An unmanned aerial vehicle autonomous tower-circulating method and system, and a storage medium

Abstract

The application relates to the technical field of power transmission line detection, in particular to a method and system for autonomous tower-circulating cruise of a UAV (unmanned aerial vehicle) and a storage medium, wherein the method comprises the following steps: obtaining initial environment data and tower parameters of a to-be-inspected power transmission tower, establishing a first cruise track and a flight safety boundary, and constructing an initial three-dimensional contour model of the to-be-inspected tower according to the tower parameters; the UAV collects actual three-dimensional point cloud data of the tower based on the first cruise track, corrects the initial three-dimensional contour model based on the actual three-dimensional point cloud data, and generates a three-dimensional entity model; the UAV identifies key inspection parts of the tower based on the three-dimensional entity model, adjusts the first cruise track by using an adaptive path search algorithm in combination with the flight safety boundary, and generates a second cruise track; and the UAV collects structure data of the tower based on the second cruise track, adjusts the second cruise track according to real-time environment data, and completes the cruise until the structure data is collected completely.

Description

Technical Field

[0001] This application relates to the field of power transmission line detection technology, and in particular to a method, system and storage medium for autonomous tower-circling cruise by unmanned aerial vehicles (UAVs). Background Technology

[0002] Transmission lines are the lifeblood of the power system, and their safe and stable operation is of paramount importance. As the supporting structure of the lines, transmission towers are exposed to complex outdoor environments for extended periods. Their tower bodies, insulators, hardware, conductor suspension points, and other parts are prone to defects such as corrosion, cracks, and loosening, requiring regular inspection and maintenance.

[0003] In related technologies, high-altitude inspection of transmission towers mainly relies on two methods: Manual climbing inspection: Workers need to climb to towers tens or even hundreds of meters high for close-up inspections. This method is labor-intensive, carries extremely high risks (such as falls from heights and electric shocks), and is limited by weather and terrain, resulting in low inspection efficiency. It is no longer able to meet the needs of modern power grid development for large-scale and intelligent operations.

[0004] Traditional UAV Inspection: In recent years, UAV technology has been widely used in power line inspection. However, most existing solutions use UAVs as "aerial cameras," relying primarily on manual remote control by the pilot or hovering and taking pictures based on preset fixed waypoints using GNSS (Global Navigation Satellite System). This approach has significant drawbacks: First, it heavily depends on the pilot's skill and experience, resulting in high training costs and fatigue during prolonged operation, posing safety risks. Second, hovering at fixed points makes it difficult to achieve continuous, comprehensive observation of the side and back structures of the towers (such as the sides of insulator strings, tower connections, and conductor clamps), leading to insufficient inspection coverage. Finally, for towers with complex structures and diverse models, preset waypoints are labor-intensive, lack adaptability, and cannot autonomously generate optimal circling flight paths based on specific tower types. Summary of the Invention

[0005] The main objective of this application is to propose a method, system, and storage medium for autonomous tower-circling cruise of unmanned aerial vehicles (UAVs), aiming to solve the problems in the background art.

[0006] To achieve the above objectives, one aspect of this application proposes a method for autonomous tower-circling cruise by an unmanned aerial vehicle (UAV), the method comprising: When the initial environmental data and tower parameters of the transmission tower to be inspected are obtained, a first cruise trajectory and flight safety boundary are established based on the initial environmental data, and an initial three-dimensional contour model of the tower to be inspected is constructed according to the tower parameters. The UAV collects actual 3D point cloud data of the tower based on the first cruise trajectory, and corrects the initial 3D contour model based on the actual 3D point cloud data to generate a 3D solid model. Based on the three-dimensional solid model, the UAV identifies the key inspection parts of the tower and, in conjunction with the flight safety boundary, uses an adaptive path search algorithm to adjust the first cruise trajectory and generate a second cruise trajectory. The drone collects structural data of the tower based on the second cruise trajectory, and adjusts the second cruise trajectory according to real-time environmental data until the structural data is collected and the cruise is completed.

[0007] In some embodiments, the UAV collects structural data of the tower based on the second cruise trajectory and adjusts the second cruise trajectory according to real-time environmental data, specifically including: The drone analyzes structural data and real-time environmental data to determine the relative distance between the current flight position and the tower structure and surrounding obstacles, as well as the coverage of key inspection areas at the current flight position. When the relative distance or coverage does not meet the preset range, the second cruise trajectory is adjusted by the attitude control algorithm to generate a third cruise trajectory. When the relative distance or coverage meets the preset range, maintain the current second cruise trajectory.

[0008] In some embodiments, the adaptive path search algorithm used to adjust the first cruise trajectory includes the A-Star algorithm and the Bézier curve fitting algorithm.

[0009] In some embodiments, the UAV collects structural data of the tower based on the second cruise trajectory, and adjusts the second cruise trajectory according to real-time environmental data until the structural data is collected. After completing the cruise, the method further includes: Drive the drone back to base and fuse and store the structural data of the tower and the second cruise trajectory; The data after fusion and storage is processed for defect identification, and the images of the defective parts are marked with their corresponding location information.

[0010] In some embodiments, when the initial environmental data and tower parameters of the transmission tower to be inspected are obtained, establishing a first cruise trajectory and flight safety boundary based on the initial environmental data specifically includes: Based on the initial environmental data, a flight safety boundary is constructed. Based on the height distribution of each crossarm layer of the tower body in the tower foundation parameters, the number of layers for layered scanning and the scanning height of each layer are determined. Based on the tower height in the tower foundation parameters, set the preset initial observation height of the UAV; Based on the preset initial observation altitude, the number of layers for layered scanning, and the scanning altitude of each layer, combined with the flight safety boundary, a first cruise trajectory is generated.

[0011] In some embodiments, adjusting the first cruise trajectory using an adaptive path search algorithm to generate a second cruise trajectory specifically includes: Within the flight safety boundary, the spatial location of each key inspection point or the corresponding optimal observation viewpoint is used as the target point for path planning to construct a target point set; Using the first cruise trajectory as the initial reference trajectory, the flight safety boundary as the search domain, and the target point set as the necessary nodes, the A-Star algorithm is used to replan the nodes of the first cruise trajectory to generate a discrete path node sequence. After sorting and globally optimizing the discrete path node sequence, the discrete path node sequence is used as control points. The Bezier curve fitting algorithm is used to fit the control points to generate a second cruise trajectory, which is a continuous spiral trajectory without breaks.

[0012] In some embodiments, the method further includes: When initial environmental data is obtained but tower parameters are not, a first cruise trajectory and flight safety boundary are established based on the initial environmental data. Based on the first cruise trajectory and flight safety boundary, the drone is driven to scan the tower and obtain the tower parameters through visual feature recognition algorithm; An initial three-dimensional profile model is established based on the tower parameters.

[0013] In some embodiments, the UAV collects actual three-dimensional point cloud data of the tower based on the first cruise trajectory, specifically including: Drive the drone to the preset initial observation height, and use the sensor module on the drone to perform layered scanning of the tower to obtain the actual three-dimensional point cloud data of the tower; The resolution of the actual 3D point cloud data acquisition is dynamically adjusted according to the current flight position of the UAV.

[0014] To achieve the above objectives, another aspect of this application proposes an autonomous tower-circling cruise system for unmanned aerial vehicles (UAVs), the system comprising: The initialization module is used to establish a first cruise trajectory and flight safety boundary based on the initial environmental data and tower parameters of the transmission tower to be inspected, and to construct an initial three-dimensional contour model of the tower to be inspected based on the tower parameters when the initial environmental data and tower parameters of the transmission tower to be inspected are obtained. The solid model generation module is used by the UAV to collect actual three-dimensional point cloud data of the tower based on the first cruise trajectory, and to correct the initial three-dimensional contour model based on the actual three-dimensional point cloud data to generate a three-dimensional solid model. The cyclic trajectory adjustment module is used by the UAV to identify key inspection parts of the tower based on the three-dimensional entity model, and in combination with the flight safety boundary, to adjust the first cruise trajectory using an adaptive path search algorithm to generate a second cruise trajectory. The autonomous flight module is used by the UAV to collect structural data of the tower based on the second cruise trajectory, and adjust the second cruise trajectory according to real-time environmental data until the structural data is collected and the cruise is completed.

[0015] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0016] The embodiments of this application include at least the following beneficial effects: This application provides a method, system and storage medium for autonomous tower-circling cruise by a UAV. This application improves the level of automation and intelligence by enabling the UAV to operate autonomously throughout the entire process. A three-dimensional solid model is constructed based on real-time three-dimensional point cloud data and tower parameters, and a second cruise trajectory is dynamically planned accordingly. This allows the UAV to actively perceive and adapt to real and complex external environments and targets, rather than executing a fixed preset cruise trajectory. This gives the method generalization ability and deployment flexibility, achieves coverage of key parts, and thus improves the integrity and accuracy of inspection. Meanwhile, by using flight safety boundaries, real-time perception of the environment and tower distance, and triggering trajectory replanning, an adaptive path search algorithm is adopted to adjust the first cruise trajectory, ensuring the safety and stability of near-tower flight and thus improving operational efficiency. Its adaptive capability is based on the fact that it does not rely on a preset cruise trajectory, but adjusts the flight trajectory according to real-time environmental data, making the solution flexible and applicable to different types and structures of power transmission towers. Attached Figure Description

[0017] Figure 1 A flowchart of an autonomous tower-circling cruise method for unmanned aerial vehicles provided in this application embodiment; Figure 2 A block diagram of an unmanned aerial vehicle (UAV) autonomous tower-circling cruise system provided in an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0019] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various concepts, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to a determination” as used herein may be interpreted as “when…” or “when…” or “in response to a determination.”

[0020] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0022] While some research in related technologies focuses on vision-based defect identification, there is a lack of in-depth research on autonomous, intelligent, and safe tower-circling cruise control methods for UAVs.

[0023] In view of this, embodiments of this application propose a method, system, and storage medium for autonomous tower-circling cruise by unmanned aerial vehicles (UAVs).

[0024] refer to Figure 1 As shown, one embodiment of this application proposes a method for autonomous tower-circling cruise by an unmanned aerial vehicle (UAV), including: S101: When the initial environmental data and tower parameters of the transmission tower to be inspected are obtained, a first cruise trajectory and flight safety boundary are established based on the initial environmental data, and an initial three-dimensional contour model of the tower to be inspected is constructed according to the tower parameters. S102: The UAV collects actual three-dimensional point cloud data of the tower based on the first cruise trajectory, and corrects the initial three-dimensional contour model based on the actual three-dimensional point cloud data to generate a three-dimensional solid model. S103: Based on the three-dimensional solid model, the UAV identifies the key inspection parts of the tower and, in conjunction with the flight safety boundary, uses an adaptive path search algorithm to adjust the first cruise trajectory and generate a second cruise trajectory. S104: The UAV collects structural data of the tower based on the second cruise trajectory, and adjusts the second cruise trajectory according to real-time environmental data until the structural data is collected and the cruise is completed.

[0025] By improving the level of automation and intelligence through steps S101-S106, a three-dimensional solid model is constructed based on real-time three-dimensional point cloud data and tower parameters. Based on this, a continuous and uninterrupted second cruise trajectory is dynamically planned, enabling the UAV to actively perceive and adapt to real and complex external environments and targets, rather than executing a fixed preset cruise trajectory. This gives the method generalization ability and deployment flexibility, achieving coverage of key parts and thus improving the integrity and accuracy of inspection. Specifically, in S101, the initial environmental data includes terrain obstacle data and airspace environmental data around the pole. The initial environmental data is obtained by using the geographic information of the pole to be tested pre-stored in the database or by quickly scanning the geographic information of the area where the pole to be tested is located before the UAV takes off. The purpose is to construct the first cruise trajectory and flight safety boundary to avoid collisions between the UAV and large obstacles. The pole parameters are intended to construct an initial three-dimensional contour model, which can be used as a reference benchmark and search space constraint for subsequent high-precision scanning and modeling.

[0026] Specifically, step S101, the generation of the first driving range trajectory, includes: The flight safety boundary is constructed based on the initial environmental data, and the number of layers for layered scanning and the scanning height of each layer are determined based on the height distribution of each crossarm layer in the tower body in the tower foundation parameters. Based on the tower height in the tower foundation parameters, set the preset initial observation height for the UAV; Based on the preset initial observation altitude, the number of layers for layered scanning, and the scanning altitude of each layer, combined with the flight safety boundary, the first cruise trajectory is generated.

[0027] Furthermore, when initial environmental data is obtained but tower parameters are not, a first cruise trajectory and flight safety boundary are established based on the initial environmental data; based on the first cruise trajectory and flight safety boundary, the UAV is driven to scan the tower and obtain tower parameters through a visual feature recognition algorithm; an initial three-dimensional contour model is established based on the tower parameters.

[0028] Furthermore, the drone in step S101 is equipped with a sensor module, which includes a vision camera, a lidar, and a millimeter-wave radar.

[0029] The visual camera uses a synchronous trigger acquisition method, with the acquisition frame rate linked to the drone's flight speed. The slower the flight speed, the higher the acquisition frame rate. This adaptive acquisition strategy ensures that higher density and clearer images can be obtained when inspecting key and delicate parts, effectively avoiding image blurring or missed shots caused by the mismatch between flight speed and shooting frequency, and providing a high-quality data source for subsequent automatic defect identification.

[0030] Specifically, in step S102, the UAV starts the sensor module it carries, takes off from the preset takeoff point to the preset initial observation height of the tower according to the first cruise trajectory, and performs real-time scanning and detection of the power transmission tower through the sensor module to obtain the actual three-dimensional point cloud data of the power transmission tower. The actual three-dimensional point cloud data is then registered and corrected with the initial three-dimensional contour model to generate a three-dimensional solid model of the power transmission tower.

[0031] Furthermore, when the UAV collects actual 3D point cloud data, a layered scanning method is adopted to collect point cloud and visual features layer by layer from the bottom to the top of the transmission tower. The collection resolution of the point cloud data is dynamically adjusted with the distance from the tower, and the closer the distance, the higher the collection resolution.

[0032] When the distance is far, a lower resolution is used for rapid panoramic modeling; when approaching key parts (such as insulators and fittings), the resolution is automatically increased to capture fine structural features, providing data support for high-precision inspection and defect identification, while balancing scanning efficiency and data quality.

[0033] Furthermore, the sensor module has a preset acquisition frequency of 10-20Hz. This acquisition frequency can quickly capture environmental changes, and the detection data from the lidar and millimeter-wave radar provide real-time image stabilization and focus compensation for the visual camera.

[0034] Specifically, the key inspection points in step S103 include tower connection points, insulator strings, hardware, conductor suspension points, and crossarm ends.

[0035] The adaptive path search algorithm of this application includes the A-Star algorithm and the Bézier curve fitting algorithm. The A-Star algorithm is used to search for the optimal discrete path node sequence passing through all key points in three-dimensional space, while the Bézier curve fitting smoothly connects these optimal discrete path node sequences into a second cruise trajectory that allows the UAV to fly smoothly and stably. Specifically, it includes: Within the flight safety boundary, the spatial location of each key inspection point or the corresponding optimal observation viewpoint is used as the target point for path planning to construct a target point set; Using the first cruise trajectory as the initial reference trajectory, the flight safety boundary as the search domain, and the target point set as the necessary nodes, the A-Star algorithm is used to replan the nodes of the first cruise trajectory to generate a discrete path node sequence. After sorting and globally optimizing the discrete path node sequence, the discrete path node sequence is used as control points. The Bezier curve fitting algorithm is used to fit the control points to generate a second cruise trajectory, which is a continuous spiral trajectory without breaks.

[0036] Furthermore, by sorting and globally optimizing the discrete path node sequence, we ensure that the node sequence is distributed along the spiral direction surrounding the tower, and use dynamic programming or genetic algorithms to optimize the connection order between nodes to minimize the total path length.

[0037] The drone flies autonomously along the second cruise trajectory. During the flight, it continuously collects real-time environmental data around the tower and structural data of the tower through the sensor module at a preset frequency. Furthermore, the drone analyzes structural data and real-time environmental data to determine the relative distance between the current flight position and the tower structure and surrounding obstacles, as well as the coverage of key inspection areas at the current flight position. When the relative distance or coverage does not meet the preset range, the current second cruise trajectory is locally corrected by the attitude control algorithm to generate a temporary compensation trajectory. The generated temporary compensation trajectory is smoothly connected with the second cruise trajectory to generate a third cruise trajectory, which ensures no sudden changes in flight attitude. Specifically, the attitude control algorithm in this application adopts a PID closed-loop control algorithm, which is combined with the UAV's inertial navigation data to adjust the flight attitude in real time, so that the flight attitude deviation of the UAV during the flight around the tower does not exceed ±3° and the flight speed fluctuation does not exceed ±0.5m / s. This application uses an attitude control algorithm to adjust the flight attitude, speed and altitude of the UAV. At the same time, the UAV's visual camera continuously collects high-definition data on all the key inspection parts during the flight until the circumnavigation and data collection of the power transmission tower is completed.

[0038] The replanned trajectory correction time is no more than 0.5 seconds, and the corrected temporary compensation trajectory is smoothly connected with the original three-dimensional surround cruise main trajectory without any sudden changes in flight attitude. Based on the adjusted second cruise trajectory, real-time environmental data around the tower and structural data of the tower are collected.

[0039] Furthermore, when the relative distance or coverage meets a preset range, the current second cruise trajectory is maintained.

[0040] This application uses continuously collected real-time environmental data for dynamic analysis. Once a situation that may exceed the preset safety threshold is detected, the trajectory is immediately adjusted to minimize the risk of the drone colliding with poles, power lines, or surrounding obstacles.

[0041] Furthermore, after step S104, the following steps are also included: Drive the drone back to base and fuse and store the structural data of the tower and the second cruise trajectory; The data after fusion and storage is processed for defect identification, and the images of the defective parts are marked with their corresponding location information.

[0042] The preset range includes a safety distance range and a coverage range. The safety distance range is dynamically set according to the structural type of the transmission tower and the location of key inspection parts. For easily accessible parts, the safety distance range is not less than 2 meters, and for the main structure of the tower body, the safety distance range is not less than 1 meter.

[0043] refer to Figure 2 As shown, to achieve the above objectives, another aspect of this application embodiment proposes an autonomous tower-circling cruise system for unmanned aerial vehicles (UAVs), the system comprising: The initialization module is used to establish a first cruise trajectory and flight safety boundary based on the initial environmental data and tower parameters of the transmission tower to be inspected, and to construct an initial three-dimensional contour model of the tower to be inspected based on the tower parameters when the initial environmental data and tower parameters of the transmission tower to be inspected are obtained. The solid model generation module is used by the UAV to collect actual three-dimensional point cloud data of the tower based on the first cruise trajectory, and to correct the initial three-dimensional contour model based on the actual three-dimensional point cloud data to generate a three-dimensional solid model. The cyclic trajectory adjustment module is used by the UAV to identify key inspection parts of the tower based on the three-dimensional entity model, and in combination with the flight safety boundary, to adjust the first cruise trajectory using an adaptive path search algorithm to generate a second cruise trajectory. The autonomous flight module is used by the UAV to collect structural data of the tower based on the second cruise trajectory, and adjust the second cruise trajectory according to real-time environmental data until the structural data is collected and the cruise is completed.

[0044] To achieve the above objectives, embodiments of this application also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0045] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0046] The methods provided in this application relate to the field of information technology. The methods provided in this application can be applied to terminals, servers, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or in-vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application implementing the method, but is not limited to the above forms.

[0047] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0048] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0049] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0050] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0051] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0052] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0053] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0054] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0055] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0056] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0057] If the integrated unit is implemented as 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 technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0058] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for autonomous tower-circling cruise by an unmanned aerial vehicle (UAV), characterized in that, The method includes: When the initial environmental data and tower parameters of the transmission tower to be inspected are obtained, a first cruise trajectory and flight safety boundary are established based on the initial environmental data, and an initial three-dimensional contour model of the tower to be inspected is constructed according to the tower parameters. The UAV collects actual 3D point cloud data of the tower based on the first cruise trajectory, and corrects the initial 3D contour model based on the actual 3D point cloud data to generate a 3D solid model. Based on the three-dimensional solid model, the UAV identifies the key inspection parts of the tower and, in conjunction with the flight safety boundary, uses an adaptive path search algorithm to adjust the first cruise trajectory and generate a second cruise trajectory. The drone collects structural data of the tower based on the second cruise trajectory, and adjusts the second cruise trajectory according to real-time environmental data until the structural data is collected and the cruise is completed.

2. The method for autonomous tower-circling cruise of an unmanned aerial vehicle according to claim 1, characterized in that, The drone collects structural data of the tower based on the second cruise trajectory and adjusts the second cruise trajectory according to real-time environmental data, specifically including: The drone analyzes structural data and real-time environmental data to determine the relative distance between the current flight position and the tower structure and surrounding obstacles, as well as the coverage of key inspection areas at the current flight position. When the relative distance or coverage does not meet the preset range, the second cruise trajectory is adjusted by the attitude control algorithm to generate a third cruise trajectory. When the relative distance or coverage meets the preset range, maintain the current second cruise trajectory.

3. The method for autonomous tower-circling cruise of an unmanned aerial vehicle according to claim 1, characterized in that, In adjusting the first cruise trajectory using an adaptive path search algorithm, the adaptive path search algorithm includes the A-Star algorithm and the Bézier curve fitting algorithm.

4. The method for autonomous tower-circling cruise of an unmanned aerial vehicle according to claim 1, characterized in that, The drone collects structural data of the tower based on the second cruise trajectory, and adjusts the second cruise trajectory according to real-time environmental data until the structural data is collected and the cruise is completed. Afterwards, the drone also includes: Drive the drone back to base and fuse and store the structural data of the tower and the second cruise trajectory; The data after fusion and storage is processed for defect identification, and the images of the defective parts are marked with their corresponding location information.

5. The method for autonomous tower-circling cruise of an unmanned aerial vehicle according to claim 1, characterized in that, When the initial environmental data and tower parameters of the transmission tower to be inspected are obtained, a first cruise trajectory and flight safety boundary are established based on the initial environmental data, specifically including: Based on the initial environmental data, a flight safety boundary is constructed. Based on the height distribution of each crossarm layer of the tower body in the tower foundation parameters, the number of layers for layered scanning and the scanning height of each layer are determined. Based on the tower height in the tower foundation parameters, set the preset initial observation height of the UAV; Based on the preset initial observation altitude, the number of layers for layered scanning, and the scanning altitude of each layer, combined with the flight safety boundary, a first cruise trajectory is generated.

6. The method for autonomous tower-circling cruise of an unmanned aerial vehicle according to claim 3, characterized in that, The step of adjusting the first cruise trajectory using an adaptive path search algorithm to generate a second cruise trajectory specifically includes: Within the flight safety boundary, the spatial location of each key inspection point or the corresponding optimal observation viewpoint is used as the target point for path planning to construct a target point set; Using the first cruise trajectory as the initial reference trajectory, the flight safety boundary as the search domain, and the target point set as the necessary nodes, the A-Star algorithm is used to replan the nodes of the first cruise trajectory to generate a discrete path node sequence. After sorting and globally optimizing the discrete path node sequence, the discrete path node sequence is used as control points. The Bezier curve fitting algorithm is used to fit the control points to generate a second cruise trajectory, which is a continuous spiral trajectory without breaks.

7. The method for autonomous tower-circling cruise of an unmanned aerial vehicle according to claim 1, characterized in that, The method further includes: When initial environmental data is obtained but tower parameters are not, a first cruise trajectory and flight safety boundary are established based on the initial environmental data. Based on the first cruise trajectory and flight safety boundary, the drone is driven to scan the tower and obtain the tower parameters through visual feature recognition algorithm; An initial three-dimensional profile model is established based on the tower parameters.

8. The method for autonomous tower-circling cruise of an unmanned aerial vehicle according to claim 1, characterized in that, The drone collects actual 3D point cloud data of the tower based on the first cruise trajectory, specifically including: Drive the drone to the preset initial observation height, and use the sensor module on the drone to perform layered scanning of the tower to obtain the actual three-dimensional point cloud data of the tower; The resolution of the actual 3D point cloud data acquisition is dynamically adjusted according to the current flight position of the UAV.

9. An autonomous tower-circling cruise system for unmanned aerial vehicles, characterized in that, The system includes: The initialization module is used to establish a first cruise trajectory and flight safety boundary based on the initial environmental data and tower parameters of the transmission tower to be inspected, and to construct an initial three-dimensional contour model of the tower to be inspected based on the tower parameters when the initial environmental data and tower parameters of the transmission tower to be inspected are obtained. The solid model generation module is used by the UAV to collect actual three-dimensional point cloud data of the tower based on the first cruise trajectory, and to correct the initial three-dimensional contour model based on the actual three-dimensional point cloud data to generate a three-dimensional solid model. The cyclic trajectory adjustment module is used by the UAV to identify key inspection parts of the tower based on the three-dimensional entity model, and in combination with the flight safety boundary, to adjust the first cruise trajectory using an adaptive path search algorithm to generate a second cruise trajectory. The autonomous flight module is used by the UAV to collect structural data of the tower based on the second cruise trajectory, and adjust the second cruise trajectory according to real-time environmental data until the structural data is collected and the cruise is completed.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 8.

Images