Route planning method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application relate to the technical field of unmanned aerial vehicles, and provide a flight path planning method and device, electronic equipment and a storage medium. The flight path is planned according to the specific position of each fruit tree point, so that targeted operation can be realized according to the differences of each fruit tree, precise spraying of each fruit tree is realized, and the first flight path is planned from any one vertex of the minimum circumscribed polygon formed by all fruit tree points, and the flight path segment formed by adjacent fruit tree points and having a distance difference greater than a distance threshold (i.e., a flight path segment with a long distance between fruit tree points) and / or the flight path segment formed by adjacent fruit tree points and having an angle greater than an angle threshold (i.e., a flight path segment with a corner) between adjacent flight path segments is deleted from the first flight path. Meanwhile, the operation flight path is generated when the first cutting result meets the set requirement, so that an operation flight path that is suitable for the planting orientation of fruit trees, has a small number of corners, and has a distance between adjacent fruit trees that is not too long can be generated, and the operation efficiency is improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of unmanned aerial vehicles, in particular, to a flight path planning method and device, an electronic device, and a storage medium. BACKGROUND

[0002] Currently, the path planning for spraying and pest control of fruit tree points using agricultural unmanned aerial vehicles mostly adopts full coverage planning, that is, only the field information is considered, and the specific fruit tree point positions are not considered for full-range operation. Such an operation mode has the problems of pesticide waste and low operation efficiency due to invalid flight segments. On the other hand, the spraying and pest control of fruit trees are not specific and comprehensive enough, and cannot achieve targeted operation according to the differences of each fruit tree. SUMMARY

[0003] Embodiments of the present application aim to provide a flight path planning method and device, an electronic device, and a storage medium, which can achieve precise spraying of each fruit tree while improving operation efficiency.

[0004] To achieve the above-mentioned purpose, the technical solutions adopted by embodiments of the present application are as follows:

[0005] In a first aspect, the embodiments of the present application provide a flight path planning method, which comprises:

[0006] obtaining position information of a plurality of fruit tree points in a field to be operated;

[0007] generating a minimum circumscribed polygon of all fruit tree points based on the position information of the plurality of fruit tree points;

[0008] starting from any one vertex of the minimum circumscribed polygon, performing greedy planning based on the shortest distance for all fruit tree points to obtain a first flight path;

[0009] performing cutting processing on the first flight path to obtain a first cutting result; the cutting processing is used to delete flight segments formed by adjacent fruit tree points and having a distance difference greater than a distance threshold with adjacent flight segments, and / or flight segments formed by adjacent fruit tree points and having an angle greater than an angle threshold with adjacent flight segments;

[0010] if the first cutting result meets a set requirement, generating an operation flight path based on the first cutting result.

[0011] Optionally, the step of starting from any one vertex of the minimum circumscribed polygon, performing greedy planning based on the shortest distance for all fruit tree points to obtain a first flight path comprises:

[0012] taking any one vertex of the minimum circumscribed polygon as a target point;

[0013] determining a reference fruit tree point closest to the target point, and connecting the target point and the reference fruit tree point;

[0014] replacing the target point with the reference fruit tree point, and returning to execute the step of determining a reference fruit tree point closest to the target point until all fruit tree points are traversed, to obtain the first flight path.

[0015] Optionally, the first cutting result includes each first candidate fruit tree point and each first candidate flight segment, and the method further comprises:

[0016] If the first cutting result does not meet the set requirement, performing a shortest distance-based greedy planning on all first candidate fruit tree points and all first candidate flight segments to obtain a second flight path;

[0017] performing the cutting processing on the second flight path to obtain a second cutting result;

[0018] If the second cutting result meets the set requirement, generating a work flight path based on the second cutting result.

[0019] Optionally, the step of performing a shortest distance-based greedy planning on all first candidate fruit tree points and all first candidate flight segments to obtain a second flight path comprises:

[0020] taking any one vertex of the minimum circumscribed polygon as a target point;

[0021] determining a reference point closest to the target point, wherein the reference point is any one of the first candidate fruit tree points or an end point of any one of the first candidate flight segments;

[0022] connecting the target point and the reference point;

[0023] replacing the target point with the reference point or an end point of the first candidate flight segment other than the reference point, and returning to execute the step of determining a reference point closest to the target point until all first candidate fruit tree points and all first candidate flight segments are traversed, to obtain the second flight path.

[0024] Optionally, the method further comprises:

[0025] If the second cutting result does not meet the set requirement, performing a shortest distance-based greedy planning on a current cutting result by changing a vertex of the minimum circumscribed polygon, until a second cutting result meeting the set requirement is obtained.

[0026] Optionally, the method further comprises:

[0027] If the second cutting result obtained after traversing all vertices of the minimum circumscribed polygon still does not satisfy the set requirement, a third flight path is obtained by using a sliding prediction method to perform a shortest-distance-based greedy planning on the current cutting result;

[0028] The third flight path is subjected to the cutting processing to obtain a third cutting result;

[0029] If the third cutting result satisfies the set requirement, a work flight path is generated based on the third cutting result.

[0030] Optionally, the current cutting result includes each current candidate fruit tree point and each current candidate flight segment;

[0031] The step of using the sliding prediction method to perform the shortest-distance-based greedy planning on the current cutting result to obtain the third flight path includes:

[0032] Starting from any one vertex of the minimum circumscribed polygon, connecting the vertex and any one of the current candidate fruit tree points or any one end point of the current candidate flight segment closest to the vertex;

[0033] Obtaining position information of each traversed fruit tree point;

[0034] According to the position information of each traversed fruit tree point, predicting position information of a next virtual point;

[0035] Determining a reference point with the minimum distance to other untraversed fruit tree points, the reference point being any one of the current candidate fruit tree points or any one end point of the current candidate flight segment;

[0036] Connecting the reference point and the last traversed fruit tree point, and returning to perform the step of obtaining the position information of each traversed fruit tree point until all current candidate fruit tree points and all current candidate flight segments are traversed to obtain the third flight path.

[0037] Optionally, the method further includes:

[0038] If the third cutting result does not satisfy the set requirement, the shortest-distance-based greedy planning on the current cutting result is performed by changing the vertices of the minimum circumscribed polygon and using the sliding prediction method until the third cutting result satisfying the set requirement is obtained.

[0039] Optionally, the method further includes:

[0040] If the third cutting result obtained after traversing all the vertices of the minimum circumscribed polygon still does not satisfy the set requirement, the distance threshold and / or the angle threshold are increased, and the step of performing the shortest distance-based greedy planning on all the fruit tree points from any one vertex of the minimum circumscribed polygon is performed again until the first cutting result or the second cutting result or the third cutting result that satisfies the set requirement is obtained.

[0041] Optionally, the method further comprises:

[0042] evaluating the cutting result, wherein the cutting result is the first cutting result or the second cutting result or the third cutting result.

[0043] Optionally, the cutting result comprises each candidate fruit tree point and each candidate flight segment, and the step of evaluating the cutting result comprises:

[0044] calculating a ratio between the number of all the candidate fruit tree points and the number of all the fruit tree points to obtain an evaluation value;

[0045] if the evaluation value is less than a set evaluation threshold, it is determined that the cutting result satisfies the set requirement;

[0046] if the evaluation value is not less than the set evaluation threshold, it is determined that the cutting result does not satisfy the set requirement.

[0047] Optionally, the cutting result is the first cutting result or the second cutting result or the third cutting result, and the cutting result comprises each candidate fruit tree point and each candidate flight segment.

[0048] generating an operation flight path based on the cutting result, comprising:

[0049] inserting each candidate fruit tree point into the candidate flight segment closest to itself;

[0050] connecting all the candidate flight segments according to the shortest distance to form the operation flight path.

[0051] In a second aspect, the embodiments of the present application further provide a flight path planning device, which comprises:

[0052] an acquisition module configured to acquire position information of a plurality of fruit tree points in a land to be operated;

[0053] a generation module configured to generate a minimum circumscribed polygon of all the fruit tree points based on the position information of the plurality of fruit tree points;

[0054] a flight path planning module configured to:

[0055] starting from any one vertex of the minimum circumscribed polygon, performing a shortest distance-based greedy planning on all the fruit tree points to obtain a first flight path;

[0056] performing cutting processing on the first flight path to obtain a first cutting result; the cutting processing is used to delete a flight path formed by adjacent fruit tree points and having a distance difference greater than a distance threshold with an adjacent flight path, and / or a flight path formed by adjacent fruit tree points and having an angle greater than an angle threshold with an adjacent flight path;

[0057] if the first cutting result meets a set requirement, generating a work flight path based on the first cutting result.

[0058] In a third aspect, an electronic device is provided, including a processor and a memory, the memory being configured to store a program, and the processor being configured to implement the flight path planning method in the first aspect when executing the program.

[0059] In a fourth aspect, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program, and the computer program is configured to implement the flight path planning method in the first aspect when executed by a processor.

[0060] Compared with the prior art, the flight path planning method, device, electronic device and storage medium provided by the embodiments of the present application first generate a minimum circumscribed polygon of all fruit tree points based on position information of the plurality of fruit tree points in the to-be-worked land; then, starting from any one vertex of the minimum circumscribed polygon, perform a shortest distance-based greedy planning on all the fruit tree points to obtain a first flight path; and then perform cutting processing on the first flight path to delete a flight path formed by adjacent fruit tree points and having a distance difference greater than a distance threshold with an adjacent flight path, and / or a flight path formed by adjacent fruit tree points and having an angle greater than an angle threshold with an adjacent flight path, to obtain a first cutting result, and generate a work flight path based on the first cutting result when the first cutting result meets a set requirement. That is, the flight path is planned according to the specific position of each fruit tree point, so that targeted work can be implemented according to the differences between each fruit tree, and precise spraying of each fruit tree is realized. At the same time, the first flight path is planned starting from any one vertex of the minimum circumscribed polygon formed by all the fruit tree points, and the flight path formed by adjacent fruit tree points and having a distance difference greater than a distance threshold with an adjacent flight path (i.e., the flight path with a long distance between fruit tree points) and / or the flight path formed by adjacent fruit tree points and having an angle greater than an angle threshold with an adjacent flight path (i.e., the flight path with a corner) is deleted, and the work flight path is generated when the first cutting result meets the set requirement, so that a work flight path that is suitable for the planting orientation of the fruit trees, has a small number of corners, and has a distance between adjacent fruit trees that is not too long can be generated, and the work efficiency is improved. BRIEF DESCRIPTION OF DRAWINGS

[0061] Figure 1A flowchart of a route planning method provided by an embodiment of the application is shown Figure 1 .

[0062] Figure 2 An effect diagram of fruit tree recognition provided by an embodiment of the application is shown.

[0063] Figure 3 An example diagram of original data information provided by an embodiment of the application is shown.

[0064] Figure 4 An example of a route planning process provided by an embodiment of the application is shown Figure 1 .

[0065] Figure 5 An example of a route planning process provided by an embodiment of the application is shown Figure 2 .

[0066] Figure 6 An example of a route planning process provided by an embodiment of the application is shown Figure 3 .

[0067] Figure 7 A flowchart of a route planning method provided by an embodiment of the application is shown Figure 2 .

[0068] Figure 8 An example of a route planning process provided by an embodiment of the application is shown Figure 4 .

[0069] Figure 9 An example of a route planning process provided by an embodiment of the application is shown Figure 5 .

[0070] Figure 10 An example of a route planning process provided by an embodiment of the application is shown Figure 6 .

[0071] Figure 11 An example diagram of a work route provided by an embodiment of the application is shown.

[0072] Figure 12 A block diagram of a route planning device provided by an embodiment of the application is shown.

[0073] Figure 13 A block diagram of an electronic device provided by an embodiment of the application is shown.

[0074] Icon: 100-route planning device; 101-acquisition module; 102-generation module; 103-route planning module; 10-electronic device; 11-processor; 12-memory; 13-bus. DETAILED DESCRIPTION

[0075] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.

[0076] Currently, the path planning for spraying and pest control of fruit tree points using agricultural unmanned aerial vehicles usually adopts the following two methods:

[0077] The first method is full coverage planning, that is, only the field information is considered, and full-range operation is performed without considering the specific positions of the fruit tree points. This operation method has the problems of pesticide waste and low operation efficiency due to invalid flight segments. On the other hand, the spraying and pest control of the fruit trees are not specific and comprehensive enough, and cannot achieve targeted operation according to the differences of each fruit tree.

[0078] The second method is to superimpose the results of fruit tree recognition on the basis of full coverage planning, that is, the flight path of full coverage planning is adjusted according to the results of fruit tree recognition. However, since only the flight path of full coverage planning is adjusted, there are still too many invalid flight segments. In addition, due to the different scenes of different fruit trees, the planting distance and planting orientation of each row of fruit trees need to be designed or adjusted by the user on site. The intelligent level is not high enough, the universality is not strong, the robustness to different fruit trees is low, the arrangement of actual fruit trees is not considered comprehensively, and the planning effect is not good for some scenes with multiple orientations or higher complexity of fruit tree arrangement, resulting in low operation efficiency.

[0079] To solve the above problems, the embodiments of the present application plan a flight path according to the specific position of each fruit tree point, so as to achieve targeted operation according to the differences of each fruit tree, and realize precise spraying of each fruit tree. At the same time, the first flight path is planned from any one vertex of the minimum circumscribed polygon formed by all fruit tree points, and the segments in the first flight path that are formed by adjacent fruit tree points and have a distance difference greater than a distance threshold (i.e., the segments with long distance between fruit tree points) and / or the segments in the first flight path that are formed by adjacent fruit tree points and have an angle greater than an angle threshold (i.e., the segments with corners) are deleted. At the same time, the operation flight path is generated when the first cutting result meets the set requirements, so as to generate an operation flight path that adapts to the planting orientation of the fruit trees, has fewer turning angles, and has a distance between adjacent fruit trees that is not too long, thereby improving the operation efficiency.

[0080] The flight path planning technology provided by the embodiments of the present application can be applied to electronic devices. The electronic devices can be smart phones, tablet computers, notebook computers, desktop computers, servers, etc., or unmanned aerial vehicles (such as agricultural unmanned aerial vehicles, forestry unmanned aerial vehicles, surveying unmanned aerial vehicles, etc.). Users can select different devices according to actual application scenarios, and the embodiments of the present application do not make any limitation in this regard.

[0081] The embodiments of the present application will be described in detail below with reference to the drawings.

[0082] Please refer toFigure 1 , Figure 1 A flowchart of a route planning method provided by an embodiment of the present application is shown. The route planning method is applied to an electronic device and can include the following steps:

[0083] S101, position information of a plurality of fruit tree points in a to-be-worked land plot is obtained.

[0084] In this embodiment, the position information of the fruit tree points in the to-be-worked land plot can be obtained by identifying each fruit tree in the to-be-worked land plot using visual technology and artificial intelligence technology.

[0085] Alternatively, a surveying drone can be used to pre-fly the to-be-worked land plot (for example, an orchard), and visual technology and artificial intelligence technology can be used to identify the position information of each fruit tree in the to-be-worked land plot. For example, as shown in Figure 2 , each fruit tree in the to-be-worked land plot is identified as shown by the small circles. Figure 2 After that, the obtained position information of each fruit tree point can be fed back to the user for confirmation of whether there is misidentification or missed identification, and whether the position information needs to be corrected. After the user confirms that there is no error, the position information of each fruit tree point is saved, for example, the position information is converted into a json format file and uploaded to the cloud.

[0086] It should be noted that the position information of the plurality of fruit tree points obtained in step S101 is the position information of each fruit tree point that needs to be worked (for example, sprayed). For example, it can be the position information of all fruit tree points in the to-be-worked land plot, or the position information of all fruit tree points in a certain area of the to-be-worked land plot. The user can flexibly select according to actual needs, and the present application does not make any limitation in this regard.

[0087] That is, if the fruit trees in the to-be-worked land plot need to be sprayed with pesticides, the position information of each fruit tree point in the to-be-worked land plot is obtained; if most of the areas in the to-be-worked land plot have completed pesticide spraying, only a certain area needs to be supplemented, and the position information of each fruit tree point in the area is obtained. For example, as shown in Figure 3 , the original data information includes the position information of each fruit tree point that needs to be worked in the to-be-worked land plot.

[0088] S102, based on the position information of the plurality of fruit tree points, a minimum circumscribed polygon of all fruit tree points is generated.

[0089] In this embodiment, after obtaining the position information of the plurality of fruit tree points that need to be worked, a minimum circumscribed polygon enclosing the plurality of fruit tree points can be generated based on the position information of the plurality of fruit tree points.

[0090] Optionally, the minimum circumscribed polygon can be a minimum circumscribed rectangle, a minimum circumscribed pentagon, a minimum circumscribed hexagon, etc., and the number of sides of the minimum circumscribed polygon is not limited herein, as long as all the fruit tree points that need to be worked on are included. The following embodiments are described by taking the minimum circumscribed rectangle as an example.

[0091] It should be noted that the existing minimum circumscribed polygon algorithm can be used to generate the minimum circumscribed polygon that encloses all the fruit tree points, and the embodiments of the present application will not be described again.

[0092] S103, starting from any one vertex of the minimum circumscribed polygon, performing greedy planning based on the shortest distance on all fruit tree points to obtain a first flight route.

[0093] In the present embodiment, after generating the minimum circumscribed polygon of all fruit tree points based on the position information of the plurality of fruit tree points, the coordinates of each vertex of the minimum circumscribed polygon can be obtained. Since the position information of each fruit tree point that needs to be worked on and the minimum circumscribed polygon of all fruit tree points are known at this time, the shortest distance point planning can be used to generate a first flight route that starts from any one vertex of the minimum circumscribed polygon and connects each fruit tree point.

[0094] It should be noted that starting from any one vertex of the minimum circumscribed polygon, performing greedy planning based on the shortest distance on all fruit tree points is to make the final work flight route adapt to the fruit tree planting orientation. For example, if a work flight route cannot be planned starting from a vertex of the minimum circumscribed polygon, it means that the current predicted fruit tree planting orientation can not be appropriate, and the vertex of the minimum circumscribed polygon needs to be replaced and re-planned. In this way, the user does not need to specify the fruit tree planting orientation, but the work flight route that adapts to the fruit tree planting orientation can be finally generated based on the minimum circumscribed polygon.

[0095] In the present embodiment, starting from any one vertex of the minimum circumscribed polygon, performing greedy planning based on the shortest distance on all fruit tree points, i.e., the shortest distance point planning, means that each fruit tree point is taken as a separate individual, and starting from any one vertex of the minimum circumscribed polygon, the next fruit tree point is found based on the shortest distance each time until the last fruit tree point, and a first flight route is obtained.

[0096] In an alternative implementation, the process of starting from any one vertex of the minimum circumscribed polygon, performing greedy planning based on the shortest distance on all fruit tree points to obtain a first flight route in step S103 can include sub-steps S1031-S1033.

[0097] S1031, taking any one vertex of the minimum circumscribed polygon as a target point.

[0098] S1032, determine the reference fruit tree point closest to the target point, and connect the target point and the reference fruit tree point.

[0099] S1033, replace the target point with the reference fruit tree point, and return to execute sub-step S1032 until all fruit tree points are traversed to obtain the first flight path.

[0100] It can be understood that after returning to execute sub-step S1032, step S1033 will continue to be executed until all fruit tree points are traversed to obtain the first flight path.

[0101] For example, please refer to Figure 4 From any one vertex A of the minimum circumscribed polygon, find the fruit tree point 1 closest to the vertex A, and connect the vertex A and the fruit tree point 1; then, continue to find the fruit tree point 2 closest to the fruit tree point 1, and connect the fruit tree point 1 and the fruit tree point 2; and so on, until the last fruit tree point 6, to obtain the first flight path A→1→2→3→7→8→4→5→9→10→6.

[0102] S104, cutting processing is performed on the first flight path to obtain a first cutting result; the cutting processing is used to delete a flight path formed by adjacent fruit tree points and having a distance difference greater than a distance threshold between adjacent flight segments, and / or a flight path formed by adjacent fruit tree points and having an angle greater than an angle threshold between adjacent flight segments.

[0103] In this embodiment, from Figure 4 It can be seen that the first flight path obtained by using the shortest distance point planning has more corners, resulting in high energy consumption of the unmanned aerial vehicle and low work efficiency, and the first flight path is unreasonable in the eyes of the user and does not conform to the direction of fruit tree planting.

[0104] Therefore, after the first flight path is obtained by using the shortest distance point planning, cutting processing needs to be performed on the first flight path to delete a flight path formed by adjacent fruit tree points and having a distance difference greater than a distance threshold between adjacent flight segments (i.e., a flight path with a long distance between fruit tree points) and / or a flight path formed by adjacent fruit tree points and having an angle greater than an angle threshold between adjacent flight segments (i.e., a flight path with a corner).

[0105] Optionally, the distance threshold can be 3-5 m, and the angle threshold can be 30-60°. In this embodiment, the distance threshold and the angle threshold can be smaller at the beginning of flight path planning, for example, the distance threshold is 3 m and the angle threshold is 30°. If the work flight path cannot be planned, the distance threshold and the angle threshold are gradually increased. In this way, a tight-to-loose planning process is adopted, so that the final obtained work flight path has fewer corners and the distance between adjacent fruit trees is not too long.

[0106] In practice, the planting interval distance of different types of fruit trees in different regions is not fixed, but the distance difference of the line segment formed between adjacent fruit trees in the same plot is often small. For example, referring to FIG. 1, a fruit tree point 1 and a fruit tree point 2 form a line segment S1, the fruit tree point 2 and a fruit tree point 3 form a line segment S2, and the distance difference between S1 and S2 is usually close. Figure 5

[0107] Therefore, the distance difference of the line segment formed between adjacent fruit tree points can be sequentially judged from the starting point of the first line to determine whether the distance difference is greater than the distance threshold value, so as to delete the line segment with a long distance between the fruit tree points. For example, if the distance difference of S2-S1 is greater than the distance threshold value, it means that the distance between the fruit tree point 2 and the fruit tree point 3 is too long, and S2 is deleted at this time. If the distance difference of S2-S1 is not greater than the distance threshold value, S1 and S2 are connected to form a candidate line segment.

[0108] Meanwhile, the angle of the line segment formed between adjacent fruit trees planted in the same row is often small, and the angle of the line segment formed between adjacent fruit trees planted in different rows is often large. For example, referring again to FIG. 1, the fruit tree point 1 and the fruit tree point 2 form a line segment S1, the fruit tree point 2 and the fruit tree point 3 form a line segment S2, and the fruit tree point 3 and the fruit tree point 7 form a line segment S3. The angle between S1 and S2 is small, and the angle between S2 and S3 is large. Figure 5

[0109] Therefore, the angle of the line segment formed between adjacent fruit tree points can be sequentially judged from the starting point of the first line to determine whether the angle is greater than the angle threshold value, so as to delete the line segment with a bend. For example, as shown in FIG. 2, S2 and S3 form an angle, and it is judged whether the angle is greater than the angle threshold value. If it is greater than the angle threshold value, it means that there is a bend, and S2 is deleted at this time. Correspondingly, the angle formed by S1 and S2 is not greater than the angle threshold value, and S1 and S2 are connected to form a candidate line segment. Figure 5

[0110] In this embodiment, the line segment formed between adjacent fruit tree points and having a distance difference greater than the distance threshold value from the adjacent line segment is deleted, that is, the line segment with a long distance between the fruit tree points is deleted. The line segment formed between adjacent fruit tree points and having an angle greater than the angle threshold value from the adjacent line segment is deleted, that is, the line segment at the bend is deleted. Therefore, the operation line with less bending times and the distance between adjacent fruit trees not too long can be ensured.

[0111] In this embodiment, after the cutting processing of the first line is performed, the cutting result containing the candidate fruit tree points and the candidate line segments is obtained, and each candidate line segment is straight and no bending line segment exists.

[0112] For example, the first line in FIG. 1 is subjected to cutting processing, and the cutting result is as shown in FIG. 2. Figure 4 Figure 6 ​​​​As shown, it includes one candidate fruit tree point and four candidate flight segments.

[0113] S105, if the first cutting result meets the set requirement, generating a work flight path based on the first cutting result.

[0114] In this embodiment, after the first flight path is cut to obtain the first cutting result, if the number of candidate fruit tree points in the first cutting result is large, the work flight path generated based on the first cutting result will have many turns. Therefore, it is necessary to first determine whether there are a large number of candidate fruit tree points in the first cutting result, and if not, then generate a work flight path based on the first cutting result.

[0115] Optionally, the set requirement can be that the ratio of the number of all candidate fruit tree points in the first cutting result to the number of all fruit tree points obtained in step S101 is less than a set value, for example, less than 5% to 10%, etc.

[0116] In a possible case, if there are a large number of candidate fruit tree points in the first cutting result, in order to avoid many turns in the work flight path, the work flight path cannot be directly generated based on the first cutting result, at this time, further planning based on the first cutting result is needed, that is, further planning of the candidate fruit tree points and the candidate flight segments.

[0117] Therefore, on the basis of Figure 1 , please refer to Figure 7 After step S104, the flight path planning method provided by the embodiment of the application further includes steps S106-S108.

[0118] S106, if the first cutting result does not meet the set requirement, performing a greedy planning based on the shortest distance on all first candidate fruit tree points and all first candidate flight segments to obtain a second flight path.

[0119] In this embodiment, if the first cutting result does not meet the set requirement, a greedy planning based on the shortest distance is performed on all first candidate fruit tree points and all first candidate flight segments from the same vertex (for example, vertex A) in step S103, that is, the current predicted fruit tree planting orientation is kept unchanged, and the number of candidate fruit tree points after cutting is reduced through the shortest distance point line planning.

[0120] In the shortest distance point line planning, the candidate flight segment is taken as a whole, that is, only the two end points of the candidate flight segment are considered, and from any one vertex of the minimum circumscribed polygon, the next point is found based on the shortest distance each time, which can be a candidate fruit tree point or an end point of a candidate flight segment, if it is an end point of a candidate flight segment, the next point is directly found based on the other end point of the candidate flight segment next time, and the process is repeated until all first candidate fruit tree points and all first candidate flight segments are traversed to obtain a second flight path.

[0121] In this way, the candidate flight segment is considered as a whole, and only the two end points of the candidate flight segment are considered, so that the planning time can be effectively shortened and the planning efficiency can be improved.

[0122] In an optional implementation, the process of performing the shortest distance-based greedy planning on all the first candidate fruit tree points and all the first candidate flight segments in step S106 to obtain the second flight route can include sub-steps S1061-S1064.

[0123] S1061, taking any one vertex of the minimum circumscribed polygon as a target point.

[0124] S1062, determining a reference point closest to the target point, wherein the reference point is any one first candidate fruit tree point or an end point of any one first candidate flight segment.

[0125] S1063, connecting the target point and the reference point.

[0126] S1064, replacing the target point with the reference point or an end point other than the reference point on the first candidate flight segment, and returning to execute the sub-step S1062 until all the first candidate fruit tree points and all the first candidate flight segments are traversed to obtain the second flight route.

[0127] It can be understood that after returning to execute the sub-step S1062, the steps S1063-S1064 will be continuously executed until all the first candidate fruit tree points and all the first candidate flight segments are traversed to obtain the second flight route.

[0128] For example, please refer to Figure 8 From any one vertex A of the minimum circumscribed polygon, since the vertex A is an end point of the candidate flight segment L1 at this time, the point closest to the other end point of the candidate flight segment L1 is directly found, which is assumed to be an end point of the candidate flight segment L2, and then the other end point of the candidate flight segment L1 and the end point of the candidate flight segment L2 are connected (as shown by the dashed line in Figure 8 ); then, the point closest to the other end point of the candidate flight segment L2 is continuously found, which is assumed to be a candidate fruit tree point, and then the other end point of the candidate flight segment L2 and the candidate fruit tree point are connected; and the process is continued in this way until all the first candidate fruit tree points and all the first candidate flight segments are traversed to obtain the second flight route as shown in Figure 8 .

[0129] S107, performing cutting processing on the second flight route to obtain a second cutting result.

[0130] S108, if the second cutting result meets the set requirement, generating a work flight route based on the second cutting result.

[0131] In the embodiment, after the second route is obtained by using the shortest distance point line planning, in order to ensure that the generated operation route is adapted to the planting orientation of the fruit trees, has few turns, and the distance between adjacent fruit trees is not too long, the second route also needs to be cut, and it is judged whether the obtained second cutting result meets the set requirement. If the second cutting result meets the set requirement, the operation route is generated based on the second cutting result.

[0132] It should be noted that the process of cutting the second route is similar to the process of cutting the first route in step S104, and the process of judging whether the second cutting result meets the set requirement is similar to the process of judging whether the first cutting result meets the set requirement in step S105. Therefore, the embodiment of the present application will not be described again.

[0133] In a possible case, if the second cutting result does not meet the set requirement, it means that the predicted planting orientation of the fruit trees may not be suitable. In order to avoid that there are many turns in the operation route, the operation route cannot be directly generated based on the second cutting result, and the predicted planting orientation of the fruit trees needs to be changed (that is, the vertex of the minimum circumscribed polygon is changed) and then re-planned.

[0134] Therefore, please refer to the following Figure 7 After step S107, the route planning method provided by the embodiment of the present application further includes step S109.

[0135] In step S109, if the second cutting result does not meet the set requirement, the vertex of the minimum circumscribed polygon is changed, and the current cutting result is planned based on the shortest distance by using the greedy algorithm until the second cutting result that meets the set requirement is obtained.

[0136] It can be understood that the vertex of the minimum circumscribed polygon is changed, for example, the vertex B of the minimum circumscribed polygon is changed, the current cutting result is planned based on the shortest distance by using the greedy algorithm, that is, steps S106-S108 are executed again until the second cutting result that meets the set requirement is obtained, and then the operation route is generated based on the second cutting result.

[0137] In a possible case, if the second cutting result obtained after all the vertices of the minimum circumscribed polygon are changed still does not meet the set requirement, that is, all the predicted planting orientations of the fruit trees have been tried, and the second cutting result that meets the set requirement still cannot be obtained, it means that there are still a large number of candidate fruit tree points in the obtained second cutting result. In order to avoid that there are many turns in the operation route, the operation route cannot be directly generated based on the current second cutting result, and further planning needs to be performed based on the current second cutting result.

[0138] Therefore, please refer to the following Figure 7After step S109, the flight path planning method provided by the embodiment of the present application further includes steps S110-S112.

[0139] S110, if the second cutting result obtained by traversing all vertices of the minimum circumscribed polygon still does not satisfy the set requirement, a shortest distance-based greedy planning is performed on the current cutting result in a sliding prediction manner to obtain a third flight path.

[0140] In the embodiment, if the first cutting result does not satisfy the set requirement, a shortest distance-based greedy planning is performed on the current second cutting result in a sliding prediction manner from the same vertex (for example, vertex A) in step S103, that is, the number of candidate fruit tree points after cutting is reduced through the shortest distance sliding prediction planning according to the initially predicted fruit tree planting orientation.

[0141] In the shortest distance sliding prediction planning, the position of a virtual point needs to be predicted according to the position information of the planned fruit tree points, the prediction manner can be to estimate according to the deviation of the previous fruit tree points, and at the same time, the point with the minimum sum of the distance from itself to other un-planned fruit tree points and the distance from the virtual point to other un-planned fruit tree points among all un-planned fruit tree points is taken as the next point, which can be a candidate fruit tree point or an end point of a candidate flight segment, if it is an end point of a candidate flight segment, all fruit tree points in the candidate flight segment are directly regarded as planned fruit tree points in the next prediction to find the next point, until all candidate fruit tree points and candidate flight segments are traversed to obtain the third flight path.

[0142] In this way, since the next point is found each time according to the position information of the planned fruit tree points to predict a virtual point and the point with the minimum sum of the distance from itself to other un-planned fruit tree points and the distance from the virtual point to other un-planned fruit tree points among all un-planned fruit tree points is taken as the next point, the third flight path to be planned will be more consistent with the flight direction of the unmanned aerial vehicle and more consistent with the planting direction of the fruit trees.

[0143] As can be seen from the foregoing, the shortest distance point planning introduced in steps S103-S105 and the shortest distance point-line planning introduced in steps S106-S108 are both to find the nearest next point, but in practice, the shortest distance point-line planning is combined with the shortest distance point planning to find the nearest next point in the direction of the fruit tree planting orientation. Figure 4For example, taking fruit tree points 2, 3 and 4 as an example, when identifying the positions of the fruit tree points, fruit tree point 3 is missed, so that the positions of the fruit tree points obtained in step S101 are only fruit tree points 2 and 4. In this case, when the next point is searched based on fruit tree point 2, since fruit tree point 3 is missed, the next point found is likely to be fruit tree point 7, which obviously does not conform to the direction of fruit tree planting and needs to be turned. Therefore, in order to avoid the above situation, the shortest distance sliding prediction planning is adopted to predict a virtual point, which is equivalent to the missed fruit tree point 3, so as to assist in finding the next fruit tree point 4, so that the planned route is more consistent with the flight direction of the unmanned aerial vehicle and the direction of fruit tree planting.

[0144] In an alternative implementation, the current cutting result can include each current candidate fruit tree point and each current candidate flight segment, and the process of step S110 of performing the shortest distance-based greedy planning on the current cutting result by using the sliding prediction to obtain the third route can include sub-steps S1101-S1105.

[0145] S1101, starting from any one vertex of the minimum circumscribed polygon, connecting the vertex and the end point of any one current candidate fruit tree point or any one current candidate flight segment closest to the vertex.

[0146] S1102, obtaining the position information of each traversed fruit tree point.

[0147] S1103, predicting the position information of the next virtual point according to the position information of each traversed fruit tree point.

[0148] S1104, determining a reference point between other untraversed fruit tree points, the distance between the reference point and other untraversed fruit tree points being the smallest, the reference point being any one untraversed current candidate fruit tree point or the end point of any one current candidate flight segment.

[0149] S1105, connecting the reference point and the last traversed fruit tree point, and returning to execute sub-step S1102 until all current candidate fruit tree points and all current candidate flight segments are traversed, and the third route is obtained.

[0150] It can be understood that after returning to execute sub-step S1102, steps S1103-S1105 will be continuously executed until all current candidate fruit tree points and all current candidate flight segments are traversed, and the third route is obtained.

[0151] For example, please refer to Figure 9From any one vertex A of the minimum circumscribed polygon, since the vertex A is one end point of the candidate flight segment L1 at this time, the fruit tree points 1, 2, 3 in the candidate flight segment L1 all become the traversed fruit tree points. At this time, according to the position information of the fruit tree points 1, 2, 3, the position of the next virtual point can be predicted. The position of the virtual point can be predicted according to the interval between the fruit tree point 1 and the fruit tree point 2 and the interval between the fruit tree point 2 and the fruit tree point 3 as shown in FIG. 10. Figure 9 Then, among all the un-planned fruit tree points (i.e., fruit tree points 4, 5, 6, 7, 8, 9, 10), the fruit tree point with the smallest sum of the distance from itself to other un-planned fruit tree points and the distance from the virtual point to other un-planned fruit tree points is found, i.e., the fruit tree point 4. The fruit tree point 4 is the reference point in the sub-step S1104. Then, the fruit tree point 4 and the fruit tree point 3 are connected. Since the fruit tree point 4 is one end point of the candidate flight segment L2, the traversed fruit tree points become the fruit tree points 1, 2, 3, 4, 5. According to all or part of the traversed fruit tree points (for example, the fruit tree points 3, 4, 5), the position of the next virtual point can be predicted as shown in FIG. 11. Figure 9 Then, among all the un-planned fruit tree points (i.e., fruit tree points 4, 5, 6, 7, 8, 9, 10), the fruit tree point with the smallest sum of the distance from itself to other un-planned fruit tree points and the distance from the virtual point to other un-planned fruit tree points is found, i.e., the fruit tree point 4. The fruit tree point 4 is the reference point in the sub-step S1104. Then, the fruit tree point 4 and the fruit tree point 3 are connected. Since the fruit tree point 4 is one end point of the candidate flight segment L2, the traversed fruit tree points become the fruit tree points 1, 2, 3, 4, 5. According to all or part of the traversed fruit tree points (for example, the fruit tree points 3, 4, 5), the position of the next virtual point can be predicted as shown in FIG. 11. Figure 9

[0152] S111, the third flight path is cut to obtain a third cutting result.

[0153] S112, if the third cutting result meets the set requirement, generating the operation flight path based on the third cutting result.

[0154] In this embodiment, after the third flight path is obtained by the shortest distance sliding prediction planning, in order to ensure that the operation flight path generated is suitable for the fruit tree planting orientation, has few turns and the distance between adjacent fruit trees is not too long, the third flight path also needs to be cut, and it is judged whether the third cutting result meets the set requirement. If the third cutting result meets the set requirement, the operation flight path is generated based on the third cutting result.

[0155] It should be noted that the process of cutting the third flight path is similar to the process of cutting the first flight path in step S104. The process of judging whether the third cutting result meets the set requirement is similar to the process of judging whether the first cutting result meets the set requirement in step S105. The embodiments of the present application will not be described here.

[0156] In a possible case, if the third cutting result does not meet the set requirement, it means that the predicted fruit tree planting orientation may not be suitable. In order to avoid more turns in the operation flight path, the operation flight path cannot be directly generated based on the third cutting result, and the predicted fruit tree planting orientation (i.e., the vertex of the minimum circumscribed polygon) needs to be changed and then re-planned. ​

[0157] Therefore, please refer to continue Figure 7 After step S111, the route planning method provided by the embodiment of the present application further includes step S113.

[0158] S113, if the third cutting result does not meet the set requirement, the vertex of the minimum circumscribed polygon is changed, and the current cutting result is cyclically planned based on the shortest distance by using the sliding prediction method until the third cutting result meeting the set requirement is obtained.

[0159] It can be understood that the vertex of the minimum circumscribed polygon is changed, for example, starting from the vertex B of the minimum circumscribed polygon, the current cutting result is planned based on the shortest distance by using the sliding prediction method, that is, steps S110-S112 are executed again until the third cutting result meeting the set requirement is obtained, and then the work route is generated based on the third cutting result.

[0160] In a possible case, if the third cutting result obtained after changing all the vertices of the minimum circumscribed polygon still does not meet the set requirement, that is, the predicted planting direction of each fruit tree has been tried, and the third cutting result meeting the set requirement still cannot be obtained, it means that there are still a large number of candidate fruit tree points in the current third cutting result. In order to avoid too many turns in the work route, the work route cannot be directly generated based on the current third cutting result. Since the work route cannot be planned at this time, it means that the distance threshold and the angle threshold set for cutting the route are too strict, and the distance threshold and the angle threshold need to be improved for re-planning.

[0161] Therefore, please refer to continue Figure 7 After step S113, the route planning method provided by the embodiment of the present application further includes step S114.

[0162] S114, if the third cutting result obtained after traversing all the vertices of the minimum circumscribed polygon still does not meet the set requirement, the distance threshold and / or the angle threshold are improved, and step S103 is executed again until the first cutting result or the second cutting result or the third cutting result meeting the set requirement is obtained.

[0163] It can be understood that after step S103 is executed again, steps S104-S114 are continued to be executed until the first cutting result or the second cutting result or the third cutting result meeting the set requirement is obtained, and the work route is generated based on the first cutting result or the second cutting result or the third cutting result.

[0164] That is, if the work flight path still cannot be planned through the processes of steps S101-S113, the distance threshold and the angle threshold used in the flight path cutting process need to be increased (for example, the distance threshold is increased from 3m to 4m, and the angle threshold is increased from 30° to 40°), and the work flight path is re-planned according to the processes of steps S101-S113 after the standard of the flight path cutting process is relaxed. If the work flight path still cannot be planned, the distance threshold and the angle threshold continue to be increased, and so on, until the work flight path is planned.

[0165] It should be noted that there is an upper limit for the increase of the distance threshold and the angle threshold, for example, the distance threshold is 5m and the angle threshold is 60°, so as to ensure that the finally generated work flight path is adapted to the planting direction of the fruit trees, has few turns, and the distance between adjacent fruit trees is not too long.

[0166] From the foregoing, it can be seen that after the first cutting result is obtained by cutting the first flight path, or the second cutting result is obtained by cutting the second flight path, or the third cutting result is obtained by cutting the third flight path, it is necessary to determine whether there are a large number of candidate fruit tree points in the cutting result. If not, the work flight path is generated based on the cutting result.

[0167] Therefore, after step S104, after step S107, and after step S111, the flight path planning method provided in the embodiments of the present application further includes step S10A.

[0168] S10A, evaluating the cutting result, wherein the cutting result is the first cutting result or the second cutting result or the third cutting result.

[0169] It can be understood that after step S104, the first cutting result is evaluated; after step S107, the second cutting result is evaluated; and after step S111, the third cutting result is evaluated.

[0170] In the present embodiment, the cutting result is evaluated, that is, it is determined whether there are a large number of candidate fruit tree points in the cutting result. If there are a large number of candidate fruit tree points in the cutting result, the work flight path cannot be generated based on the cutting result; if there are no a large number of candidate fruit tree points in the cutting result, the work flight path can be generated based on the cutting result.

[0171] In one possible implementation, the cutting result can include each candidate fruit tree point and each candidate flight segment, and the process of evaluating the cutting result in step S10A can include sub-steps S10A1-S10A3.

[0172] S10A1, calculating the ratio between the number of all candidate fruit tree points and the number of all fruit tree points to obtain an evaluation value.

[0173] S10A2, if the evaluation value is less than the set evaluation threshold, it is determined that the cutting result meets the set requirement.

[0174] S10A3, if the evaluation value is not less than the set evaluation threshold, it is determined that the cutting result does not meet the set requirement.

[0175] In this embodiment, the evaluation threshold can be set to 5% to 10%, which can be flexibly set by the user according to the actual fruit tree planting situation (for example, topography, planting orientation, planting spacing, etc.), and the present application does not make any limitation on this.

[0176] In one possible case, the final cutting result that meets the set requirement is obtained, which may contain a small amount of candidate fruit tree points. When generating the operation route based on the cutting result, each independent candidate fruit tree point needs to be inserted into the candidate flight segment closest to itself, and then each candidate flight segment is connected to form the operation route.

[0177] Therefore, the cutting result can be the first cutting result or the second cutting result or the third cutting result, and the cutting result includes each candidate fruit tree point and each candidate flight segment, then the process of generating the operation route based on the cutting result in steps S105, S108 and S112 can include sub-steps S1-S2.

[0178] S1, each candidate fruit tree point is inserted into the candidate flight segment closest to itself.

[0179] In this embodiment, since the candidate flight segment is also obtained by connecting each fruit tree point, taking one candidate fruit tree point as an example, the fruit tree point closest to the candidate fruit tree point can be found in all candidate flight segments first, for example, please refer to Figure 10 , for candidate fruit tree point 4, the closest fruit tree point 3 is found; then, the total length of the candidate flight segment before inserting the candidate fruit tree point into the fruit tree point and the total length of the candidate flight segment after inserting the candidate fruit tree point into the fruit tree point are calculated, for example, the total length of candidate flight segment L1 in the case of inserting candidate fruit tree point 4 before fruit tree point 3, and the total length of candidate flight segment L1 in the case of inserting candidate fruit tree point 4 after fruit tree point 3; then, the candidate fruit tree point is inserted into the candidate flight segment in the way of the smallest total length, for example, the total length of candidate flight segment L1 in the case of inserting candidate fruit tree point 4 after fruit tree point 3 is the smallest, then the candidate fruit tree point 4 is inserted after fruit tree point 3 as shown in Figure 10 .

[0180] S2, all candidate flight segments are connected in the shortest distance to form the operation route.

[0181] In this embodiment, after inserting each candidate fruit tree point into the candidate flight segment closest to it, all candidate flight segments are connected according to the shortest distance, for example, such as... Figure 10 As shown, candidate segment L1 and candidate segment L2 are connected to obtain the operational route.

[0182] For example, following the route planning method described above, for Figure 3 The final operation route is planned for each fruit tree point that needs to be worked on, as shown below. Figure 11 As shown, from Figure 11 As can be seen, the operating route is adapted to the orientation of the fruit trees, has few turns, and the distance between adjacent fruit trees is not too long.

[0183] Compared with the prior art, the route planning method provided in this application has the following advantages:

[0184] First, flight routes are planned according to the specific location of each fruit tree, so that targeted operations can be carried out based on the differences of each fruit tree, achieving precise spraying of each fruit tree.

[0185] Then, the first route is planned starting from any vertex of the smallest bounded polygon formed by all fruit tree points. In the first route, segments formed by adjacent fruit tree points and whose distance difference with adjacent segments is greater than the distance threshold (i.e., segments with long distances between fruit tree points) and / or segments formed by adjacent fruit tree points and whose angle with adjacent segments is greater than the angle threshold (i.e., segments with corners) are deleted. At the same time, the operation route is generated when the first cutting result meets the set requirements. This enables the generation of operation routes that are adapted to the fruit tree planting orientation, have fewer turns, and have shorter distances between adjacent fruit trees, thus improving operation efficiency.

[0186] Third, the route is divided based on the distance difference and angle between adjacent segments, rather than simply based on the distance of the segments. This is more in line with the actual planting conditions of fruit trees and can be adapted to different types of fruit trees in different regions.

[0187] Fourth, it does not require users to specify the orientation of fruit tree planting. Instead, it is planned based on the minimum bounding polygon, and can ultimately generate a working route that adapts to the orientation of fruit tree planting.

[0188] Fifth, if the operation route cannot be planned after shortest distance point planning, shortest distance point line planning, and changing the predicted orientation of the fruit tree points, the shortest distance sliding prediction planning is adopted. By predicting a virtual point to assist in finding the next point, the route planning error caused by missed or misidentified causal tree points can be avoided, and the planned route is more in line with the flight direction of the UAV and the planting direction of the fruit trees.

[0189] In order to perform the above-mentioned method embodiments and respective steps in various possible implementations, an implementation of a route planning device is given below.

[0190] Reference is made to Figure 12 , Figure 12 A block schematic diagram of a route planning device 100 provided by an embodiment of the present application is shown. The route planning device 100 is applied to an electronic device and includes an acquisition module 101, a generation module 102, and a route planning module 103.

[0191] The acquisition module 101 is configured to acquire position information of a plurality of fruit tree points in a to-be-worked land plot.

[0192] The generation module 102 is configured to generate a minimum circumscribed polygon of all the fruit tree points based on the position information of the plurality of fruit tree points.

[0193] The route planning module 103 is configured to:

[0194] perform, starting from an arbitrary vertex of the minimum circumscribed polygon, a shortest-distance-based greedy planning on all the fruit tree points to obtain a first route;

[0195] perform cutting processing on the first route to obtain a first cutting result; the cutting processing is configured to delete a flight segment formed by adjacent fruit tree points and having a distance difference greater than a distance threshold with an adjacent flight segment, and / or a flight segment formed by adjacent fruit tree points and having an angle greater than an angle threshold with an adjacent flight segment;

[0196] generate a work route based on the first cutting result if the first cutting result meets a set requirement.

[0197] Optionally, the route planning module 103 performs the shortest-distance-based greedy planning starting from an arbitrary vertex of the minimum circumscribed polygon to obtain the first route in the following manner:

[0198] taking the arbitrary vertex of the minimum circumscribed polygon as a target point;

[0199] determining a reference fruit tree point closest to the target point and connecting the target point and the reference fruit tree point;

[0200] replacing the target point with the reference fruit tree point and returning to perform the step of determining the reference fruit tree point closest to the target point until all the fruit tree points are traversed to obtain the first route.

[0201] Optionally, the first cutting result includes each first candidate fruit tree point and each first candidate flight segment; the route planning module 103 is further configured to:

[0202] If the first cutting result does not meet the set requirement, a shortest distance-based greedy planning is performed on all the first candidate fruit tree points and all the first candidate flight segments to obtain a second flight route;

[0203] The second flight route is subjected to cutting processing to obtain a second cutting result;

[0204] If the second cutting result meets the set requirement, a work flight route is generated based on the second cutting result.

[0205] Optionally, the flight route planning module 103 performs the shortest distance-based greedy planning on all the first candidate fruit tree points and all the first candidate flight segments to obtain the second flight route in the following manner:

[0206] Taking any one vertex of the minimum circumscribed polygon as a target point;

[0207] Determining a reference point closest to the target point, wherein the reference point is any one first candidate fruit tree point or an end point of any one first candidate flight segment;

[0208] Connecting the target point and the reference point;

[0209] Replacing the target point with the reference point or an end point other than the reference point on the first candidate flight segment, and returning to perform the step of determining the reference point closest to the target point until all the first candidate fruit tree points and all the first candidate flight segments are traversed to obtain the second flight route.

[0210] Optionally, the flight route planning module 103 is further configured to:

[0211] If the second cutting result does not meet the set requirement, the shortest distance-based greedy planning is performed on the current cutting result by changing the vertex of the minimum circumscribed polygon in a loop until the second cutting result meeting the set requirement is obtained.

[0212] Optionally, the flight route planning module 103 is further configured to:

[0213] If the second cutting result obtained after traversing all the vertices of the minimum circumscribed polygon still does not meet the set requirement, the shortest distance-based greedy planning is performed on the current cutting result in a sliding prediction manner to obtain a third flight route;

[0214] The third flight route is subjected to cutting processing to obtain a third cutting result;

[0215] If the third cutting result meets the set requirement, a work flight route is generated based on the third cutting result.

[0216] Optionally, the current cutting result includes each current candidate fruit tree point and each current candidate flight segment; the flight path planning module 103 performs a shortest distance based greedy planning on the current cutting result in a sliding prediction manner to obtain a third flight path, including:

[0217] Starting from any one vertex of the minimum circumscribed polygon, connecting the vertex with an end point of any one current candidate fruit tree point or any one current candidate flight segment closest to the vertex;

[0218] Obtaining position information of each traversed fruit tree point;

[0219] Predicting position information of a next virtual point according to the position information of each traversed fruit tree point;

[0220] Determining a reference point with a minimum distance to other untraversed fruit tree points, the reference point being an end point of any one current candidate fruit tree point or any one current candidate flight segment;

[0221] Connecting the reference point with the last traversed fruit tree point, and returning to the step of obtaining the position information of each traversed fruit tree point until all current candidate fruit tree points and all current candidate flight segments are traversed, to obtain the third flight path.

[0222] Optionally, the flight path planning module 103 is further configured to:

[0223] If the third cutting result does not meet the set requirement, the current cutting result is cyclically planned in a shortest distance based greedy manner in a sliding prediction manner by changing the vertex of the minimum circumscribed polygon until the third cutting result meeting the set requirement is obtained.

[0224] Optionally, the flight path planning module 103 is further configured to:

[0225] If the third cutting result obtained after traversing all vertices of the minimum circumscribed polygon still does not meet the set requirement, the distance threshold and / or the angle threshold are increased, and the step of planning all fruit tree points in a shortest distance based greedy manner from any one vertex of the minimum circumscribed polygon is performed until the first cutting result or the second cutting result or the third cutting result meeting the set requirement is obtained.

[0226] Optionally, the flight path planning module 103 is further configured to:

[0227] Evaluating the cutting result, wherein the cutting result is the first cutting result or the second cutting result or the third cutting result.

[0228] Optionally, the cutting result includes each candidate fruit tree point and each candidate flight segment; the flight planning module 103 performs the evaluation of the cutting result in the following manner:

[0229] calculating a ratio between the number of all candidate fruit tree points and the number of all fruit tree points to obtain an evaluation value;

[0230] if the evaluation value is less than a set evaluation threshold, it is determined that the cutting result meets the set requirement;

[0231] if the evaluation value is not less than the set evaluation threshold, it is determined that the cutting result does not meet the set requirement.

[0232] Optionally, the cutting result is the first cutting result, the second cutting result or the third cutting result, and the cutting result includes each candidate fruit tree point and each candidate flight segment; the flight planning module 103 generates the operation flight route based on the cutting result in the following manner:

[0233] inserting each candidate fruit tree point into the candidate flight segment closest to itself respectively;

[0234] connecting all candidate flight segments according to the shortest distance to form the operation flight route.

[0235] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the flight planning device 100 described above can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0236] Please refer to Figure 13 , Figure 13 A block diagram of an electronic device 10 is shown. The electronic device 10 includes a processor 11, a memory 12 and a bus 13, the processor 11 is connected with the memory 12 through the bus 13.

[0237] The memory 12 is used to store programs, for example Figure 12 The flight planning device 100 shown in the figure includes at least one software function module which can be stored in the memory 12 in the form of software or firmware, and the processor 11 executes the programs to realize the flight planning method disclosed in the foregoing embodiments after receiving the execution instruction.

[0238] The memory 12 can include a high-speed random access memory (RAM), and can also include a non-volatile memory (NVM).

[0239] The processor 11 can be an integrated circuit chip with signal processing capability. In the implementation process, each step of the above method can be completed by the integrated logic circuit of hardware in the processor 11 or the instruction in the form of software. The processor 11 described above can be a general-purpose processor, including a central processing unit (CPU), a microcontroller unit (MCU), a complex programmable logic device (CPLD), a field programmable gate array (FPGA), an embedded ARM, and the like.

[0240] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by the processor 11 to realize the flight path planning method disclosed in the above embodiment.

[0241] To sum up, the flight path planning method, device, electronic equipment and storage medium provided by the embodiment of the present application plan the flight path according to the specific position of each fruit tree point, so that targeted operation can be realized according to the difference of each fruit tree, and accurate spraying of each fruit tree is realized. At the same time, the first flight path is planned from any one vertex of the minimum circumscribed polygon formed by all fruit tree points, and the flight segments formed by adjacent fruit tree points and having a distance difference greater than the distance threshold between adjacent flight segments (i.e., the flight segments with long distance between fruit tree points) and / or the flight segments formed by adjacent fruit tree points and having an angle greater than the angle threshold between adjacent flight segments (i.e., the flight segments with corners) in the first flight path are deleted, and the operation flight path is generated when the first cutting result meets the set requirement, so that the operation flight path that adapts to the planting orientation of the fruit trees, has few corners, and has a distance between adjacent fruit trees that is not too long can be generated, and the operation efficiency is improved.

[0242] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A route planning method characterized by, The method comprises: obtaining position information of a plurality of fruit tree points in a to-be-worked plot; generating a minimum circumscribed polygon of all fruit tree points based on the position information of the plurality of fruit tree points; starting from any one vertex of the minimum circumscribed polygon, performing a shortest-distance-based greedy planning on all fruit tree points to obtain a first flight route; performing cutting processing on the first flight route to obtain a first cutting result, the cutting processing being used to delete a flight segment formed by adjacent fruit tree points and having a distance difference greater than a distance threshold with an adjacent flight segment, and / or a flight segment formed by adjacent fruit tree points and having an angle greater than an angle threshold with an adjacent flight segment; if the first cutting result meets a set requirement, generating a work flight route based on the first cutting result, the set requirement including that a ratio of a number of all first candidate fruit tree points in the first cutting result to a number of all fruit tree points in the to-be-worked plot is less than a set value, and the first cutting result including each first candidate fruit tree point and each first candidate flight segment.

2. The method of claim 1, wherein, The step of starting from any one vertex of the minimum circumscribed polygon, performing a shortest-distance-based greedy planning on all fruit tree points to obtain a first flight route, comprises: taking any one vertex of the minimum circumscribed polygon as a target point; determining a reference fruit tree point closest to the target point and connecting the target point and the reference fruit tree point; replacing the target point with the reference fruit tree point and returning to perform the step of determining a reference fruit tree point closest to the target point until all fruit tree points are traversed to obtain the first flight route.

3. The method of claim 1, wherein, The method further comprises: if the first cutting result does not meet the set requirement, performing a shortest-distance-based greedy planning on all first candidate fruit tree points and all first candidate flight segments to obtain a second flight route; performing the cutting processing on the second flight route to obtain a second cutting result; if the second cutting result meets the set requirement, generating a work flight route based on the second cutting result.

4. The method of claim 3, wherein, The step of performing a shortest-distance-based greedy planning on all first candidate fruit tree points and all first candidate flight segments to obtain a second flight route, comprises: taking any one vertex of the minimum circumscribed polygon as a target point; determining a reference point closest to the target point, wherein the reference point is any one of the first candidate fruit tree points or an end point of any one of the first candidate flight segments; connecting the target point and the reference point; replacing the target point with the reference point or an end point of the first candidate flight segment other than the reference point and returning to perform the step of determining a reference point closest to the target point until all first candidate fruit tree points and all first candidate flight segments are traversed to obtain the second flight route.

5. The method of claim 3, wherein, The method further comprises: if the second cutting result does not meet the set requirement, performing a shortest-distance-based greedy planning on a current cutting result by changing a vertex of the minimum circumscribed polygon in a loop until a second cutting result meeting the set requirement is obtained.

6. The method of claim 5, wherein, The method further comprises: If the second cutting result obtained after traversing all the vertices of the minimum circumscribed polygon still does not satisfy the set requirement, a third route is obtained by using a sliding prediction manner to perform a shortest-distance-based greedy planning on the current cutting result; The third route is subjected to the cutting processing to obtain a third cutting result; If the third cutting result satisfies the set requirement, a work route is generated based on the third cutting result.

7. The method of claim 6, wherein, The current cutting result includes each current candidate fruit tree point and each current candidate flight segment; The step of obtaining the third route by using the sliding prediction manner to perform the shortest-distance-based greedy planning on the current cutting result includes: Starting from any one vertex of the minimum circumscribed polygon, connecting the vertex and any one current candidate fruit tree point or end point of any one current candidate flight segment closest to the vertex; Obtaining position information of each traversed fruit tree point; Predicting position information of a next virtual point according to the position information of each traversed fruit tree point; Determining a reference point with the minimum distance between the virtual point and other untraversed fruit tree points, the reference point being any one current candidate fruit tree point or end point of any one current candidate flight segment; Connecting the reference point and the last traversed fruit tree point, and returning to perform the step of obtaining the position information of each traversed fruit tree point until all the current candidate fruit tree points and all the current candidate flight segments are traversed to obtain the third route.

8. The method of claim 6, wherein, The method further includes: If the third cutting result does not satisfy the set requirement, the shortest-distance-based greedy planning on the current cutting result is performed by changing the vertices of the minimum circumscribed polygon and using the sliding prediction manner until the third cutting result satisfying the set requirement is obtained.

9. The method of claim 8, wherein, The method further includes: If the third cutting result obtained after traversing all the vertices of the minimum circumscribed polygon still does not satisfy the set requirement, the distance threshold and / or the angle threshold are increased, and the step of performing the shortest-distance-based greedy planning on all the fruit tree points starting from any one vertex of the minimum circumscribed polygon is performed until the first cutting result or the second cutting result or the third cutting result satisfying the set requirement is obtained.

10. The method of any one of claims 1-9, wherein, The method further includes: The cutting result is evaluated, wherein the cutting result is the first cutting result or the second cutting result or the third cutting result.

11. The method of claim 10, wherein, The cutting result includes each candidate fruit tree point and each candidate flight segment, and the step of evaluating the cutting result includes: Calculating a ratio between the number of all the candidate fruit tree points and the number of all the fruit tree points to obtain an evaluation value; If the evaluation value is less than a set evaluation threshold, it is determined that the cutting result satisfies the set requirement; If the evaluation value is not less than the set evaluation threshold, it is determined that the cutting result does not satisfy the set requirement.

12. The method of any one of claims 1-9, wherein, The cutting result is the first cutting result or the second cutting result or the third cutting result, and the cutting result includes each candidate fruit tree point and each candidate flight segment; The step of generating the work route based on the cutting result includes: insert each of the candidate fruit tree points into a candidate flight segment closest to the candidate fruit tree point; connect all candidate flight segments according to shortest distances to form the work flight path.

13. A route planning apparatus characterized by comprising: The device comprises: an acquisition module configured to acquire position information of a plurality of fruit tree points in a work plot; a generation module configured to generate a minimum circumscribed polygon of all fruit tree points based on the position information of the plurality of fruit tree points; a flight path planning module configured to: start from any vertex of the minimum circumscribed polygon, perform shortest distance-based greedy planning on all fruit tree points to obtain a first flight path; perform cutting processing on the first flight path to obtain a first cutting result, the cutting processing being configured to delete a flight segment formed by adjacent fruit tree points and having a distance difference greater than a distance threshold with an adjacent flight segment, and / or a flight segment formed by adjacent fruit tree points and having an angle greater than an angle threshold with an adjacent flight segment; if the first cutting result meets a set requirement, generate a work flight path based on the first cutting result, the set requirement including that a ratio of a number of first candidate fruit tree points in the first cutting result to a number of all fruit tree points in the work plot is less than a set value, and the first cutting result includes each first candidate fruit tree point and each first candidate flight segment.

14. An electronic device, comprising: The device comprises a processor and a memory, the memory being configured to store a program, and the processor being configured to implement the flight path planning method according to any one of claims 1-12 when executing the program.

15. A computer-readable storage medium, characterized in that, The device comprises a processor and a memory, the memory being configured to store a program, and the processor being configured to implement the flight path planning method according to any one of claims 1-12 when executing the program. The device comprises a processor and a memory, the memory being configured to store a program, and the processor being configured to implement the flight path planning method according to any one of claims 1-12 when executing the program.

Images