Method and device for planning and optimizing full-coverage operation path of agricultural machinery in farmland scene

Abstract

The invention provides an agricultural machine full-coverage operation path planning and optimizing method and device in a farmland scene, and belongs to the field of automatic driving and path planning, and the method comprises the steps: dividing a farmland into an in-field operation area and a capes area based on the coordinates of all vertexes of the polygonal farmland, the maximum curvature of an unmanned operation agricultural machine, and the operation type; based on the operation breadth of the unmanned operation agricultural machine and the operation starting point and the operation orientation of the unmanned operation agricultural machine entering the farmland, full-coverage operation strip segmentation is carried out on an in-field operation area, and an operation strip basic path is formed; determining the steering path of the capes according to the turning radius and the steering starting point of the operation strip; and determining a capes area edge closing path according to the operation strip basic path and the capes turning path, thereby generating a farmland full coverage path, and generating a path file. The operation efficiency of the agricultural machine is improved.

Description

Technical Field

[0001] The present invention relates to the fields of autonomous driving and path planning, and particularly to a method and device for path planning and optimization of full-coverage operation of agricultural machinery in a farmland scenario. Background Art

[0002] In a real farm environment, unmanned agricultural machinery is restricted by the distribution of tractor roads and farmland and the shape of the farmland, and needs to carry out full-coverage operation path planning starting from a specific starting point and in a specific direction to improve the operation efficiency of the agricultural machinery and achieve the goal of cost savings and improved operation quality. Most of the existing agricultural machinery operation path planning studies focus on single problems such as the path planning of quadrilateral farmland AB line, turning at the headland corner, or obstacle handling, and most of them are used for simulation, lacking systematic consideration of the application requirements of real farms.

[0003] In the prior art, there are already various methods for full-coverage path planning of farmland. Common ones include the straight reciprocating coverage method (Boustrophedon path), curved coverage paths, partition-based path planning, etc. Most of these methods assume that the shape of the farmland plot is regular (such as a rectangle or a trapezoid), or allow the agricultural machinery to operate in any orientation, thereby simplifying the complexity of path planning. However, in actual farm production, the operation of agricultural machinery is affected by various constraints such as irregular plot shapes, crop planting directions, obstacle distributions, etc. Especially in the scenario of unmanned farms, higher requirements are put forward for the accuracy and executability of the path. Most of the existing path planning methods are only based on geometric path planning, ignoring the influence of the turning radius, speed change, operation width, and operation mode (such as sowing and spraying) of the agricultural machinery on the path feasibility, resulting in the difficulty of tracking the planned path during execution, affecting the operation quality, and many methods are only applicable to ideal regular plots. For complex plots with irregular shapes, there are easy to appear dead ends or redundant paths in path planning, or it is difficult to achieve a high coverage rate, reducing the operation efficiency. Summary of the Invention

[0004] To solve the above problems of not considering the dynamic characteristics of agricultural machinery and poor adaptability to complex plots, the present invention provides a method and device for path planning and optimization of full-coverage operation of agricultural machinery in a farmland scenario.

[0005] To achieve the above object, the present invention adopts the following technical solutions: A method for path planning and optimization of full-coverage operation of agricultural machinery in a farmland scenario, comprising the following steps: Step 1: Divide the farmland into an in-field operation area and a headland area based on the vertex coordinates of the polygonal farmland, the maximum curvature of the unmanned operation agricultural machinery itself, and the operation type; Step 2: Based on the working width of the unmanned agricultural machinery, the starting point of operation in the farmland, and the operation orientation, divide the in-field operation area into full-coverage operation strips to form the basic path of the operation strips. Step 3: According to the turning radius and the starting point of the operation strip turning, determine the turning path in the cape area through the improved Dubins curve algorithm. Step 4: Determine the edge-trimming path in the cape area according to the basic path of the operation strip generated in Step 2 and the turning path in the cape area determined in Step 3, so as to generate the full-coverage path of the farmland and generate a path file.

[0006] The present invention also provides a device for planning and optimizing the full-coverage operation path of agricultural machinery in a farmland scenario, including the following modules: The zoning module divides the farmland into an in-field operation area and a cape area based on the coordinates of the vertices of the polygonal farmland, the maximum curvature of the unmanned agricultural machinery itself, and the operation type. The full-coverage operation strip division module divides the in-field operation area into full-coverage operation strips based on the working width of the unmanned agricultural machinery, the starting point of operation in the farmland, and the operation orientation, to form the basic path of the operation strips. The turning path determination module determines the turning path in the cape area according to the turning radius and the starting point of the operation strip turning through the improved Dubins curve algorithm. The full-coverage path generation module determines the edge-trimming path in the cape area according to the basic path of the operation strip and the turning path in the cape area, so as to generate the full-coverage path of the farmland and generate a path file.

[0007] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the method for planning and optimizing the full-coverage operation path of agricultural machinery in the farmland scenario described above are implemented.

[0008] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for planning and optimizing the full-coverage operation path of agricultural machinery in the farmland scenario described above are implemented.

[0009] Beneficial effects: (1) Based on the parameters of the unmanned agricultural machinery itself, the present invention optimizes the division method of the operation area and the cape edge-trimming area of the convex polygonal farmland, and clarifies the implementation plan of the unmanned operation in the farmland.

[0010] (2) The present invention adopts the idea of a virtual circumscribed quadrilateral combined with the parameters of the unmanned agricultural machinery to solve the full-coverage operation strips in the in-field operation area and the maximum coverage edge-trimming path in the cape edge-trimming area.

[0011] (3)The present invention realizes the solution of the turning path in the cape area according to the width of the cape area, the curvature constraint of the agricultural machinery, and the strip traversal scheme. Description of the Drawings

[0012] Figure 1 is a schematic diagram of the principle of the operation path planning and optimization method for full coverage of agricultural machinery in a farmland scenario of the present invention; Figure 2 is a schematic diagram of the division of the operation area and the cape area; Figure 3 is a schematic diagram of finding the boundary points by constructing a virtual rectangle based on the operation orientation; Figure 4 is a schematic diagram of the solution of the turning path by the conventional Dubins algorithm; Figure 5 is a schematic diagram of the solution of the turning path by the improved Dubins algorithm; Figure 6 is a schematic diagram of the smoothing at both ends of the vertex of the cape collection area; Figure 7 is a schematic diagram of the in-field operation path obtained by the present invention for the real application scenario. Detailed Embodiment

[0013] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0014] The present invention conducts full coverage path planning for convex polygon farmland and farmland with arbitrary operation orientations. The present invention divides the farmland into an in-field operation area and a cape area by using preset information, and completes the prior path planning and generates a path file based on the operation type, operation width, turning radius of the agricultural machinery, the starting point of the agricultural machinery in the farmland, and the operation orientation.

[0015] As Figure 1 shown, a method for planning and optimizing the full coverage operation path of agricultural machinery in a farmland scenario of the present invention includes the following steps: Step 1: Divide the farmland into an in-field operation area and a cape area (i.e., Figure 1 the preprocessing of the operation area) based on the coordinates of each vertex of the polygon farmland, the maximum curvature of the unmanned operation agricultural machinery itself, and the operation type; Step 2: Conduct full coverage operation strip segmentation on the in-field operation area based on the operation width of the unmanned operation agricultural machinery, the operation starting point and the operation orientation when entering the farmland, and form a basic path of the operation strip (i.e., Figure 1 the solution of the operation path); Step 3: Determine the turning path in the cape area (i.e., the solution of the cape turning path of Figure 1 ) according to the turning radius and the starting point of the turning of the operation strip (i.e., the starting point of the strip turning of Figure 1 ); Step 4: Determine the edge-closing path in the cape area according to the basic path of the operation strip generated in Step 2 and the cape turning path determined in Step 3, so as to generate a path for full coverage of the farmland and generate a path file.

[0016] Specifically, Step 1 includes: Delimit the scope of each area according to the coordinates of the vertices of the polygonal farmland, the maximum curvature of the agricultural machinery turning, and the operation type. Divide the cape area towards the centroid of the convex polygon according to the working width and the maximum curvature of the agricultural machinery. The width of the cape area is as shown in formula (1): (1) Wherein, represents the working width, represents the maximum curvature of the agricultural machinery turning, represents the ceiling operation, and max represents the maximum value operation.

[0017] The width of the cape area is obtained by taking the maximum value of 2 times the turning radius and the working width, dividing by the ceiling of the working width, and then multiplying by the working width. The width of the cape area obtained by this scheme can not only ensure that the U-turn after the operation area of the agricultural machinery does not exceed the farmland range, but also ensure that there is no double compaction during the operation in the cape area.

[0018] The present invention ensures the development of the edge-closing operation and the turning operation in the cape area through width constraints. After the width of the cape area is determined, the farmland is compressed inward to obtain the operation area, and the compression range is the cape area, as Figure 2 shown.

[0019] Specifically, Step 2 includes: Construct a virtual rectangle according to the operation orientation to find the two farthest points on both sides of the operation orientation of the convex polygon in the in-field operation area, that is, Figure 3 in , two points. Figure 3 in is the distance between the two farthest points in the operation orientation. Combine the working width to perform operation strip segmentation, and cut the operation area by equally dividing the AB line to solve the operation strip, ensuring full coverage of the in-field operation of the unmanned agricultural machinery; to meet the requirements of full coverage operation, the distance between adjacent operation strips should be equal to the working width, and the number of strips is , as shown in formula (2): (2) Wherein, is the maximum width of the operation area. It ensures that the operation strips achieve full coverage of the operation area.

[0020] Specifically, step 3 includes: When dividing the cape area in step 1, it ensures that the agricultural machinery will not exceed the farmland range when turning around in the cape area. The turning path is solved through the Dubins curve. The path set of the Dubins curve has {LSL, RSR, RSL, LSR, RLR, LRL}, where L represents the arc movement of turning left, R represents the arc movement of turning right, and S indicates moving along a straight line. When conventionally solving the Dubins curve, the optimal route is mainly selected based on the degree of radian change and the total length of the curve. When solving the Dubins turning arc of the cape turning route with the traditional optimal scheme, when the access points of two adjacent operation strips are on the same side of the operation area, a safe and smooth turning path between the operation strips can be obtained through the Dubins curve; however, when the access points of two adjacent operation strips are not on the same side of the operation area, the turning path solved by the conventional Dubins optimal curve may pose a risk of crushing the crops in the operation area, such as Figure 4 shown , is the Dubins turning arc.

[0021] Therefore, when evaluating the optimality of the Dubins path set, a collision detection factor is added to minimize the re-compression of the strip turning path on the operation area. The optimal evaluation function of the Dubins curve can be written as Equation (3): (3) where is the path cost, represents the degree of radian change, is the path length, is the number of points of the turning path in the operation area, is the total number of points of the turning path, is the radian change weight coefficient, is the path length weight coefficient, is the re-compression rate coefficient. After optimizing through the evaluation function of Equation (3), the Dubins turning arc obtained when the access points of two adjacent operation strips are not on the same side of the operation area and there is a re-compression risk is as shown in Figure 5 shown.

[0022] Specifically, step 4 includes: As can be seen from Equation (4), the number of operation strips for closing the edges of the farmland cape is . The ideal trajectory for closing the edges of the cape is convex polygon farmland borders that are widths inwardly retracted. Due to the curvature constraint in the turning movement of the unmanned agricultural machinery, it is necessary to smooth the trajectory at the turning of the cape, as shown in Figure 6 shown, where R is the minimum turning radius, determined by the maximum curvature of the agricultural machinery turning Obtained by taking the reciprocal, is the interior angle between two adjacent sides, and the minimum smoothing length at both ends of each vertex is , which can be solved by Equation (5).

[0023] (4) (5) By smoothing the edge - closing path in the cape area, the edge - closing operation at the cape can be completed at the cost of sacrificing a small amount of working space in the cape area. Smoothing the edge - closing path in the cape area is as follows: the minimum smoothing length at both ends of each vertex is L smooth =R·tan(2α), where α is the interior angle between two adjacent sides, R is the minimum turning radius, and is obtained from the reciprocal of the maximum curvature of the agricultural machine's steering obtained.

[0024] The present invention also provides a device for path planning and optimization of full - coverage operation of agricultural machines in a farmland scenario, including the following modules: A zoning module that divides the farmland into an in - field operation area and a cape area based on the coordinates of each vertex of the polygonal farmland, the maximum curvature of the unmanned operation agricultural machine itself, and the operation type; A full - coverage operation strip - dividing module that divides the in - field operation area into full - coverage operation strips based on the operation width of the unmanned operation agricultural machine and the operation starting point and operation orientation when entering the farmland, forming a basic path of the operation strip; A turning path determination module that determines the turning path in the cape area through an improved Dubins curve algorithm according to the turning radius and the turning starting point of the operation strip; A full - coverage path generation module that determines the edge - closing path in the cape area according to the basic path of the operation strip and the turning path in the cape area, thereby generating a full - coverage path for the farmland and generating a path file.

[0025] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the above - mentioned method for path planning and optimization of full - coverage operation of agricultural machines in a farmland scenario are implemented.

[0026] The present invention also provides a non - transitory computer - readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above - mentioned method for path planning and optimization of full - coverage operation of agricultural machines in a farmland scenario are implemented.

[0027] Embodiment: According to the method proposed by the present invention, the vertex information of the real plot in the WGS84 coordinate system of the Unmanned Farm Demonstration Base in Jiaqiao Town, Zouping City is brought in: [[571405.61,4089406.0],[571755.61,4089406.0],[571555.61,4089679.0],[571405.61,4089599.0],[571360.36,4089469.0]]. The working width of the agricultural machinery-mounted implement is 5m, the turning curvature constraint of the agricultural machinery is 0.18, and the working direction is 180° from north to south. The width of the cape area is obtained as 15m, that is, there are 3 edge trimming strips in the cape area; the number of strips in the working area is 48, and finally the in-field working route is as Figure 7 shown. Compared with the existing methods for solving the in-field unmanned operation path, the present invention improves the coverage rate of in-field unmanned operation and has higher applicability to the plot shape.

[0028] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention can be implemented in various computer languages. For example, object-oriented programming languages such as Java and interpreted scripting languages such as JavaScript.

[0029] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the processes and / or blocks in the flowchart and / or block diagram can also be implemented. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate for implementing in the process Figure 1 one process or multiple processes and / or blocks Figure 1 a device for the functions specified in one block or multiple blocks.

[0030] These computer program instructions can 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 generate a manufactured article including an instruction device, and the instruction device implements in the process Figure 1 one process or multiple processes and / or blocksFigure 1 The functions specified in one or more boxes.

[0031] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide for implementing the steps of the functions specified in one Figure 1 process or more processes and / or boxes Figure 1 or the functions specified in more boxes.

[0032] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0033] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A method for planning and optimizing the full coverage operation path of agricultural machinery in a farmland scene, characterized in that: The steps include: Step 1: Based on the coordinates of each vertex of the polygonal farmland, the maximum curvature of the unmanned agricultural machinery itself, and the operation type, the farmland is divided into an in-field operation area and a headland area; Step 2: Based on the working width of the unmanned agricultural machinery and the starting point and direction of entering the farmland, the field working area is divided into full-coverage working strips to form a basic path for the working strips; Step 3: According to the turning radius and the turning starting point of the working strip, the turning path of the cape area is determined by using the improved Dubins curve algorithm; Step 4: Determine the cape area edge finishing path based on the basic path of the working strip generated in step 2 and the cape turning path determined in step 3, thereby generating a full coverage path for the farmland and generating a path file.

2. According to the method for planning and optimizing the path of agricultural machinery full coverage operation in a farmland scene in claim 1, it is characterized in that: In step 1, the cape area is divided toward the centroid of the convex polygon according to the working width and maximum curvature of the unmanned agricultural machinery. The width of the cape area is obtained by taking the maximum value of twice the turning radius and the working width, dividing it by the working width, rounding up, and then multiplying by the working width.

3. The method for planning and optimizing the path of agricultural machinery full coverage operation in a farmland scene according to claim 1 is characterized in that: In step 2, a virtual rectangle is constructed according to the working direction, the farthest points on both sides of the working direction of the convex polygon of the working area in the field are found, and the working strips are divided according to the working width. The working area in the field is cut by dividing the AB line with equal width to solve the working strips. The spacing between adjacent working strips is equal to the working width, and the number of strips is for: (2) in, is the maximum width of the working area, Indicates rounding up operation. Represents the working width.

4. The method for planning and optimizing the path of agricultural machinery full coverage operation in a farmland scene according to claim 1 is characterized in that: In step 3, the improved Dubins curve algorithm includes: when evaluating the optimal Dubins path set, adding a collision detection factor, the optimized evaluation function is: (3) in, is the path cost, Describe the degree of arc change, is the path length, is the number of points on the turning path within the work area, is the total number of turning path points, is the arc change weight coefficient, is the path length weight coefficient, is the pressure re-compression coefficient.

5. The method for planning and optimizing the path of agricultural machinery full coverage operation in a farmland scene according to claim 1 is characterized in that: In step 4, the ideal cape edge trajectory is Indentation The width of the convex polygon farmland border, the minimum smooth length of each vertex of the convex polygon farmland is , Solve by formula (5): (5) in, is the maximum curvature of agricultural machinery steering, is the interior angle of two adjacent sides; Smooth the path of the cape area, and the minimum smoothing length at both ends of each vertex is L smooth =R·tan(2α), where α is the internal angle of two adjacent sides, R is the minimum turning radius, and the maximum curvature is The reciprocal of is obtained.

6. The method for planning and optimizing the path of agricultural machinery full coverage operation in a farmland scene according to claim 1 is characterized in that: The polygonal farmland is a convex polygonal farmland.

7. The method for planning and optimizing the path of agricultural machinery full coverage operation in a farmland scene according to claim 1 is characterized in that: The operation types include sowing and spraying.

8. A device for planning and optimizing the operation path of agricultural machinery in full coverage in a farmland scene, characterized in that: Includes the following modules: The partitioning module divides the farmland into the field operation area and the headland area based on the coordinates of each vertex of the polygonal farmland, the maximum curvature of the unmanned agricultural machinery itself, and the operation type; The full-coverage operation strip segmentation module divides the field operation area into full-coverage operation strips based on the operation width of the unmanned agricultural machinery and the operation starting point and operation direction of entering the farmland to form the basic path of the operation strip; The turning path determination module determines the turning path of the cape area through the improved Dubins curve algorithm according to the turning radius and the turning starting point of the working strip; The full coverage path generation module determines the cape area edge path based on the basic path of the operating strip and the cape turning path, thereby generating a full coverage path for the farmland and generating a path file.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method for planning and optimizing the full coverage operation path of agricultural machinery in the farmland scene described in one of claims 1-7 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for planning and optimizing the full coverage operation path of agricultural machinery in a farmland scenario as described in any one of claims 1 to 7 are implemented.

Images