Unmanned aerial vehicle path planning method, device, equipment and storage medium

Abstract

The application relates to the technical field of photovoltaic devices, and particularly discloses a method and device for planning a path of a UAV, equipment and a storage medium, the method comprising the following steps: acquiring a survey image of a target photovoltaic station, and determining endpoint coordinates of each photovoltaic string contained in the survey image; obtaining waypoint coordinates corresponding to each photovoltaic string based on the endpoint coordinates; calculating a waypoint flight sequence of the UAV according to the waypoint coordinates corresponding to each photovoltaic string, and determining a target planning route of the UAV based on the waypoint flight sequence. The waypoints of a photovoltaic array are identified through a survey image, an optimal route is generated by fitting the actual arrangement of the photovoltaic array, the UAV can automatically fly along the route to perform cleaning work, and the work efficiency and the utilization rate of the endurance of the UAV are improved.

Description

Technical Field

[0001] This application relates to the field of photovoltaic equipment technology, and in particular to a method, apparatus, device and storage medium for unmanned aerial vehicle (UAV) path planning. Background Technology

[0002] Currently, there are many photovoltaic cleaning drones on the market, such as those with attached water tanks and tethered designs. These solutions all share a common drawback: they rely entirely on pilot control. In centralized facility environments, the cleaning workload is large, the outdoor environment is harsh, and the length of a single row of photovoltaic panels is relatively long, making pilot operation prone to accidents.

[0003] Some drones that support serpentine path planning simply draw flight paths at specified intervals within a designated area, without referencing the actual photovoltaic panels. Since the arrangement of photovoltaic panels is random, serpentine path planning is completely unsuitable for centralized photovoltaic cleaning scenarios, resulting in poor path planning rationality. Summary of the Invention

[0004] The main purpose of this application is to provide a drone path planning method, which aims to solve the technical problem of low automation in the operation of photovoltaic cleaning drones in the prior art.

[0005] To achieve the above objectives, this application provides a method for unmanned aerial vehicle (UAV) path planning, the method comprising the following steps: Obtain a mapping image of the target photovoltaic power station; Determine the endpoint coordinates of each photovoltaic string contained in the survey image; Based on the endpoint coordinates, obtain the waypoint coordinates corresponding to each photovoltaic string; The waypoint flight sequence of the UAV is calculated based on the waypoint coordinates corresponding to each of the photovoltaic strings, and the target planned route of the UAV is determined based on the waypoint flight sequence.

[0006] In one embodiment, the step of determining the endpoint coordinates of each photovoltaic string included in the survey image includes: The rectangular boundary regions of each photovoltaic string contained in the survey image are determined based on the rotating frame detection model. The endpoint coordinates of each photovoltaic string are calculated based on the coordinates of the rectangular boundary region.

[0007] In one embodiment, the step of calculating the endpoint coordinates of each photovoltaic string based on the coordinates of the rectangular boundary region includes: Determine whether there is an inclusion relationship between the rectangular boundary regions; If so, then perform boundary filtering on the rectangular boundary regions that are in an inclusive relationship to obtain the remaining boundary regions after filtering. The endpoint coordinates of each photovoltaic string are obtained based on the remaining boundary region.

[0008] In one embodiment, the step of obtaining the waypoint coordinates corresponding to each of the photovoltaic strings based on the endpoint coordinates includes: The short side coordinates corresponding to each photovoltaic string are obtained based on the endpoint coordinates; The waypoint coordinates corresponding to each photovoltaic string are determined based on the coordinates of the shorter side.

[0009] In one embodiment, the step of calculating the waypoint flight sequence of the UAV based on the waypoint coordinates corresponding to each of the photovoltaic strings, and determining the target planned route of the UAV based on the waypoint flight sequence, includes: A continuous sequence is constructed based on the waypoint coordinates of each photovoltaic string, wherein the two waypoint coordinates corresponding to each photovoltaic string in the continuous sequence constitute mutually bound odd-numbered nodes and even-numbered nodes; Calculate multiple node paths along the odd-numbered nodes and the even-numbered nodes to access the continuous sequence; The waypoint flight sequence is constructed by selecting the shortest node path from all the node paths. The coordinate transformation of the waypoint flight sequence generates the target planned flight path of the UAV.

[0010] In one embodiment, the step of selecting the shortest node path from all the node paths to construct the target path sequence includes: Obtain all the discontinuous paths in the node paths that do not consecutively pass through the odd-numbered nodes and the even-numbered nodes; Remove all remaining node paths that contain the discontinuous path from all the node paths; The target path sequence is constructed by selecting the shortest path from the remaining node paths.

[0011] In one embodiment, the step of acquiring a mapping image of the target photovoltaic power station includes: Obtain a mapping image of the target photovoltaic power station; Set the preset pixel size of the path to be tested area; According to the preset pixel size, multiple path test areas containing photovoltaic strings are cropped from the survey image, and there are overlapping areas between adjacent path test areas; The step of determining the endpoint coordinates of each photovoltaic string contained in the survey image includes: Determine the endpoint coordinates of each photovoltaic string contained in the area to be tested along the path.

[0012] Furthermore, to achieve the above objectives, this application also provides a drone path planning device, the device comprising: The image acquisition module is used to acquire survey images of the target photovoltaic power station and select the area to be measured that contains the path of the photovoltaic panels in the survey image; The coordinate calculation module is used to calculate the endpoint coordinates of each photovoltaic panel in the area to be measured along the path; The waypoint acquisition module is used to perform endpoint filtering based on the endpoint coordinates to obtain the waypoint coordinates of each photovoltaic panel; The route planning module is used to calculate the target path sequence of the UAV based on the waypoint coordinates, and to perform coordinate transformation on the target path sequence to generate the target planned route of the UAV.

[0013] In addition, to achieve the above objectives, this application also provides a drone path planning device, which includes: a memory, a processor, and a drone path planning processing program stored in the memory and executable on the processor. When the drone path planning processing program is executed by the processor, it implements the steps of the above-described drone path planning method.

[0014] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the UAV path planning method described above.

[0015] The above-mentioned one or more technical solutions provided in this application may have the following advantages or at least achieve the following technical effects: This application discloses a method, apparatus, device, and storage medium for unmanned aerial vehicle (UAV) path planning. The method includes: acquiring a survey image of a target photovoltaic (PV) power station; selecting a path to be planned area containing PV panels in the survey image; calculating the endpoint coordinates of each PV panel in the path to be planned area; performing endpoint filtering based on the endpoint coordinates to obtain the waypoint coordinates of each PV panel; calculating the target path sequence of the UAV based on the waypoint coordinates; and performing coordinate transformation on the target path sequence to generate the target planned flight path of the UAV. By identifying waypoints of the PV panel array through surveying, and generating the optimal flight path based on the actual arrangement of the PV array, the UAV can automatically fly according to the flight path to perform cleaning operations, improving operational efficiency and endurance utilization. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating the first embodiment of the UAV path planning method of this application; Figure 2 This is a schematic diagram showing the clipping of the first embodiment of the UAV path planning method of this application; Figure 3 This is a flowchart illustrating the second embodiment of the UAV path planning method of this application; Figure 4 This is a flowchart illustrating the third embodiment of the UAV path planning method of this application; Figure 5 This is a flowchart illustrating the fourth embodiment of the UAV path planning method of this application; Figure 6 This is a schematic diagram of the module structure of the UAV path planning device of this application; Figure 7 This is a schematic diagram of the structure of the UAV path planning device, which is the hardware operating environment involved in the UAV path planning method of this application.

[0018] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0020] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a specific posture. If the specific posture changes, the directional indicators will also change accordingly.

[0021] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the use of "and / or" or "and / or" throughout the text includes three parallel solutions. For example, "A and / or B" includes solution A, solution B, or a solution that simultaneously satisfies A and B. Furthermore, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0022] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or a drone path planning device capable of performing the above functions. The following description uses a drone path planning device as an example to illustrate this embodiment and the subsequent embodiments.

[0023] Based on this, embodiments of this application provide a method for UAV path planning, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the UAV path planning method of this application.

[0024] Step S10: Obtain a mapping image of the target photovoltaic power station.

[0025] It should be noted that the target photovoltaic (PV) power station can be a centralized PV power plant area to be cleaned. The target PV power station typically contains multiple rows and groups of PV strings (formed by multiple PV panels connected in series). The PV panels can be individual power generation components that make up a PV array. During cleaning, the entire row of PV arrays is considered as a unit, and the left and right ends of the row need to be identified. The survey image can be a high-precision site map (TIF format) obtained from aerial photography by a surveying drone, which can be overlaid with a Digital Surface Model (DSM). This provides pixel coordinates, latitude, longitude, and altitude information for any point in the image; unlike ordinary aerial photographs, it has georeferencing and high-precision positioning capabilities.

[0026] Furthermore, the survey image can be cropped so that it contains at least one photovoltaic string, forming a path to be tested for drone cleaning. The path to be tested can be a local image block cropped from the whole survey image for identifying photovoltaic panels. A fixed pixel size (e.g., 2560×2560) is set, and adjacent areas overlap to ensure that at least one complete photovoltaic array is not segmented in each cropped survey image.

[0027] It is understood that by setting a preset pixel size for the path to be tested area, at least one path to be tested area containing a photovoltaic panel is cropped from the survey image according to the preset pixel size, and there is an overlapping area between adjacent path to be tested areas.

[0028] It should be understood that because a single TIFF image file is very large (approximately 500MB-2GB per image), it is first cropped using the GDAL library before being processed by YOLO for recognition. Our tool crops to a fixed size of 2560x2560 pixels. The cropping area logic is designed to overlap, ensuring that at least one array is completely contained within a single area. For example, selecting 2560 pixels can encompass most of the array, and adjacent boxes overlap by 50% in both length and width.

[0029] Step S20: Determine the endpoint coordinates of each photovoltaic string contained in the survey image.

[0030] It should be noted that the endpoint coordinates can be the pixel coordinates of the four vertices (xmin, ymin, xmax, and ymax) of the identified photovoltaic panel bounding box, which contains a large number of duplicate, contained, and truncated invalid boxes.

[0031] Understandably, the path to be measured region can be processed based on the Oriented Bounding Box (OBB) detection model to determine the rectangular boundary regions of each photovoltaic string contained in the surveyed image; the endpoint coordinates of each photovoltaic string can then be calculated based on the coordinates of the rectangular boundary regions. A large number of photovoltaic array images are used for training, and cropped images of a specified size are then fed into YOLO for recognition. YOLO identifies the photovoltaic panel boundaries in the surveyed image and calculates the pixel coordinates of the four vertices.

[0032] Step S30: Obtain the waypoint coordinates corresponding to each photovoltaic string based on the endpoint coordinates.

[0033] It should be noted that algorithms can be used to remove invalid endpoint boxes: filtering out small rectangles completely contained within large rectangles, removing false endpoints generated by array truncation, and retaining the bounding boxes of the complete photovoltaic array; and introducing tolerance to handle pixel recognition errors. Waypoint coordinates can be the actual flight points of the cleaning task: taking the pixel coordinates of the center points of the left and right short sides of the complete photovoltaic array, with each row of photovoltaic arrays corresponding to a pair of waypoints (left waypoint and right waypoint).

[0034] Understandably, because adjacent clipping boxes have significant overlap, a considerable portion of the identified vertices will also overlap. (See reference...) Figure 2 , Figure 2 This is a schematic diagram illustrating the clipping process in the first embodiment of the UAV path planning method of this application. During endpoint identification, a large number of rectangles composed of four vertices are obtained. Some regions are repetitive, and some points at the cut points are incorrectly identified due to the photovoltaic array being cut. Therefore, it is necessary to identify the rectangles composed of the four vertices of the complete photovoltaic array (e.g., ...). Figure 2 The complete photovoltaic panel of ACGI (in the image).

[0035] Step S40: Calculate the waypoint flight sequence of the UAV based on the waypoint coordinates corresponding to each of the photovoltaic strings, and determine the target planned route of the UAV based on the waypoint flight sequence.

[0036] It should be noted that the waypoint flight sequence can be the optimal order of visiting waypoints. The optimal rule can be to ensure that each pair of waypoints is visited consecutively (left then right or right then left), the total distance is minimized, and the route starts from the starting point and returns to the starting point. The target planned route can be the final flight command issued to the UAV, which includes the latitude and longitude waypoint sequence, flight order, and cleaning start / stop control (e.g., start the nozzle at the left endpoint, stop the nozzle at the right endpoint), supporting fully automatic execution by the UAV. The conversion of the waypoint flight sequence into the target planned route can be achieved through coordinate transformation, mapping the waypoint coordinates of the photovoltaic panel from image pixel coordinates to real geographic coordinates (latitude and longitude / UTM). Relying on the georegistration information of the GDAL library and the survey image, the UAV can fly according to the real geographic coordinates.

[0037] In this embodiment, the UAV path planning method includes: acquiring a mapping image of the target photovoltaic power station and determining the endpoint coordinates of each photovoltaic string contained in the mapping image; obtaining the waypoint coordinates corresponding to each photovoltaic string based on the endpoint coordinates; calculating the waypoint flight sequence of the UAV based on the waypoint coordinates corresponding to each photovoltaic string; and determining the target planned route of the UAV based on the waypoint flight sequence. By identifying the waypoints of the photovoltaic array through mapping, the optimal route is generated by matching the actual arrangement of the photovoltaic array. The UAV can then automatically fly along the route to perform cleaning operations, improving operational efficiency and endurance utilization.

[0038] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Please refer to Figure 3 , Figure 3 This is a flowchart illustrating a second embodiment of the UAV path planning method of this application. In this embodiment, step 30 includes: Step S301: Determine whether there is an inclusion relationship between the rectangular boundary regions.

[0039] It should be noted that containment relationship can refer to a rectangular boundary region (small box) completely falling inside another rectangular boundary region (large box); in the context of photovoltaic array recognition, this means that a partially truncated or repeated box is wrapped by the complete array box. The containment relationship can be determined using the Shapely algorithm with added tolerance attributes.

[0040] It is understood that the logic of the Shapely algorithm may include: comparing the size relationship of the boundary regions indicated by each endpoint coordinate; and determining that there is an inclusion relationship between the endpoint coordinates if all the boundary regions indicated by one endpoint coordinate are within a preset tolerance range of all the boundary regions indicated by another endpoint coordinate.

[0041] Step S302: If yes, then perform boundary filtering on the rectangular boundary regions that are in an inclusive relationship to obtain the remaining boundary regions after filtering.

[0042] It should be noted that the remaining boundary region can be the rectangular boundary region remaining after filtering out the smaller rectangles completely enclosed by the larger rectangle. The core formula is rect = (xmin, ymin, xmax, ymax), where xmin ≤ xmax, ymin ≤ ymax. rect represents a rectangle, (xmin, ymin, xmax, ymax) represent the four vertices of the rectangle, xmin represents the leftmost x-coordinate, ymin represents the bottommost y-coordinate, xmax represents the rightmost x-coordinate, and ymax represents the topmost y-coordinate. The formula for determining whether rectangle B is contained within rectangle A is: the left boundary of A ≤ the left boundary of B, the bottom boundary of A ≤ the bottom boundary of B, the right boundary of B ≤ the right boundary of A, and the top boundary of B ≤ the top boundary of A.

[0043] Understandably, considering that the pixel coordinates of the same vertex may have slight differences in different cutting regions, a tolerance parameter is introduced. This involves slightly expanding the rectangle outwards for calculation. All rectangles that are "almost contained" within the tolerance range will be considered as containing the array. After filtering for containing the array, what remains is the rectangle formed by the four vertices of the complete photovoltaic array.

[0044] Step S303: Obtain the endpoint coordinates of each photovoltaic string based on the remaining boundary region.

[0045] It should be noted that the short side coordinates corresponding to each photovoltaic string are obtained based on the endpoint coordinates; and the waypoint coordinates corresponding to each photovoltaic string are determined based on the short side coordinates.

[0046] It is understandable that waypoint coordinates can be the coordinates of the center points of the left and right edges of the photovoltaic panel. Therefore, after obtaining the coordinates of the four vertices, the two short sides obtained by combining the vertices in pairs are the left and right sides of the photovoltaic panel. Then, by calculating the coordinates of their center points, the waypoint coordinates can be obtained.

[0047] In this embodiment, it is determined whether there is an inclusion relationship between the rectangular boundary regions. If so, boundary filtering is performed on the rectangular boundary regions with the inclusion relationship to obtain the remaining boundary regions after filtering. The endpoint coordinates of each photovoltaic string are obtained based on the remaining boundary regions. By judging the inclusion relationship and tolerating errors, all duplicate, truncated, or partially invalid boxes are eliminated, and only the complete photovoltaic array boundary is retained, which greatly improves the filtering accuracy and strengthens the algorithm stability. The size relationship of the boundary regions indicated by the endpoint coordinates is compared. If all the boundary regions indicated by one endpoint coordinate are within the preset tolerance range of all the boundary regions indicated by another endpoint coordinate, it is determined that there is an inclusion relationship between the endpoint coordinates. This reduces the computational load of the path planning algorithm, avoids the generation of invalid paths, and ensures the efficiency of the final route.

[0048] Based on the above embodiments of this application, in the third embodiment of this application, the same or similar content as the above embodiments can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 4 , Figure 4 This is a schematic diagram of the first process of the third embodiment of the UAV path planning method of this application. In this embodiment, step 40 includes: Step S401: Construct a continuous sequence based on the waypoint coordinates of each photovoltaic string, wherein the two waypoint coordinates corresponding to each photovoltaic string in the continuous sequence constitute mutually bound odd-numbered nodes and even-numbered nodes.

[0049] It should be noted that waypoints for the photovoltaic array are numbered to form a continuous sequence. Each row of waypoints forms a pair: odd-numbered nodes = left waypoint, even-numbered nodes = right waypoint (or vice versa); for example, 1-2, 3-4, 5-6 are paired one-to-one, enabling continuous access to each node in pairs. That is, odd-numbered nodes (1, 3, 5...) are paired with the next even-numbered node (2, 4, 6...), and even-numbered nodes (2, 4, 6...) are paired with the previous odd-numbered node (1, 3, 5...). Left and right waypoints in the same row are forced to be paired; logically, they cannot be separated and must be accessed consecutively. Furthermore, a pair of nodes must appear adjacent to each other in the path; no other waypoints can be inserted in between.

[0050] Step S402: Calculate multiple node paths along the odd-numbered nodes and the even-numbered nodes to access the continuous sequence.

[0051] It should be noted that a node path can be a flight sequence scheme that traverses all waypoints, and is a candidate solution for path planning.

[0052] Step S403: Select the shortest node path from all the node paths to construct the waypoint flight sequence.

[0053] It should be noted that the waypoint flight sequence can be a filtered sequence of consecutive waypoints with the shortest distance, while the target path sequence is the optimal path ultimately issued to the UAV. The maximum total flight distance of the UAV is limited to ensure the path remains within a reasonable range. An algorithm is used to prioritize the search for the path with the lowest cost, gradually optimizing to find the optimal solution. The OR-Tools engine is used to calculate the shortest path satisfying all pairing rules based on cost and constraints. The total travel cost is then combined with the base distance and violation penalties and input into the path planning model for processing to obtain the waypoint flight sequence.

[0054] Step S404: Perform coordinate transformation on the waypoint flight sequence to generate the target planned route of the UAV.

[0055] It should be noted that when using YOLO to identify the left and right endpoints of the photovoltaic panel, the output data includes the pixel coordinates of the endpoints in the cropped image. These pixel coordinates are then converted using the open-source GDAL library, and their API can be directly called to obtain accurate latitude and longitude coordinates. The flight path is then sent to the drone, which can then fly sequentially according to the waypoints in the flight path.

[0056] Furthermore, refer to Figure 5 , Figure 5 This is a schematic diagram of the second process of the third embodiment of the UAV path planning method of this application. Step 403 includes: Step S501: Obtain the discontinuous paths in all the node paths that do not consecutively pass through the odd-numbered nodes and the even-numbered nodes.

[0057] Step S502: Remove all remaining node paths that contain the discontinuous path from all the node paths.

[0058] It should be noted that discontinuous paths can be path schemes where the sequence is discontinuous or pairs are broken, while remaining node paths can be the set of all pairs of continuous paths after removing discontinuous paths.

[0059] Understandably, the algorithm doesn't directly prohibit illegal paths, but instead imposes high penalties on violations: Violation 1: After visiting a paired node, instead of immediately visiting its paired node, go to another point; Violation 2: Jump directly from the starting point 0 to the second node of a pair of nodes (e.g., directly from 0 to 2, skipping 1). The penalties make the "total cost" of illegal paths extremely high, and the algorithm will automatically abandon such paths, choosing only compliant paths.

[0060] Step S503: Select the shortest node path from the remaining node paths to construct the target path sequence.

[0061] It should be noted that the total target cost of all paths is calculated from the remaining node paths (combining distance and penalties, with a penalty of 0 for compliant target path sequences). As long as the drone flies along the flight path and sets the nozzle to turn on at the left end of the photovoltaic panel and turn off at the right end, it can achieve fully automatic cleaning without the need for pilot intervention.

[0062] In this embodiment, a continuous sequence is constructed based on the waypoint coordinates of each photovoltaic string. The two waypoint coordinates corresponding to each photovoltaic string in the continuous sequence form mutually bound odd-numbered nodes and even-numbered nodes. Multiple node paths to the continuous sequence are calculated along the odd-numbered and even-numbered nodes. The shortest node path is selected from all the node paths to construct the waypoint flight sequence. Coordinate transformation is performed on the waypoint flight sequence to generate the target planned flight path for the UAV. This method forces paired continuous matching of the photovoltaic cleaning operation logic, retaining only paths that conform to the cleaning rules and preventing skipping or interleaving of paths during the cleaning process. Paired constraints significantly reduce the number of candidate paths and improve the efficiency of automated calculations.

[0063] This application also provides a drone path planning device; please refer to... Figure 6 The UAV path planning device includes: Image acquisition module 10 is used to acquire survey images of the target photovoltaic power station; The coordinate calculation module 20 is used to determine the endpoint coordinates of each photovoltaic string contained in the survey image; The waypoint acquisition module 30 is used to obtain the waypoint coordinates corresponding to each of the photovoltaic strings based on the endpoint coordinates. The route planning module 40 is used to calculate the waypoint flight sequence of the UAV based on the waypoint coordinates corresponding to each of the photovoltaic strings, and to determine the target planned route of the UAV based on the waypoint flight sequence.

[0064] The UAV path planning device provided in this application, employing the UAV path planning method in the above embodiments, can solve the technical problem of low automation in the operation of photovoltaic cleaning UAVs. Compared with the prior art, the beneficial effects of the UAV path planning device provided in this application are the same as those of the UAV path planning method provided in the above embodiments, and other technical features in the UAV path planning device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0065] This application provides a drone path planning device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the drone path planning method in the above embodiment 1.

[0066] The following is for reference. Figure 7 The diagram illustrates a structural schematic of a drone path planning device suitable for implementing embodiments of this application. The drone path planning device in these embodiments may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), and vehicle-mounted terminals (e.g., vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 7 The drone path planning device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0067] like Figure 7As shown, the UAV path planning device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the UAV path planning device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. The communication device 1009 allows the UAV path planning device to communicate wirelessly or wiredly with other devices to exchange data. While the figure shows UAV path planning devices with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0068] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0069] The UAV path planning device provided in this application adopts the UAV path planning method in the above embodiments. Compared with the prior art, the beneficial effects of the UAV path planning device provided in this application are the same as the beneficial effects of the UAV path planning method provided in the above embodiments. Moreover, the other technical features of the UAV path planning device are the same as the features disclosed in the method of the previous embodiment, and will not be repeated here.

[0070] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0071] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0072] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the UAV path planning method in the above embodiments.

[0073] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0074] The aforementioned computer-readable storage medium may be included in the UAV path planning device; or it may exist independently and not be assembled into the UAV path planning device.

[0075] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0076] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0077] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0078] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., computer programs) for executing the above-described UAV path planning method, which can solve the technical problem of low automation in the operation of photovoltaic cleaning UAVs. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the UAV path planning method provided in the above embodiments, and will not be repeated here.

[0079] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for unmanned aerial vehicle (UAV) path planning, characterized in that, The UAV path planning method includes the following steps: Obtain a mapping image of the target photovoltaic power station; Determine the endpoint coordinates of each photovoltaic string contained in the survey image; Based on the endpoint coordinates, obtain the waypoint coordinates corresponding to each photovoltaic string; The waypoint flight sequence of the UAV is calculated based on the waypoint coordinates corresponding to each of the photovoltaic strings, and the target planned route of the UAV is determined based on the waypoint flight sequence.

2. The UAV path planning method as described in claim 1, characterized in that, The step of determining the endpoint coordinates of each photovoltaic string contained in the survey image includes: The rectangular boundary regions of each photovoltaic string contained in the survey image are determined based on the rotating frame detection model. The endpoint coordinates of each photovoltaic string are calculated based on the coordinates of the rectangular boundary region.

3. The UAV path planning method as described in claim 2, characterized in that, The step of calculating the endpoint coordinates of each photovoltaic string based on the coordinates of the rectangular boundary region includes: Determine whether there is an inclusion relationship between the rectangular boundary regions; If so, then perform boundary filtering on the rectangular boundary regions that are in an inclusive relationship to obtain the remaining boundary regions after filtering. The endpoint coordinates of each photovoltaic string are obtained based on the remaining boundary region.

4. The UAV path planning method as described in claim 1, characterized in that, The step of obtaining the waypoint coordinates corresponding to each photovoltaic string based on the endpoint coordinates includes: The short side coordinates corresponding to each photovoltaic string are obtained based on the endpoint coordinates; The waypoint coordinates corresponding to each photovoltaic string are determined based on the coordinates of the shorter side.

5. The UAV path planning method as described in claim 1, characterized in that, The step of calculating the waypoint flight sequence of the UAV based on the waypoint coordinates corresponding to each of the photovoltaic strings, and determining the target planned route of the UAV based on the waypoint flight sequence, includes: A continuous sequence is constructed based on the waypoint coordinates of each photovoltaic string, wherein the two waypoint coordinates corresponding to each photovoltaic string in the continuous sequence constitute mutually bound odd-numbered nodes and even-numbered nodes; Calculate multiple node paths along the odd-numbered nodes and the even-numbered nodes to access the continuous sequence; The waypoint flight sequence is constructed by selecting the shortest node path from all the node paths. The coordinate transformation of the waypoint flight sequence generates the target planned flight path of the UAV.

6. The UAV path planning method as described in claim 5, characterized in that, The step of selecting the shortest node path from all the node paths to construct the target path sequence includes: Obtain all the discontinuous paths in the node paths that do not consecutively pass through the odd-numbered nodes and the even-numbered nodes; Remove all remaining node paths that contain the discontinuous path from all the node paths; The target path sequence is constructed by selecting the shortest path from the remaining node paths.

7. The UAV path planning method as described in claim 1, characterized in that, The step of acquiring the mapping image of the target photovoltaic power station includes: Obtain a mapping image of the target photovoltaic power station; Set the preset pixel size of the path to be tested area; According to the preset pixel size, multiple path test areas containing photovoltaic strings are cropped from the survey image, and there are overlapping areas between adjacent path test areas; The step of determining the endpoint coordinates of each photovoltaic string contained in the survey image includes: Determine the endpoint coordinates of each photovoltaic string contained in the area to be tested along the path.

8. A path planning device for unmanned aerial vehicles (UAVs), characterized in that, The device includes: The image acquisition module is used to acquire survey images of the target photovoltaic power station; The coordinate calculation module is used to determine the endpoint coordinates of each photovoltaic string contained in the survey image; The waypoint acquisition module is used to obtain the waypoint coordinates corresponding to each of the photovoltaic strings based on the endpoint coordinates; The route planning module is used to calculate the waypoint flight sequence of the UAV based on the waypoint coordinates corresponding to each of the photovoltaic strings, and to determine the target planned route of the UAV based on the waypoint flight sequence.

9. A path planning device for unmanned aerial vehicles (UAVs), characterized in that, The UAV path planning device includes: a memory, a processor, and a UAV path planning processing program stored in the memory and executable on the processor. When the UAV path planning processing program is executed by the processor, it implements the steps of the UAV path planning method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the UAV path planning method as described in any one of claims 1 to 7.

Images