A Method for Multi-Agricultural-Machine Cooperative Dynamic Task Allocation of the Same Type

Abstract

A method for multi-machine collaborative dynamic task allocation of the same type of agricultural machinery. This method for multi-machine collaborative dynamic task allocation of the same type of agricultural machinery performs dynamic task allocation based on an improved contract net algorithm, and includes the following steps: constructing a multi-machine collaborative cost function based on the performance of agricultural machinery and task parameters according to the multi-machine collaborative operation scenario; constructing a bidding cost function for agricultural machinery and a cost function for the machine group after tendering; constructing a multi-machine collaborative dynamic task allocation system based on a remote cloud service platform and a wireless ad hoc network; and when there is a new task to be allocated, the system allocates the new task through the improved contract net algorithm to finally obtain an optimal task allocation result. The present invention solves the problem of how to reasonably dynamically allocate tasks and the task execution order in the process of multi-vehicle operation of the same type of agricultural machinery in an agricultural machinery cooperative or a farm when a new task is added or a piece of agricultural machinery breaks down.

Description

Technical Field

[0001] The invention relates to a task allocation technology for cooperative operation of multiple agricultural machines, in particular to a method for dynamic cooperative task allocation of multiple agricultural machines of the same type based on an improved contract network algorithm. Background Art

[0002] With the development and promotion of agricultural machinery cooperatives and farm operation models in my country, land and agricultural machinery are showing a trend of concentration. The most common operation scenario is to assign tasks and sequences to designated agricultural machinery before operation, and each agricultural machinery returns to the garage after completing its respective operation tasks. In the process of cooperative operation of multiple agricultural machinery, new tasks are often added or agricultural machinery fails. Real-time and effective dynamic allocation of tasks to be assigned can effectively reduce the operation cost and shorten the operation time.

[0003] Common methods for solving dynamic task allocation are: 1. Use heuristic algorithms to reallocate unfinished tasks through a remote service platform; 2. Use contract network algorithms to reallocate unfinished tasks through the bidding process between agricultural machinery. The first method belongs to centralized task allocation, which concentrates a large amount of calculations on the server, which puts a lot of pressure on the server and has a good allocation effect; the second method belongs to distributed task allocation, which uses the computing power of each agricultural machinery's onboard computer and the mutual communication between agricultural machinery to complete task allocation, which takes a short time and does not put pressure on the server, but the allocation effect is poor. In order to reduce the amount of server calculations and reduce the probability of server failure, this field urgently needs a method that can fully utilize the computing power of onboard computers to achieve task allocation. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method for dynamic task allocation of multiple agricultural machines of the same type based on an improved contract network algorithm.

[0005] In order to achieve the above object, the present invention provides a method for dynamic task allocation of multiple agricultural machines of the same type, wherein the method for dynamic task allocation of multiple agricultural machines of the same type performs dynamic task allocation based on an improved contract network algorithm, and comprises the following steps:

[0006] S100, according to the multi-machine collaborative operation scenario, construct a multi-machine collaborative cost function based on agricultural machinery performance and task parameters;

[0007] S200, constructing a bidding cost function for agricultural machinery and a cost function for a group of agricultural machinery after the bidding is completed;

[0008] S300, build a multi-machine collaborative dynamic task allocation system based on remote cloud service platform and wireless ad hoc network;

[0009] S400. When a new task needs to be assigned, the system assigns the new task by improving the contract network algorithm, and finally obtains the optimal task assignment result.

[0010] In the above-mentioned method for dynamic task allocation of multiple agricultural machines of the same type, step S100 further comprises:

[0011] S101. Define symbols. Assume that m agricultural machines are operating, and use the set {a 1 , …, a m}; the number of job tasks is n, represented by the set {T 1 ,…,T n} represents; the performance parameter of the i-th agricultural machine is represented by a i = {v wi , d i , w i , v i , t ti} T , (i = 1, 2, ..., m), where v wi represents the average operating speed of the i-th agricultural machine (km / h), d i represents the operating width of the i-th agricultural machine (m), w i represents the average operating capacity of the i-th agricultural machine (m 2 / h), v i represents the average speed of the i-th agricultural machine in non-operating state (km / h), t ti represents the average time (h) of each U-turn of the i-th agricultural machine operation; the parameter of the j-th task is expressed as: T j ={x 1j ,y 1j , x 2j ,y 2j , x 3j ,y 3j , x 4j ,y 4j , d Tj , l Tj , S i} T , (j = 1, 2, ..., n, where (x1j, y1j), (x2j, y2j), (x3j, y3j) and (x4j, y4j) represent the tasks T j Coordinates of the four vertices of the plot, d Tj Represents task T j Width of vertical working path, l Tj Represents task T j The length of the parallel operation path, S j Represents task T j area;

[0012] S102. Calculate the non-operating distance of each agricultural machine using the following formula:

[0013]

[0014] Among them, s(a i , T j ) indicates agricultural machinery a i To its first task T j distance; s(a i , T j T k ) indicates agricultural machinery a i From the jth task T j To the kth task T k distance; s(a i , T l ) indicates agricultural machinery a i From the last task T l The distance back to the garage; j, k, l ∈ {1, ..., n};

[0015]

[0016]

[0017]

[0018] S103, calculating the total time for each agricultural machine to complete the task, where the total time includes the time the agricultural machine is on the road, the time the agricultural machine is operating, and the time the agricultural machine is turning around in the field;

[0019]

[0020] in, k ij is the number of rows operated by the i-th agricultural machine in the j-th task plot, In the formula is the symbol for rounding up, and its value is the smallest integer not less than the value within the symbol;

[0021] S104. Calculate the distance between tasks, take the garage as the starting point, and the n tasks as the 2nd to n+1th points in sequence, and establish the shortest distance matrix D between any two points.

[0022] In the above-mentioned method for dynamic task allocation of multiple agricultural machines of the same type, the shortest distance matrix D is:

[0023] where d ij It represents the shortest drivable distance between the i-1th task point and the j-1th task point, (i, j = {2, ..., n+1}, i ≠ j).

[0024] In the above-mentioned method for dynamic task allocation of multiple agricultural machines of the same type, if two task sites are adjacent, it is considered that the shortest drivable distance between the two task points is 0; if the two task sites are not adjacent, the shortest drivable distance between the two task points is equal to the distance on the road between the two tasks.

[0025] The above-mentioned method for dynamic task allocation of multiple agricultural machines of the same type, wherein in step 102, s(a i , T j ) = d 1，j+1 ,s(a i , T l ) = d 1，l+1 ;

[0026] Among them, the ways for agricultural machinery to enter the task plot include entering from the road and entering from the field end connection. When the agricultural machinery enters the task plot from the road, x=0, and when the agricultural machinery enters the task plot from the field end connection, x=1; when the agricultural machinery returns to the roadside after completing the task, y=0, and when the agricultural machinery returns to the field end connection after completing the task, y=1;

[0027] The agricultural machine enters the first task plot from the road. The position of the i-th agricultural machine after completing the operation on the j-th task plot is: ij =(k ij +x ij )%2, where x ij is the way that the i-th agricultural machine enters the j-th task plot, and % is the remainder;

[0028] When j+1，k+1 ≠0, tasks i and j are not connected, and agricultural machinery a i The distance from task j to task k is: s(a i , T j T k ) = d j+1，k+1 +y ij l Tj , x ik =0; when d j+1，k+1 = 0, tasks i and j are connected to each other. i The distance from task j to task k is:

[0029] s(a i , T j T k ) = d′ j+1，k+1 +|y ij -1|l Tj , x ik =1.

[0030] In the above-mentioned method for dynamic task allocation of multiple agricultural machines of the same type, in step 105, the operation time of the agricultural machine with the longest operation time in the multiple machine collaboration is used as the cost of the multiple machine collaboration:

[0031] f=max(t i )

[0032] The multi-machine collaboration objective function is to minimize the cost, that is:

[0033] min(f)=min(max(t i ))

[0034] Among them, f represents the multi-machine coordination cost.

[0035] In the above-mentioned method for dynamic task allocation of multiple agricultural machines of the same type, step S200 further comprises:

[0036] S201, build agricultural machinery a i For task T j The cost function of bidding:

[0037]

[0038] Add task T for the i-th agricultural machine j The total time required for the operation after max The maximum working time of the entire fleet before the bidding begins;

[0039] S202, construct the i-th agricultural machinery bidding task T j The cost of the entire cluster is f′=f+Δf i j , where f′ is the total cost of the fleet after bidding is completed; f is the cost of multi-machine coordination before bidding.

[0040] In the above-mentioned method for dynamic task allocation of multiple agricultural machines of the same type, step S400 further comprises:

[0041] S401, determine the bidder, the platform selects the normal operation agricultural machinery as the bidder, and selects the bidder to minimize the communication distance during the bidding process. Where (x i ,y i ) is the current position of the i-th agricultural machine;

[0042] S402, the tenderer sets the tender threshold. j Before bidding, first calculate the minimum cost Δf for performing the task j As a dynamic threshold, in Execute additional tasks for the tenderer T jThe price of the bidder a i Receive bidding information and calculate the minimum cost Δf to perform the task i J , if Δf i J <Δf j Send a bid if Δf i J ≥Δf j , no bidding information will be sent;

[0043] S403, bidding process based on threshold contract network algorithm;

[0044] S404, bidding the task with the smallest area for the winning bidder;

[0045] S405: Execute task exchange between agricultural machines. Suppose agricultural machine i executes task T j The journey cost Among them, s i-j Remove task T for agricultural machinery i j The journey after

[0046] S406: Obtain the final dynamic task allocation result.

[0047] In the above-mentioned method for dynamic task allocation for multiple agricultural machines of the same type, the step S405 of performing task exchange between agricultural machines further includes:

[0048] S4051. The agricultural machine i with the highest task cost calculates the maximum journey cost. and the corresponding task number j;

[0049] S4052, agricultural machinery i acts as a bidder to exchange bids for task j;

[0050] S4053, other agricultural machinery that works normally is used as a bidder. The bidder uses the "deletion-insertion" method to delete its unexecuted tasks in turn, and uses the insertion method to calculate its minimum cost after replacement;

[0051] S4054: If the cost after replacement is less than the cost before replacement, the task is used as bidding information;

[0052] S4055. The bidder uses the "delete-insert" method to calculate the cost of deleting task j and adding each bidding task, and takes the minimum cost f i k and the corresponding task k;

[0053] S4056, if f i k <f i , then tasks j and k are swapped.

[0054] The above-mentioned method for dynamic task allocation for multiple agricultural machines of the same type, wherein the multi-machine collaborative dynamic task allocation system includes agricultural machinery, a server and a client, the agricultural machinery is equipped with a vehicle-mounted computer, a Beidou positioning module and a wireless ad hoc network module for realizing self-positioning and communicating with other agricultural machinery; the server includes a computing module and a storage module, and the storage module is used to store plot information and agricultural machinery information; the client is used to select and issue tasks to a designated operating machine group.

[0055] The technical effects of the present invention are:

[0056] The present invention solves the problem of how to reasonably and dynamically allocate tasks and the order of task execution when a new task is added or an agricultural machine fails during the operation of multiple agricultural machines of the same type in an agricultural machinery cooperative or a farm.

[0057] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments, but is not intended to limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 A flow chart of dynamic task allocation according to an embodiment of the present invention;

[0059] Figure 2 FIG. 4 is a flowchart of task exchange according to an embodiment of the present invention. DETAILED DESCRIPTION

[0060] The structural principle and working principle of the present invention are described in detail below in conjunction with the accompanying drawings:

[0061] See also Figure 1 , Figure 1 The following is a flow chart of dynamic task allocation according to an embodiment of the present invention. The method for dynamic task allocation of multiple agricultural machines of the same type according to the present invention performs dynamic task allocation based on an improved contract network algorithm, and includes the following steps:

[0062] Step S100: construct a multi-machine collaborative cost function based on the multi-machine collaborative operation scenario and the performance and task parameters of the agricultural machinery;

[0063] Step S200, constructing a bidding cost function for agricultural machinery and a cost function for the group of agricultural machinery after the bidding is completed;

[0064] Step S300, constructing a multi-machine collaborative dynamic task allocation system based on a remote cloud service platform and a wireless ad hoc network; the multi-machine collaborative dynamic task allocation system may include an agricultural machine, a server and a client, the agricultural machine may be equipped with a vehicle-mounted computer, a Beidou positioning module and a wireless ad hoc network module for realizing self-positioning and communicating with other agricultural machines; the server includes a computing module and a storage module, the storage module is used to store plot information and agricultural machine information, and the computing module is used to realize computing functions; the client is used to select and issue tasks to a designated operation machine group;

[0065] Step S400: When a new task needs to be assigned, the multi-machine collaborative dynamic task allocation system allocates the new task by improving the contract network algorithm and obtains the optimal task allocation result.

[0066] Wherein, step S100 further includes:

[0067] Step S101, define symbols, assuming that m agricultural machines are operating, and use the set {a 1 , …, a m}; the number of job tasks is n, represented by the set {T 1 ,…,T n} represents; the performance parameter of the i-th agricultural machine is represented by a i = {v wi , d i , w i , v i , t ti} T , (i = 1, 2, ..., m), where v wi represents the average operating speed of the i-th agricultural machine (km / h), d i represents the operating width of the i-th agricultural machine (m), w i represents the average operating capacity of the i-th agricultural machine (m 2 / h), v i represents the average speed of the i-th agricultural machine in non-operating state (km / h), t ti represents the average time (h) of each U-turn of the i-th agricultural machine operation; the parameter of the j-th task is expressed as: T j ={x 1j ,y 1j , x 2j ,y 2j , x 3j ,y 3j , x 4j ,y 4j , d Tj , l Tj , S i} T , (j=1, 2, ..., n), where (x1j ,y 1j )、(x 2j ,y 2j )、(x 3j ,y 3j ) and (x 4j ,y 4j ) represent tasks T j Coordinates of the four vertices of the plot, d Tj Represents task T j Width of vertical working path, l Tj Represents task T j The length of the parallel operation path, S j Represents task T j area;

[0068] Step S102: Calculate the non-operating distance of each agricultural machine using the following formula:

[0069]

[0070] Among them, s(a i , T j ) indicates agricultural machinery a i To its first task T j distance; s(a i , T j T k ) indicates agricultural machinery a i From the jth task T j To the kth task T k distance; s(a i , T l ) indicates agricultural machinery a i From the last task T l The distance back to the garage; j, k, l ∈ {1, ..., n};

[0071]

[0072]

[0073]

[0074] Step S103, calculating the total time for each agricultural machine to complete the task, the total time includes the time the agricultural machine is on the road, the time the agricultural machine is operating, and the time the agricultural machine is turning around in the field;

[0075]

[0076] in, k ij is the number of rows operated by the i-th agricultural machine in the j-th task plot, In the formula is the symbol for rounding up, and its value is the smallest integer not less than the value within the symbol;

[0077] Step S104, calculate the distance between tasks, take the garage as the starting point, that is, the first point, and the n tasks as the second to n+1 points in sequence, and establish the shortest distance matrix D between any two points.

[0078] Wherein, the shortest distance matrix D is:

[0079] where d ij It represents the shortest drivable distance between the i-1th task point and the j-1th task point, (i, j = {2, ..., n+1}, i ≠ j).

[0080] If two task locations are adjacent, the shortest drivable distance between the two task points is considered to be 0; if the two task locations are not adjacent, the shortest drivable distance between the two task points is equal to the distance on the road between the two tasks.

[0081] In step 102 of this embodiment, s(a i , T j ) = d 1，j+1 ,s(a i , T l ) = d 1，l+1 ;

[0082] Among them, the ways for agricultural machinery to enter the task plot include entering from the road and entering from the field end connection. When the agricultural machinery enters the task plot from the road, x=0, and when the agricultural machinery enters the task plot from the field end connection, x=1; when the agricultural machinery returns to the roadside after completing the task, y=0, and when the agricultural machinery returns to the field end connection after completing the task, y=1;

[0083] The agricultural machine enters the first task plot from the road. The position of the i-th agricultural machine after completing the operation on the j-th task plot is: ij =(k ij +x ij )%2, where x ij is the way that the i-th agricultural machine enters the j-th task plot, and % is the remainder;

[0084] When j+1，k+1 ≠0, tasks i and j are not connected, and agricultural machinery a i The distance from task j to task k is: s(a i , T j T k ) = d j+1，k+1 +y ij l Tj , x ik =0; when dj+1，k+1 = 0, tasks i and j are connected to each other. i The distance from task j to task k is:

[0085] s(a i , T j T k ) = d′ j+1，k+1 +|y ij -1|l Tj , x ik =1.

[0086] In step 105, a multi-machine collaborative cost function is constructed with the longest agricultural machine operation time as the cost: f = max(t i ).

[0087] The multi-machine collaboration objective function is to minimize the cost, that is:

[0088] min(f)=min(max(t i ))

[0089] Among them, f represents the multi-machine coordination cost.

[0090] In this embodiment, step S200 further includes:

[0091] Step S201: construct agricultural machinery a i For task T j The cost function of bidding:

[0092]

[0093] Add task T for the i-th agricultural machine j The total time required for the operation after max The maximum working time of the entire fleet before the bidding begins;

[0094] Step S202: Construct the i-th agricultural machinery winning bid task T j The cost of the entire cluster is f′=f+Δf i j , where f′ is the total cost of the fleet after bidding is completed; f is the cost of multi-machine coordination before bidding.

[0095] Step S400 further includes:

[0096] Step S401: Determine the bidder. The platform selects a normal operating agricultural machine as the bidder. To minimize the communication distance during the bidding process, the bidder is selected. Where (x i ,y i ) is the current position of the i-th agricultural machine;

[0097] Step S402: The tenderer sets the tender threshold. j Before bidding, first calculate the minimum cost Δf for performing the task j As a dynamic threshold, in Execute additional tasks for the tenderer T j The price of the bidder a i Receive bidding information and calculate the minimum cost Δf to perform the task i J , if Δf i J <Δf j Send a bid if Δf i J ≥Δf j , no bidding information will be sent;

[0098] Step S403: Conduct bidding based on the threshold contract network algorithm;

[0099] Step S404, bidding the task with the smallest area among the winning bidders;

[0100] Step S405: Execute task exchange between agricultural machines. Suppose agricultural machine i executes task T j The journey cost Among them, s i-j Remove task T for agricultural machinery i j The journey after

[0101] Step S406: Obtain the final dynamic task allocation result.

[0102] See also Figure 2 , Figure 2 The task exchange flow chart of an embodiment of the present invention is shown in FIG. 1 . The step S405 of the present embodiment further includes:

[0103] Step S4051: The agricultural machine i with the highest task cost calculates the maximum distance cost. and the corresponding task number j;

[0104] Step S4052: Agricultural machine i acts as a bidder to exchange bids for task j;

[0105] Step S4053: other agricultural machines that work normally are used as bidders. The bidders use the "delete-insert" method to delete their unexecuted tasks in turn, and use the insertion method to calculate their minimum cost after replacement;

[0106] Step S4054: If the cost after replacement is less than the cost before replacement, the task is used as bidding information;

[0107] Step S4055: The bidder uses the "delete-insert" method to calculate the cost of deleting task j and adding each bidding task, and takes the minimum cost f i k and the corresponding task k;

[0108] Step S4056: If f i k <f i , then tasks j and k are swapped.

[0109] The present invention solves the problem of how to reasonably and dynamically allocate tasks and the order of task execution when a new task is added or an agricultural machine fails during the operation of multiple agricultural machines of the same type in an agricultural machinery cooperative or a farm.

[0110] Of course, the present invention may have many other embodiments. Without departing from the spirit and essence of the present invention, those skilled in the art may make various corresponding changes and modifications based on the present invention, but these corresponding changes and modifications should all fall within the scope of protection of the claims attached to the present invention.

Claims

1. A method for multi - machine collaborative dynamic task allocation of the same type of agricultural machinery, characterized in that, this method for multi - machine collaborative dynamic task allocation of the same type of agricultural machinery performs dynamic task allocation based on an improved contract net algorithm, including the following steps: S100. According to the multi - machine collaborative operation scenario, construct a multi - machine collaborative cost function based on the performance of agricultural machinery and task parameters; S200. Construct an agricultural machinery bidding cost function and a cost function of the machine group after bidding; S300. Construct a multi - machine collaborative dynamic task allocation system based on a remote cloud service platform and a wireless ad - hoc network; and S400. When a new task needs to be allocated, the system allocates the new task through the improved contract net algorithm and obtains the task allocation result; Among them, step S100 further includes: S101. Define symbols. Assume that there are m agricultural machines for operation, which are represented by the set {a 1 , …, a m}; the number of operation tasks is n, which is represented by the set {T 1 , …, T n}; the performance parameters of the i-th agricultural machine are expressed as a i = {v wi , d i , w i , v i , t ti} T , (i = 1, 2, …, m), where v wi represents the average operation speed of the i-th agricultural machine, with the unit of km / h, d i represents the operation width of the i-th agricultural machine, with the unit of m, w i represents the average operation ability of the i-th agricultural machine, with the unit of m 2 / h, v i represents the average non-operation driving speed of the i-th agricultural machine, with the unit of km / h, t ti represents the average turning time of the i-th agricultural machine during operation, with the unit of h; the parameters of the j-th task are expressed as: T j = {x 1j , y 1j , x 2j , y 2j , x 3j , y 3j , x 4j , y 4j , d Tj , l Tj , S j} T , (j = 1, 2, …, n), where (x 1j , y 1j ), (x 2j , y 2j ), (x 3j , y 3j ) and (x 4j , y 4j ) respectively represent the coordinates of the four vertices of the plot of task T j , d Tj represents the width of the vertical operation path of task T j , l Tj represents the length of the parallel operation path of task T j , S j represents the area of task T j ; S102. Calculate the non - operating distance of each agricultural machinery using the following formula: Among them, s(a i , T j ) represents the distance of agricultural machine a i to its first task T j ; s(a i , T j T k ) represents the distance of agricultural machine a i from the j-th task T j to the k-th task T k ; s(a i , T l ) represents the distance of agricultural machine a i from the last task T l back to the garage; j, k, l ∈ {1,..., n}; S103. Calculate the total time for each agricultural machinery to complete the task, and the total time includes the time on the road, the time of agricultural machinery operation, and the time of agricultural machinery turning around in the field; Among them, k ij is the number of operating rows of the i-th agricultural machine in the j-th task plot, In the formula is the ceiling symbol, and its value is the smallest integer not less than the value inside the symbol; S104. Calculate the distance between tasks. Taking the garage as the starting point, and n tasks as the 2nd to n + 1th points in turn, establish the shortest distance matrix D that can be traveled between any two points; The shortest distance matrix D is: where d ij represents the shortest distance that can be traveled between the (i-1)-th task point and the (j-1)-th task point, (i, j = {2, …, n + 1}, i ≠ j); If the fields of two tasks are adjacent, it is considered that the shortest distance that can be traveled between the two task points is 0; if the fields of two tasks are not adjacent, then the shortest distance that can be traveled between the two task points is equal to the distance on the road between the two tasks; S105. Construct a multi-machine collaboration cost function at the cost of the longest operation time of agricultural machinery in multi-machine collaborative operation: f = max(t i ); The multi - machine collaborative objective function is to minimize the cost: min(f) = min(max(t i )); Among them, f represents the multi - machine collaborative cost; Step S200 further includes: S201. Construct agricultural machinery a i For task T j Cost function for bidding: wherein Add task T to the i-th agricultural machine j The total time required for the subsequent operations; t max The maximum working time of the entire fleet before the start of the tender S202. Construct the winning bid task T for the i-th agricultural machine j The cost of the entire fleet of machines Among them, f' is the total cost of the fleet of machines after the bidding is completed; f is the collaborative cost of multiple machines before the bidding; Step S400 further includes: S401. Determine the bidder. The platform selects a normal operating agricultural machine as the bidder. To minimize the communication distance during the bidding process, the bidder is selected. where (x i , y i ) is the current position of the i-th agricultural machine; S402. The tenderer sets a tender threshold. Before tendering for task T j the tenderer first calculates the minimum cost Δf j for itself to execute this task as a dynamic threshold, where is the cost for the tenderer to execute the new task T j ; Tenderer a i receives the tender information and calculates the minimum cost Δf i j for itself to execute this task. If Δf i j < Δf j it sends a tender message. If Δf i j ≥ Δf j it does not send a tender message; S403. The bidding and tendering process based on the contract net algorithm with a threshold; S404. Tender the task with the smallest area of the winner; S405. Perform task exchange among agricultural machines. Assume that agricultural machine i performs task T j The distance cost where s i-j is the distance of agricultural machine i after removing task T j from its itinerary; S406. Obtain the final dynamic task allocation result; In step S405, the execution of task exchange between agricultural machineries further includes: The agricultural machine i with the highest cost for completing the task calculates the maximum distance cost and the corresponding task number j; S4052. Agricultural machinery i acts as the tenderer to exchange and tender for task j; S4053. Other normal - working agricultural machineries act as bidders. The bidders use the "delete - insert" method to delete their unexecuted tasks in turn, and calculate their own minimum cost after replacement using the insertion method; S4054. If the cost after replacement is less than that before replacement, this task is used as bidding information; S4055. The tenderer uses the "delete-insert" method to calculate the cost after deleting task j and adding each tender task, and takes the minimum cost f i k and the corresponding task k; S4056. If f i k <f i , then swap tasks j and k.

2. The method for multi - machine collaborative dynamic task allocation of the same type of agricultural machinery according to claim 1, characterized in that, the multi - machine collaborative dynamic task allocation system described in step S300 includes agricultural machineries, a server, and a client. The agricultural machineries are equipped with in - vehicle computers, Beidou positioning modules, and wireless ad - hoc network modules for realizing self - positioning and communicating with other agricultural machineries; the server includes a calculation module and a storage module, and the storage module is used to store plot information and agricultural machinery information; the client is used to select and send tasks to a specified operation machine group.

Images