Planar region coverage path generation method, computer equipment and storage medium

Abstract

The invention discloses a planar region coverage path generation method, computer equipment and a storage medium. The planar region coverage path generation method comprises the following steps: acquiring related parameters of a planar region to obtain a polygonal region to be planned; decomposing the polygonal region to be planned to obtain a plurality of sub-regions without obstacles; generating four kinds of scanning lines in the sub-regions; constructing a weighted graph model of which sub-regions comprise four scanning lines; according to the weighted graph models of all the sub-regions, obtaining all global scanning lines of the polygonal region; global search optimization is carried out on all the scanning lines, and a total scanning line with the shortest global total path length is obtained; and performing path restoration on the total scanning line to obtain a complete planar region coverage path generation graph. According to the planar region coverage path generation method, the computer equipment and the storage medium, better performance can be obtained when the planar region coverage path is generated.

Description

Technical Field

[0001] This invention relates to the technical field of unmanned equipment path planning, and in particular to a method for generating a path covering a planar area, a computer device, and a storage medium. Background Technology

[0002] With societal development, unmanned equipment is being used more and more widely in production and daily life. Area coverage route planning is a fundamental capability for autonomous mobile unmanned equipment such as drones, robots, and robotic dogs in scenarios including surveying and inspection, security monitoring, security patrols, agricultural spraying, and cleaning operations.

[0003] In existing technologies, methods for planning routes for surface coverage mainly include rasterization scanning, regular scan line methods, and graph theory-based region traversal methods.

[0004] However, existing methods for planning routes for area coverage have the following drawbacks: (1) The rasterization scanning method has a large computational load, and a large number of redundant nodes will appear when used in complex areas, making it difficult to meet the requirements of real-time path generation. (2) The simple rule scanline method cannot handle obstacles and is prone to generating infeasible paths; (3) Graph theory-based region traversal methods are poorly adaptable to environments with concave polygons or multi-obstacle planar areas, resulting in discontinuous coverage paths, numerous turns, and large total path lengths. For example, Chinese patent CN119043340A, "A method for planning UAV coverage paths in urban areas," proposes a coverage scheme based on concave angle extension combined with GTSP, but it still has limitations: it relies on rasterization and height models, making it difficult to use in non-elevation data scenarios; the segmentation method is complex, requiring integer planning to merge sub-regions; the use of GTSP causes the scale of optimization variables to expand rapidly, affecting the real-time performance of path generation; no scan line generation logic is provided, the path continuity is unclear, the path is determined by the planning algorithm, and the planning results are difficult to adapt to different actual scenarios. Summary of the Invention

[0005] To overcome several technical problems existing in the prior art, the present invention provides a method for generating planar region coverage paths, a computer device, and a storage medium to achieve better performance when generating planar region coverage paths.

[0006] In a first aspect, the present invention provides a method for generating a planar region coverage path, comprising the steps of: Obtain the parameters of the planar region to get the polygonal region to be planned; The polygonal region to be planned is decomposed to obtain multiple sub-regions after obstacles have been removed; Four types of scan lines are generated within the sub-region; Construct a weighted graph model for sub-regions containing four types of scan lines; Based on the weighted graph model of all sub-regions, obtain all scan lines of the polygon region globally; Perform a global search optimization on all scan lines to obtain the total scan line with the shortest global total path length; The path of the total scan line is restored to obtain a complete planar area coverage path generation map.

[0007] As a preferred implementation, the parameters of the planar region are obtained to obtain the polygonal region to be planned. The specific steps include: Obtain the external polygon boundaries of the planar region, the polygon boundaries of obstacles, the scan interval, the scan direction, and the starting point; The outer polygonal boundary of the planar region, the polygonal boundary of the obstacle, and the starting point are rotated around the origin with the center point of the outer polygonal boundary of the planar region as the origin and the oblique angle of the scanning direction as the rotation angle, to form the polygonal region to be planned.

[0008] As a preferred implementation method, the polygonal region to be planned is decomposed, specifically by using the Boustrophedon Cellular Decomposition method to decompose the polygonal region to be planned, which contains obstacles, into multiple sub-regions.

[0009] As a preferred embodiment, four scan lines are generated within a sub-region, including the steps of: The vertices of the polygonal region to be planned are traversed and calculated to determine the starting offset in the global scan direction; The concave polygon sub-region is divided into several convex polygon sub-units from the concave point, and the common vertex of the adjacent sub-units is set as the connection node of the scan line at the concave point. On the boundary of the sub-region, four corner points are selected as the starting points of different scan lines according to the scanning direction, and four candidate scan lines are generated respectively. Then, the path length of each candidate scan line is calculated.

[0010] As a preferred implementation, a weighted map model is constructed in which the sub-region contains the four scan lines. The specific steps include: Number the vertices of the polygons in each sub-region and the starting points of the four scan lines, and establish a mapping relationship between the vertices and the starting points to the number indexes; Construct a weighted graph model.

[0011] As a further preferred implementation method, the specific process of constructing the weighted graph model is as follows: Establish edges between adjacent vertices, with the Euclidean distance between the vertices as the weight of the edges; Establish connecting line segments between the endpoints of the scan line and the vertices of the sub-region polygon; When establishing connecting line segments, geometric intersection detection is required; Geometric intersection detection is as follows: determine whether the connecting line segment intersects with other line segments in the sub-region, and the connecting line segment must be inside the sub-region. If so, no connecting line segment is established between the corresponding points.

[0012] As a preferred implementation, based on the weighted graph model of all sub-regions, all scan lines of the polygon region are obtained. The specific steps are as follows: the Floyd algorithm is used to calculate the shortest path between any two points in the weighted graph model, thereby obtaining the optimal connected path of the sub-region as the scan line.

[0013] As a preferred implementation, a global search optimization is performed on all scan lines to obtain the total scan line with the shortest global total path length. The specific steps are as follows: Traverse all sub-regions, calculate the cumulative distance of the scan lines from the four scan lines in each sub-region, and select the scan line combination with the shortest total path length from the cumulative distance as the total scan line.

[0014] In a second aspect, the present invention provides a computer device, including a processor and a computer-readable and writable storage medium; The computer-readable and writable storage medium stores executable instructions; when the processor reads the executable instructions from the computer-readable and writable storage medium, the aforementioned planar region coverage path generation method is executed.

[0015] Thirdly, the present invention provides a storage medium, the storage device storing a computer program, the computer program being used to implement the aforementioned method for generating planar region coverage paths.

[0016] Compared to existing marketing information push technologies, the method for generating planar area coverage paths, computer equipment, and storage medium of the present invention have the following advantages: It avoids the influence of obstacles, ensuring the uniformity and consistency of scan lines at the global scale; it effectively handles concave polygons, improving the geometric feasibility of scan lines; it provides four scan line start point selections, ensuring the quality of subsequent global search optimization and facilitating path restoration; it achieves the global optimal combination of coverage order, paths connecting sub-regions, and scan lines, enabling the acquisition of continuous, non-redundant coverage paths in planar regions during path restoration. Attached Figure Description

[0017] Figure 1 This is a flowchart of one embodiment of the planar region coverage path generation method of the present invention.

[0018] Figure 2 for Figure 1The flowchart for step S1.

[0019] Figure 3 for Figure 1 The flowchart for step S3.

[0020] Figure 4 for Figure 1 The flowchart for step S4.

[0021] Figure 5 for Figure 4 The flowchart for step S42.

[0022] Figure 6 for Figure 1 The flowchart for step S7. Detailed Implementation

[0023] Please refer to the diagrams, where the same component symbols represent the same components. The principles of the invention are illustrated by way of example implementation in a suitable operating environment. The following description is based on the illustrative specific embodiments of the invention and should not be construed as limiting the invention to other specific embodiments not detailed herein.

[0024] In the following description, specific embodiments of the invention will be illustrated with reference to the steps and symbols of operations performed by one or more computers, unless otherwise stated. Therefore, it will be understood that these steps and operations, which are repeatedly mentioned as being performed by a computer, include manipulation by a computer processing unit representing electronic signals of data in a structured format. This manipulation transforms the data or maintains it at a location in the computer's memory system, which can be reconfigured or otherwise alter the operation of the computer in a manner well known to those skilled in the art. The data structure maintained by the data is the physical location of the memory, which has specific characteristics defined by the data format. However, the principles of the invention described above are not intended to be limiting, and those skilled in the art will understand that many of the following steps and operations can also be implemented in hardware.

[0025] As used herein, the terms “component,” “module,” “system,” “interface,” “process,” etc., generally refer to computer-related entities: hardware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable application, an executing thread, a program, and / or a computer. As illustrated, both an application running on a controller and the controller itself can be components. Multiple components can exist within executing processes and / or threads, and components can reside on a single computer and / or be distributed across two or more computers.

[0026] Furthermore, the claimed subject matter can be implemented as a method, apparatus, or article of manufacture that uses standard programming and / or engineering techniques to produce software, firmware, hardware, or any combination thereof to control a computer to implement the disclosed subject matter. As used herein, the term "article of manufacture" is intended to include computer programs accessible from any computer-readable device, carrier, or medium. Of course, those skilled in the art will recognize that many modifications can be made to this configuration without departing from the scope or spirit of the claimed subject matter.

[0027] Although not required, embodiments are described within the general context of "computer-executable instructions" being executed by multiple electronic devices. Computer-executable instructions can be distributed via computer-readable media. They can be implemented as program modules, such as functions, objects, application programming interfaces (APIs), data structures, etc., that perform specific tasks or implement specific abstract data types. Typically, the functionality of these computer-executable instructions can be freely combined or distributed across various environments.

[0028] This document provides various operations of the embodiments. In one and / or more embodiments, the multiple operations may constitute multiple computer-executable instructions stored on a computer-readable medium, which, when executed by an electronic device, will cause a computing device to perform operations. The order in which some or all of the operations are described should not be construed as implying that these operations must be sequentially related. Those skilled in the art will understand alternative orderings that have the benefits of this specification. Moreover, it should be understood that not all operations are required to be present in every embodiment provided herein.

[0029] Furthermore, the term "preferred" as used herein is intended to refer to an example, illustration, or illustration. Any aspect or design described herein as "preferred" need not be construed as being more advantageous than other aspects or designs. Rather, the use of the term "preferred" is intended to present the concept in a concrete manner. The term "or" as used in this application is intended to mean an inclusive "or" rather than an exclusionary "or." That is, unless otherwise specified or clear from the context, "X uses A or B" naturally includes either of the permutations. Specifically, if X uses A; X uses B; or X uses both A and B, then "X uses A or B" is satisfied in any of the foregoing examples.

[0030] Furthermore, although this disclosure has been shown and described with respect to various implementations, equivalent variations and modifications will occur to those skilled in the art based on a reading and understanding of this specification and drawings. This disclosure includes all such modifications and variations and is limited only by the scope of the appended claims. In particular, with respect to the various functions performed by the aforementioned components (e.g., elements, resources, etc.), the terminology used to describe such components is intended to correspond to any component (unless otherwise indicated) that performs the specified function of the component (e.g., is functionally equivalent to it), even if it is not structurally equivalent to the disclosed structure that performs the function in the exemplary implementation of this disclosure shown herein. Moreover, although a particular feature of this disclosure has been disclosed with respect to only one of several implementations, such feature may be combined with several other features of other implementations that may be desirable and advantageous for a given or particular application. Moreover, with respect to the use of the terms “comprising,” “having,” “containing,” or variations thereof in the embodiment or claims, such terms are intended to be included in a manner similar to the term “including.”

[0031] A planar region is usually a closed polygon. If there are obstacles inside, when planning a path, it is necessary to remove the polygon formed by the boundaries of the obstacles from the interior of the planar region.

[0032] Please refer to Figures 1 to 6 The method for generating a planar region coverage path in this embodiment includes the following steps.

[0033] S1. Obtain the relevant parameters of the initial planar region to obtain the polygonal region to be planned.

[0034] In step S1, the specific steps include: S11. Obtain parameters such as the outer polygon boundary of the planar region, the polygon boundary of the obstacle, the scanning interval (i.e., the vertical distance between two adjacent scanning lines), the scanning direction, and the starting point. In this embodiment, the scanning interval, scanning direction, and starting point are set according to the type of unmanned equipment and the actual application scenario. For example, in the case of drone use, they can be set according to the current drone's attitude, camera parameters, zoom magnification, FOV, etc., while in the case of robot dog or robot use, they can be set by stride, body position, etc.

[0035] S12. Based on the parameters obtained in step S11, the outer polygonal boundary of the planar region, the polygonal boundary of the obstacle, and the starting point are rotated around the origin with the center point of the outer polygonal boundary of the planar region as the origin and the oblique angle of the scanning direction as the rotation angle, so that the scanning direction is vertical, thereby constructing the polygonal region to be planned.

[0036] S2. Decompose the polygonal region to be planned to obtain multiple sub-regions with the polygonal boundaries removed from obstacles.

[0037] In step S2, the Boustrophedon Cellular Decomposition (BCD) method is preferably used to decompose the polygonal region to be planned, which contains obstacles, into multiple sub-regions without obstacles. Using the Boustrophedon method to decompose and obtain sub-regions can ensure that the interior of each sub-region is a connected space when scanning lines are subsequently applied.

[0038] S3. Generate scan lines within the sub-region.

[0039] In step S3, the specific steps include: S31. Perform traversal calculations on the vertices of the polygonal region to be planned, and then determine the starting offset in the global scanning direction. In step S31, once the starting offset of the first sub-region scan line is determined, when generating scan lines in subsequent sub-regions, the starting position of the first scan line of each subsequent sub-region can be deduced by "starting offset + integer multiple of scan interval", thereby maintaining the spacing and alignment relationship of scan lines between all sub-regions on the global scale and ensuring the uniformity and consistency of scan lines. S32. Divide the concave polygon sub-region into several convex polygon sub-units from the concave point, and set the common vertex of adjacent sub-units as the connection node of the scan line at the concave point. In step S3, if scan lines are directly generated along the scanning direction within the sub-region of the concave polygon, some scan lines may cross the boundary of the sub-region near the concave point of the concave polygon, resulting in discontinuous paths and / or boundary crossings. To avoid this problem, step S32 performs structured processing on all the concave points of the sub-region of the concave polygon. By using the concave points as dividing points, the sub-region of the concave polygon is divided into several convex polygon sub-units. For the transition between these several convex polygon sub-units, step S32 uses the common vertex of the corresponding concave points of adjacent sub-units as a connection node, and connects the scan lines through the common vertex when the scan lines pass through adjacent sub-units, thereby ensuring the continuity of the scan lines and preventing the scan lines from crossing outside the sub-region of the concave polygon. S33. On the boundary of the sub-region, select four corner points as the starting points of different scan lines according to the scanning direction, generate four candidate scan lines respectively, and then calculate the path length of each candidate scan line. In step S3, considering that the starting position of the scan line will affect the final coverage path structure, step S33 uses the four corner points of the sub-region in the scanning direction (upper left, lower left, upper right, and lower right) as the starting points of the scan line to generate corresponding scan lines, and calculates the path length of each of the four scan lines. Since different starting points will cause changes in the scan line generation order and the position of the ending point, and the position of the ending point directly affects the path length when transitioning from the current sub-region to the next sub-region, step S33 retains the four scan lines and calculates and records the path length of each of the four scan lines, so that there is a basis for selecting the optimal coverage path in the subsequent global path optimization stage.

[0040] S4. Construct a weighted graph model for the sub-regions.

[0041] In step S4, the specific steps include: S41. Number the vertices of the polygons in each sub-region and the starting points of the four scan lines, and establish a mapping relationship between the vertices and the starting points and the number indexes. S42. Construct a weighted graph model. The specific process is as follows: S421. Establish edges between adjacent vertices, with the Euclidean distance between the vertices as the weight of the edges; S422. Between the endpoints of the scan line and the vertices of the sub-region polygon, establish connecting line segments according to the mapping relationship between the vertex and the starting point to the index number. When establishing connecting line segments, necessary geometric intersection checks are required to determine whether the connecting line segment intersects with other line segments in the sub-region and whether the connecting line segment is inside the sub-region. If the geometric intersection check is not satisfied, no connecting line segment is established between the corresponding points. This step S422 realizes the global connectivity of the sub-region at key points inside and outside. S5. Based on the weighted graph model of all sub-regions, obtain all scan lines of the global polygon region in step S2.

[0042] In step S5, the specific process is as follows: the Floyd algorithm (also known as the interpolation method or Floyd's algorithm) is used to calculate the shortest path between any two points in the weighted graph model and its predecessor relationship, so as to obtain the optimal connected path of the sub-region as the scan line; the predecessor relationship refers to the next point from point A to point B. The predecessor relationship is used so that when restoring the entire planned path in the later stage, a complete path from point A to point B can be formed.

[0043] S6. Perform a global search optimization on all scan lines to obtain the total scan line with the shortest global total path length.

[0044] In step S6, a combination of dynamic programming (DP) and depth-first search (DFS) is used to perform a global search optimization on all scan lines. The specific process is as follows: traverse all sub-regions, calculate the cumulative distance of the scan lines from the four types of scan lines in each sub-region, and select the scan line combination with the shortest total path length from the cumulative distance as the total scan line. Step S6 ensures the global optimality of the total scan line.

[0045] S7. Perform path restoration on the total scan lines to obtain a complete planar region coverage path generation map.

[0046] Step S7 includes the following steps: S71. Based on the shortest total scan line obtained in step S6, sequentially stitch together the shortest distance scan lines of each sub-region, insert the stitched total scan line into the polygon region to be planned, then remove duplicate nodes to keep the scan lines continuous, and output the complete total scan line; the starting point of the total scan line is the starting point in step S1, and the total scan line covers the entire polygon region. S72. Flip the total scan line and polygonal region in reverse order of the center point and rotation angle in step S12 to obtain the final coverage path area coverage path generation map. In step S72, the total scan line and the polygon region are restored by the inverse operation of the same rotation matrix. The rotation process is a rigid body transformation, which does not change the distance, order, or topology. Therefore, it avoids the problem that the final coverage path is inconsistent with the actual path of the planar region, and it does not require multiple iterations to obtain the optimized final coverage path.

[0047] Compared with existing technologies, the planar region coverage path generation method in this embodiment avoids the influence of obstacles by generating scan lines for sub-regions after region decomposition, ensuring the uniformity and consistency of scan lines at the global scale; it effectively handles concave polygons in the decomposed sub-regions, improving the geometric feasibility of scan lines; it provides four scan line starting point selections to ensure the quality of subsequent global search optimization, making the search result with the shortest global path length accurate and easy to restore the path; it uses the Floyd algorithm to construct the shortest path and predecessor matrix, combined with dynamic programming and depth-first search, to achieve the globally optimal combination of coverage order, paths connecting sub-regions, and scan lines, enabling the acquisition of continuous and non-redundant coverage path trajectories in the planar region during path restoration.

[0048] A computer device according to this embodiment includes a processor and a computer-readable and writable storage medium; the computer-readable and writable storage medium stores executable instructions; when the processor reads the executable instructions from the computer-readable and writable storage medium, the planar region coverage path generation method of the aforementioned embodiment is executed.

[0049] For the computer device in this embodiment, its computer-readable and writable storage medium and processor can be located in a server on the same computer motherboard, or they can be located on different computers in a server network using distributed processing, or they can be located in the same user terminal and / or electronic terminal device and / or data relay point device and / or edge computing device.

[0050] For the computer device in this embodiment, its computer storage medium is a writable mechanical hard disk and / or a solid-state hard disk and / or an optical disk and / or a floppy disk.

[0051] For the computer device in this embodiment, the executable instructions are used to drive the corresponding peripheral electronic devices to realize the transmission and reception of information data and / or electromechanical control functions.

[0052] For the computer device in this embodiment, a single processor may execute a computer program, or multiple processors may execute a computer program concurrently. The type of processor may be a CPU and / or a GPU and / or an NPU and / or a system-on-a-chip (SoC) and / or an AI chip.

[0053] The computer device in this embodiment may also be a combination of other corresponding functional modules and / or units, or an integrated processing unit.

[0054] The computer device of this embodiment can achieve better performance when generating planar area coverage paths compared to the prior art.

[0055] In this embodiment, a storage medium is provided, and the storage device stores a computer program that is used to implement the planar region coverage path generation method of the aforementioned embodiment.

[0056] For the storage medium in this embodiment, the computer program is one or more structured executable code modules.

[0057] Compared with existing technologies, the storage medium of this embodiment can achieve better performance when generating planar area coverage paths.

[0058] Although the present invention has been disclosed above with reference to preferred embodiments, the above preferred embodiments are not intended to limit the present invention. Those skilled in the art can make various modifications and alterations without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be determined by the scope defined in the claims.

Claims

1. A method for generating a coverage path for a planar region, characterized in that, Including the following steps: Obtain the parameters of the planar region to get the polygonal region to be planned; The polygonal region to be planned is decomposed to obtain multiple sub-regions after obstacles have been removed; Four types of scan lines are generated within the sub-region; Construct a weighted graph model for sub-regions containing four types of scan lines; Based on the weighted graph model of all sub-regions, obtain all scan lines of the polygon region globally; Perform a global search optimization on all scan lines to obtain the total scan line with the shortest global total path length; The path of the total scan line is restored to obtain a complete planar area coverage path generation map.

2. The method for generating a planar region coverage path according to claim 1, characterized in that, The steps for obtaining the parameters of the planar region to obtain the polygonal region to be planned include: Obtain the external polygon boundaries of the planar region, the polygon boundaries of obstacles, the scan interval, the scan direction, and the starting point; The outer polygonal boundary of the planar region, the polygonal boundary of the obstacle, and the starting point are rotated around the origin with the center point of the outer polygonal boundary of the planar region as the origin and the oblique angle of the scanning direction as the rotation angle, to form the polygonal region to be planned.

3. The method for generating a planar region coverage path according to claim 1, characterized in that, The polygonal region to be planned is decomposed, specifically by using the Boustrophedon Cellular Decomposition method to decompose the polygonal region containing obstacles into multiple sub-regions.

4. The method for generating a planar region coverage path according to claim 1, characterized in that, Four types of scan lines are generated within the sub-region, including the following steps: The vertices of the polygonal region to be planned are traversed and calculated to determine the starting offset in the global scan direction; The concave polygon sub-region is divided into several convex polygon sub-units from the concave point, and the common vertex of the adjacent sub-units is set as the connection node of the scan line at the concave point. On the boundary of the sub-region, four corner points are selected as the starting points of different scan lines according to the scanning direction, and four candidate scan lines are generated respectively. Then, the path length of each candidate scan line is calculated.

5. The method for generating a planar region coverage path according to claim 1, characterized in that, The specific steps for constructing a weighted map model of the sub-region containing the four scan lines include: Number the vertices of the polygons in each sub-region and the starting points of the four scan lines, and establish a mapping relationship between the vertices and the starting points to the number indexes; Construct a weighted graph model.

6. The method for generating a planar region coverage path according to claim 5, characterized in that, The specific process of constructing the weighted graph model is as follows: Establish edges between adjacent vertices, with the Euclidean distance between the vertices as the weight of the edges; Establish connecting line segments between the endpoints of the scan line and the vertices of the sub-region polygon; When establishing connecting line segments, geometric intersection detection is required; Geometric intersection detection is as follows: determine whether the connecting line segment intersects with other line segments in the sub-region, and the connecting line segment must be inside the sub-region. If so, no connecting line segment is established between the corresponding points.

7. The method for generating a planar region coverage path according to claim 1, characterized in that, Based on the weighted graph model of all sub-regions, obtain all scan lines of the polygon region globally. The specific steps are as follows: use the Floyd algorithm to calculate the shortest path between any two points in the weighted graph model, thereby obtaining the optimal connected path of the sub-region as the scan line.

8. The method for generating a planar region coverage path according to claim 1, characterized in that, A global search optimization is performed on all scan lines to obtain the total scan line with the shortest global total path length. The specific steps are as follows: Traverse all sub-regions, calculate the cumulative distance of the scan lines from the four scan lines in each sub-region, and select the scan line combination with the shortest total path length from the cumulative distance to form the total scan line.

9. A computer device, characterized in that, Includes processors and computer-readable and writable storage media; The computer-readable and writable storage medium stores executable instructions; when the processor reads the executable instructions from the computer-readable and writable storage medium, the planar region coverage path generation method of any one of claims 1-8 is executed.

10. A storage medium, characterized in that, The storage device stores a computer program that is used to implement the planar region coverage path generation method of any one of claims 1-8.

Images