Agricultural machinery path planning method and system

Abstract

The present invention discloses a method and system for agricultural machinery path planning. The system determines whether the longest side of a farmland is a straight line. If so, the farmland is regular in shape; if not, the farmland is irregular in shape. If the farmland is regular, the planned path is represented by a linear function corresponding to the straight line. After translation, a new linear function is formed, which serves as the basis for path tracking. If the farmland is irregular, the planned path is formed by sampling the coordinates of the farmland's long side to form a sparse discrete coordinate point set. Based on the current positional relationship between the agricultural machinery and the sparse path, some discrete points are intercepted from the sparse path as a local path. After translation, a new local path is formed. The sparse local path is then interpolated to form a dense local path, which serves as the basis for path tracking. Advantages: The system is applicable to path planning for farmland of various shapes; it eliminates the adverse effects of implement installation deviation on path planning, thereby improving operational accuracy.

Description

Technical Field

[0001] The present invention relates to a method and system for agricultural machinery path planning, belonging to the technical field of automatic driving of agricultural machinery. Background Art

[0002] In recent years, the intelligentization of agricultural machinery has developed rapidly, and autonomous driving technology has played an important role in various agricultural production processes. However, agricultural production operation scenarios have their own particularities, which brings challenges to the implementation of autonomous driving technology.

[0003] Farmland shapes vary. Some are regular, such as rectangles and squares, and can be described using geometric parameters; others are irregular, such as arbitrarily shaped curves, which defy geometrical expression. However, farmland shape is not static and can change with seasons, ownership, or crop changes. This requires farmland path planning to adapt to these changes, quickly generating results based on operational needs and ensuring smooth and continuous paths, enabling agricultural machinery to better track their paths. Furthermore, due to factors such as implement installation deviations, path planning must consider the connectivity between adjacent rows, ensuring that adjacent rows' working areas do not overlap and are spaced at regular intervals.

[0004] Existing technologies are suitable for single-shaped farmland paths. Some path generation methods only work with curves, not straight lines. Path translation fails to account for implement installation deviations, making it impossible to achieve precise operation. Local tracking path interception is not considered; if a local path is too long, it will cause memory and computing resource consumption, while if it is too short, it will cause tracking failure. Curve interpolation is also impossible. Other methods use global path point planning only for straight lines, and these lines are represented using discrete points, wasting memory and computing resources. Path translation fails to account for implement installation deviations, making it impossible to achieve precise operation. Local paths are poorly selected; if they are too long, they will cause memory and computing resource consumption, while if they are too short, they will cause tracking failure. Interpolation methods only work with straight lines, making it difficult to ensure the smoothness of curved planning paths. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to overcome the defects of the prior art and provide an agricultural machinery path planning method and system, which is suitable for path planning of farmlands of various shapes.

[0006] To solve the above technical problems, the present invention provides an agricultural machinery path planning method, comprising:

[0007] According to whether the longest side of the farmland is a straight line, if yes, the farmland shape is regular, if not, the farmland shape is irregular;

[0008] If the farmland has a regular shape, the planned path is represented by a straight line function corresponding to the straight line, and after translation, a new straight line function is formed, which is used as the basis for path tracking;

[0009] If the shape of the farmland is irregular, the planned path is formed by sampling the long side coordinates of the farmland to form a sparse discrete coordinate point set. According to the current positional relationship between the agricultural machinery and the sparse path, some discrete points of the sparse path are intercepted as a local path. After the path is translated, a new local path is formed. The sparse local path is then interpolated to form a dense local path, and the dense local path is used as the basis for path tracking.

[0010] Furthermore, the planned path is represented by a straight line function, and after translation, a new straight line function is formed, including:

[0011] Record the position points A(x,y) and B(x,y) near the two ends of the long side of the farmland, and determine a straight line through these two points as the reference path for planning:

[0012] y=kx+b(1)

[0013] Where k is the slope of the line and b is the intercept of the line;

[0014] By S = (α k-1 ,α k ,β,D) to represent the translation parameter of the path, where α k-1 is the driving direction of the agricultural machinery in the previous row, α k is the current driving direction of the agricultural machinery, β is the path translation direction, which is perpendicular to the reference path direction, and D is the translation distance. If it is the reference path itself, D is 0, indicating no translation.

[0015] According to the translation parameter S=(α k-1 ,α k ,β,D) after translation, we get the new straight line function:

[0016] y=kx+b new (2)

[0017]

[0018] Furthermore, the determination of the translation distance includes:

[0019] The relative driving status of adjacent rows is determined by α k-1 and α k If the two are in the same direction, they are traveling in the same direction. If the two are in opposite directions, they are traveling in opposite directions. The translation direction is directly determined by β to determine whether it is left or right. D is:

[0020] If traveling in opposite directions - right translation, then D = 2WL + d;

[0021] If traveling in the same direction - right translation, then D = WR + WL + d;

[0022] If the vehicles are traveling in opposite directions and moving left, then D = 2WR + d;

[0023] If traveling in the same direction - translating to the left, then D = WR + WL + d;

[0024] Among them, WR is the left width of the agricultural implement installation, WL is the right width of the agricultural implement installation, and d is the fixed connecting row spacing maintained by the agricultural machinery when entering the next row of operation.

[0025] Furthermore, the planned path is formed into a sparse discrete coordinate point set by sampling the long side coordinates of the farmland, including:

[0026] The discrete points between the two end points A and B along the long side of the farmland are recorded, where the sampling distance interval is L.

[0027] Furthermore, according to the current positional relationship between the agricultural machine and the sparse path, the sparse path is intercepted with some discrete points as a local path, and then a new local path is formed after the path is translated, including:

[0028] Find the nearest point N(x, y) on the reference path between the agricultural machinery and the machine, and then use N(x, y) as the starting point to intercept the points that meet the conditions according to the distance H in the driving direction. The calculation method of H and the method of selecting points are shown in formulas (4) and (5):

[0029] H=vt p (4)

[0030] (ii N )L≤H (5)

[0031] Where v is the vehicle speed, t p is the time constant, i is the index number of the path point, i N is the index number of point N;

[0032] By S = (α k-1 ,α k ,β,D) to represent the translation parameter of the path, where α k-1 is the driving direction of the agricultural machinery in the previous row, α k is the current driving direction of the agricultural machinery, β is the path translation direction, which is perpendicular to the reference path direction, and D is the translation distance. If it is the reference path itself, D is 0, indicating no translation.

[0033] The relative driving status of adjacent rows can be determined based on α k-1 and α k If the two are in the same direction, they are traveling in the same direction. If the two are in opposite directions, they are traveling in opposite directions. The translation direction can be directly determined by β to determine whether it is left or right. D is:

[0034] If traveling in opposite directions - right translation, then D = 2WL + d;

[0035] If traveling in the same direction - right translation, then D = WR + WL + d;

[0036] If the vehicles are traveling in opposite directions and moving left, then D = 2WR + d;

[0037] If traveling in the same direction - translating to the left, then D = WR + WL + d;

[0038] Where WR is the left width of the agricultural implement, WL is the right width of the agricultural implement, and d is the fixed row spacing maintained when the agricultural machine enters the next row of operation;

[0039] The original sampled path points are translated point by point to obtain a new local path. i ,y i ) is translated to the point (x' i ,y' i ) is represented as follows:

[0040]

[0041] Furthermore, the interpolation of the sparse local paths to form a dense local path includes:

[0042] A hybrid method of quadratic and cubic B-spline is used to interpolate the local path points after translation to form a dense local path. The starting point and the end point are interpolated by quadratic B-spline, and the remaining points are interpolated by cubic B-spline.

[0043] Furthermore, the selection of control points for the cubic B-spline interpolation includes:

[0044] A control point is arranged before and after the sampling point in the tangent direction. The distance between the front control point and the sampling point is one third of the distance between the previous sampling point and the sampling point, and the distance between the rear control point and the sampling point is one third of the distance between the next sampling point and the sampling point.

[0045] An agricultural machinery path planning system, comprising:

[0046] The judgment module is used to determine whether the longest side of the farmland is a straight line. If so, the farmland has a regular shape; if not, the farmland has an irregular shape.

[0047] A first path determination module is used to determine, when the farmland has a regular shape, the planned path as a straight line function corresponding to the straight line, and to form a new straight line function after translation, and to use the new straight line function as the basis for path tracking;

[0048] The second path determination module is used to determine the planned path when the farmland has an irregular shape. The path is formed by sampling the long side coordinates of the farmland to form a sparse discrete coordinate point set. According to the current positional relationship between the agricultural machinery and the sparse path, some discrete points of the sparse path are intercepted as a local path. After the path is translated, a new local path is formed. The sparse local path is interpolated to form a dense local path, and the dense local path is used as the basis for path tracking.

[0049] A computer-readable storage medium storing one or more programs, the one or more programs comprising instructions that, when executed by a computing device, cause the computing device to perform any of the methods described.

[0050] A computing device comprising:

[0051] One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing any of the methods described.

[0052] The beneficial effects achieved by the present invention are:

[0053] (1) Applicable to path planning for farmlands of various shapes;

[0054] (2) Eliminate the adverse effects of implement installation deviation on path planning through the associative translation method, and improve operation accuracy;

[0055] (3) Reduce memory and computing resource consumption through differentiated linear expressions, as well as curve local path interception and interpolation processing;

[0056] (4) By improving the spline curve interpolation method, the smoothness of the curve planning path is improved, and the driving smoothness of agricultural machinery is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a schematic flow diagram of the present invention;

[0058] Figure 2-1 、 2-2 , 2-3 and 2-4 are schematic diagrams of path translation in different directions for regular farmland shapes;

[0059] Figure 3 This is the principle diagram of curve planning when the farmland is irregular in shape;

[0060] Figure 4 This is the path interpolation principle diagram. DETAILED DESCRIPTION

[0061] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and are not intended to limit the scope of protection of the present invention.

[0062] like Figure 1 As shown, a method for agricultural machinery path planning includes:

[0063] According to whether the longest side of the farmland is a straight line, if yes, the farmland shape is regular, if not, the farmland shape is irregular;

[0064] If the farmland has a regular shape, the planned path is represented by a straight line function corresponding to the straight line, and after translation, a new straight line function is formed, which is used as the basis for path tracking;

[0065] If the shape of the farmland is irregular, the planned path is formed by sampling the long side coordinates of the farmland to form a sparse discrete coordinate point set. According to the current positional relationship between the agricultural machinery and the sparse path, some discrete points of the sparse path are intercepted as a local path. After the path is translated, a new local path is formed. The sparse local path is then interpolated to form a dense local path, and the dense local path is used as the basis for path tracking.

[0066] like Figure 2-1 、 2-2 , 2-3 and 2-4, wherein, Figure 2-1 To travel in opposite directions - move horizontally to the right, Figure 2-2 For the same direction of travel - rightward shift, Figure 2-3 To travel in opposite directions - move horizontally to the left, Figure 2-4 The planned path is represented by a straight line function, and after translation, a new straight line function is formed, including:

[0067] Record the position points A(x,y) and B(x,y) near the two ends of the long side of the farmland, and determine a straight line through these two points as the reference path for planning:

[0068] y=kx+b (1)

[0069] Where k is the slope of the line and b is the intercept of the line;

[0070] The purpose of translation is to enable the agricultural machinery to enter the next row of operation while maintaining a fixed connecting row distance d. Due to reasons such as deviation in the installation of agricultural implements, the translation distances of adjacent paths may be different when the driving direction and translation direction change. Therefore, each path translation needs to refer to the status information of the previous row to form an associated translation. k-1 ,α k ,β,D) to represent the translation parameter of the path, where α k-1 is the driving direction of the agricultural machinery in the previous row, α kis the current driving direction of the agricultural machinery, β is the path translation direction, which is perpendicular to the reference path direction (the direction of the line connecting points A to B), and D is the translation distance. If it is the reference path itself, D is 0, indicating no translation.

[0071] According to the translation parameter S=(α k-1 ,α k ,β,D) after translation, we get the new straight line function:

[0072] y=kx+b new (2)

[0073]

[0074] The determination of the translation distance includes:

[0075] The relative driving status of adjacent rows is determined by α k-1 and α k If the two are in the same direction, they are traveling in the same direction. If the two are in opposite directions, they are traveling in opposite directions. The translation direction is directly determined by β to determine whether it is left or right. D is:

[0076] If traveling in opposite directions - right translation, then D = 2WL + d;

[0077] If traveling in the same direction - right translation, then D = WR + WL + d;

[0078] If the vehicles are traveling in opposite directions and moving left, then D = 2WR + d;

[0079] If traveling in the same direction - translating to the left, then D = WR + WL + d;

[0080] Among them, WR is the left width of the agricultural implement installation, WL is the right width of the agricultural implement installation, and d is the fixed connecting row spacing maintained by the agricultural machinery when entering the next row of operation.

[0081] like Figure 3 As shown in the figure, due to the irregular shape of the farmland, the planning path is formed by sampling the long side coordinates of the farmland to form a sparse discrete coordinate point set, including:

[0082] The discrete points between the two end points A and B along the long side of the farmland are recorded, where the sampling distance interval is L.

[0083] If all the discrete points on the long side are used as the path to be tracked, it will cause a waste of memory and computing resources. Instead, some points can be intercepted as a local path to shorten the tracking path length. The method of intercepting some discrete points on the sparse path as a local path based on the current position relationship between the agricultural machine and the sparse path, and then forming a new local path after path translation, includes:

[0084] Find the nearest point N(x, y) on the reference path between the agricultural machinery and the machine, and then use N(x, y) as the starting point to intercept the points that meet the conditions according to the distance H in the driving direction. The calculation method of H and the method of selecting points are shown in formulas (4) and (5):

[0085] H=vt p (4)

[0086] (ii N )L≤H (5)

[0087] Where v is the vehicle speed, t p is the time constant, i is the index number of the path point, i N is the index number of point N;

[0088] By S = (α k-1 ,α k ,β,D) to represent the translation parameter of the path, where α k-1 is the driving direction of the agricultural machinery in the previous row, α k is the current driving direction of the agricultural machinery, β is the path translation direction, which is perpendicular to the reference path direction, and D is the translation distance. If it is the reference path itself, D is 0, indicating no translation.

[0089] The relative driving status of adjacent rows can be determined based on α k-1 and α k If the two are in the same direction, they are traveling in the same direction. If the two are in opposite directions, they are traveling in opposite directions. The translation direction can be directly determined by β to determine whether it is left or right. D is:

[0090] If traveling in opposite directions - right translation, then D = 2WL + d;

[0091] If traveling in the same direction - right translation, then D = WR + WL + d;

[0092] If the vehicles are traveling in opposite directions and moving left, then D = 2WR + d;

[0093] If traveling in the same direction - translating to the left, then D = WR + WL + d;

[0094] Where WR is the left width of the agricultural implement, WL is the right width of the agricultural implement, and d is the fixed row spacing maintained when the agricultural machine enters the next row of operation;

[0095] The original sampled path points are translated point by point to obtain a new local path. i ,y i ) is translated to the point (x' i ,y' i ) is represented as follows:

[0096]

[0097] The interpolation of the sparse local paths to form a dense local path includes:

[0098] like Figure 4 As shown in the figure, a hybrid method of quadratic and cubic B-spline is used to interpolate the local path points after translation to form a dense local path, so that the curve contour is restored to the greatest extent and is smooth and continuous and suitable for tracking; the starting point and the end point (such as Figure 4 The quadratic B-spline interpolation is used for points 0 and 3 in the middle, and the cubic B-spline interpolation is used for the remaining points.

[0099] The selection of control points for the cubic B-spline interpolation includes:

[0100] Regarding the selection of B-spline interpolation control points, in addition to the starting and ending points, a control point is placed before and after the sampling point in the tangent direction. The distance between the front control point and the sampling point (e.g., point 2) is one-third of the distance between the previous sampling point (e.g., point 1) and the sampling point (e.g., point 2), and the distance between the back control point and the sampling point (e.g., point 2) is one-third of the distance between the next sampling point (e.g., point 3) and the sampling point (e.g., point 2). This makes the selection of B-spline interpolation control points simpler and more reasonable, and ensures that the curve generated by interpolation between two sampling points is monotonic and smoother.

[0101] An agricultural machinery path planning system, comprising:

[0102] The judgment module is used to determine whether the longest side of the farmland is a straight line. If so, the farmland has a regular shape; if not, the farmland has an irregular shape.

[0103] A first path determination module is used to determine, when the farmland has a regular shape, the planned path as a straight line function corresponding to the straight line, and to form a new straight line function after translation, and to use the new straight line function as the basis for path tracking;

[0104] The second path determination module is used to determine the planned path when the farmland has an irregular shape. The path is formed by sampling the long side coordinates of the farmland to form a sparse discrete coordinate point set. According to the current positional relationship between the agricultural machinery and the sparse path, some discrete points of the sparse path are intercepted as a local path. After the path is translated, a new local path is formed. The sparse local path is interpolated to form a dense local path, and the dense local path is used as the basis for path tracking.

[0105] It also includes a positioning module, which is used to output the coordinate information of the current agricultural machine and indicate the position of the current agricultural machine in the global coordinate system.

[0106] A computer-readable storage medium storing one or more programs, the one or more programs comprising instructions that, when executed by a computing device, cause the computing device to perform any of the methods described.

[0107] A computing device comprising:

[0108] One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing any of the methods described.

[0109] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0110] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0111] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0112] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0113] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for agricultural machinery path planning, characterized in that: include: According to whether the longest side of the farmland is a straight line, if yes, the farmland shape is regular, if not, the farmland shape is irregular; If the farmland has a regular shape, the planned path is represented by a straight line function corresponding to the straight line, and after translation, a new straight line function is formed, which is used as the basis for path tracking; Record the position points A(x,y) and B(x,y) near the two ends of the long side of the farmland, and determine a straight line through these two points as the reference path for planning: y = kx + b （1）； Where k is the slope of the line and b is the intercept of the line; pass S =( α k-1 , α k , β , D ) to represent the translation parameters of the path, where α k-1 The direction of travel of the agricultural machinery in the previous row. α k The current direction of the agricultural machinery travel. β is the path translation direction, which is perpendicular to the reference path direction, D is the translation distance. If it is the reference path itself, then D 0 means no translation; Follow the translation parameters S =( α k-1 , α k , β , D )After translation, we get the new straight line function: y = kx + b new （2）； （3）； If the shape of the farmland is irregular, the planned path is formed by sampling the long side coordinates of the farmland to form a sparse discrete coordinate point set. According to the current position relationship between the agricultural machinery and the sparse path, some discrete points of the sparse path are intercepted as a local path. After the path is translated, a new local path is formed. The sparse local path is then interpolated to form a dense local path, and the dense local path is used as the basis for path tracking. The planned path is formed by sampling the long side coordinates of the farmland to form a sparse discrete coordinate point set, including: Record the discrete points between the two end points A and B along the long side of the farmland, where the sampling distance interval is L; According to the current positional relationship between the agricultural machine and the sparse path, the sparse path is intercepted with some discrete points as a local path, and then a new local path is formed after the path is translated, including: Find the closest point on the reference path to the agricultural machine N ( x , y ), then N ( x , y ) is the starting point and the points that meet the conditions are intercepted according to the distance H in the direction of travel. The calculation method of H and the method of selecting points are shown in formulas (4) and (5): H=vt p （4）； ( i - i N ) L ≤ H （5）； in, v is the vehicle speed, t p is the time constant, i is the index number of the path point, i N is the index number of point N; The relative driving status of adjacent rows can be determined based on α k-1 and α k If the two are in the same direction, they are traveling in the same direction. If the two are in opposite directions, they are traveling in opposite directions. The translation direction is directly determined by β Determine whether to go left or right: If traveling in opposite directions - right translation, then D= 2 WL+d ; If traveling in the same direction - right translation, then D=WR + WL+d ; If traveling in opposite directions - shifting left, then D= 2 WR+d ; If traveling in the same direction - shifting left, then D=WR + WL+d ; in, WR For the left width of the implement installation, WL Install the right width for the implement, d A fixed row spacing is maintained for agricultural machinery to enter the next row of operations; The original sampled path points are translated point by point to obtain a new local path. x i , y i ) is translated into the point It is expressed as follows: （6）； The interpolation of the sparse local paths to form a dense local path includes: A hybrid method of quadratic and cubic B-spline is used to interpolate the local path points after translation to form a dense local path. The starting point and the end point are interpolated by quadratic B-spline, and the remaining points are interpolated by cubic B-spline.

2. The agricultural machinery path planning method according to claim 1, characterized in that: The selection of control points for the cubic B-spline interpolation includes: A control point is arranged before and after the sampling point in the tangent direction. The distance between the front control point and the sampling point is one third of the distance between the previous sampling point and the sampling point, and the distance between the rear control point and the sampling point is one third of the distance between the next sampling point and the sampling point.

3. An agricultural machinery path planning system, characterized in that: include: The judgment module is used to determine whether the longest side of the farmland is a straight line. If so, the farmland has a regular shape; if not, the farmland has an irregular shape; A first path determination module is used to determine, when the farmland has a regular shape, the planned path as a straight line function corresponding to the straight line, and to form a new straight line function after translation, and to use the new straight line function as the basis for path tracking; Record the position points A(x,y) and B(x,y) near the two ends of the long side of the farmland, and determine a straight line through these two points as the reference path for planning: y = kx + b （1）； Where k is the slope of the line and b is the intercept of the line; pass S =( α k-1 , α k , β , D ) to represent the translation parameters of the path, where α k-1 The direction of travel of the agricultural machinery in the previous row. α k The current direction of the agricultural machinery travel. β is the path translation direction, which is perpendicular to the reference path direction, D is the translation distance. If it is the reference path itself, then D 0 means no translation; Follow the translation parameters S =( α k-1 , α k , β , D )After translation, we get the new straight line function: y = kx + b new （2）； （3）； If the shape of the farmland is irregular, the planned path is formed by sampling the long side coordinates of the farmland to form a sparse discrete coordinate point set. According to the current position relationship between the agricultural machinery and the sparse path, some discrete points of the sparse path are intercepted as a local path. After the path is translated, a new local path is formed. The sparse local path is then interpolated to form a dense local path, and the dense local path is used as the basis for path tracking. The planned path is formed by sampling the long side coordinates of the farmland to form a sparse discrete coordinate point set, including: Record the discrete points between the two end points A and B along the long side of the farmland, where the sampling distance interval is L; According to the current positional relationship between the agricultural machine and the sparse path, the sparse path is intercepted with some discrete points as a local path, and then a new local path is formed after the path is translated, including: Find the closest point on the reference path to the agricultural machine N ( x , y ), then N ( x , y ) is the starting point and the points that meet the conditions are intercepted according to the distance H in the direction of travel. The calculation method of H and the method of selecting points are shown in formulas (4) and (5): H=vt p （4）； ( i - i N ) L ≤ H （5）； in, v is the vehicle speed, t p is the time constant, i is the index number of the path point, i N is the index number of point N; The relative driving status of adjacent rows can be determined based on α k-1 and α k If the two are in the same direction, they are traveling in the same direction. If the two are in opposite directions, they are traveling in opposite directions. The translation direction is directly determined by β Determine whether to go left or right: If traveling in opposite directions - right translation, then D= 2 WL+d ; If traveling in the same direction - right translation, then D=WR + WL+d ; If traveling in opposite directions - shifting left, then D= 2 WR+d ; If traveling in the same direction - shifting left, then D=WR + WL+d ; in, WR For the left width of the implement installation, WL Install the right width for the implement, d A fixed row spacing is maintained for agricultural machinery to enter the next row of operations; The original sampled path points are translated point by point to obtain a new local path. x i , y i ) is translated into the point It is expressed as follows: （6）； The interpolation of the sparse local paths to form a dense local path includes: A hybrid method of quadratic and cubic B-spline is used to interpolate the local path points after translation to form a dense local path. The starting point and the end point are interpolated by quadratic B-spline, and the remaining points are interpolated by cubic B-spline.

4. A computer-readable storage medium storing one or more programs, characterized in that: The one or more programs include instructions that, when executed by a computing device, cause the computing device to perform any one of the methods according to claims 1 to 2.

5. A computing device, characterized in that include, One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for executing any one of the methods according to claims 1 to 3.

Images