UAV single building survey path planning method, device, equipment and medium

By using background grid processing based on survey granularity and genetic algorithm to generate UAV survey paths, the safety and efficiency issues of single-building survey tasks were solved, ensuring the safety of surveyors and the smooth completion of the task.

CN114942650BActive Publication Date: 2025-09-16SANMING UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202210616363.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-06-01
Publication Date
2025-09-16
Estimated Expiration
2042-06-01

AI Technical Summary

Technical Problem

Existing drone survey technology cannot effectively solve the survey tasks during and after a single building disaster, resulting in the inability to guarantee the safety of survey personnel and the inability to conduct dangerous scene surveys.

Method used

The background grid processing based on the survey granularity is used to generate the pending points, the check-in points are screened out, the initial genes are generated through spatial coding, and the survey path is generated using genetic algorithm and simulated annealing algorithm.

Benefits of technology

It realizes safe and efficient survey route planning in single buildings, ensuring the smooth progress of survey tasks and the safety of surveyors.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114942650B_ABST
    Figure CN114942650B_ABST
Patent Text Reader

Abstract

The present invention provides a method, device, equipment, and medium for planning a path for surveying a single building using an unmanned aerial vehicle (UAV), including the following steps: obtaining the structure of the single building to be surveyed, performing background grid processing on the structure, and generating multiple pending points that the UAV needs to reach; performing distance calculation on each pending point to generate multiple check-in points, where the check-in point is the pending point whose closest distance to the building entity does not exceed a preset distance value; performing spatial encoding processing on the coordinates of each check-in point to generate an initial gene, so that when the UAV flies to the check-in point, it can generate a valid gene segment, each valid gene segment can be integrated into a complete valid gene segment, and the initial gene is formed by integrating each complete valid gene segment; and performing genetic algorithm and simulated annealing algorithm operations on the initial gene to generate a survey path. Furthermore, existing UAV survey solutions cannot be used to conduct surveys during and after a single building disaster, which has a certain impact on the safety of survey personnel and the performance of the survey mission.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of building survey route planning, and in particular to a method, device, equipment and medium for planning a path for a single building survey by an unmanned aerial vehicle (UAV). Background Art

[0002] Drones are currently being used for surveys in dangerous and unmanageable environments. Currently, existing drone survey technologies are primarily used for surveying routes, such as roads, energy pipelines, municipal corridors, and equipment lines. Industries like geology, forestry, and agriculture use drones for general surveys or detailed investigations.

[0003] With the development of technology, drone survey technologies currently available on the market, such as drone reconnaissance of unknown streets and alleys and corresponding path planning technology, drone survey technology for mine tunnels, and drone survey technology for maze caves, have all been developed accordingly. However, there are currently no route planning technology solutions specifically for drone surveys inside and outside single buildings. In addition, due to the great diversity of survey tasks, the evaluation standards for building survey tasks currently available on the market do not have corresponding evaluation standards for survey route planning for single building modeling, especially indicators related to survey route quality. This makes it impossible to use existing drone survey technology solutions to conduct surveys during the occurrence of single building disasters and survey tasks after the disaster (such as structural damage to buildings and personnel search and rescue). The surveys can only be conducted manually, and the safety of the surveyors cannot be guaranteed. At the same time, some dangerous work scenes that cannot be manually inspected cannot be surveyed, affecting the progress of the entire survey task.

[0004] In view of this, this application is filed. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide a method, device, equipment and medium for planning a drone single-building survey path, which can effectively solve the problem that the drone survey scheme in the existing technology is unable to survey the survey tasks during the occurrence of a single-building disaster and the survey tasks after the disaster, making it impossible to guarantee the safety of the survey personnel and affecting the progress of the survey tasks.

[0006] The present invention discloses a method for planning a path for surveying a single building using an unmanned aerial vehicle, comprising:

[0007] Obtain a single building structure to be surveyed, and perform background mesh processing on the single building structure to generate multiple pending points that the drone needs to reach;

[0008] Performing distance calculation on each of the pending points to generate multiple check-in points, wherein the check-in points are the pending points whose closest distance to the building entity does not exceed a preset distance value;

[0009] The coordinates of each of the check-in points are spatially encoded to generate an initial gene. When the drone flies to the check-in point, it can generate a valid gene segment. The valid gene segments generated at each of the check-in points can be integrated into a complete valid gene segment. The initial gene is formed by integrating each of the complete valid gene segments.

[0010] Genetic algorithm operations and simulated annealing algorithm operations are performed on the initial genes to generate an exploration path.

[0011] Preferably, background grid processing is performed on the single building structure data to generate multiple pending points that the drone needs to reach, specifically:

[0012] Calling a background grid based on the survey granularity to cover the single building structure and generate background grid nodes;

[0013] Pre-processing the minimum distance between the single building structure and the drone for obstacle avoidance to generate a physical space;

[0014] The background grid nodes and the physical space are compared and processed to generate a plurality of pending points that the drone needs to reach, wherein the pending points are the background grid nodes that fall outside the physical space.

[0015] Preferably, the distance calculation is performed on each of the pending points to generate multiple check-in points, specifically:

[0016] Calculating the shortest distance between each of the pending points and the building entity;

[0017] Determining whether the closest distance exceeds a preset distance value;

[0018] If so, remove the pending point;

[0019] If not, the pending point is marked as a check-in point.

[0020] Preferably, the preset distance value is twice the survey granularity and is not less than twice the minimum turning radius of the UAV.

[0021] Preferably, the coordinates of each of the check-in points are spatially encoded to generate an initial gene, specifically:

[0022] Divide the drone's flight ranges into multiple ranges, where the flight ranges include the range that the drone can reach after one flight, the range that the drone can reach after two flights, and the range that the drone can reach after three flights, until the flight range includes all check-in points;

[0023] Numbering each of the check-in points within the flight range so that the drone can perform flight surveys according to the number and generate valid gene segments corresponding to the number;

[0024] Integrating each of the effective gene segments to generate a complete effective gene segment;

[0025] Repeat the above steps until the preset number of times is reached, and multiple complete and effective gene segments are generated for integration processing to generate the initial gene.

[0026] The present invention also provides a UAV single-building survey path planning device, comprising:

[0027] A pending point generation unit is used to obtain a single building structure to be surveyed, and perform background mesh processing on the single building structure to generate multiple pending points that the UAV needs to reach;

[0028] A check-in point generating unit is used to calculate the distance of each of the pending points to generate a plurality of check-in points, wherein the check-in point is the pending point whose closest distance to the building entity exceeds a preset distance value;

[0029] An initial gene generation unit is used to perform spatial encoding processing on the coordinates of each check-in point to generate an initial gene. When the drone flies to the check-in point, it can generate a valid gene segment. The valid gene segments generated at each check-in point can be integrated into a complete valid gene segment. The initial gene is formed by integrating each complete valid gene segment.

[0030] The exploration path generating unit is used to perform genetic algorithm operation and simulated annealing algorithm operation on the initial gene to generate an exploration path.

[0031] The present invention also provides a UAV single-building survey path planning device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the UAV single-building survey path planning method described above.

[0032] The present invention also provides a readable storage medium storing a computer program, wherein the computer program can be executed by a processor of a device where the storage medium is located to implement the UAV single-building survey path planning method as described in any one of the above.

[0033] In summary, the method, device, equipment, and medium for planning a single-building survey path for drones provided in this embodiment first uses a background grid based on the survey granularity to cover the acquired single-building structure to be surveyed and determine the pending points that the drone needs to reach; secondly, by calculating whether the closest distance from each pending point to the building entity does not exceed a preset distance value, the check-in points for drone survey are screened; thirdly, the valid gene segments generated by all the check-in points flown to by the drone are integrated into a complete valid gene segment, and each complete valid gene segment is integrated into an initial gene; finally, the initial gene is subjected to genetic algorithm and simulated annealing algorithm operations to generate a survey path. This solves the problem that drone survey solutions in the prior art are unable to survey the survey tasks during the occurrence of a single-building disaster or the survey tasks after the disaster is completed, making the safety of the survey personnel unguaranteed and affecting the progress of the survey tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 The figure is a flow chart of a method for planning a path for surveying a single building using a drone provided by an embodiment of the present invention.

[0035] Figure 2 This is a schematic diagram of a drone flight check-in point provided by an embodiment of the present invention.

[0036] Figure 3 This is a schematic diagram of a single-unit UAV survey provided by an embodiment of the present invention.

[0037] Figure 4 This is a schematic diagram of a multi-drone survey using drones provided by an embodiment of the present invention.

[0038] Figure 5 This is a schematic diagram of indoor survey using a drone provided by an embodiment of the present invention.

[0039] Figure 6 This is a schematic diagram of an outdoor survey using a drone provided by an embodiment of the present invention.

[0040] Figure 7 This is a module diagram of a single-building survey path planning device for a UAV provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the invention for which protection is sought, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0042] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0043] Please refer to Figure 1 A first embodiment of the present invention provides a method for planning a path for surveying a single building using a drone, comprising:

[0044] S101: Acquire a single building structure to be surveyed, and perform background mesh processing on the single building structure to generate a plurality of pending points that the drone needs to reach.

[0045] Specifically, in this embodiment, background grid processing is performed on the single building structure data to generate multiple pending points that the drone needs to reach, specifically:

[0046] Calling a background grid based on the survey granularity to cover the single building structure and generate background grid nodes;

[0047] Pre-processing the minimum distance between the single building structure and the drone for obstacle avoidance to generate a physical space;

[0048] The background grid nodes and the physical space are compared and processed to generate a plurality of pending points that the drone needs to reach, wherein the pending points are the background grid nodes that fall outside the physical space.

[0049] With the development of technology, drone survey technologies currently available on the market, such as drone reconnaissance of unknown streets and alleys and corresponding path planning technology, drone survey technology for mine tunnels, and drone survey technology for maze caves, have all been developed accordingly. However, there are currently no route planning technology solutions specifically for drone surveys inside and outside single buildings. In addition, due to the great diversity of survey tasks, the evaluation standards for building survey tasks currently available on the market do not have corresponding evaluation standards for survey route planning for single building modeling, especially indicators related to survey route quality. This makes it impossible to use existing drone survey technology solutions to conduct surveys during the occurrence of single building disasters and survey tasks after the disaster (such as structural damage to buildings and personnel search and rescue). The surveys can only be conducted manually, and the safety of the surveyors cannot be guaranteed. At the same time, some dangerous work scenes that cannot be manually inspected cannot be surveyed, affecting the progress of the entire survey task.

[0050] In this embodiment, the UAV single-building survey path planning method uses a background grid based on the survey granularity to cover the single-building structure to be surveyed, and all the background grid nodes falling within the building nodes are marked as background grid nodes that the UAV cannot reach; wherein, based on the known single-building structure, the single-building outer skin, and the minimum distance for the UAV to avoid obstacles, a physical space can be generated, and all the background grid nodes falling outside the physical space are marked as pending points that the UAV needs to reach.

[0051] Among them, the grid granularity of the background grid technology adopted by the UAV single-building survey path planning method is determined by the level of the task, and the survey path is divided into 6 levels of granularity: one hundred meters, ten meters, meters, decimeters, centimeters, millimeters, and 0.1 millimeters; the granularity of one hundred meters corresponds to the grid survey of super-large single buildings or building groups or communities, and the granularity of 0.1 millimeters corresponds to interior decoration, carvings, precision instruments, and structural damage details; during the execution process, if it is necessary to adjust the survey granularity of a local area, the new flight mission points to be punched in can be calculated according to the corresponding granularity requirements. If the granularity becomes smaller, the mission points increase; if the granularity becomes larger, the mission points decrease; and the UAV single-building survey path planning method also fully considers the turning radius of different types of UAVs, reasonable flight speed, obstacle avoidance technical requirements, and the impact of single flight time on survey path planning, so that the generated survey path is more accurate.

[0052] S102, performing distance calculation on each of the pending points to generate a plurality of check-in points, wherein the check-in points are the pending points whose closest distance to the building entity does not exceed a preset distance value.

[0053] Specifically, in this embodiment, the distance calculation is performed on each of the pending points to generate multiple check-in points, specifically:

[0054] Calculating the shortest distance between each of the pending points and the building entity;

[0055] Determining whether the closest distance exceeds a preset distance value;

[0056] If so, remove the pending point;

[0057] If not, the pending point is marked as a check-in point.

[0058] See also Figure 2 In this embodiment, the points to be determined can be divided into points inside the building and points outside the building. The closest distance from each point inside the building to the building entity is calculated, and the points inside the building that are greater than or equal to the preset distance value are removed. The remaining points inside the building are the check-in points for the drone survey flight. Similarly, the closest distance from each point outside the building to the building entity is calculated, and the points outside the building that are greater than or equal to the preset distance value are removed. The remaining points outside the building are the check-in points for the drone survey flight. Among them, the preset distance value can be twice the survey granularity and not less than twice the minimum turning radius of the drone. It should be noted that in other embodiments, other types of distance preset values ​​can also be used, which are not specifically limited here, but these solutions are all within the scope of protection of the present invention.

[0059] S103, spatially encode the coordinates of each of the check-in points to generate an initial gene, wherein the drone can generate a valid gene segment when it flies to the check-in point, and the valid gene segments generated by each of the check-in points can be integrated into a complete valid gene segment, and the initial gene is formed by the integration of each of the complete valid gene segments.

[0060] Specifically, in this embodiment, the coordinates of each check-in point are spatially encoded to generate an initial gene, specifically:

[0061] Divide the drone's flight ranges into multiple ranges, where the flight ranges include the range that the drone can reach after one flight, the range that the drone can reach after two flights, and the range that the drone can reach after three flights, until the flight range includes all check-in points;

[0062] Numbering each of the check-in points within the flight range so that the drone can perform flight surveys according to the number and generate valid gene segments corresponding to the number;

[0063] Integrating each of the effective gene segments to generate a complete effective gene segment;

[0064] Repeat the above steps until the preset number of times is reached, and multiple complete and effective gene segments are generated for integration processing to generate the initial gene.

[0065] In this embodiment, the initial gene generation code follows a regular pattern. First, a flight range is defined for each drone. Checkpoints within this range are randomly coded and sequentially numbered. The drones fly according to these numbers until they reach a checkpoint where they cannot return after a further flight. These checkpoints form a small, valid gene segment. These checkpoints are then removed from the total number of checkpoints, and the remaining checkpoints become the target points for the remaining drones. The first, second, and third drones then perform these basic steps in sequence, generating initial gene segments for each drone flight within the different areas. If any checkpoints remain unreached, the drones perform a second flight to generate subsequent gene segments. After a limited number of such missions, upon completing each checkpoint mission, the resulting small, valid gene segments are integrated into a complete, valid gene segment. Finally, this process is repeated a predetermined number of times to generate an initial gene segment.

[0066] See also Figures 3 to 6 If the surveyed scene, i.e., the building's interior and exterior, is equipped with surveillance cameras, the route planning can exclude unnecessary flight areas identified by the cameras. During a drone flight, one, two, three, or more drones can be assigned to a mission. If additional drones withdraw or join the survey, the route can be adjusted based on the new mission. For example, if three drones are assigned to a mission and one withdraws midway, the remaining two drones can replan their route based on the unfinished mission. If an impassable area is encountered during a mission, making the planned point unreachable, for example, if a building's windows are closed and impassable, and doors are open, the drone will re-execute the single-building survey path planning method and adjust the route based on the calculated results if it encounters a closed door during actual flight. Furthermore, real-time flight conditions must be recorded. For unreachable checkpoints, the reasons for the inability to reach the designated checkpoints should be recorded using image information transmitted by the drone.

[0067] S104, performing genetic algorithm operations and simulated annealing algorithm operations on the initial genes to generate a survey path.

[0068] Specifically, in this embodiment, the evaluation standard of the survey path quality is measured by "number of spatial survey (modeling) entity particles / (∑task execution time)", where ∑ represents the total time of the drones performing the task, and the higher the calculated value, the better the route quality.

[0069] In one possible embodiment of the present invention, the drone path planning method for surveying a single building can also generate a node diagram for the building's interior space, using the geometric centers of each room and door as nodes. For exterior building space nodes, nodes are generated based on the geometric centers of the building's facades and roofs. If there are multiple faces, the geometric centers of each face are used. The takeoff point and each node form a flyable route network, where nodes are divided into two categories: door nodes, which may or may not be flown over; and nodes other than doors, which must be reached. A deep search algorithm is used for traversal, and the shortest route is selected as the optimal route based on the traversal results. Each room is then surveyed in detail according to granularity requirements. Specifically, six interior surfaces (top, bottom, left, right, front, and back) are photographed. For irregular surfaces in irregular spaces and irregular building exteriors, the optimal photographic location can be calculated for each surface according to granularity requirements to obtain survey information for that surface.

[0070] See also Figure 7 A second embodiment of the present invention provides a UAV single-building survey path planning device, comprising:

[0071] The pending point generation unit 201 is used to obtain a single building structure to be surveyed, and perform background mesh processing on the single building structure to generate multiple pending points that the UAV needs to reach;

[0072] A check-in point generating unit 202 is configured to calculate the distance of each of the pending points to generate a plurality of check-in points, wherein the check-in point is the pending point whose closest distance to the building entity exceeds a preset distance value;

[0073] The initial gene generation unit 203 is used to perform spatial encoding processing on the coordinates of each check-in point to generate an initial gene. When the drone flies to the check-in point, it can generate a valid gene segment. The valid gene segments generated at each check-in point can be integrated into a complete valid gene segment. The initial gene is formed by integrating each complete valid gene segment.

[0074] The exploration path generating unit 204 is configured to perform genetic algorithm and simulated annealing algorithm operations on the initial genes to generate an exploration path.

[0075] A third embodiment of the present invention provides a drone single-building survey path planning device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the drone single-building survey path planning method described in any one of the above.

[0076] A fourth embodiment of the present invention provides a readable storage medium storing a computer program, wherein the computer program can be executed by a processor of a device where the storage medium is located to implement a method for planning a path for surveying a single building using a drone as described in any one of the above.

[0077] For example, the computer programs described in the third and fourth embodiments of the present invention can be divided into one or more modules, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules can be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program in the device for implementing a single-building survey path planning system using a drone. For example, the device described in the second embodiment of the present invention.

[0078] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the method for planning a path for surveying a single building by a drone, and utilizes various interfaces and lines to connect the various parts of the method for planning a path for surveying a single building by a drone.

[0079] The memory can be used to store the computer program and / or module. The processor implements various functions of a method for planning a path for surveying a single building by using an unmanned aerial vehicle by running or executing the computer program and / or module stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area. The program storage area can store an operating system, at least one application required for a function (such as a sound playback function, a text conversion function, etc.), etc.; the data storage area can store data created based on the use of the mobile phone (such as audio data, text message data, etc.). In addition, the memory can include a high-speed random access memory and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0080] Wherein, if the implemented module is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of each of the above-mentioned method embodiments. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0081] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement the present invention without inventive effort.

[0082] The above are only preferred embodiments of the present invention. The protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention.

Claims

1. A method for planning a path for surveying a single building using an unmanned aerial vehicle, characterized in that: include: Obtain a single building structure to be surveyed, and perform background mesh processing on the single building structure to generate multiple pending points that the drone needs to reach; Performing distance calculation on each of the pending points to generate multiple check-in points, wherein the check-in points are the pending points whose closest distance to the building entity does not exceed a preset distance value; The coordinates of each of the check-in points are spatially encoded to generate an initial gene. When the drone flies to the check-in point, it can generate a valid gene segment. The valid gene segments generated at each of the check-in points can be integrated into a complete valid gene segment. The initial gene is formed by integrating each of the complete valid gene segments. Performing genetic algorithm operations and simulated annealing algorithm operations on the initial genes to generate an exploration path; The background grid processing is performed on the single building structure data to generate multiple pending points that the drone needs to reach, specifically: Calling a background grid based on the survey granularity to cover the single building structure and generate background grid nodes; Pre-processing the minimum distance between the single building structure and the drone for obstacle avoidance to generate a physical space; Comparing the background grid nodes and the physical space to generate a plurality of pending points that the drone needs to reach, wherein the pending points are the background grid nodes that fall outside the physical space; Calculate the distance of each of the pending points to generate multiple check-in points, specifically: Calculating the shortest distance between each of the pending points and the building entity; Determining whether the closest distance exceeds a preset distance value; If so, remove the pending point; If not, the pending point is marked as a check-in point; The preset distance value is twice the survey granularity and is not less than twice the minimum turning radius of the drone.

2. The method for planning a single-building survey path using an unmanned aerial vehicle according to claim 1, wherein: The coordinates of each check-in point are spatially encoded to generate the initial gene, specifically: Divide the drone's flight ranges into multiple ranges, where the flight ranges include the range that the drone can reach after one flight, the range that the drone can reach after two flights, and the range that the drone can reach after three flights, until the flight range includes all check-in points; Numbering each of the check-in points within the flight range so that the drone can perform flight surveys according to the number and generate valid gene segments corresponding to the number; Integrating each of the effective gene segments to generate a complete effective gene segment; Repeat the above steps until the preset number of times is reached, and multiple complete and effective gene segments are generated for integration processing to generate the initial gene.

3. A UAV single building survey path planning device, characterized in that: include: A pending point generation unit is used to obtain a single building structure to be surveyed, and perform background mesh processing on the single building structure to generate multiple pending points that the UAV needs to reach; A check-in point generating unit is used to calculate the distance of each of the pending points to generate a plurality of check-in points, wherein the check-in point is the pending point whose closest distance to the building entity exceeds a preset distance value; An initial gene generation unit is used to perform spatial encoding processing on the coordinates of each check-in point to generate an initial gene. When the drone flies to the check-in point, it can generate a valid gene segment. The valid gene segments generated at each check-in point can be integrated into a complete valid gene segment. The initial gene is formed by integrating each complete valid gene segment. A survey path generating unit, configured to perform genetic algorithm and simulated annealing algorithm operations on the initial genes to generate a survey path; The background grid processing is performed on the single building structure data to generate multiple pending points that the drone needs to reach, specifically: Calling a background grid based on the survey granularity to cover the single building structure and generate background grid nodes; Pre-processing the minimum distance between the single building structure and the drone for obstacle avoidance to generate a physical space; Comparing the background grid nodes and the physical space to generate a plurality of pending points that the drone needs to reach, wherein the pending points are the background grid nodes that fall outside the physical space; Calculate the distance of each of the pending points to generate multiple check-in points, specifically: Calculating the shortest distance between each of the pending points and the building entity; Determining whether the closest distance exceeds a preset distance value; If so, remove the pending point; If not, the pending point is marked as a check-in point; The preset distance value is twice the survey granularity and is not less than twice the minimum turning radius of the drone.

4. A UAV single building survey path planning device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the method for planning a path for surveying a single building by an unmanned aerial vehicle as described in any one of claims 1 to 2 is implemented.

5. A readable storage medium, characterized in that: A computer program is stored, and the computer program can be executed by a processor of the device where the storage medium is located to implement the drone single building survey path planning method as described in any one of claims 1 to 2.

Citation Information

Patent Citations

  • Task allocation method for earthquake post-disaster investigation of heterogeneous unmanned aerial vehicle formation

    CN111309046A

  • Building appearance surveying method, device and equipment based on unmanned aerial vehicle and medium

    CN113110567A