision variable; For each raccoon individual in the raccoon population, when the fitness value corresponding to the adjusted position of the raccoon individual is less than the fitness value corresponding to the position of the raccoon individual before adjustment, the adjusted position of the raccoon individual is determined as the first position of the raccoon individual; when the fitness value corresponding to the adjusted position of the raccoon individual is greater than or equal to the fitness value corresponding to the position of the raccoon individual before adjustment, the adjusted position of the raccoon individual is adjusted again through the Levy flight strategy to determine the second position of the raccoon individual, and the second position of the raccoon individual is determined as the first position of the raccoon individual.
5. The method for multi-agricultural machinery coordinated dispatching path planning according to any one of claims 1 to 4, characterized in that: Determining the location of each individual raccoon in the raccoon population includes: Determine multiple path planning schemes corresponding to the coordinated dispatch of multiple agricultural machines through random functions; Based on the good point set initialization method, multiple path planning schemes are allocated one-to-one to multiple raccoon individuals to determine the position of each raccoon individual.
6. The method for multi-agricultural machinery coordinated dispatching path planning according to any one of claims 1 to 4, characterized in that: The calculating the fitness value of the raccoon individual based on the path planning scheme corresponding to the raccoon individual includes: Determine the agricultural machinery transfer cost, the agricultural machinery waiting cost and the agricultural machinery dispatching cost corresponding to the path planning scheme based on the path planning scheme corresponding to the raccoon individual; The weighted sum of the agricultural machinery transfer cost, the agricultural machinery waiting cost and the agricultural machinery dispatching cost is determined as the fitness value of the individual raccoon.
7. The method for multi-agricultural machinery coordinated dispatching path planning according to any one of claims 1 to 4, characterized in that: The method of determining a target path planning scheme based on the fitness value of each raccoon individual in each iteration round includes: Determine the raccoon individual with the highest fitness value in each iteration round as the global optimal raccoon individual; The path planning scheme represented by the position corresponding to the global optimal raccoon individual is determined as the target path planning scheme.
8. A multi-agricultural machinery coordinated dispatching path planning device, characterized in that: include: An initialization module, used to initialize the raccoon population of the raccoon optimization algorithm, determine the position of each raccoon individual in the raccoon population, and the position represents the path planning scheme corresponding to the coordinated scheduling of multiple agricultural machinery; A calculation module, for calculating the fitness value of each raccoon individual based on the path planning scheme corresponding to the raccoon individual, wherein the fitness value is determined based on the agricultural machinery transfer cost, agricultural machinery waiting cost and agricultural machinery dispatching cost corresponding to the path planning scheme; A determination module, used to determine whether an iteration termination condition of the raccoon optimization algorithm is met, and when the iteration termination condition is met, determine a target path planning scheme based on the fitness value of each raccoon individual in each iteration round; An updating module is used to update the position of each raccoon individual based on the fitness value of each raccoon individual when the iteration termination condition is not met; recalculate the fitness value of each raccoon individual based on the updated position; and continuously repeat the steps of updating the position and calculating the fitness value until the iteration termination condition is met, and determine the target path planning scheme based on the fitness value of each raccoon individual in each iteration round.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the multi-agricultural machinery collaborative scheduling path planning method as described in any one of claims 1 to 7 is implemented.
10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for path planning for coordinated scheduling of multiple agricultural machines as described in any one of claims 1 to 7 is implemented.
Citation Information
Patent Citations
Multi-agricultural machinery scheduling operation method based on improved artificial fish swarm algorithm
CN113095726A
Flexible workshop collaborative production method and system based on improved raccoon optimization algorithm
CN116933939A
Raccoon optimization algorithm-based multi-torpedo-tank multi-track walking path optimization method
CN117371638A
Inspection robot global path planning method, system, equipment and medium
CN117556863A
Cited By
Vibration robot group walking path optimization method based on improved raccoon algorithm
CN120669693A
