A diagonal harrowing path planning method, device, equipment, medium and agricultural machinery

Abstract

The present application relates to a diagonal harrowing path planning method, device, equipment, medium and agricultural machinery. The method includes: S1, obtaining a plurality of first working lines planned at a first working line angle and a plurality of second working lines planned at a second working line angle in a target plot; S2, obtaining a plurality of candidate starting points closest to the end point of the current working line, and each candidate starting point corresponds to a candidate working line; S3, based on a preset cost function, taking the candidate working line with the lowest path cost as the target working line; S4, obtaining a sub-path between the current working line and the corresponding target working line; S5, taking the target working line as the new current working line, and repeating S2 to S4. Based on the cost function, the present application dynamically selects the candidate working line with the lowest path cost, reduces the ineffective movement of agricultural machinery, reduces the total length of the sub-path, and improves the efficiency of agricultural operations.

Description

Technical Field

[0001] The present application relates to the technical field of agricultural machinery navigation planning, and particularly relates to a diagonal harrowing path planning method, device, equipment, medium and agricultural machinery. Background Art

[0002] In agricultural mechanized operations, harrowing is an important link in soil tillage. The automatic driving system of agricultural machinery can greatly improve the operation efficiency of harrowing. Most of the existing navigation systems for diagonal harrowing path planning methods are limited to regular terrains, such as rectangular plots and square plots, and cannot meet the needs of irregular plots such as polygonal plots and concave polygonal plots for diagonal harrowing path planning. However, in actual farm operation scenarios, the vast majority of plots are irregular plots. Therefore, the current diagonal harrowing operation path planning method severely limits the actual application range of the agricultural machinery navigation system and fails to fully meet the diverse needs of farmers in harrowing operations. Summary of the Invention

[0003] In order to be based on the actual operation needs of users, be compatible with regular and irregular, concave and convex polygonal plots, improve the efficiency of agricultural operations, and reduce the driving fatigue of operators, the present application provides a diagonal harrowing path planning method, device, equipment, medium and agricultural machinery.

[0004] In a first aspect, the present application provides a diagonal harrowing path planning method, including:

[0005] S1. Based on the harrowing starting point, obtain a plurality of first working lines planned at a first working line angle and a plurality of second working lines planned at a second working line angle in the target plot, and the plurality of first working lines intersect with the plurality of second working lines;

[0006] S2. For any current working line among the plurality of first working lines or the plurality of second working lines, obtain a plurality of candidate starting points closest to the end point of the current working line, and each candidate starting point corresponds to a candidate working line;

[0007] S3. Based on a preset cost function, obtain the path cost corresponding to each candidate working line, and use the candidate working line with the lowest path cost as the target working line;

[0008] S4. For each current working line, obtain the sub-path between the current working line and the corresponding target working line;

[0009] S5. Use the target working line as the new current working line, and repeat S2 to S4 until no candidate starting point closest to the end point of any new current working line can be obtained. Based on the obtained sub-paths, obtain the total planned path.

[0010] The beneficial effects of the present application are as follows: The first working line angle or the second working line angle of the working line in diagonal harrowing can be customarily adjusted according to soil characteristics, so as to facilitate optimizing the soil breaking effect. Based on the cost function, the candidate working line with the lowest path cost can be dynamically selected, enabling the agricultural machine to move from the current working line to the target working line along the optimal turning path, thereby reducing the ineffective movement of the agricultural machine, decreasing the total length of the sub-path, reducing the fuel consumption of the agricultural machine, and improving the efficiency of agricultural operations. By connecting each sub-path, the total planned path can be obtained, and the autonomous navigation of the agricultural machine can be realized based on the total planned path, improving the efficiency of agricultural operations and reducing the driving fatigue of the operator.

[0011] Further, before obtaining multiple first working lines planned at the first working line angle and multiple second working lines planned at the second working line angle in the target plot based on the harrowing starting point, it further includes:

[0012] Obtaining the initial boundary data of the target plot and the minimum circumscribed rectangle corresponding to the initial boundary data;

[0013] Based on the preset Douglas-Peucker algorithm, obtaining the contracted boundary corresponding to the target plot, where the contracted boundary is the boundary of the contracted plot obtained by contracting the initial boundary data according to the preset contraction distance, so as to obtain multiple first working lines and multiple second working lines based on the minimum circumscribed rectangle and the contracted boundary.

[0014] The beneficial effect of adopting the above further solution is that by performing data point simplification processing on the initial boundary data, the density of data points is reduced, and the unnecessary computational burden in navigation is decreased.

[0015] Further, for each current working line, obtaining the sub-path between the current working line and the corresponding target working line includes:

[0016] For each current working line, using the Dubins curve to plan the turning path between the current working line and the corresponding target working line, and obtaining the sub-path based on the turning path, the path corresponding to the current working line, and the path corresponding to the target working line.

[0017] The beneficial effect of adopting the above further solution is that by using the Dubins curve, smooth connection between the current working line and the target working line is achieved.

[0018] Further, based on the preset cost function, obtaining the path cost corresponding to each candidate working line includes:

[0019] For each of the candidate operation lines, obtain the turning type corresponding to the candidate operation line and the cost function corresponding to the turning type;

[0020] For each of the candidate operation lines, based on the cost function, obtain the path cost corresponding to the candidate operation line, so as to compare the path costs of each candidate operation line and obtain the candidate operation line with the lowest path cost.

[0021] The beneficial effect of adopting the above further solution is: setting corresponding cost functions for different turning types, and selecting the candidate operation line with the lowest path cost as the optimized target operation line.

[0022] Further, the turning type is the first type, the second type, the third type or the fourth type, and the cost function is the first function corresponding to the first type, the second function corresponding to the second type, the third function corresponding to the third type or the fourth function corresponding to the fourth type;

[0023] The first type is a reverse turning type in which the total turning angle between the current operation line and the corresponding candidate operation line satisfies a preset first angle relationship, and the first angle relationship is expressed as:

[0024]

[0025] Or,

[0026]

[0027] Wherein, represents the angle between the current operation line and the inner contraction boundary, represents the angle between the candidate operation line and the inner contraction boundary, represents the angle of the current operation line relative to the horizontal direction;

[0028] The second type is a turning type in which the total turning angle between the current operation line and the corresponding candidate operation line satisfies a preset second angle relationship, the current operation line and the corresponding candidate operation line are parallel, and the traveling direction of the path corresponding to the current operation line is opposite to the traveling direction of the path corresponding to the candidate operation line, and the second angle relationship is expressed as:

[0029]

[0030] The third type is a turning type in which the total turning angle between the current operation line and the corresponding candidate operation line satisfies a preset third angle relationship, the current operation line and the corresponding candidate operation line have different operation line angles and are obliquely intersecting, and the third angle relationship is expressed as:

[0031]

[0032] Or,

[0033]

[0034] When the total turning angles between the current operation line and the corresponding candidate operation lines do not satisfy the first angular relationship, the second angular relationship, and the third angular relationship, the turning type is the fourth type.

[0035] The beneficial effect of adopting the above further solution is that according to the total turning angles between operation lines, the turning types are divided into four types, and the cost functions are designed respectively based on these four turning types, which provides an important reference for optimizing the operation path, reducing the turning time, and ensuring smoothness.

[0036] Further, for any current operation line among the multiple first operation lines or the multiple second operation lines, obtaining multiple candidate starting points closest to the end point of the current operation line includes:

[0037] Based on a pre-constructed KD tree, taking the end point of the current operation line as the query point, starting from the root node of the KD tree, recursively searching in the left and right subtrees of the KD tree to obtain multiple nearest intersections in the input data set that are not in the taboo list, and taking the multiple nearest intersections as the candidate starting points respectively. The input data set includes the intersections of all operation lines and the inner contraction boundary, and the taboo list is used to store the currently processed or disabled intersections.

[0038] The beneficial effect of adopting the above further solution is that through the pre-constructed KD tree, the nearest neighbor search for subsequent intersections not in the taboo list can be accelerated, quickly locking a group of candidate starting points closest to the end point of the current operation line, and reducing the path planning time.

[0039] In a second aspect, the present application provides a diagonal harrowing path planning device, including:

[0040] An operation line acquisition module, configured to obtain multiple first operation lines planned at a first operation line angle and multiple second operation lines planned at a second operation line angle in a target plot based on a harrowing starting point, and the multiple first operation lines and the multiple second operation lines intersect with each other;

[0041] A starting point acquisition module, configured to obtain, for any current operation line among the multiple first operation lines or the multiple second operation lines, multiple candidate starting points closest to the end point of the current operation line, and each candidate starting point corresponds to a candidate operation line;

[0042] Obtain a target line module, and based on a preset cost function, obtain the path cost corresponding to each of the candidate operation lines, and use the candidate operation line with the lowest path cost as the target operation line;

[0043] Generate a path module, which is used to obtain a sub-path between each current operation line and the corresponding target operation line;

[0044] A repeated execution module, which is used to use the target operation line as the new current operation line, and repeat the processing from the starting point obtaining module to the path generation module until no candidate starting point closest to the end point of any new current operation line can be obtained, and based on the obtained sub-paths, obtain the total planned path.

[0045] In a third aspect, the present application provides an electronic device, including a processor and a memory, and the processor is coupled to the memory;

[0046] The processor is used to execute a computer program stored in the memory, so that the electronic device executes the method according to any one of the first aspects.

[0047] In a fourth aspect, the present application provides a computer-readable storage medium, including a computer program or instruction, and when the computer program or instruction runs on a computer, the computer is caused to execute the method according to any one of the first aspects.

[0048] In a fifth aspect, the present application provides an agricultural machine for diagonal harrowing path planning of navigation autonomous operation, including the electronic device described in the third aspect and a vehicle body, and the electronic device is communicatively connected to the vehicle body to control the vehicle body to perform harrowing operations according to the total planned path. Description of the Drawings

[0049] Figure 1 It is a schematic flow chart of the diagonal harrowing path planning method according to the embodiment of the present application;

[0050] Figure 2 It is a schematic diagram showing different operation lines in the target plot according to the embodiment of the present application;

[0051] Figure 3 It is a schematic diagram showing the turning path according to the embodiment of the present application;

[0052] Figure 4 It is a schematic diagram showing the total planned path according to the embodiment of the present application;

[0053] Figure 5 It is a schematic path diagram corresponding to the first type of turning type according to the embodiment of the present application;

[0054] Figure 6Schematic diagram of the path corresponding to the second type of turning in the embodiment of the present application;

[0055] Figure 7 Schematic diagram of the path corresponding to the third type of turning in the embodiment of the present application;

[0056] Figure 8 Schematic diagram of the path corresponding to the fourth type of turning in the embodiment of the present application;

[0057] Figure 9 Structural block diagram of the diagonal harrowing path planning device in the embodiment of the present application;

[0058] Figure 10 Structural block diagram of the electronic device in the embodiment of the present application;

[0059] Figure 11 Schematic diagram of the display interface of the intelligent display terminal in the embodiment of the present application. Detailed implementation manners

[0060] The present application will be further described in detail below with reference to the accompanying drawings.

[0061] The embodiment of the present application provides a diagonal harrowing path planning method, which can be executed by a device. The device can be a server or a terminal device. The server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a desktop computer, etc., but is not limited thereto.

[0062] As Figure 1 shown, a diagonal harrowing path planning method with an electronic device as the execution subject, the main process of the method is described as follows (Steps S1 to S5):

[0063] Step S1: Based on the harrowing starting point, obtain a plurality of first working lines planned at a first working line angle and a plurality of second working lines planned at a second working line angle in the target plot. The plurality of first working lines and the plurality of second working lines intersect with each other.

[0064] As Figure 2 shown, in this embodiment, a plurality of parallel first working lines can form a set of working lines, which can be defined as set A. Similarly, a plurality of parallel second working lines can form a set of working lines, which can be defined as set B. The distance between every two adjacent first working lines in set A can be one working width, and the distance between every two adjacent second working lines in set B can be one working width. The user can customize and adjust the first working line angle or the second working line angle of the working lines in the diagonal harrowing according to the soil characteristics, so as to facilitate optimizing the soil breaking effect.

[0065] The target plot is the plot that needs to be harrowed currently. According to the harrowing starting point selected by the user, multiple operation lines of group A and group B corresponding to the target plot are generated.

[0066] As Figure 2 shown, in this embodiment, before step S1, it may further include: obtaining the initial boundary data of the target plot and the minimum bounding rectangle corresponding to the initial boundary data; based on the preset Douglas-Peucker algorithm, obtaining the contracted boundary corresponding to the target plot, where the contracted boundary is the boundary of the contracted plot obtained by contracting the initial boundary data according to a preset contraction distance, so as to obtain multiple first operation lines and multiple second operation lines based on the minimum bounding rectangle and the contracted boundary.

[0067] After the tractor driver turns on the autonomous navigation and determines that the diagonal harrowing function key starts, the tractor can be manually controlled to run around the edge of the target plot. During this period, the positioning module in the tractor will record the current position of the tractor in real time, and then record the complete initial boundary data and feed it back to the electronic device. It should be noted that the shape of the target plot may be irregular, so the figure enclosed by the plot boundary obtained according to the initial boundary data of the target plot may also be an irregular figure, and the harrowing starting point can be any point on the initial boundary data.

[0068] However, the collected data points corresponding to the initial boundary data are usually too dense, including every tiny bend and turn of the plot, which will bring unnecessary computational burden to the electronic device when directly used for tractor navigation. Therefore, the Douglas-Peucker algorithm can be used to simplify the collected data points, and while ensuring the basic features of the polygon of the target plot, the number of vertices of the polyline or polygon is reduced as much as possible. The basic features may include the overall trend of the boundary of the polygon of the target plot.

[0069] Among them, the specific implementation method of obtaining the minimum bounding rectangle corresponding to the initial boundary data is as follows: perform a convex hull calculation on the initial boundary data of the target plot to obtain the smallest convex polygon containing all points in the initial boundary data; obtain the minimum bounding rectangle of the convex polygon, and use the minimum bounding rectangle as the minimum bounding rectangle corresponding to the initial boundary data. Among them, the convex hull of the boundary data of the plot can be calculated by the Graham scan method or the Jarvis march method to obtain the smallest convex polygon.

[0070] After obtaining the processed polygon, according to the set shrinkage distance, the shrinkage boundary of the target plot for actual operation can be obtained. The shrinkage distance can be set as: L = 0.5×W + S, where L represents the shrinkage distance, W represents the operation width, and S represents the safety distance, reducing the possibility of agricultural machinery colliding with the plot edge. Through the automatic generation of the shrinkage boundary and the intersecting operation line groups, the complete coverage of the target plot by the planned path is ensured, and the missed harrowing rate and repeated harrowing rate are reduced.

[0071] According to the first operation line angle and the second operation line angle, multiple first operation lines and multiple second operation lines are planned in the minimum bounding rectangle, and then the multiple first operation lines and multiple second operation lines are trimmed so that each operation line shrinks from the boundary of the minimum bounding rectangle to the shrinkage boundary along the corresponding operation line angle. The trimmed multiple first operation lines are used as the multiple first operation lines corresponding to the target plot, and the trimmed multiple second operation lines are used as the multiple second operation lines corresponding to the target plot.

[0072] Step S2: For any current operation line among the multiple first operation lines or the multiple second operation lines, obtain multiple candidate starting points that are the closest to the end point of the current operation line. Each candidate starting point corresponds to a candidate operation line.

[0073] The end point of the current operation line is the turning starting point of the turning path between the current operation line and the next operation line, and the candidate starting point is the turning end point of the turning path. At the same time, the candidate starting point is the starting point where the agricultural machinery needs to travel on the next operation line.

[0074] Step S2 may include: Based on a pre-constructed KD tree, using the end point of the current operation line as the query point, starting from the root node of the KD tree, recursively searching in the left and right subtrees of the KD tree to obtain multiple nearest intersections in the input data set that are not in the taboo list, and using the multiple nearest intersections as the candidate starting points respectively. The input data set includes all intersections of the operation lines and the shrinkage boundary, and the taboo list is used to store the intersections that have been processed or disabled currently.

[0075] Specifically, obtain all intersections of the operation lines and the shrinkage boundary, and use the multiple intersections as the input data set of the pre-constructed KD tree. The intersections represent the potential starting points and potential ending points of the operation lines where the agricultural machinery can drive in and out; the KD tree (k-dimensional tree) is a data structure used to organize points in a k-dimensional space. It is a special binary tree mainly used for queries in a multi-dimensional space.

[0076] Set a taboo list. The taboo list is used to store the intersection points in the currently processed or disabled input dataset. The intersection points in the taboo list can be marked as "visited", thus avoiding repeated selection of these intersection points during the subsequent path generation process, ensuring the uniqueness of the path, and reducing the operation risk.

[0077] Based on the pre-constructed KD tree, take the end point of the current operation line as the query point. When it is necessary to find the n nearest intersection points to the query point, start from the root node of the KD tree and recursively search in the left and right subtrees of the KD tree to obtain multiple nearest intersection points not in the taboo list, and use the multiple nearest intersection points as the candidate starting points respectively.

[0078] In this embodiment, the root node is the top-level node of the KD tree, representing the initial division of the entire data space. The root node divides the entire input dataset into two subspaces (left subtree and right subtree). When searching for the nearest neighbor intersection points, start recursively searching downward from the root node. The left and right subtrees can subdivide the data space layer by layer, enabling the search range to be quickly narrowed. There is a hierarchical relationship between the nodes in the KD tree. The KD tree realizes efficient data organization and search by dividing the space layer by layer. The nodes below the root node can be called child nodes, including the nodes of the left subtree and the right subtree. Each child node can further divide the space represented by its parent node to form smaller subspaces. The root node is located on the first layer, its child nodes are located on the second layer, and the child nodes of the child nodes are located on the third layer, and so on. The level of each node determines its depth in the space division.

[0079] Through the pre-constructed KD tree, the nearest neighbor search for the subsequent intersection points not in the taboo list can be accelerated, quickly locking a group of candidate starting points closest to the end point of the current operation line, and reducing the path planning time.

[0080] The candidate operation line can be parallel to the current operation line, that is, the two belong to the operation lines of the same operation line group; the candidate operation line can also intersect with the current operation line, that is, the two belong to the operation lines of different operation line groups. The candidate operation line can be an operation line adjacent to the current operation line. Due to the irregular shape of the target plot, the candidate operation line can also be an operation line not adjacent to the current operation line.

[0081] Step S3: Based on the preset cost function, obtain the path cost corresponding to each candidate operation line, and use the candidate operation line with the lowest path cost as the target operation line.

[0082] In this embodiment, based on the cost function, the candidate operation line with the lowest path cost can be dynamically selected, enabling the agricultural machinery to move from the current operation line to the target operation line with the optimal turning path, thereby reducing the ineffective movement of the agricultural machinery, reducing the total length of the sub-path, reducing the fuel consumption of the agricultural machinery, and improving the efficiency of agricultural operations.

[0083] Step S4: For each of the current working lines, obtain the sub-path between the current working line and the corresponding target working line;

[0084] Step S5: Take the target working line as the new current working line, and repeat S2 to S4 until no candidate starting point closest to the end point of any of the new current working lines can be obtained. Based on the obtained sub-paths, obtain the overall planned path.

[0085] After generating the sub-path corresponding to the current working line each time, check whether there are still unprocessed candidate starting points and corresponding target working lines. If no qualified candidate starting points and corresponding target working lines are found, it means that the diagonal harrowing plan for the target plot is completed. Connecting the sub-paths can obtain the overall planned path, so as to realize the autonomous navigation of agricultural machinery based on the overall planned path, improve the efficiency of agricultural operations, and reduce the driving fatigue of the operator.

[0086] As Figure 3 shown, in this embodiment, step S4 may specifically include: for each of the current working lines, use the Dubins curve to plan the turning path between the current working line and the corresponding target working line, and based on the turning path, the path corresponding to the current working line, and the path corresponding to the target working line, obtain the sub-path. It is easy to understand that Figure 3 the working line angles of the current working line and the target working line are different.

[0087] Based on the Dubins algorithm, plan the turning path between the end point of the current working line and the starting point of the target working line, so that the agricultural machinery can turn without exceeding the inner shrinkage boundary. By introducing the Dubins curve, smooth connection between the current working line and the target working line is realized.

[0088] As Figure 4 shown, connecting the sub-paths can obtain the overall planned path.

[0089] In this embodiment, step S3 may specifically include: for each of the candidate working lines, obtain the turning type corresponding to the candidate working line and the cost function corresponding to the turning type; for each of the candidate working lines, based on the cost function, obtain the path cost corresponding to the candidate working line, and compare the path costs to obtain the candidate working line with the lowest path cost.

[0090] The turning type corresponding to the candidate working line is the turning type corresponding to the turning path formed between the candidate working line and the current working line, and the corresponding relationship between each turning type and different cost functions is stored in the electronic device.

[0091] The path cost is the output value of the cost function. By comprehensively considering factors such as turning time, turning smoothness, reducing the heavy harrow, and avoiding crossing boundaries, corresponding cost functions are set for different turning types, and the candidate working line with the lowest path cost is selected as the optimized target working line.

[0092] As Figures 5 to 8 shown, in this embodiment, during the process of designing different working line connection strategies in diagonal harrowing operations, according to the total turning angle between working lines, the turning types can be divided into four types, that is, any one of the first type, the second type, the third type, or the fourth type. The cost function is the first function corresponding to the first type, the second function corresponding to the second type, the third function corresponding to the third type, or the fourth function corresponding to the fourth type. The cost function is designed based on these four turning types respectively, which provides an important reference for optimizing the working path, reducing the turning time, and ensuring smoothness.

[0093] As Figure 5 shown, the first type is a reverse turning type where the total turning angle between the current working line and the corresponding candidate working line satisfies a preset first angle relationship, and the first angle relationship is expressed as:

[0094]

[0095] Or,

[0096]

[0097] Wherein, represents the angle between the current working line and the inner contraction boundary, represents the angle between the candidate working line and the inner contraction boundary, represents the angle of the current working line relative to the horizontal direction, Figure 5 The inner contraction boundary can be parallel to the horizontal direction. Due to the irregular shape of the target plot, there is a situation where the inner contraction boundary is not parallel to the horizontal direction.

[0098] In this embodiment, the turning method of the first type can correspond to the highest priority level. According to different path lengths (i.e., the connection length between the current working line and the candidate working line), the turning form will be different. Considering the inner contraction of the working line, the minimum turning distance threshold corresponding to the turning method of the first type can be expressed as:

[0099] Wherein, represents the turning radius of the agricultural machine, represents the angle of the current working line relative to the horizontal direction.

[0100] According to the path length , the minimum turning distance threshold and the preset maximum allowable search distance , the maximum allowable search distance is a constant set by a person, that is, the threshold parameter set in path planning, which is used to limit the farthest connection distance acceptable for the agricultural machinery when switching operation lines. The first function can be expressed as:

[0101]

[0102] Among them, represents the preset penalty coefficient, represents the path length, represents the minimum turning distance threshold.

[0103] Such as Figure 6 shown, the second type is the turning type in which the total turning angle between the current operation line and the corresponding candidate operation line satisfies a preset second angle relationship. The current operation line and the corresponding candidate operation line are parallel, and the traveling direction of the path corresponding to the current operation line is opposite to the traveling direction of the path corresponding to the candidate operation line. The second angle relationship is expressed as:

[0104]

[0105] Among them, represents the angle between the current operation line and the inner contraction boundary, represents the angle between the candidate operation line and the inner contraction boundary. Figure 6 The inner contraction boundary in can be parallel to the horizontal direction.

[0106] When the turning type is the second type, the current operation line is parallel to the target operation line but in the opposite direction, and the agricultural machinery needs to turn to enter the next operation row. Although the turning amplitude of this kind of turning is large, it can still be optimized to shorten the U-turn path in some cases, which is suitable for the switching of long operation lines and is the second preferred choice of users. Considering the inner contraction of the operation line, the minimum turning distance threshold corresponding to the turning method of the second type can be expressed as:

[0107]

[0108] Among them, represents the turning radius of the agricultural machinery, represents the operation width, represents the width adjustment coefficient (which needs to be calibrated manually), represents the angle between the current operation line and the inner contraction boundary.

[0109] According to the path length and the minimum turning distance threshold , the second function can be expressed as:

[0110]

[0111] wherein, and respectively represent penalty coefficients with different numerical values, represents the path length, represents the minimum turning distance threshold.

[0112] As Figure 7 shown, the third type is the turning type in which the total turning angle between the current operation line and the corresponding candidate operation line satisfies a preset third angle relationship. The operation line angles of the current operation line and the corresponding candidate operation line are different and skew. The third angle relationship is expressed as:

[0113]

[0114] Or,

[0115]

[0116] wherein, represents the angle between the current operation line and the inner contraction boundary, represents the angle between the candidate operation line and the inner contraction boundary, represents the angle of the current operation line relative to the horizontal direction. Figure 7 The inner contraction boundary in

[0117] can be parallel to the horizontal direction. When the turning type is the third type, the current operation line and the candidate operation line come from different operation groups and are skew to each other. This turning method requires a large-angle turn. The total turning angle from the current operation line to the candidate operation line satisfies: Or . The turn of the third type can be used as the third choice of the user.

[0118] Whether there is an intersection point between the current operation line and the candidate operation line within the inner contraction boundary, the calculation logic of the corresponding path cost is different. The path cost calculation logic of the turn of the third type mainly considers the intersection point between the operation lines, the turning span and its impact on the path length and cost. When the turning type is the third type, the minimum turning threshold should ensure that the path distance is not lower than the safe range. Therefore, the minimum turning threshold corresponding to the turning method of the third type

[0119]

[0120] Among them, represents the turning radius adjustment coefficient (which needs to be calibrated manually), represents the angle of the current working line relative to the horizontal direction, represents the turning radius of the agricultural machinery.

[0121] The third function can be expressed as:

[0122]

[0123] Among them, and respectively represent penalty coefficients with different values, represents the distance from the end point of the current working line to the intersection point, represents the distance from the candidate starting point corresponding to the candidate working line to the intersection point, represents the path length, represents the minimum turning threshold.

[0124] As Figure 8 shown, when the total turning angles between the current working line and the corresponding candidate working line do not satisfy the first angle relationship, the second angle relationship, and the third angle relationship, the turning type is the fourth type.

[0125] When the total turning angle between the current working line and the candidate working line is any angle other than the above first type, second type, and third type, it is usually used for agricultural machinery to cross the plot and enter the target working zone. The sub-path generated based on this turning type has the characteristics of a large turning angle, a large turning radius, and a long turning path, and is suitable for situations where a large change in the traveling direction is required, such as crossing plots. The minimum turning distance corresponding to the turning method of the fourth type can be expressed as:

[0126]

[0127] Among them, represents the turning radius adjustment coefficient (which needs to be calibrated manually), represents the turning radius of the agricultural machinery.

[0128] The fourth function can be expressed as:

[0129]

[0130] Among them, and respectively represent penalty coefficients with different values, represents the distance from the starting point of the current working line (i.e., the turning end point of the previous turning path) to the corresponding contracted boundary, Indicates the distance between the candidate starting point corresponding to the candidate operation line (i.e., the turning end point of the previous turning path) and the corresponding inner contraction boundary. Indicates the path length. Indicates the minimum turning threshold.

[0131] This solution comprehensively considers factors such as turning smoothness, reducing reharrowing, and avoiding crossing boundaries. It sets corresponding cost functions for different turning types, and selects the candidate operation line with the lowest path cost as the optimized target operation line. It can effectively handle various types of plots, such as regular and irregular, concave and convex polygons, support the operation line to go online at any point of the plot, and achieve a low reharrowing rate, a low missed harrowing rate, and a reduction in the number of bulb turns in the overall planning, significantly improving the efficiency and intelligent level of agricultural machinery operations.

[0132] Based on the same technical concept, the present application also provides a diagonal harrowing path planning device, as Figure 9 shown. The diagonal harrowing path planning device 200 mainly includes:

[0133] An operation line acquisition module 201, configured to obtain, based on the harrowing starting point, a plurality of first operation lines planned at a first operation line angle and a plurality of second operation lines planned at a second operation line angle in the target plot, and the plurality of first operation lines and the plurality of second operation lines intersect with each other;

[0134] A starting point acquisition module 202, configured to, for any current operation line among the plurality of first operation lines or the plurality of second operation lines, obtain a plurality of candidate starting points that are the closest to the end point of the current operation line, and each candidate starting point corresponds to a candidate operation line;

[0135] A target line acquisition module 203, configured to obtain the path cost corresponding to each candidate operation line based on a preset cost function, and use the candidate operation line with the lowest path cost as the target operation line;

[0136] A path generation module 204, configured to, for each current operation line, obtain a sub-path between the current operation line and the corresponding target operation line;

[0137] A repeated execution module 205, configured to use the target operation line as the new current operation line, and repeat the processing from the starting point acquisition module to the path generation module until no candidate starting point closest to the end point of any new current operation line can be obtained, and obtain the total planned path based on the obtained sub-paths.

[0138] Optionally, before the operation line acquisition module 201, it further includes:

[0139] An external rectangle acquisition module, configured to acquire initial boundary data of the target plot and the minimum external rectangle corresponding to the initial boundary data;

[0140] A shrinking processing module, configured to obtain a shrunk boundary corresponding to the target plot based on a preset Douglas - Peucker algorithm, where the shrunk boundary is the boundary of the shrunk plot obtained by shrinking the initial boundary data according to a preset shrinking distance, so as to obtain a plurality of the first working lines and a plurality of the second working lines based on the minimum external rectangle and the shrunk boundary.

[0141] Optionally, the path generation module 204 includes:

[0142] A turning planning sub - module, configured to, for each of the current working lines, use a Dubins curve to plan a turning path between the current working line and the corresponding target working line, and obtain the sub - path based on the turning path, the path corresponding to the current working line, and the path corresponding to the target working line.

[0143] Optionally, the target line acquisition module 203 includes:

[0144] An acquisition type sub - module, configured to, for each of the candidate working lines, acquire the turning type corresponding to the candidate working line and the cost function corresponding to the turning type;

[0145] A cost calculation sub - module, configured to, for each of the candidate working lines, obtain the path cost corresponding to the candidate working line based on the cost function, and compare the path costs to obtain the candidate working line with the lowest path cost.

[0146] Optionally, the turning type is the first type, the second type, the third type, or the fourth type, and the cost function is the first function corresponding to the first type, the second function corresponding to the second type, the third function corresponding to the third type, or the fourth function corresponding to the fourth type;

[0147] The first type is a reverse turning type in which the total turning angle between the current working line and the corresponding candidate working line satisfies a preset first angle relationship, and the first angle relationship is expressed as:

[0148]

[0149] Or,

[0150]

[0151] Wherein, represents the angle between the current working line and the shrunk boundary, Represents the angle between the to-be-selected operation line and the retracted boundary. Represents the angle of the current operation line relative to the horizontal direction;

[0152] The second type is a turning type where the total turning angle between the current operation line and the corresponding to-be-selected operation line satisfies a preset second angle relationship. The current operation line and the corresponding to-be-selected operation line are parallel, and the traveling direction of the path corresponding to the current operation line is opposite to the traveling direction of the path corresponding to the to-be-selected operation line. The second angle relationship is expressed as:

[0153]

[0154] The third type is a turning type where the total turning angle between the current operation line and the corresponding to-be-selected operation line satisfies a preset third angle relationship. The current operation line and the corresponding to-be-selected operation line have different operation line angles and are obliquely intersecting. The third angle relationship is expressed as:

[0155]

[0156] Or,

[0157] When the total turning angle between the current operation line and the corresponding to-be-selected operation line does not satisfy the first angle relationship, the second angle relationship, and the third angle relationship, the turning type is the fourth type.

[0158] Optionally, the starting point acquisition module 202 includes:

[0159] A KD-tree search sub-module, which is used to, based on a pre-constructed KD-tree, take the end point of the current operation line as a query point, start from the root node of the KD-tree, recursively search in the left and right sub-trees of the KD-tree, obtain multiple nearest intersection points in the input data set that are not in the taboo list, and use the multiple nearest intersection points as the to-be-selected starting points respectively. The input data set includes the intersection points of all operation lines and the retracted boundary, and the taboo list is used to store the currently processed or disabled intersection points.

[0160] In one example, the modules in any of the above devices may be one or more integrated circuits configured to implement the above methods. For example: one or more application specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0161] For another example, when the modules in the device can be implemented in the form of a processing element scheduler, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processors that can call programs. For another example, these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0162] In this application, names may be assigned to various objects such as various messages / information / devices / network elements / systems / devices / actions / operations / processes / concepts, etc. It can be understood that these specific names do not constitute a limitation on the relevant objects, and the assigned names may change with factors such as scenarios, contexts, or usage habits. The understanding of the technical meaning of the technical terms in this application should be mainly determined from the functions and technical effects embodied / executed in the technical solution.

[0163] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices, and modules described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0164] Those of ordinary skill in the art can realize that the modules and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0165] Based on the same technical concept, this application also provides an electronic device, as Figure 10 shown, the electronic device 300 includes a processor 301 and a memory 302, and may further include one or more of an information input / output (I / O) interface 303, a communication component 304, and a communication bus 305.

[0166] Among them, the processor 301 is used to control the overall operation of the electronic device 300 to complete all or part of the steps in the above diagonal harrowing path planning method; the memory 302 is used to store various types of data to support the operation of the electronic device 300. These data may include, for example, instructions for any application or method operating on the electronic device 300, as well as application-related data. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic memory, flash memory, one or more of a magnetic disk or an optical disc.

[0167] The I / O interface 303 provides an interface between the processor 301 and other interface modules. The above other interface modules may be a keyboard, a mouse, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 304 is used to test the wired or wireless communication between the electronic device 300 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them. Therefore, the corresponding communication component 304 may include: a Wi-Fi component, a Bluetooth component, an NFC component.

[0168] The communication bus 305 may include a path for transmitting information between the above components. The communication bus 305 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 305 can be divided into an address bus, a data bus, a control bus, etc.

[0169] The electronic device 300 can be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components, and is used to execute the diagonal harrowing path planning method given in the above embodiments.

[0170] The electronic device 300 can include, but is not limited to, mobile terminals such as digital broadcast receivers, PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), etc., and fixed terminals such as digital TVs, desktop computers, etc., and can also be a server, etc.

[0171] Based on the same technical concept, the present application also provides a 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 diagonal harrowing path planning method are implemented.

[0172] The computer-readable storage medium can include various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks or optical discs, etc.

[0173] Based on the same technical concept, the present application also provides an agricultural machine for diagonal harrowing path planning of navigation autonomous operation, including the above-mentioned electronic device and a vehicle body. The electronic device is communicatively connected to the vehicle body to control the vehicle body to perform harrowing operations according to the overall planned path.

[0174] Specifically, the agricultural machine further includes a receiver, a domain controller, an electric steering wheel, a positioning module, a decision-making module, a communication module, and a control module. The positioning module is used to realize real-time positioning of the current position coordinates of the agricultural machine based on the positioning board in the receiver, obtain the boundary data of the plot during the process of enclosing the plot by the agricultural machine, and record the path traveled by the agricultural machine; the decision-making module is used to obtain the real-time heading of the agricultural machine through the positioning information, and judge the path closest to the agricultural machine according to the heading and positioning points, generate an operation guiding line, and send it to the control module to guide the agricultural machine to accurately complete the entire path.

[0175] The communication module is used to transmit corresponding data in real time according to the corresponding communication protocols for the receiver, domain controller, and electric power steering. The control module is used to enable the agricultural machine to accurately follow a preset path during operation, thereby improving operation efficiency and quality, reducing duplicate and omitted operation areas, and enhancing operation accuracy.

[0176] Among them, the positioning module can rely on the combined positioning of GPS and Beidou, and this positioning module can be integrated into the receiver; the decision-making module, communication module, and control module can all be integrated into the domain controller; the electric power steering serves as the execution module and receives the communication instructions sent by the communication module to achieve automatic navigation of the vehicle body.

[0177] As Figure 11 shown, the agricultural machine may further include an intelligent display terminal, which can display information such as the operation path, width, starting point of harrowing, and ending point of harrowing.

[0178] The term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device.

[0179] Furthermore, the terms "first" and "second" are used for descriptive purposes only and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may expressly or implicitly include at least one of such features. In the description of this application, "a plurality" means at least two, such as two, three, etc., unless otherwise expressly and specifically defined.

[0180] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0181] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A diagonal harrowing path planning method, characterized in that: include: S1, based on the harrowing starting point, obtaining a plurality of first operating lines planned at a first operating line angle and a plurality of second operating lines planned at a second operating line angle in a target plot, wherein the plurality of the first operating lines and the plurality of the second operating lines intersect each other; S2, for any current operation line among the plurality of the first operation lines or the plurality of the second operation lines, obtaining a plurality of candidate starting points closest to the end point of the current operation line, each of the candidate starting points corresponding to a candidate operation line; S3, based on a preset cost function, obtaining the path cost corresponding to each of the candidate operation lines, and taking the candidate operation line with the lowest path cost as the target operation line; S4, for each of the current operation lines, obtaining a subpath between the current operation line and the corresponding target operation line; S5, taking the target operation line as the new current operation line, repeatedly executing S2 to S4 until no candidate starting point closest to the end point of any new current operation line can be obtained, and obtaining a total planned path based on each of the obtained sub-paths; Before obtaining a plurality of first working lines planned at a first working line angle and a plurality of second working lines planned at a second working line angle in a target plot based on the harrowing starting point, the method further includes: obtaining initial boundary data of the target plot and a minimum circumscribed rectangle corresponding to the initial boundary data; obtaining an indentation boundary corresponding to the target plot based on a preset Douglas-Peucker algorithm, the indentation boundary being a boundary of the indented plot obtained after the initial boundary data is indented according to a preset indentation distance, so as to obtain a plurality of the first working lines and a plurality of the second working lines based on the minimum circumscribed rectangle and the indentation boundary; The method of obtaining the path cost corresponding to each of the candidate operation lines based on the preset cost function includes: for each of the candidate operation lines, obtaining the turning type corresponding to the candidate operation line and the cost function corresponding to the turning type; for each of the candidate operation lines, obtaining the path cost corresponding to the candidate operation line based on the cost function, so as to compare the path costs and obtain the candidate operation line with the lowest path cost.

2. A diagonal harrowing path planning method according to claim 1, characterized in that: For each current operation line, obtaining a subpath between the current operation line and a corresponding target operation line includes: For each current work line, the Dubins curve is used to plan the turning path between the current work line and the corresponding target work line, and the sub-path is obtained based on the turning path, the path corresponding to the current work line and the path corresponding to the target work line.

3. A diagonal harrowing path planning method according to claim 1, characterized in that: The turn type is a first type, a second type, a third type or a fourth type, and the cost function is a first function corresponding to the first type, a second function corresponding to the second type, a third function corresponding to the third type or a fourth function corresponding to the fourth type; The first type is a type of out-of-direction turning in which the total turning angle between the current operation line and the corresponding operation line to be selected satisfies a preset first angle relationship, and the first angle relationship is expressed as: or, in, represents the angle between the current operation line and the indentation boundary, represents the angle between the selected operation line and the indentation boundary, Indicates the angle of the current operating line relative to the horizontal direction; The second type is a turning type in which the total turning angle between the current operation line and the corresponding operation line to be selected satisfies a preset second angle relationship, the current operation line and the corresponding operation line to be selected are parallel, and the travel direction of the path corresponding to the current operation line is opposite to the travel direction of the path corresponding to the operation line to be selected, and the second angle relationship is expressed as: The third type is a turning type in which the total turning angle between the current operation line and the corresponding operation line to be selected satisfies a preset third angle relationship. The operation line angles of the current operation line and the corresponding operation line to be selected are different and oblique. The third angle relationship is expressed as: or, When the total turning angle between the current operation line and the corresponding to-be-selected operation line does not satisfy the first angle relationship, the second angle relationship and the third angle relationship, the turning type is the fourth type.

4. A diagonal harrowing path planning method according to claim 1, characterized in that: For any current operation line among the plurality of the first operation lines or the plurality of the second operation lines, obtaining a plurality of candidate starting points closest to the end point of the current operation line comprises: Based on the pre-constructed KD tree, the end point of the current work line is used as the query point, starting from the root node of the KD tree, the left and right subtrees of the KD tree are searched recursively to obtain multiple nearest intersections in the input data set that are not in the taboo list, and the multiple nearest intersections are respectively used as the candidate starting points. The input data set includes all the intersections of the work lines and the indented boundary, and the taboo list is used to store the currently processed or disabled intersections.

5. A diagonal harrowing path planning device, characterized in that: include: An operation line acquisition module is used to acquire, based on a harrowing starting point, a plurality of first operation lines planned at a first operation line angle and a plurality of second operation lines planned at a second operation line angle in a target plot, wherein the plurality of first operation lines and the plurality of second operation lines intersect each other; A starting point acquisition module is used to acquire, for any current operation line among the plurality of the first operation lines or the plurality of the second operation lines, a plurality of candidate starting points closest to the end point of the current operation line, each of the candidate starting points corresponding to a candidate operation line; The target line acquisition module acquires the path cost corresponding to each of the candidate operation lines based on a preset cost function, and takes the candidate operation line with the lowest path cost as the target operation line; A path generation module is used to obtain, for each current operation line, a sub-path between the current operation line and a corresponding target operation line; A repeated execution module is used to take the target operation line as a new current operation line, repeat the processing from the acquisition of starting point module to the generation of path module, until no candidate starting point closest to the end point of any new current operation line can be obtained, and obtain the total planned path based on each of the obtained sub-paths; Before the operation line acquisition module, it also includes: an external rectangle acquisition module, which is used to acquire the initial boundary data of the target plot and the minimum external rectangle corresponding to the initial boundary data; an indentation processing module, which is used to acquire the indentation boundary corresponding to the target plot based on a preset Douglas-Peucker algorithm, wherein the indentation boundary is the boundary of the indented plot obtained after the initial boundary data is indented according to a preset indentation distance, so as to obtain a plurality of the first operation lines and a plurality of the second operation lines based on the minimum external rectangle and the indentation boundary; The module for obtaining the target line includes: an acquisition type submodule, which is used to obtain, for each of the candidate operation lines, the turning type corresponding to the candidate operation line and the cost function corresponding to the turning type; and a cost calculation submodule, which is used to obtain, for each of the candidate operation lines, the path cost corresponding to the candidate operation line based on the cost function, so as to compare the path costs and obtain the candidate operation line with the lowest path cost.

6. An electronic device, characterized in that: comprising a processor and a memory, wherein the processor is coupled to the memory; The processor is configured to execute a computer program stored in the memory, so that the electronic device executes the method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The method comprises a computer program or an instruction, which, when executed on a computer, causes the computer to execute the method according to any one of claims 1 to 4.

8. An agricultural machine capable of autonomous navigation and diagonal harrowing path planning, characterized in that: It comprises the electronic device as claimed in claim 6 and a vehicle body, wherein the electronic device is communicatively connected with the vehicle body to control the vehicle body to perform a raking operation according to a generally planned path.

Images