Joint agricultural machine operation path planning method and device

Abstract

The invention discloses a combined agricultural machine operation path planning method and device, and the method comprises the steps: dividing a target farmland into a plurality of operation lines based on agricultural machine parameters and farmland parameters; distributing a plurality of operation rows to a plurality of agricultural machines to be operated which perform combined operation in the target farmland; and under a preset constraint condition, determining an optimal combined agricultural machine operation path based on the transfer cost of each to-be-operated agricultural machine, the transfer cost comprises an entry cost of each agricultural machine to be operated starting from a starting point corresponding to a warehouse where the agricultural machine to be operated is located to enter a corresponding distributed operation row, a row feed cost when the agricultural machine to be operated is operated through all the corresponding distributed operation rows, and a departure cost of returning to the corresponding starting point after the operation is completed; the optimal combined agricultural machine operation path corresponds to a path that the plurality of to-be-operated agricultural machines start from the corresponding starting points of the warehouse, pass through all the correspondingly distributed operation rows and then return to the corresponding starting points.

Description

Technical Field

[0001] The present application relates to the technical field of path planning, and in particular to a method and device for planning a path for combined agricultural machinery operations. Background Art

[0002] In modern agricultural production, path planning is the key technology for modern intelligent agricultural machinery to achieve autonomous navigation, movement and operation. It determines the total consumption of agricultural machinery work and affects the actual operation efficiency and quality of agricultural machinery work. As the farmland operation scene gradually changes to large-scale standard farmland, research on the joint operation of multiple agricultural machinery and scientific allocation and scheduling resources can improve production efficiency.

[0003] Most of the existing combined agricultural machinery operation path planning methods only study the operation paths of each combined operation agricultural machinery in the farmland and the transfer paths between operation rows, ignoring the specific transfer paths of agricultural machinery entering or leaving the farmland. This will lead to insufficient accuracy of the planned path and reduce the environmental adaptability and safety of autonomous operation of agricultural machinery. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a method and device for planning a path for combined agricultural machinery operations, so as to solve the problem of insufficient accuracy in existing path planning for combined agricultural machinery operations.

[0005] In order to solve the above technical problems, this specification is implemented as follows: In a first aspect, a method for planning a joint agricultural machinery operation path is provided, comprising: Based on the agricultural machinery parameters and the farmland parameters, the target farmland is divided into a plurality of operation rows; Allocating a plurality of operation rows to a plurality of agricultural machines to be operated in a joint operation on the target farmland; Under preset constraints, the optimal combined agricultural machinery operation path is determined based on the transfer cost of each agricultural machinery to be operated, the transfer cost includes the entry cost of each agricultural machinery to be operated starting from the starting point corresponding to the warehouse where it is located and entering the corresponding assigned operation row, the row change cost when passing through all the corresponding assigned operation rows to perform the operation, and the exit cost of returning to the corresponding starting point after completing the operation. The optimal combined agricultural machinery operation path corresponds to the path of the multiple agricultural machinery to be operated starting from the starting point corresponding to the warehouse where they are located, passing through all the corresponding assigned operation rows and returning to the corresponding starting point.

[0006] Optionally, the target farmland is divided into a plurality of operation rows based on the agricultural machinery parameters and the farmland parameters, including: Based on the farmland parameters of the target farmland, the longest boundary among the boundaries of the target farmland is selected as a baseline; Parallel to the baseline, the agricultural machinery is translated at equal intervals according to the agricultural machinery operating width in the agricultural machinery parameters to generate multiple operating rows until the entire target farmland is covered.

[0007] Optionally, the determining of the optimal joint agricultural machinery operation path based on the transfer cost of each agricultural machinery to be operated under preset constraints includes: The starting point of a single agricultural machine to be operated among the agricultural machines to be operated and a plurality of operation rows assigned to the single operating agricultural machine are used as nodes; The transfer costs between the nodes are stored in an adjacency matrix, wherein the transfer costs correspond to the entry cost and the exit cost between the starting node and the corresponding working row node, and the line change cost between the working row nodes; Determine the node traversal order with the minimum transfer cost by using a preset global search algorithm; Determine the optimal operation path of a single agricultural machine to be operated based on the node traversal order with the minimum transfer cost; The optimal combined agricultural machinery operation path is determined based on the optimal operation paths of each agricultural machine to be operated.

[0008] Optionally, the allocating the plurality of operation rows to the plurality of agricultural machines to be operated in the joint operation on the target farmland comprises: allocating the plurality of operation rows to the plurality of agricultural machines to be operated in the joint operation on the target farmland by using an outer layer simulated annealing algorithm of a double layer simulated annealing algorithm; The method of determining the node traversal order when the transfer cost of each agricultural machine to be operated is minimized under the assigned operation row by using a preset global search algorithm includes: determining the node traversal order when the transfer cost is minimized by using the inner layer simulated annealing algorithm of the double-layer simulated annealing algorithm.

[0009] Optionally, the outer layer simulated annealing algorithm of the double layer simulated annealing algorithm is used to allocate multiple operation rows to multiple agricultural machines to be operated in joint operation in the target farmland, including: The number and positions of the multiple work rows divided into the target farmland and the number of the multiple agricultural machines to be operated are provided as input to the outer layer simulated annealing algorithm to obtain an outer layer solution output by the outer layer simulated annealing algorithm, wherein the outer layer solution includes the number and position of the work rows allocated to each agricultural machine to be operated.

[0010] Optionally, the inner layer simulated annealing algorithm of the double layer simulated annealing algorithm is used to determine the node traversal order when the transfer cost of each agricultural machine to be operated is the smallest under the assigned operation row, including: Passing the outer layer solution to the inner layer simulated annealing algorithm, wherein the inner layer simulated annealing algorithm is used to calculate inner layer solutions and corresponding transfer costs at different inner layer temperatures based on the outer layer solution; Lowering the current inner layer temperature to the target inner layer temperature, and adjusting the traversal order of the operation rows assigned to each agricultural machine to be operated in the inner layer solution, so as to obtain an updated inner layer solution and a corresponding transfer cost, wherein the inner layer solution includes the traversal order of the operation rows assigned to each agricultural machine to be operated corresponding to the outer layer solution, and the target inner layer temperature includes one of the inner layer temperatures gradually decreasing from the inner layer initial temperature preset by the inner layer simulated annealing algorithm and the inner layer termination temperature preset by the inner layer simulated annealing algorithm; Based on the difference between the corresponding transfer costs before and after the inner solution is updated, the historical optimal inner solution is updated, and the transfer cost corresponding to the optimal inner solution is the smallest; If the target inner layer temperature reaches the inner layer termination temperature, output the historical optimal inner layer solution, otherwise return to the step of lowering the current inner layer temperature to the target inner layer temperature until the inner layer termination temperature is reached; The optimal combined agricultural machinery operation path is determined based on the traversal order of the nodes of the operation row corresponding to the outputted historical optimal inner layer solution and the number and position of the operation rows allocated corresponding to the outer layer solution.

[0011] Optionally, before determining the optimal combined agricultural machinery operation path based on the traversal order of the nodes of the operation row corresponding to the outputted historical optimal inner layer solution and the number and position of the operation row corresponding to the outer layer solution, the method further includes: Determining the transfer cost corresponding to the outer solution of the outer simulated annealing algorithm based on the transfer cost corresponding to the outputted historical optimal inner solution and the penalty item corresponding to the outer solution; Lowering the current outer layer temperature to a target outer layer temperature, and adjusting the number and position of the operation rows allocated to each agricultural machine to be operated in the outer layer solution to obtain an updated outer layer solution, wherein the target outer layer temperature includes one of the outer layer temperatures gradually decreasing from the outer layer initial temperature preset by the outer layer simulated annealing algorithm and the outer layer termination temperature preset by the outer layer simulated annealing algorithm; Based on the updated outer solution, returning to the step of passing the outer solution to the inner simulated annealing algorithm until the inner simulated annealing algorithm outputs an updated historical optimal inner solution; Determining a transfer cost corresponding to the updated outer solution based on the transfer cost corresponding to the updated historical optimal inner solution and the penalty item corresponding to the outer solution; Based on the difference in the transfer costs before and after the outer solution is updated, the historical optimal outer solution is updated, and the transfer cost corresponding to the optimal outer solution is the smallest; If the target outer layer temperature reaches the outer layer termination temperature, output the historical optimal outer layer solution, otherwise return to the step of lowering the current outer layer temperature to the target outer layer temperature until the outer layer termination temperature is reached; The method of determining the optimal combined agricultural machinery operation path based on the traversal order of the nodes of the operation row corresponding to the outputted historical optimal inner layer solution and the number and position of the operation rows corresponding to the outer layer solution includes: The optimal combined agricultural machinery operation path is determined based on the traversal order of the nodes of the operation row corresponding to the output historical optimal inner solution and the number and position of the operation rows allocated corresponding to the output historical optimal outer solution.

[0012] Optionally, it also includes: In the optimal combined agricultural machinery operation path, if there is a conflict in the line-changing paths of the corresponding working rows of two agricultural machines, an obstacle circle with a diameter of the agricultural machine width is set between two starting points of the two agricultural machines in their respective line-changing paths; Determine the target waypoints of the two agricultural machines on the obstacle circle respectively, and the vertical distance between the two target waypoints and the line connecting the two starting points is the largest; Based on the starting points and waypoints corresponding to the two agricultural machines respectively, the detour paths corresponding to the two agricultural machines on the line-changing path are determined by using the Dubins path algorithm.

[0013] Optionally, the target agricultural machinery to be operated is assigned multiple operating rows, and the row change cost corresponding to the target agricultural machinery to be operated is related to different turning methods, and the row change cost includes a combination of one or more of the distance cost, time cost and reserved turning distance generated by the corresponding turning method.

[0014] In a second aspect, a combined agricultural machinery operation path planning device is provided, comprising a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of the method described in the first aspect are implemented.

[0015] In an embodiment of the present application, the target farmland is divided into multiple work rows based on agricultural machinery parameters and farmland parameters; the multiple work rows are allocated to multiple agricultural machinery to be operated in joint operation in the target farmland; under preset constraints, the optimal joint agricultural machinery operation path is determined based on the transfer cost of each agricultural machinery to be operated, the transfer cost includes the entry cost of each agricultural machinery to be operated starting from the starting point corresponding to the warehouse where it is located and entering the corresponding assigned work row, the row change cost when passing through all the corresponding assigned work rows to perform the operation, and the exit cost of returning to the corresponding starting point after completing the operation. The optimal joint agricultural machinery operation path corresponds to the path of the multiple agricultural machinery to be operated starting from the starting point corresponding to the warehouse where it is located, passing through all the corresponding assigned work rows and returning to the corresponding starting point. In this way, the operation paths of the agricultural machinery in the farmland for each joint operation, the transfer paths between the work rows, and the specific transfer paths of the agricultural machinery entering or leaving the farmland can be comprehensively considered to plan the optimal joint agricultural machinery operation path, thereby improving the accuracy of the planned path and improving the environmental adaptability and safety of autonomous operation of agricultural machinery. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 It is a flow chart of the combined agricultural machinery operation path planning method of the embodiment of the present application.

[0017] Figure 2 It is a schematic diagram of the turning method of the operation row changing in the embodiment of the present application.

[0018] Figure 3 This is a schematic diagram of the combined agricultural machinery operation path planning of an embodiment of the present application.

[0019] Figure 4 This is a schematic diagram of the multi-agricultural machinery path conflict in an embodiment of the present application.

[0020] Figure 5 This is a schematic diagram of the detour of multiple agricultural machinery paths in an embodiment of the present application.

[0021] Figure 6 It is a schematic diagram of the overall process of the combined agricultural machinery operation path planning method of an embodiment of the present application.

[0022] Figure 7 It is a structural block diagram of the combined agricultural machinery operation path planning device of an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application. The numbering of the drawings in this application is only used to distinguish the various steps in the scheme, and is not used to limit the execution order of the various steps. The specific execution order is subject to the description in the specification.

[0024] In order to solve the problems existing in the prior art, the present application embodiment provides a method for planning a joint agricultural machinery operation path, such as Figure 1 As shown, the following steps 102 to 106 are included.

[0025] Step 102: Divide the target farmland into a plurality of operation rows based on the farm machine parameters and the farmland parameters.

[0026] Agricultural machinery needs to cover the entire area of ​​the farmland when operating in the farmland, and perform reciprocating traversal and parallel operations based on the operation rows divided in the entire area of ​​the farmland. Agricultural machinery parameters mainly include the operating width of the agricultural machinery, and farmland parameters include the boundary and boundary length of the farmland.

[0027] Based on the solution provided in the above embodiment, optionally, in the above step 102, the target farmland is divided into multiple work rows based on the agricultural machinery parameters and the farmland parameters, including: based on the farmland parameters of the target farmland, selecting the longest boundary among the boundaries of the target farmland as a baseline; parallel to the baseline, equidistantly translating according to the agricultural machinery operation width in the agricultural machinery parameters to generate multiple work rows until the entire target farmland is covered.

[0028] For farmlands in regular boundary areas, we can use the baseline translation method to generate multiple straight line working paths by using a baseline parallel to the longer boundary of the farmland, according to the working width of the agricultural machinery that will operate in the farmland, and translate them at equal intervals until the entire area of ​​the farmland is covered, thus obtaining multiple working rows corresponding to the working width of the agricultural machinery.

[0029] Step 104 , allocating a plurality of operation rows to a plurality of agricultural machines to be operated in a joint operation on the target farmland.

[0030] In the embodiment of the present application, it is applied to the scenario of joint operation of multiple agricultural machines. Therefore, it is necessary to allocate the multiple divided operation rows to the multiple agricultural machines to be operated corresponding to the joint operation.

[0031] According to the arrangement and combination of different agricultural machines and different operation rows, multiple different allocation schemes can be obtained. For example, there are two agricultural machines to be operated in the target farmland, agricultural machine No. 1 and agricultural machine No. 2; there are 6 operation rows divided, and the adjacent rows are numbered as row 1, row 2, ... row 6, then the allocation scheme 1 can be obtained as follows: agricultural machine No. 1 is allocated to rows 1 to 3, and agricultural machine No. 2 is allocated to rows 4 to 6; allocation scheme 2 is: agricultural machine No. 1 is allocated to rows 1, 3 to 4, and agricultural machine No. 2 is allocated to rows 2, 5 to 6, and so on.

[0032] Step 106, under preset constraints, determine the optimal combined agricultural machinery operation path based on the transfer cost of each agricultural machinery to be operated, the transfer cost includes the entry cost of each agricultural machinery to be operated starting from the corresponding starting point of the warehouse where it is located and entering the corresponding assigned operation row, the row change cost when passing through all the corresponding assigned operation rows to perform the operation, and the exit cost of returning to the corresponding starting point after completing the operation. The optimal combined agricultural machinery operation path corresponds to the path of the multiple agricultural machinery to be operated starting from the corresponding starting point of the warehouse where they are located, passing through all the corresponding assigned operation rows and returning to the corresponding starting point.

[0033] After the scheme of allocating the divided operation rows to multiple agricultural machines to be operated is determined in step 104, the joint operation path corresponding to each allocation scheme can be determined. For example, the operation path of agricultural machine No. 1 in the joint agricultural machinery operation path corresponding to allocation scheme 1 is: agricultural machine No. 1 starts from the starting point a corresponding to the warehouse where it is located and enters the first row of the allocated operation row, transfers to the second row after the operation of the first row is completed, transfers to the third row after the operation of the second row is completed, and returns to the corresponding starting point a after the operation of the third row is completed; or, agricultural machine No. 1 starts from the starting point a corresponding to the warehouse where it is located and enters the third row of the allocated operation row, transfers to the second row after the operation of the third row is completed, transfers to the first row after the operation of the second row is completed, and returns to the corresponding starting point a after the operation of the first row is completed. Correspondingly, the operation path of agricultural machine No. 2 in the joint agricultural machinery operation path corresponding to allocation scheme 1 can be determined.

[0034] If the target agricultural machinery to be operated is assigned an odd number of operation rows, when the target agricultural machinery to be operated completes the operation and returns to the warehouse, it needs to move to the machine path, and then return to the corresponding starting position of the warehouse from the machine path. The machine path is a road where the agricultural machinery does not operate. If the machine path is not used, and the operation rows of other agricultural machinery to be operated are selected to return to the warehouse, it will cause a conflict with the operation paths of other agricultural machinery to be operated. Therefore, in the embodiment of the present application, the machine path can be used to return to the warehouse, and the problem of odd number of operation rows can be solved by adding machine paths.

[0035] For example, the machine path can be configured to allocate row 0 to the corresponding agricultural machine. Taking the above agricultural machine No. 1 as an example, the normal assigned operation rows are rows 1 to 3, so it is necessary to increase the machine path to allocate rows 0 to 3. Correspondingly, the operation rows assigned to agricultural machine No. 2 are row 0 and rows 4 to 6.

[0036] By analogy, the joint agricultural machinery operation path corresponding to each allocation scheme can be determined. Under the preset constraints, the transfer costs generated by different allocation schemes corresponding to the joint agricultural machinery operation path are different. The transfer cost includes the entry cost of each agricultural machinery waiting to be operated from the starting point corresponding to the warehouse to enter the corresponding assigned operation line, the line change cost when passing through all the corresponding assigned operation lines to perform operations, and the exit cost of returning to the corresponding starting point after completing the operation.

[0037] The closer the joint agricultural machinery operation path determined by the allocation scheme is to satisfying the preset constraints, the smaller the corresponding transfer cost. The preset constraints include, for example, the shortest distance of the joint agricultural machinery operation path, the shortest time of the joint agricultural machinery operation, the minimum turning distance reserved when the joint agricultural machinery switches between different operation rows, etc. The joint agricultural machinery operation path with the minimum transfer cost is the optimal joint agricultural machinery operation path for each agricultural machinery to be operated. Multiple agricultural machinery to be operated start from the starting point corresponding to the warehouse where they are located, follow the optimal joint agricultural machinery operation path to reach the corresponding assigned operation row to perform the operation, and return to the corresponding starting point after completing the assigned operation row, and the transfer cost generated is the minimum.

[0038] In one embodiment, under preset constraints, the optimal combined agricultural machinery operation path is determined based on the transfer cost of each agricultural machinery to be operated, including: taking the starting point of a single agricultural machinery to be operated among the agricultural machinery to be operated and the multiple operation rows assigned to the single operation agricultural machinery as nodes; storing the transfer cost between each node in an adjacency matrix, and the transfer cost corresponds to the entry cost, exit cost, and row change cost between the node of the starting point and the node of the corresponding operation row; determining the node traversal order when the transfer cost is minimized through a preset global search algorithm; determining the optimal operation path of a single agricultural machinery to be operated based on the node traversal order when the transfer cost is minimized; and determining the optimal combined agricultural machinery operation path based on the optimal operation path of each agricultural machinery to be operated.

[0039] In order to meet the needs of multiple agricultural machinery automatically navigating back and forth to traverse parallel work rows, the embodiment of the present application takes into account the cost of a single agricultural machinery entering and exiting the farmland, and allocates each work row divided by the entire farmland to each agricultural machine respectively. The joint agricultural machinery work path optimization problem is redescribed as dividing the joint agricultural machinery work path into multiple sub-operation paths and assigning them to individual agricultural machines respectively.

[0040] For a single agricultural machine, the optimal path for the agricultural machine to start from the starting point and return to the starting point of the agricultural machine after passing through all the divided operation rows under multiple constraints is determined. The path in the operation row is fixed, so the operation path optimization problem is essentially the problem of finding the minimum cost of switching between different operation rows during the operation process. The starting point of the agricultural machine and each operation row are regarded as nodes, and the transfer cost between each node is stored in the adjacency matrix. The transfer cost and the minimum operation row traversal order can be searched through the search algorithm.

[0041] Adjacency Matrix For a size The square array, Indicates the number of operation rows assigned to a single target agricultural machine. If the traversal order of the operation row is , then the transfer cost and ,in are the numbers of different job row nodes. is the starting point.

[0042] The feasible solution of the traversal order is the full arrangement of N operation row nodes. The global optimal solution is found by traversing each feasible solution. Based on the node traversal order corresponding to the global optimal solution, the optimal operation path of a single agricultural machinery is determined, and then the optimal joint agricultural machinery operation path of multiple agricultural machinery is obtained.

[0043] As the number of nodes in a job row increases, the time cost of traversing all feasible solutions becomes high. In one embodiment, the present application uses a heuristic algorithm to search for a global optimal solution.

[0044] Specifically, the allocating multiple work rows to multiple agricultural machines to be operated in joint operation on the target farmland includes: allocating multiple work rows to multiple agricultural machines to be operated in joint operation on the target farmland through the outer layer simulated annealing algorithm of the double-layer simulated annealing algorithm; determining the node traversal order when the transfer cost is minimized through the preset global search algorithm, includes: determining the node traversal order when the transfer cost of each agricultural machine to be operated is minimized under the assigned work row through the inner layer simulated annealing algorithm of the double-layer simulated annealing algorithm.

[0045] In the above embodiment, the inner layer simulated annealing algorithm of the double-layer simulated annealing algorithm is used to search for the optimal operation row traversal sequence of a single agricultural machine, and then the outer layer simulated annealing algorithm of the double-layer simulated annealing algorithm is used to optimize the operation plan of multiple agricultural machines as a whole. The simulated annealing algorithm (SA) is derived from the solid annealing principle and was first proposed by N. Metropolis et al. The simulated annealing algorithm accepts the difference solution with a certain probability and can jump out of the local optimal solution to obtain the global optimal solution.

[0046] Specifically, the outer layer simulated annealing algorithm of the double-layer simulated annealing algorithm allocates multiple work rows to multiple agricultural machines to be operated in conjunction in the target farmland, including: providing the number and positions of the multiple work rows divided by the target farmland and the number of the multiple agricultural machines to be operated as input to the outer layer simulated annealing algorithm to obtain an outer layer solution output by the outer layer simulated annealing algorithm, wherein the outer layer solution includes the number and position of the work rows allocated to each agricultural machine to be operated.

[0047] In the embodiment of the present application, the outer layer simulated annealing algorithm is first started. According to the number and position of the operation rows divided into farmland and the number of multiple agricultural machines for joint operation, the outer layer simulated annealing algorithm randomly generates the outer layer solution global_solution1, which includes the allocation scheme of each agricultural machine to be operated, that is, the operation row position and the number of crop rows allocated to each agricultural machine to be operated. For example, the randomly generated allocation scheme is: agricultural machine No. 1 is allocated to rows 0 to 3, and agricultural machine No. 2 is allocated to rows 0 and rows 4 to 6.

[0048] Specifically, the inner layer simulated annealing algorithm of the double-layer simulated annealing algorithm is used to determine the node traversal order when the transfer cost of each agricultural machinery to be operated is minimized under the assigned operation row, including: passing the outer layer solution to the inner layer simulated annealing algorithm, and the inner layer simulated annealing algorithm is used to calculate the inner layer solution and the corresponding transfer cost under different inner layer temperatures based on the outer layer solution; lowering the current inner layer temperature to the target inner layer temperature, and adjusting the traversal order of the operation rows assigned to each agricultural machinery to be operated in the inner layer solution to obtain an updated inner layer solution and the corresponding transfer cost, the inner layer solution includes the traversal order of the operation rows assigned to each agricultural machinery to be operated corresponding to the outer layer solution, and the target inner layer temperature The degree includes the inner layer temperatures that gradually decrease from the inner layer initial temperature preset by the inner layer simulated annealing algorithm and one of the inner layer termination temperatures preset by the inner layer simulated annealing algorithm; based on the difference in the transfer costs corresponding to the inner layer solution before and after the update, the historical optimal inner layer solution is updated, and the transfer cost corresponding to the optimal inner layer solution is the smallest; if the target inner layer temperature reaches the inner layer termination temperature, the historical optimal inner layer solution is output, otherwise the step of lowering the current inner layer temperature to the target inner layer temperature is returned; based on the traversal order of the nodes of the operation row corresponding to the output historical optimal inner layer solution, and the number and position of the operation rows corresponding to the outer layer solution, the optimal combined agricultural machinery operation path is determined.

[0049] In this embodiment, the outer simulated annealing algorithm passes the outer solution global_solution1 to the inner simulated annealing algorithm for optimization. Set the initial temperature of the inner simulated annealing algorithm , cooling rate and stop temperature According to the position and number of the operation rows assigned in the outer solution global_solution1, the inner solution of the outer solution at the corresponding inner temperature is calculated by the inner simulated annealing algorithm. , that is, the operation row traversal order assigned to each agricultural machine, and the transfer cost corresponding to the assigned operation row traversal order .

[0050] The inner layer simulated annealing algorithm can be obtained from the initial temperature The temperature is gradually reduced, for example, by a preset temperature interval, and the target inner layer temperature can be the temperature after each reduction. After each temperature reduction, the adjustment factor is calculated according to the current inner layer temperature T2. , from the inner layer Randomly select elements are randomly exchanged, that is, the inner solution is randomly adjusted The traversal order of the corresponding operation rows assigned to each agricultural machine to be operated, such as the inner solution The traversal order of the corresponding operation rows is: No. 1 agricultural machine traverses the operation in the order of row 1, row 2, row 3, and row 0, and No. 2 agricultural machine traverses the operation in the order of row 4, row 0, row 5, and row 6. The traversal order of the operation rows after random adjustment is: No. 1 agricultural machine traverses the operation in the order of row 2, row 0, row 3, and row 1, and No. 2 agricultural machine traverses the operation in the order of row 5, row 6, row 4, and row 0.

[0051] Adjust the inner solution of After the inner layer simulated annealing algorithm is used to obtain a new inner layer solution and its cost Among them, the adjustment factor , is the floor factor, and Respectively represent the maximum and minimum number of job rows that can be adjusted.

[0052] Calculate the corresponding transfer cost before and after the inner solution is updated If the difference between Better than ,Right now , represents the inner solution The corresponding transfer cost is smaller, then the inner solution is accepted. , and update the historical optimal inner solution Otherwise, with probability Accept new inner solution . At the same time, it is consistent with the historical optimal inner solution Compare, if The corresponding transfer cost is less than The corresponding transfer cost is updated for , keeping the transfer cost of the historical optimal inner solution to the minimum.

[0053] Determine whether the current inner layer temperature T2 drops to the set temperature stop temperature If so, output the historical optimal inner solution , the optimal traversal order of the operation rows of each agricultural machine corresponding to the outer layer solution is obtained. Thus, based on the traversal order of the nodes of the operation rows corresponding to the historical optimal inner layer solution and the number and position of the operation rows corresponding to the outer layer solution, the optimal joint agricultural machine operation path of each agricultural machine to be operated is determined.

[0054] If the current inner layer temperature T2 does not drop to the set temperature stop temperature , then return to the above step of gradually reducing the inner layer temperature, and repeat the above steps until the current inner layer temperature drops to the set temperature stop temperature .

[0055] In one embodiment, the historical optimal inner layer solutions output by the inner layer simulated annealing algorithm at different temperatures can be further and the corresponding transfer cost are passed to the outer simulated annealing algorithm for optimization.

[0056] Specifically, before determining the optimal combined agricultural machinery operation path based on the traversal order of the nodes of the operation row corresponding to the output historical optimal inner solution and the number and position of the operation rows allocated to the outer solution, the method also includes: determining the transfer cost corresponding to the outer solution of the outer layer simulated annealing algorithm based on the transfer cost corresponding to the output historical optimal inner solution and the penalty item corresponding to the outer solution; reducing the current outer layer temperature to the target outer layer temperature, and adjusting the number and position of the operation rows allocated to each agricultural machinery to be operated in the outer layer solution to obtain an updated outer layer solution, wherein the target outer layer temperature includes one of the outer layer temperatures that gradually decrease from the outer layer initial temperature preset by the outer layer simulated annealing algorithm and the outer layer termination temperature preset by the outer layer simulated annealing algorithm; returning to the step of passing the outer layer solution to the inner layer simulated annealing algorithm based on the updated outer layer solution until the inner layer simulated annealing algorithm outputs the updated historical optimal solution. The optimal inner layer solution is output; based on the transfer cost corresponding to the updated historical optimal inner layer solution and the penalty item corresponding to the outer layer solution, the transfer cost corresponding to the updated outer layer solution is determined; based on the difference in the transfer costs before and after the outer layer solution is updated, the historical optimal outer layer solution is updated, and the transfer cost corresponding to the optimal outer layer solution is the smallest; if the target outer layer temperature reaches the outer layer termination temperature, the historical optimal outer layer solution is output, otherwise the step of lowering the current outer layer temperature to the target outer layer temperature is returned until the outer layer termination temperature is reached; wherein, the optimal combined agricultural machinery operation path is determined based on the traversal order of the nodes of the operation row corresponding to the output historical optimal inner layer solution and the number and position of the operation row assigned to the outer layer solution, including: determining the optimal combined agricultural machinery operation path based on the traversal order of the nodes of the operation row corresponding to the output historical optimal inner layer solution and the number and position of the operation row assigned to the output historical optimal outer layer solution.

[0057] In the above embodiment, when it is determined that the current inner layer temperature T2 drops to the set temperature stop temperature And output the historical optimal inner solution Afterwards, the inner layer simulated annealing algorithm converts the historical optimal inner layer solution The corresponding transfer cost is passed to the outer simulated annealing algorithm. The outer simulated annealing algorithm determines the transfer cost corresponding to the current outer solution according to the transfer cost and the penalty item corresponding to the allocation scheme of the current outer solution (for example, if the operation rows of the case are not balanced, a certain penalty item will be generated). , and will be based on the historical optimal inner solution As the historical optimal outer layer solution of the outer layer simulated annealing algorithm at the current temperature .

[0058] In this embodiment, the outer simulated annealing algorithm passes the outer solution global_solution1 to the inner simulated annealing algorithm for optimization. Set the initial temperature of the outer simulated annealing algorithm and stop temperature .

[0059] The outer layer simulated annealing algorithm can be obtained from the initial temperature The temperature is gradually reduced, for example, by a preset temperature interval, and the target outer layer temperature can be the temperature after each reduction. After each temperature reduction, the adjustment factor is calculated according to the current outer layer temperature T1. , from the outside Randomly select elements are randomly exchanged, that is, the outer solution is randomly adjusted The corresponding allocation scheme for each agricultural machine to be operated, for example, The corresponding allocation plan: agricultural machinery No. 1 is allocated to rows 0 to 3, agricultural machinery No. 2 is allocated to rows 0 and rows 4 to 6, and randomly adjusted to: agricultural machinery No. 1 is allocated to rows 0, 2, 4, and 6, and agricultural machinery No. 2 is allocated to rows 0, 1, 3, and 5.

[0060] Adjust the outer solution After the elements are obtained, a new outer layer solution is obtained through the outer layer simulated annealing algorithm. and its cost Among them, the adjustment factor , is the floor factor, and Respectively represent the maximum and minimum number of job rows that can be adjusted.

[0061] Calculate the corresponding transfer cost before and after the outer solution is updated If the difference between Better than ,Right now , represents the outer solution The corresponding transfer cost is smaller, then accept the outer solution , and update the historical optimal inner solution Otherwise, with probability Accept new outer solutions . At the same time, it is consistent with the historical optimal outer solution Compare, if The corresponding transfer cost is less than The corresponding transfer cost is updated for , keeping the transfer cost of the historical optimal outer solution to the minimum.

[0062] Determine whether the current outer layer temperature T1 drops to the set temperature stop temperature If so, output the historical optimal outer solution , and obtain the allocation scheme corresponding to the outer layer solution, as well as the optimal traversal order of the operation rows assigned to each agricultural machine corresponding to the inner layer solution at the current outer layer temperature. Thus, based on the traversal order of the nodes of the operation rows corresponding to the historical optimal inner layer solution and the number and position of the operation rows assigned to the outer layer solution, the optimal joint agricultural machine operation path for each agricultural machine to be operated is determined.

[0063] If the current outer layer temperature T1 does not drop to the set temperature stop temperature , then return to the above step of gradually lowering the temperature, and repeat the above steps until the current outer layer temperature drops to the set temperature stop temperature .

[0064] By using a double-layer simulated annealing search algorithm to search for the operation row allocation scheme and traversal order of each agricultural machinery, the search process is simplified and the planning efficiency is improved.

[0065] In the above embodiment, the transfer cost calculated by the inner simulated annealing algorithm is determined based on the entry cost, line change cost and exit cost of the path corresponding to the traversal order of the operation line of each agricultural machine assigned. The entry cost of each agricultural machine to be operated starting from the starting point corresponding to the warehouse where it is located and entering the corresponding operation line and the exit cost of returning to the corresponding starting point after completing the operation can be determined based on the path length determined by the Dubins path algorithm. When the path length determined by the Dubins path algorithm is the shortest, the corresponding entry cost or exit cost is the smallest.

[0066] In two-dimensional Euclidean space, for two given points and their velocity vectors and minimum curvature radius , its reasonable shortest path has the following situations: ① The radius is An arc of radius , followed by a line segment, and then The arc is represented by CLC (circle-line-circle); ② The radius is The sequence of three arcs is represented by CCC (circle-circle-circle); ③ is a subpath of CLC or CCC type path. This is the famous Dubins path problem.

[0067] For the radius The arc has two rotation directions: clockwise and counterclockwise. The motion primitives right turn (R) and left turn (L) can be used to represent the specific rotation direction respectively. For line segments, the motion primitive straight (S) is used to represent their directions. Therefore, the CCC path can be specifically represented as a combination of two motion primitives: LRL and RLR; the CLC path can be specifically represented as a combination of four motion primitives: LSL, RSR, RSL and LSR. Based on the Dubins path algorithm, a local path planning method can be implemented. This method can be used to plan a path at a given starting position. , departure speed , end point position Terminal velocity and the minimum radius of curvature In this case, the paths corresponding to the six optimal path combinations are planned, and the optimal path that meets the constraints is selected, that is, the shortest path.

[0068] When the starting positions of each agricultural machine to be operated are known is the starting point of the corresponding warehouse, and the departure speed of each agricultural machine to be operated is the speed of the agricultural machinery, and the terminal position The position of the first entry of the assigned job row, the terminal speed is the speed of the agricultural machinery and the minimum curvature radius When is the turning radius of the agricultural machinery, the Dubins path algorithm can be used to calculate the entry cost of each agricultural machinery waiting to be operated from the starting point corresponding to the warehouse to enter the corresponding assigned operation row.

[0069] Similarly, the Dubins path algorithm can be used to calculate the departure cost of each agricultural machine to return to the corresponding starting point after completing the work.

[0070] The row change cost of each agricultural machine to be operated when operating in the corresponding assigned operation row can be determined based on different turning methods. Common turning methods include the following four types: bow-shaped, pear-shaped, fishtail-shaped and hook-shaped, and different turning methods have different requirements on the path.

[0071] Optionally, the target agricultural machinery to be operated is assigned multiple operating rows, and the row change cost corresponding to the target agricultural machinery to be operated is related to different turning methods, and the row change cost includes a combination of one or more of the distance cost, time cost and reserved turning distance generated by the corresponding turning method.

[0072] exist Figure 2 In, use Indicates the minimum turning radius of agricultural machinery. Indicates the number of operation rows between turns. For example, if the target agricultural machine is assigned to the 1st and 3rd rows, the interval between turns from the 1st row to the 3rd row is 1 row. Indicates the operating width of agricultural machinery. It indicates the angle between the driving direction of the agricultural machine when leaving or entering the current operation row and the farmland boundary in front. Indicates the linear operation speed of agricultural machinery. represents the turning speed of the agricultural machinery, θ represents the angle between the driving direction of the agricultural machinery when leaving or entering the current operation row and the direction of the current operation row. A, B, C, and D represent the waypoints passed in sequence when turning.

[0073] Bow turning method Figure 2 As shown in (a) in the figure, the distance cost (the length of the path required to turn) is , the time cost (the time required to turn) is , the reserved turning distance (the maximum length occupied by the agricultural machinery when turning) is .

[0074] Pear-shaped turn Figure 2 As shown in (b) in the figure, the distance cost is , the time cost is , the reserved turning distance is ,in .

[0075] Fishtail turn method Figure 2 As shown in (c) in the figure, the distance cost is , the time cost is , the reserved turning distance is , Indicates the reversing speed. Since the fishtail includes a reversing operation, its cost is generally less than the pear-shaped turn, but the performance requirements of the agricultural machinery are also higher.

[0076] Hook-type turning method Figure 2 As shown in (d) in the figure, the distance cost is ,in , the time cost is , the reserved turning distance is .

[0077] In order to facilitate the search for the optimal operation row traversal order, the row switching costs between different operation rows are combined into a row switching cost matrix (adjacency matrix) according to the desired turning method. For a single agricultural machine, the total number of operation rows assigned is N, then the corresponding adjacency matrix is ​​a matrix of size N*N, denoted as H, where the elements Indicates that from the job line To job row The cost of line breaking. Its turning radius Interval with job row The relationship is . When there is one line between Established, you can choose pear-shaped, fishtail-shaped and bow-shaped turning methods; when the interval is 2 rows or more, there is Set up, select bow turn method.

[0078] According to different turning methods, the minimum row-changing cost of each agricultural machine to be operated when it switches between different operation rows can be calculated, and the turning method corresponding to the minimum row-changing cost is determined as the optimal row-changing path of each agricultural machine to be operated.

[0079] Therefore, based on the entry cost of each agricultural machinery to be operated from the corresponding starting point of the warehouse where it is located to enter the corresponding assigned work row, the row change cost when passing through all the corresponding assigned work rows to perform the work, and the exit cost of returning to the corresponding starting point after completing the work, the optimal joint agricultural machinery operation path for each agricultural machinery to be operated can be determined.

[0080] In this application example, the calculation accuracy of path planning can be improved by introducing the row-break cost adjacency matrix and Dubins algorithm path of agricultural machinery to quantify the performance indicators corresponding to various turning methods of agricultural machinery and the paths in and out of the farmland.

[0081] For example Figure 3 Schematic diagram of the joint agricultural machinery operation path planning of the embodiment of the present application. In this example, there are 4 agricultural machinery 100 for joint operation. Each agricultural machinery 100 starts from the starting point corresponding to the warehouse where it is located, passes through all the corresponding assigned operation lines, and returns to the corresponding starting point. Figure 3 The triangle indicates entering the operation line, and the five-pointed star indicates leaving the operation line.

[0082] After planning the optimal joint agricultural machinery operation path for each agricultural machinery to be operated, it is necessary to consider that the agricultural machinery may conflict during the row change process of the working row. Therefore, it is necessary to set up agricultural machinery to avoid obstacles from each other to ensure the safety of the work.

[0083] In one embodiment, the method further includes: in the optimal combined agricultural machinery operation path, if there is a conflict in the line-changing paths corresponding to the working rows of two agricultural machines, an obstacle circle with the width of the agricultural machine as a diameter is set between the two starting points of the two agricultural machines in their respective line-changing paths; the target waypoints of the two agricultural machines on the obstacle circle are determined, and the vertical distance between the two target waypoints and the line connecting the two starting points is the largest; based on the starting points and waypoints corresponding to the two agricultural machines, the detour paths corresponding to the two agricultural machines on the line-changing paths are determined by the Dubins path algorithm.

[0084] like Figure 4As shown in the figure, when two agricultural machines change paths in different working rows, a path conflict occurs. For example, when the planned paths 10 and 20 have overlapping forward paths P1, if the forward path P1 is long enough, an obstacle avoidance path needs to be designed to allow the two agricultural machines to bypass each other. If the forward length P1 is insufficient, the two agricultural machines cannot bypass obstacles at the same time because the width of the farmland is limited. It is necessary to make the agricultural machine with a lower priority stop moving before leaving the current working row, while the agricultural machine with a higher priority continues to move along the original planned path until the agricultural machine with a higher priority bypasses it. The agricultural machine with a lower priority continues to move forward.

[0085] If the starting points of the two agricultural machines leaving the corresponding operation row are known and the conflict path length is sufficient, such as Figure 5 As shown, when the path 10 corresponding to one agricultural machine leaves the corresponding working row 12 to change lines, the starting point of the path P2 that ends the turn and starts to go straight is a1, and when the path 20 corresponding to another agricultural machine leaves the corresponding working row 22 to change lines, the starting point of the path P2 that ends the turn and starts to go straight is a2.

[0086] If detour is to be achieved, an obstacle circle Q with the width of the agricultural machine as the diameter needs to be set between the two starting points a1 and a2, and the upper and lower points on the obstacle circle Q with the largest vertical distance L2 from the line L1 connecting the two starting points a1 and a2 are set as the waypoints b1 and b2. The line connecting the starting points a1 and a2 should pass through the center of the obstacle circle Q. In this way, the two points on the obstacle circle Q farthest from the line L1 connecting the starting points a1 and a2 are the top and bottom points on the obstacle circle Q. After determining the starting points a1 and a2 and the waypoints b1 and b2 corresponding to the two agricultural machines, the detour paths corresponding to the two agricultural machines on the line change path P1 are determined by the Dubins path algorithm. For one agricultural machine, the starting point a1 corresponds to the starting position of the Dubins path algorithm, and the waypoint b1 corresponds to the end position of the Dubins path algorithm. For another agricultural machine, the starting point a2 corresponds to the starting position of the Dubins path algorithm, and the waypoint b2 corresponds to the end position of the Dubins path algorithm. Therefore, the Dubins path can be used to determine the optimal detour path that meets the constraints when there is a path conflict between two agricultural machines.

[0087] like Figure 5 As shown in the figure, when a conflicting path occurs, two agricultural machines drive out from different working rows and drive into other working rows. When more agricultural machines work together, the lengths of the forward paths P1 of different conflicts between two agricultural machines may be different. Therefore, it is necessary to adjust the position of the obstacle circle Q and the starting point of the detour accordingly to determine whether mutual detours can be achieved and find the optimal detour plan.

[0088] After obtaining the length of the conflicting forward path P1, it is only necessary to determine the starting points a1 and a2 of the two detours, and then the obstacle circle Q can be placed at the midpoint between the starting points a1 and a2, and then the Dubins detour paths of the two agricultural machines and the paths for entering the new working row can be obtained.

[0089] The determination of the starting points a1 and a2 can be based on a search scheme based on a genetic algorithm. To facilitate subsequent writing, the process of determining the detour path based on the starting points a1 and a2 is defined as , where x1 and x2 correspond to two starting points a1 and a2 respectively.

[0090] Individuals are represented as vectors ,in ( is the length of the forward path P1). The population size is N1, the evolutionary generation is G, and the mutation rate is μ. The genetic algorithm steps are as follows.

[0091] (a) Initialize the population:

[0092] in and yes Random numbers on .

[0093] (b) For each generation , perform the following steps: b1. Calculate fitness: for each individual , calculate its fitness:

[0094] b2. Use roulette wheel selection method. Individual The probability of being selected is:

[0095] b3. Crossover operation: for the two selected parent individuals and , generating offspring , ,in yes Random numbers on .

[0096] b4. Mutation operation: for each gene , with probability To mutate:

[0097] in is a small variance value.

[0098] if ,but ;if ,but .

[0099] b5. Elite retention: retain the individuals with the highest fitness in the previous generation

[0100] b6. Formation of a new generation of population:

[0101] Termination condition: When When , the algorithm terminates.

[0102] (d) Output result: optimal solution .

[0103] Among them, the superscript Indicates Subscript Indicates Individuals, represents the elite individuals of the g-th generation, and They represent the independent variables that make the objective function take the maximum and minimum values ​​respectively. According to the optimal solution output, the corresponding , that is, the starting points a1 and a2 of the two agricultural machines are determined. Therefore, the obstacle circle Q can be placed at the midpoint between the starting points a1 and a2 in combination with the length of the conflicting forward path P1, and then the optimal Dubins detour path of the two agricultural machines and the path to enter the new working row can be obtained.

[0104] If a detour plan that meets the conditions cannot be found, the above-mentioned priority strategy must be adopted to make the two agricultural machines move alternately in order to avoid path conflicts and improve the safety of agricultural machinery operations.

[0105] Figure 6 It is a schematic diagram of the overall process of the combined agricultural machinery operation path planning method of an embodiment of the present application. In this example, a two-layer simulated annealing search algorithm and a Dubins path algorithm are combined to comprehensively consider the agricultural machinery allocation plan, the operation line traversal order, and the agricultural machinery conflict path obstacle avoidance to achieve the optimal combined agricultural machinery operation path.

[0106] like Figure 6 As shown, the following steps are included: Step 202, based on the agricultural machine parameters and the farm (i.e., farmland) parameters, and the turning mode of the agricultural machine changing rows, determine the turning cost matrix, the operation row parameters, and the number of agricultural machines; Step 204, based on the parameters determined in step 202, combined with a specific search method, such as the outer layer simulated annealing search algorithm of the double-layer simulated annealing search algorithm, searching for an allocation scheme for the sub-operation rows corresponding to each agricultural machine of the combined agricultural machine; Step 206, based on the allocation scheme determined in step 204 and the inner layer simulated annealing search algorithm of the double layer simulated annealing search algorithm, searching for the traversal order of the allocation operation rows with the minimum turning cost for a single agricultural machine, wherein the optimal results searched by the outer layer simulated annealing search algorithm and the outer layer simulated annealing search algorithm optimize each other; Step 208, combining the agricultural machinery path conflict information and the Dubins path algorithm to determine mutually bypassing operation planning obstacle avoidance paths; Step 210, calculating the operation path of a single agricultural machine according to the traversal order outputted from step 206 and the obstacle avoidance path outputted from step 208, and obtaining the final path of each combined agricultural machine.

[0107] In an embodiment of the present application, the target farmland is divided into multiple work rows based on agricultural machinery parameters and farmland parameters; the multiple work rows are allocated to multiple agricultural machinery to be operated in joint operation in the target farmland; under preset constraints, the optimal joint agricultural machinery operation path is determined based on the transfer cost of each agricultural machinery to be operated, the transfer cost includes the entry cost of each agricultural machinery to be operated starting from the starting point corresponding to the warehouse where it is located and entering the corresponding assigned work row, the row change cost when passing through all the corresponding assigned work rows to perform the operation, and the exit cost of returning to the corresponding starting point after completing the operation. The optimal joint agricultural machinery operation path corresponds to the path of the multiple agricultural machinery to be operated starting from the starting point corresponding to the warehouse where it is located, passing through all the corresponding assigned work rows and returning to the corresponding starting point. In this way, the operation paths of the agricultural machinery in the farmland for each joint operation, the transfer paths between the work rows, and the specific transfer paths of the agricultural machinery entering or leaving the farmland can be comprehensively considered to plan the optimal joint agricultural machinery operation path, thereby improving the accuracy of the planned path and improving the environmental adaptability and safety of autonomous operation of agricultural machinery.

[0108] Alternatively, if Figure 7 As shown, an embodiment of the present application also provides a combined agricultural machinery operation path planning device 2000, including a processor 2400 and a memory 2200, and the memory 2200 stores programs or instructions that can be run on the processor 2400. When the program or instructions are executed by the processor 2400, the various steps of the above-mentioned combined agricultural machinery operation path planning method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, they are not repeated here.

[0109] The embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of any of the above-mentioned combined agricultural machinery operation path planning method embodiments is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. Among them, the readable storage medium includes a computer-readable storage medium, such as a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0110] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0111] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0112] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A method for planning a path for a combined agricultural machinery operation, characterized in that: include: Based on the agricultural machinery parameters and the farmland parameters, the target farmland is divided into a plurality of operation rows; Allocating a plurality of operation rows to a plurality of agricultural machines to be operated in a joint operation on the target farmland; Under preset constraints, the optimal combined agricultural machinery operation path is determined based on the transfer cost of each agricultural machinery to be operated, the transfer cost includes the entry cost of each agricultural machinery to be operated starting from the starting point corresponding to the warehouse where it is located and entering the corresponding assigned operation row, the row change cost when passing through all the corresponding assigned operation rows to perform the operation, and the exit cost of returning to the corresponding starting point after completing the operation. The optimal combined agricultural machinery operation path corresponds to the path of the multiple agricultural machinery to be operated starting from the starting point corresponding to the warehouse where they are located, passing through all the corresponding assigned operation rows and returning to the corresponding starting point.

2. The method according to claim 1, characterized in that The target farmland is divided into a plurality of operation rows based on the agricultural machinery parameters and the farmland parameters, including: Based on the farmland parameters of the target farmland, the longest boundary among the boundaries of the target farmland is selected as a baseline; Parallel to the baseline, the agricultural machinery is translated at equal intervals according to the agricultural machinery operating width in the agricultural machinery parameters to generate multiple operating rows until the entire target farmland is covered.

3. The method according to claim 1, characterized in that The method of determining the optimal joint agricultural machinery operation path based on the transfer cost of each agricultural machinery to be operated under the preset constraint conditions includes: The starting point of a single agricultural machine to be operated among the agricultural machines to be operated and a plurality of operation rows assigned to the single operating agricultural machine are used as nodes; The transfer costs between the nodes are stored in an adjacency matrix, wherein the transfer costs correspond to the entry cost and the exit cost between the starting node and the corresponding working row node, and the line change cost between the working row nodes; Determine the node traversal order with the minimum transfer cost by using a preset global search algorithm; Determine the optimal operation path of a single agricultural machine to be operated based on the node traversal order with the minimum transfer cost; The optimal combined agricultural machinery operation path is determined based on the optimal operation paths of each agricultural machine to be operated.

4. The method according to claim 3, characterized in that The allocating the plurality of operation rows to the plurality of agricultural machines to be operated in the joint operation on the target farmland comprises: allocating the plurality of operation rows to the plurality of agricultural machines to be operated in the joint operation on the target farmland by using an outer layer simulated annealing algorithm of a double layer simulated annealing algorithm; The method of determining the node traversal order when the transfer cost is the smallest by using a preset global search algorithm includes: determining the node traversal order when the transfer cost of each agricultural machine to be operated is the smallest under the assigned operation row by using the inner layer simulated annealing algorithm of the double layer simulated annealing algorithm.

5. The method according to claim 4, characterized in that The outer layer simulated annealing algorithm of the double layer simulated annealing algorithm is used to allocate multiple operation rows to multiple agricultural machines to be operated in the target farmland, including: The number and positions of the multiple work rows divided into the target farmland and the number of the multiple agricultural machines to be operated are provided as input to the outer layer simulated annealing algorithm to obtain an outer layer solution output by the outer layer simulated annealing algorithm, wherein the outer layer solution includes the number and position of the work rows allocated to each agricultural machine to be operated.

6. The method according to claim 5, characterized in that The inner layer simulated annealing algorithm of the double layer simulated annealing algorithm is used to determine the node traversal order of each agricultural machine to be operated when the transfer cost is the smallest under the assigned operation row, including: Passing the outer layer solution to the inner layer simulated annealing algorithm, wherein the inner layer simulated annealing algorithm is used to calculate inner layer solutions and corresponding transfer costs at different inner layer temperatures based on the outer layer solution; Lowering the current inner layer temperature to the target inner layer temperature, and adjusting the traversal order of the operation rows assigned to each agricultural machine to be operated in the inner layer solution, so as to obtain an updated inner layer solution and a corresponding transfer cost, wherein the inner layer solution includes the traversal order of the operation rows assigned to each agricultural machine to be operated corresponding to the outer layer solution, and the target inner layer temperature includes one of each inner layer temperature gradually decreasing from the inner layer initial temperature preset by the inner layer simulated annealing algorithm and the inner layer termination temperature preset by the inner layer simulated annealing algorithm; Based on the difference between the corresponding transfer costs before and after the inner solution is updated, the historical optimal inner solution is updated, and the transfer cost corresponding to the optimal inner solution is the smallest; If the target inner layer temperature reaches the inner layer termination temperature, output the historical optimal inner layer solution, otherwise return to the step of lowering the current inner layer temperature to the target inner layer temperature until the inner layer termination temperature is reached; The optimal combined agricultural machinery operation path is determined based on the traversal order of the nodes of the operation row corresponding to the outputted historical optimal inner layer solution and the number and position of the operation rows allocated corresponding to the outer layer solution.

7. The method according to claim 6, characterized in that Before determining the optimal combined agricultural machinery operation path based on the traversal order of the nodes of the operation row corresponding to the outputted historical optimal inner layer solution and the number and position of the operation row corresponding to the outer layer solution, the method further includes: Determining the transfer cost corresponding to the outer solution of the outer simulated annealing algorithm based on the transfer cost corresponding to the outputted historical optimal inner solution and the penalty item corresponding to the outer solution; Lowering the current outer layer temperature to a target outer layer temperature, and adjusting the number and position of the operation rows allocated to each agricultural machine to be operated in the outer layer solution to obtain an updated outer layer solution, wherein the target outer layer temperature includes one of the outer layer temperatures gradually decreasing from the outer layer initial temperature preset by the outer layer simulated annealing algorithm and the outer layer termination temperature preset by the outer layer simulated annealing algorithm; Based on the updated outer solution, return to the step of passing the outer solution to the inner simulated annealing algorithm until the inner simulated annealing algorithm outputs an updated historical optimal inner solution; Determining a transfer cost corresponding to the updated outer solution based on the transfer cost corresponding to the updated historical optimal inner solution and the penalty item corresponding to the outer solution; Based on the difference in the transfer costs before and after the outer solution is updated, the historical optimal outer solution is updated, and the transfer cost corresponding to the optimal outer solution is the smallest; If the target outer layer temperature reaches the outer layer termination temperature, output the historical optimal outer layer solution, otherwise return to the step of lowering the current outer layer temperature to the target outer layer temperature until the outer layer termination temperature is reached; The method of determining the optimal combined agricultural machinery operation path based on the traversal order of the nodes of the operation row corresponding to the outputted historical optimal inner layer solution and the number and position of the operation rows corresponding to the outer layer solution includes: The optimal combined agricultural machinery operation path is determined based on the traversal order of the nodes of the operation row corresponding to the output historical optimal inner solution and the number and position of the operation rows allocated corresponding to the output historical optimal outer solution.

8. The method according to claim 1, characterized in that: Also includes: In the optimal combined agricultural machinery operation path, if there is a conflict in the line-changing paths of the corresponding working rows of two agricultural machines, an obstacle circle with a diameter of the agricultural machine width is set between two starting points of the two agricultural machines in their respective line-changing paths; Determine the target waypoints of the two agricultural machines on the obstacle circle respectively, and the vertical distances between the two target waypoints and the line connecting the two starting points are the largest; Based on the starting points and waypoints corresponding to the two agricultural machines respectively, the detour paths corresponding to the two agricultural machines on the line-changing path are determined by using the Dubins path algorithm.

9. The method according to claim 1, characterized in that: The target agricultural machinery to be operated is assigned multiple operating rows, and the row change cost corresponding to the target agricultural machinery to be operated is related to different turning methods. The row change cost includes a combination of one or more of the distance cost, time cost and reserved turning distance generated by the corresponding turning method.

10. A combined agricultural machinery operation path planning device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the method according to any one of claims 1 to 9 are implemented.

Images