Method and device for generating patrol route of unmanned aerial vehicle

Abstract

The embodiment of the invention provides an unmanned aerial vehicle patrol route generation method and equipment, and relates to the technical field related to unmanned aerial vehicles. The method comprises the following steps: identifying a three-dimensional space model of a target substation, and obtaining a key node list; the key node list comprises N key patrol points, and the key patrol points represent equipment points needing to be patrolled in the target substation; acquiring an obstacle list; generating a first route by using an A star algorithm and a preset evaluation function according to the starting point, the terminal point, the key node list and the obstacle list of the unmanned aerial vehicle; the preset evaluation function is used for describing the total cost of each waypoint in the first route, the preset evaluation function comprises a dynamic weight factor, and the dynamic weight factor is used for balancing the total cost of the waypoints based on the actual distance between the key patrol point and the unmanned aerial vehicle and the corresponding minimum safety distance; and optimizing the first route to obtain a target route. The method is used for achieving the effect of improving the route planning efficiency and the route safety.

Description

Technical Field

[0001] This application relates to the technical field of unmanned aerial vehicles (UAVs), and particularly to a method and device for generating a UAV inspection route. Background Art

[0002] With the progress of technology and the development of UAV technology, UAVs are widely used in the inspection and detection tasks of substations. UAVs can fly flexibly in complex environments, and through the cameras and sensors carried, they can conduct real-time monitoring and data collection on substation equipment, thereby improving the inspection efficiency and safety.

[0003] In the prior art, the generation of UAV inspection routes usually relies on manual experience or simple algorithm planning. However, simple path planning algorithms often ignore the influence of obstacles, resulting in the UAV being at risk of collision. Moreover, simple algorithms are also difficult to effectively handle the diversity and complexity of the equipment distribution in substations and cannot plan effective inspection routes.

[0004] Therefore, how to effectively consider the relationship between key inspection points and obstacles in path planning and optimize the flight path and inspection efficiency of UAVs has become an urgent problem to be solved. Summary of the Invention

[0005] The UAV inspection route generation method and device provided in the embodiments of this application are used to achieve effects such as improving the route planning efficiency and route safety.

[0006] In a first aspect, an embodiment of this application provides a method for generating a UAV inspection route, including:

[0007] Identifying a three-dimensional space model of a target substation and obtaining a list of key nodes; the list of key nodes includes N key inspection points, and the key inspection points represent the equipment points in the target substation that need to be inspected;

[0008] Obtaining a list of obstacles; the list of obstacles includes M obstacle nodes, and the obstacle nodes represent the waypoints corresponding to the obstacles that the UAV needs to avoid;

[0009] Using the A* algorithm and a preset evaluation function, generating a first route according to the starting point and ending point of the UAV, the list of key nodes, and the list of obstacles; the preset evaluation function is used to describe the total cost of each waypoint in the first route, and the preset evaluation function includes a dynamic weight factor, and the dynamic weight factor is used to balance the total cost of the waypoint based on the actual distance between the key inspection point and the UAV and the corresponding minimum safety distance;

[0010] Optimizing the first route to obtain a target route.

[0011] In a possible implementation, the method of generating a first flight path based on the A* algorithm and a preset evaluation function according to the starting point, ending point, the list of key nodes, and the list of obstacles of the unmanned aerial vehicle includes:

[0012] Obtain the waypoints corresponding to each key inspection point in the list of key nodes, and optimize the waypoints corresponding to the key inspection points according to the obstacle nodes in the list of obstacles, so that the waypoints corresponding to the key inspection points avoid the obstacle nodes;

[0013] Use the A* algorithm and a preset evaluation function to determine the priorities of the waypoints corresponding to each key inspection point in the list of key nodes according to the starting point and ending point of the unmanned aerial vehicle;

[0014] Generate a first flight path based on the priorities.

[0015] In a possible implementation, the method of using the A* algorithm and a preset evaluation function to determine the priorities of the waypoints corresponding to each key inspection point in the list of key nodes according to the starting point and ending point of the unmanned aerial vehicle includes:

[0016] Calculate the actual distances between each key inspection point in the list of key nodes and the waypoints corresponding to the key inspection points, and determine the dynamic weight factors of the waypoints corresponding to the key inspection points according to the actual distances and the corresponding minimum safety distances;

[0017] Use the A* algorithm and a preset evaluation function to calculate the total costs of the waypoints corresponding to the key inspection points based on the dynamic weight factors of the waypoints corresponding to the key inspection points, the starting point, and the ending point of the unmanned aerial vehicle;

[0018] Determine the priorities of the waypoints corresponding to each key inspection point according to the total costs.

[0019] In a possible implementation, the method of determining the dynamic weight factors of the waypoints corresponding to the key inspection points according to the actual distances and the corresponding minimum safety distances includes:

[0020] Calculate the difference between the corresponding minimum safety distance and the actual distance, and determine the reciprocal of the difference as the dynamic weight factor of the waypoint corresponding to the key inspection point.

[0021] In a possible implementation, the method of optimizing the first flight path to obtain a target flight path includes:

[0022] Calculate the distances between adjacent waypoints in the first flight path, and determine the waypoints with distances less than or equal to a preset distance as redundant points;

[0023] Remove the redundant points from the first flight path to obtain a target flight path.

[0024] In a possible implementation manner, identifying the three-dimensional space model of the target substation and obtaining a list of key nodes includes:

[0025] Input the three-dimensional space model of the target substation into a preset recognition model for recognition processing to obtain key inspection points, and construct a list of key nodes based on the key inspection points; wherein, the preset recognition model is a pre-trained deep learning model for identifying the three-dimensional space model of the target substation to determine key inspection points.

[0026] In a possible implementation manner, before identifying the three-dimensional space model of the target substation and obtaining a list of key nodes, the method further includes:

[0027] Obtain the real construction drawings of the target substation from multiple different shooting perspectives;

[0028] Input the real construction drawings into data visualization software to construct the three-dimensional space model of the target substation.

[0029] In a second aspect, an embodiment of the present application provides a device for generating an unmanned aerial vehicle (UAV) inspection route, including:

[0030] An identification unit, configured to identify the three-dimensional space model of the target substation and obtain a list of key nodes; the list of key nodes includes N key inspection points, and the key inspection points represent the equipment points in the target substation that need to be inspected;

[0031] An acquisition unit, configured to acquire a list of obstacles; the list of obstacles includes M obstacle nodes, and the obstacle nodes represent the waypoints corresponding to the obstacles that the UAV needs to avoid;

[0032] A processing unit, configured to use the A* algorithm and a preset evaluation function to generate a first route according to the starting point, the ending point, the list of key nodes, and the list of obstacles of the UAV; the preset evaluation function is used to describe the total cost of each waypoint in the first route, and the preset evaluation function includes a dynamic weight factor, and the dynamic weight factor is used to balance the total cost of the waypoints based on the actual distance between the key inspection point and the UAV and the corresponding minimum safety distance;

[0033] An optimization unit, configured to optimize the first route to obtain a target route.

[0034] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0035] The memory stores computer execution instructions;

[0036] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the first aspect and / or various possible implementation manners of the first aspect as described above.

[0037] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, they are used to implement the first aspect and / or various possible implementation manners of the first aspect as described above.

[0038] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the first aspect and / or various possible implementation manners of the first aspect as described above.

[0039] The method and device for generating a drone inspection route provided by the embodiments of the present application can automatically generate the inspection path of the drone by identifying the three-dimensional space model of the substation and using the A* algorithm, reducing manual intervention and planning time, and improving the route planning efficiency. In addition, during the process of using the A* algorithm for route planning, the influence of obstacles and the minimum safety distance on the route is also considered, and the drone route is optimized by introducing a dynamic weight factor to ensure that the drone can effectively avoid obstacles, reducing the collision risk. It is applicable to substation environments of different scales and complexities, has good scalability, and improves flight safety. Through automated, optimized, and intelligent path planning, the present application significantly improves the inspection efficiency, safety, and accuracy of drones in substation environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings here are incorporated into the description and form a part of this description, showing embodiments consistent with the present application, and are used together with the description to explain the principles of the present application.

[0041] Figure 1 It is an architecture diagram for generating a drone inspection route provided by an embodiment of the present application;

[0042] Figure 2 It is a schematic flowchart of a method for generating a drone inspection route provided by an embodiment of the present application;

[0043] Figure 3 It is a schematic flowchart of another method for generating a drone inspection route provided by an embodiment of the present application;

[0044] Figure 4 It is a schematic structural diagram of a device for generating a drone inspection route provided by an embodiment of the present application;

[0045] Figure 5 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0046] Through the above-mentioned accompanying drawings, specific embodiments of the present application have been shown, and there will be a more detailed description hereinafter. These drawings and textual descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. Detailed Description of Specific Embodiments

[0047] Exemplary embodiments will be described in detail herein, and examples thereof are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numerals in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0048] With the rapid development of the power system, the scale and complexity of substations have been continuously increasing. Traditional manual inspection methods for personnel have gradually exposed problems such as low efficiency and many potential safety hazards. In recent years, due to its high efficiency and flexibility, unmanned aerial vehicle (UAV) technology has been widely used in the field of power inspection. Before using a UAV for power inspection, it is necessary to first determine the inspection route so that the UAV can complete the inspection based on the inspection route.

[0049] Currently, most UAV inspection solutions rely on manual route planning by humans or planning through simple algorithms. However, manual route planning takes a long time. Especially in large substations, where there are a large number of devices and complex distributions, the efficiency of manual route planning is too low. In addition, manual planning may not be able to accurately evaluate the safety distances between equipment and facilities, resulting in the possibility of collisions between UAVs and equipment and facilities, presenting relatively large potential safety hazards. And simple algorithm planning lacks in-depth analysis of substation buildings and equipment, making it difficult to achieve precise route optimization.

[0050] In summary, the current UAV route planning solutions have deficiencies such as low efficiency, insufficient safety, and limited optimization capabilities, making it difficult to meet the requirements of large-scale substations and difficult to find the optimal route in complex environments.

[0051] To solve the above technical problems, an embodiment of the present application provides a method for generating a drone inspection route. Based on the establishment of a three-dimensional spatial model of a substation, by identifying the three-dimensional spatial model, key inspection points to be inspected can be determined. Then, the A* algorithm is used to plan the route, and an evaluation function including a dynamic weight factor is used to evaluate the total cost of the waypoints. The priority of each waypoint is determined through the total cost, so as to generate an initial route, and then optimize it to output the target route. Based on this, compared with the existing manual planning and simple algorithm route planning, it can not only meet the requirements of large-scale substations, but also quickly generate inspection routes in complex scenarios, improving the route planning efficiency and route safety.

[0052] The following uses specific embodiments to elaborate in detail on the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems. These several specific embodiments below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below with reference to the accompanying drawings.

[0053] It should be noted that the execution subject of the drone inspection route generation method provided in the embodiment of the present application can be a drone inspection route generation device, and this device can be deployed on an electronic device. The electronic device can be a device such as a mobile phone, a computer, a computer, a server, etc., and the embodiment of the present application does not make any restrictions. The embodiment of the present application takes the execution subject as the drone inspection route generation device as an example for detailed description.

[0054] Exemplarily, Figure 1 is an architecture diagram for generating a drone inspection route provided in an embodiment of the present application. As Figure 1 shown, the process of generating a drone inspection route can include: data acquisition, three-dimensional modeling, equipment identification and classification, route planning, route optimization, and output and execution. Among them, the data acquisition process performs: obtaining building and equipment model data from the substation; the three-dimensional modeling process performs: converting the obtained data into a three-dimensional spatial model; the equipment identification and classification process performs: identifying and classifying the equipment in the model; the route planning process performs: generating a preliminary route based on the improved A* algorithm; the route optimization process performs: optimizing the generated route to avoid redundant paths or cross flights; the output and execution process performs: exporting the optimized route as a flight plan file executable by the drone.

[0055] Figure 2 is a schematic flowchart of a method for generating a drone inspection route provided in an embodiment of the present application. As Figure 2 shown, the method for generating a drone inspection route provided in the embodiment of the present application includes:

[0056] S201. Identify the three-dimensional spatial model of the target substation and obtain a list of key nodes. Among them, the list of key nodes includes N key inspection points, and the key inspection points represent the equipment points in the target substation that need to be inspected.

[0057] Among them, N is an integer greater than or equal to 1. Exemplarily, the three-dimensional spatial model of the target substation describes the real structure of the target substation. In the case where the three-dimensional spatial model of the target substation has been pre-constructed, by identifying the three-dimensional spatial model of the target substation, the key equipment in the substation can be identified. These equipment usually include transformers, switches, lightning arresters, etc., all of which are objects that need to be inspected and maintained regularly. For each type of equipment, due to different equipment types, the key points to be inspected are different. For example, for a transformer, the oil level gauge of the transformer usually needs to be inspected; for a switch, the pressure gauge of the switch usually needs to be inspected; for a lightning arrester, the on-line detector of the lightning arrester usually needs to be inspected, etc.

[0058] In the embodiment of the present application, each equipment position point that needs to be inspected is defined as a key inspection point. These points are the points that the drone must observe when performing the inspection task. By regularly inspecting these key inspection points, the normal operation of the substation equipment can be ensured and potential problems can be discovered in time. The positions of these key inspection points in the three-dimensional space are usually represented by three-dimensional coordinates (x, y, z). All key inspection points are sorted into a list, called the list of key nodes. This list usually includes the coordinates of each key inspection point and possible additional information such as equipment type, inspection priority, etc., which are not limited in the embodiment of the present application.

[0059] Optionally, in a possible embodiment, identifying the three-dimensional spatial model of the target substation and obtaining the list of key nodes may include:

[0060] Input the three-dimensional spatial model of the target substation into a preset recognition model for recognition processing to obtain key inspection points, and construct a list of key nodes based on the key inspection points. Among them, the preset recognition model is a pre-trained deep learning model for identifying the three-dimensional spatial model of the target substation to determine key inspection points.

[0061] Exemplarily, the preset recognition model can be a deep learning model that combines computer vision and deep learning technologies to identify the device types in the three-dimensional space model and select key inspection points according to the device types. Specifically, the preset recognition model includes at least one device classifier model. The device classifier model can use a deep convolutional neural network architecture such as the open-source ResNet50. It is used to load and preprocess the three-dimensional space model of the target substation, adjust it to the input size required by the model (such as 224×224), then expand the dimensions to match the model input format, and then use the model for detection to obtain the probability distribution of the device types and determine the device types (such as transformers, switchgear, or lightning arresters, etc.) according to the detection results. In addition, the preset recognition model further includes at least one selection function, which is used to select different key inspection points according to the device types output by the device classifier model. For example: for transformers, positions such as oil level gauges, temperature sensors, and terminal blocks can be selected as key inspection points; for switchgear, positions such as pressure gauges and bus connections can be selected as key inspection points; for lightning arresters, positions such as leakage current monitors can be selected as key inspection points. Each key inspection point has its corresponding position coordinates, which can be calculated based on information such as the coordinates and dimensions of the device, or directly identified by the preset recognition model. The embodiments of the present application do not make restrictions on this.

[0062] During use, the three-dimensional space model of the target substation is input into the preset recognition model for processing. The preset recognition model will analyze the input data, identify the key devices in the substation, and extract the key inspection points from the identified devices. Then, the identified key inspection points are sorted into a list, and the three-dimensional coordinates of each point are recorded. According to needs, the node list can also include additional data such as device types, inspection priorities, and status information, so as to obtain a key node list for subsequent path planning and inspection tasks.

[0063] The embodiments of the present application automatically identify and extract key inspection points through the recognition model, reducing the workload of manual annotation and improving efficiency; in addition, as the substation equipment is updated or the environment changes, the model can re-identify and update the key node list to maintain the timeliness and accuracy of the data; the model can efficiently and accurately extract the device points that need to be focused on from the complex three-dimensional space model, providing reliable data support for the drone inspection task.

[0064] S202. Obtain an obstacle list; where the obstacle list includes M obstacle nodes, and the obstacle nodes represent the waypoints corresponding to the obstacles that the drone needs to avoid.

[0065] Exemplarily, during the inspection of the drone, in addition to accurately and efficiently completing the inspection of key inspection points, there are still some areas that the drone cannot reach or temporarily cannot reach during the actual inspection process, such as areas with obstacles such as trees and utility poles. The waypoints corresponding to these obstacle areas are the obstacle nodes of the embodiments of the present application.

[0066] Optionally, these obstacle nodes can be manually marked. When the three-dimensional space model of the target substation includes recognizable obstacles, the obstacles can also be determined by identifying the three-dimensional space model of the target substation, and then the position coordinates of the waypoints corresponding to the obstacles can be determined according to the positions of the obstacles as the obstacle nodes of the embodiments of the present application. The present application does not make any restrictions. The obtained obstacle nodes are sorted into a list to obtain an obstacle list. The obstacle list is used to avoid the drone passing through these obstacle nodes during path planning.

[0067] In some possible embodiments, there may also be no waypoints corresponding to the obstacles that the drone needs to avoid. Therefore, M is an integer greater than or equal to 0.

[0068] S203. Using the A* algorithm and a preset evaluation function, generate a first flight path according to the starting point, ending point, key node list and obstacle list of the drone; wherein, the preset evaluation function is used to describe the total cost of each waypoint in the first flight path, and the preset evaluation function includes a dynamic weight factor, and the dynamic weight factor is used to balance the total cost of the waypoints based on the actual distance between the key inspection point and the drone and the corresponding minimum safety distance.

[0069] Exemplarily, the A* algorithm is a heuristic-based path planning algorithm widely used in robot navigation and drone path planning. It finds the optimal path from the starting point to the ending point by evaluating the total cost of each possible path. In the A* algorithm, the evaluation function is used to calculate the total cost of the path, and the function usually includes a heuristic estimate and the actual cost of the path. In the embodiments of the present application, a dynamic weight factor is introduced into the preset evaluation function to balance the total cost of the path. The dynamic weight factor is dynamically adjusted according to the actual distance between the key inspection point and the drone and the minimum safety distance, making it more applicable.

[0070] In the embodiments of the present application, using the A* algorithm and a preset evaluation function, combined with the starting point, ending point, key node list and obstacle list of the drone, a preliminary drone flight path can be generated.

[0071] Optionally, in a possible embodiment, using the A* algorithm and a preset evaluation function, generating a first flight path according to the starting point, ending point, key node list and obstacle list of the drone may include:

[0072] S10. Obtain the waypoints corresponding to each key inspection point in the key node list, and optimize the waypoints corresponding to the key inspection points according to the obstacle nodes in the obstacle list, so that the waypoints corresponding to the key inspection points avoid the obstacle nodes;

[0073] S20. Use the A-star algorithm and a preset evaluation function to determine the priorities of the waypoints corresponding to each key inspection point in the key node list according to the starting point and the ending point of the UAV;

[0074] S30. Generate a first flight path based on the priorities.

[0075] Exemplarily, the waypoints corresponding to each key inspection point in the key node list can be obtained first. These waypoints are the specific positions that the UAV needs to pass through when performing tasks and can be represented by three-dimensional coordinates. When the UAV passes through the waypoints corresponding to the key inspection points, cameras and sensors carried on the UAV can perform real-time monitoring and data collection on the equipment at the key inspection points.

[0076] Optionally, the waypoints corresponding to each key inspection point can be comprehensively determined based on parameters such as the coordinate positions of each key inspection point, combined with inspection requirements, set inspection distances and angles, and performance parameters of the UAV (such as flight altitude, camera resolution, etc.). Each key inspection point can correspond to one or more waypoints to facilitate the collection of equipment data at the key inspection point from different angles. The embodiments of the present application do not limit this. After obtaining the waypoints corresponding to each key inspection point in the key node list, based on the obstacle nodes in the obstacle list, adjust the positions of the waypoints corresponding to the key inspection points so that the waypoints corresponding to the key inspection points avoid the obstacle nodes, thereby ensuring that the UAV will not collide with obstacles during flight and improving flight safety.

[0077] Furthermore, use the A-star algorithm and a preset evaluation function to determine the priorities of the waypoints corresponding to each key inspection point in the key node list according to the starting point and the ending point of the UAV, and generate the first flight path of the UAV according to the priorities of the waypoints. Among them, the generated first flight path is the preliminary path for the UAV to perform the inspection task and includes all the waypoints that need to be passed through. The waypoints with higher priorities will be preferentially included in the flight path. When the UAV performs the inspection task, it will preferentially pass through the waypoints with higher priorities.

[0078] By optimizing the waypoints and determining the priorities, it can be ensured that the UAV can efficiently complete the inspection task; through obstacle avoidance optimization and path evaluation, the flight risk can be reduced and the safety of the task can be improved; based on the above solutions, the present application can generate a preliminary flight path that takes into account key inspection points, obstacles, and priorities, providing effective guidance for the inspection task of the UAV.

[0079] Optionally, in a possible embodiment, step S20 of determining the priorities of the waypoints corresponding to each key inspection point in the key node list according to the starting point and the ending point of the UAV by using the A* algorithm and a preset evaluation function may include:

[0080] S21. Calculate the actual distance between each key inspection point in the key node list and the waypoint corresponding to the key inspection point, and determine the dynamic weight factor of the waypoint corresponding to the key inspection point according to the actual distance and the corresponding minimum safety distance;

[0081] S22. Use the A* algorithm and the preset evaluation function to calculate the total cost of the waypoint corresponding to the key inspection point based on the dynamic weight factor of the waypoint corresponding to the key inspection point, the starting point and the ending point of the UAV;

[0082] S23. Determine the priorities of the waypoints corresponding to each key inspection point according to the total cost.

[0083] Exemplarily, the actual distance between the key inspection point and the waypoint corresponding to the key inspection point, that is, the distance between the key inspection point and the UAV during inspection, can be calculated by using the Euclidean distance calculation formula or the Manhattan distance calculation formula. Preferably, the Euclidean distance calculation formula is used for calculation in the embodiments of the present application. Since the types of equipment for each key inspection point are different, the corresponding minimum safety distances may be different. In the embodiments of the present application, the minimum safety distance between the UAV and the equipment can be set according to the performance parameters of the UAV (such as flight altitude, camera resolution, etc.) and the safety distance requirements of each equipment.

[0084] Among them, the embodiments of the present application do not limit the specific values of the minimum safety distances corresponding to each key inspection point. For example, for a transformer, its minimum safety distance can be set to 1 meter; for a lightning arrester, its minimum safety distance can be set to 2 meters; and so on.

[0085] According to the actual distance between the key inspection point and the waypoint corresponding to the key inspection point and the corresponding minimum safety distance, the dynamic weight factor of the waypoint corresponding to the key inspection point can be determined. If the actual distance is close to or less than the minimum safety distance, the weight factor may increase to emphasize safety. If the actual distance is much greater than the minimum safety distance, the weight factor may decrease to optimize the path efficiency.

[0086] Optionally, in a possible embodiment, determining the dynamic weight factor of the waypoint corresponding to the key inspection point according to the actual distance and the corresponding minimum safety distance may include: calculating the difference between the corresponding minimum safety distance and the actual distance, and determining the reciprocal of the difference as the dynamic weight factor of the waypoint corresponding to the key inspection point.

[0087] Exemplarily, the calculation formula of the dynamic weight factor can be as shown in the following formula (1):

[0088] (1)

[0089] Wherein, represents the minimum safety distance; represents the actual distance between the key inspection point and the waypoint corresponding to the key inspection point; represents the weight factor of the waypoint corresponding to the key inspection point.

[0090] When calculating the dynamic weight factor, the difference between the corresponding minimum safety distance and the actual distance can be calculated first, and then the reciprocal of the difference can be obtained, so as to obtain the dynamic weight factor of the waypoint corresponding to the key inspection point.

[0091] Furthermore, the A* algorithm and a preset evaluation function are used to find the optimal path between the starting point and the ending point of the UAV. Among them, the formula of the preset evaluation function can be as shown in the following formula (2):

[0092] (2)

[0093] Wherein, f(n) represents the total cost; g(n) represents the actual cost from the starting point to the current node (e.g., represented by the available path length); h(n) represents the heuristic estimate from the current node to the next target node (e.g., represented by the available Euclidean distance).

[0094] In this application, the A* algorithm can be adopted to traverse and calculate the total cost of the waypoints corresponding to each key inspection point in the key node list based on the dynamic weight factor of the waypoint corresponding to each key inspection point, the starting point and the ending point of the UAV, and find the waypoint corresponding to the key inspection point with the lowest total cost as the current optimal node, and sequentially determine the current node and the next target node in the route until the priorities of the waypoints corresponding to all key inspection points are determined. Among them, the waypoint with a lower total cost represents a better path selection, and a higher priority is given to it.

[0095] The priority information is used to guide the task execution order of the UAV. Using the priority information to optimize the path planning can ensure that the UAV passes through the waypoints with lower total cost first, improving the efficiency and safety of the inspection task.

[0096] The embodiment of this application considers the minimum safety distance, optimizes the path selection of the UAV through the calculation of the dynamic weight factor and the total cost, reasonably arranges the execution order of the inspection task, improves the overall task management level, and also improves the flight safety and flight efficiency.

[0097] S204. Optimize the first route to obtain the target route.

[0098] Exemplarily, the first flight path is a preliminary UAV flight path generated by using the A* algorithm and a preset evaluation function, in combination with the starting point, the ending point, the list of key nodes, and the list of obstacles. To improve the feasibility of the flight path and ensure that the UAV can efficiently and safely complete the inspection task of the substation, and to avoid redundant paths or cross flights during the flight of the UAV, the first flight path needs to be optimized. Optionally, the optimization may include path smoothing, reducing unnecessary turns, ensuring better obstacle avoidance performance, etc., which are not limited in the embodiments of the present application.

[0099] Optionally, in a possible embodiment, optimizing the first flight path to obtain a target flight path may include:

[0100] S100. Calculate the distance between two adjacent waypoints in the first flight path, and determine that the waypoints with a distance less than or equal to the preset distance are redundant points;

[0101] S200. Remove the redundant points from the first flight path to obtain the target flight path.

[0102] Exemplarily, the distance between adjacent waypoints can help identify the redundant parts in the flight path, that is, unnecessary waypoints. For each pair of adjacent waypoints in the first flight path, the Euclidean distance formula can be used to calculate the distance between them. If the distance between adjacent waypoints is less than or equal to the preset distance, one or more of the waypoints are considered redundant. Among them, the embodiments of the present application do not limit the value of the preset distance, which can be set according to the actual situation. For example, it can be 0.5 m, etc. After removing the identified redundant points from the first flight path, the obtained flight path is output as the target flight path. The optimized flight path is exported as a flight plan file executable by the UAV and sent to the UAV. The UAV will perform actual inspections according to the generated flight path and real-time feedback inspection data to complete the inspection as required.

[0103] By removing redundant points, not only can the flight time and energy consumption of the UAV be reduced, the overall efficiency of the inspection task be improved, the simplified flight path is also easier to execute, the path complexity is reduced, and the difficulty of navigation and control is reduced. In addition, reducing unnecessary waypoints also helps to reduce the flight risk. By optimizing the flight path, redundant paths during the flight of the UAV are avoided.

[0104] In addition, in some possible embodiments, the effectiveness of the target flight path can also be verified by simulating the flight to ensure that the UAV can complete all inspection tasks within the specified time.

[0105] The method for generating a drone inspection route provided by the embodiment of the present application can automatically generate the inspection path of the drone by identifying the three-dimensional space model of the substation and using the A* algorithm, reducing manual intervention and planning time, and improving the efficiency of route planning. In addition, during the process of using the A* algorithm for route planning, the impacts of obstacles and the minimum safety distance on the route are also considered, and the drone route is optimized by introducing a dynamic weight factor to ensure that the drone can effectively avoid obstacles, reducing the collision risk. It is applicable to substation environments of different scales and complexities, has good scalability, and improves flight safety. Through automated, optimized, and intelligent path planning, the present application significantly improves the inspection efficiency, safety, and accuracy of the drone in the substation environment.

[0106] Figure 3 It is a schematic flowchart of another method for generating a drone inspection route provided by the embodiment of the present application. As Figure 3 shown, the method for generating a drone inspection route provided by the embodiment of the present application may include:

[0107] S301. Obtain the real construction maps of the target substation from multiple different shooting perspectives.

[0108] Exemplarily, in the case where the three-dimensional space model of the target substation has not been pre-constructed, it is necessary to first construct the three-dimensional space model of the target substation. Specifically, the target substation can be photographed by using a high-resolution camera, a drone, etc., to ensure that the photographed images have sufficient resolution and clarity. When photographing, the real construction maps of the target substation from multiple different shooting perspectives are taken from the ground, the air, and different orientations to ensure that all key areas and equipment of the substation are covered for subsequent processing and modeling.

[0109] It can be understood that based on the real construction maps of the target substation from multiple different shooting perspectives, the complete view of the substation can be reproduced, and the position coordinates, dimensions (such as length, width, height, etc.) of buildings, substation equipment, etc. in the three-dimensional space can also be determined, facilitating numerical calculations and the visualization of three-dimensional data.

[0110] S302. Input the real construction maps into data visualization software to construct the three-dimensional space model of the target substation.

[0111] Exemplarily, the multi-perspective images obtained are imported into the selected data visualization software, and the data visualization software will process the input images to construct the three-dimensional space model of the target substation. Optionally, the data visualization software can be the ax.bar3d function in the open-source Python plotting library, etc., and the embodiment of the present application does not make any restrictions.

[0112] The data visualization software aligns images from different perspectives through feature point matching and image registration techniques to ensure that all images are processed in the same coordinate system. Then, through multi-view stereo vision technology, a three-dimensional point cloud of the substation is generated. Based on the point cloud data, the buildings, ground, top surface, side surfaces, main equipment bodies, key equipment points, etc. in the target substation are drawn in sequence to generate a three-dimensional mesh model, which provides the detailed geometric structure of the substation. Finally, the color information of the original images is mapped onto the three-dimensional model to generate a three-dimensional model with a realistic appearance structure. In addition, the generated three-dimensional model can be denoised and thinned to enhance the detailed parts of the model, improve the clarity of the model, and ensure the accuracy of the equipment and structures.

[0113] Among them, constructing a three-dimensional space model of the target substation is the basis for realizing the automatic planning of the UAV inspection route. An accurate three-dimensional space model can provide reliable data support for the UAV inspection task. Based on the three-dimensional space model of the target substation, the efficiency of the UAV inspection route planning can be effectively improved.

[0114] S303. Identify the three-dimensional space model of the target substation, and obtain the key node list and obstacle list.

[0115] Among them, the key node list includes N key inspection points, and the key inspection points represent the equipment points that need to be inspected in the target substation; the obstacle list includes M obstacle nodes, and the obstacle nodes represent the waypoints corresponding to the obstacles that the UAV needs to avoid.

[0116] S304. Obtain the waypoints corresponding to each key inspection point in the key node list, and optimize the waypoints corresponding to the key inspection points according to the obstacle nodes in the obstacle list, so that the waypoints corresponding to the key inspection points avoid the obstacle nodes.

[0117] S305. Calculate the actual distance between each key inspection point in the key node list and the waypoint corresponding to the key inspection point, and determine the dynamic weight factor of the waypoint corresponding to the key inspection point according to the actual distance and the corresponding minimum safety distance.

[0118] S306. Use the A* algorithm and a preset evaluation function to calculate the total cost of the waypoint corresponding to the key inspection point based on the dynamic weight factor of the waypoint corresponding to the key inspection point, the starting point and the ending point of the UAV.

[0119] S307. Determine the priority of the waypoint corresponding to each key inspection point according to the total cost.

[0120] S308. Generate the first route based on the priority.

[0121] S309. Optimize the first route to obtain the target route.

[0122] It should be noted that for the specific implementation of steps S303 to S309, reference can be made to the descriptions of other embodiments, and details will not be elaborated here. In practical applications, when generating the drone inspection route, some or all of the above steps may be included, and the embodiments of this application do not make any restrictions.

[0123] The drone inspection route generation method provided by the embodiments of this application first generates a three-dimensional space model of the target substation, then identifies the three-dimensional space model of the substation, and then uses the A* algorithm for route planning, which can automatically generate the inspection path of the drone, reducing manual intervention and planning time, and improving the route planning efficiency. In addition, during the process of using the A* algorithm for route planning in this application, the impacts of obstacles and the minimum safety distance on the route are also considered. By introducing a dynamic weight factor to optimize the drone route, it is ensured that the drone can effectively avoid obstacles, reducing the collision risk. It is applicable to substation environments of different scales and complexities, has good scalability, and improves flight safety.

[0124] Figure 4 It is a schematic structural diagram of a drone inspection route generation device provided by the embodiments of this application. As Figure 4 shown, the drone inspection route generation device 40 provided in this embodiment includes an identification unit 401, an acquisition unit 402, a processing unit 403, and an optimization unit 404.

[0125] Among them, the identification unit 401 is used to identify the three-dimensional space model of the target substation and obtain a list of key nodes. The list of key nodes includes N key inspection points, and the key inspection points represent the equipment points that need to be inspected in the target substation.

[0126] The acquisition unit 402 is used to obtain a list of obstacles. The list of obstacles includes M obstacle nodes, and the obstacle nodes represent the waypoints corresponding to the obstacles that the drone needs to avoid.

[0127] The processing unit 403 is used to use the A* algorithm and a preset evaluation function to generate a first route according to the starting point, ending point, list of key nodes, and list of obstacles of the drone. The preset evaluation function is used to describe the total cost of each waypoint in the first route. The preset evaluation function includes a dynamic weight factor, and the dynamic weight factor is used to balance the total cost of the waypoints based on the actual distance between the key inspection points and the drone and the corresponding minimum safety distance.

[0128] The optimization unit 404 is used to optimize the first route to obtain the target route.

[0129] The device provided in this embodiment can execute the method provided by the above method embodiment, and its implementation principle and technical effects are similar, and details will not be elaborated here.

[0130] Based on the above device embodiments, in some possible implementation manners, the processing unit 403 is specifically configured to:

[0131] Obtain the waypoints corresponding to each key inspection point in the key node list, and optimize the waypoints corresponding to the key inspection points according to the obstacle nodes in the obstacle list, so that the waypoints corresponding to the key inspection points avoid the obstacle nodes;

[0132] Use the A* algorithm and a preset evaluation function to determine the priorities of the waypoints corresponding to each key inspection point in the key node list according to the starting point and the ending point of the UAV;

[0133] Generate a first flight path based on the priorities.

[0134] Based on the above device embodiments, in some possible implementation manners, the processing unit 403 is specifically configured to:

[0135] Calculate the actual distances between each key inspection point in the key node list and the waypoints corresponding to the key inspection points, and determine the dynamic weight factors of the waypoints corresponding to the key inspection points according to the actual distances and the corresponding minimum safety distances;

[0136] Use the A* algorithm and a preset evaluation function to calculate the total cost of the waypoints corresponding to the key inspection points based on the dynamic weight factors of the waypoints corresponding to the key inspection points, the starting point and the ending point of the UAV;

[0137] Determine the priorities of the waypoints corresponding to each key inspection point according to the total cost.

[0138] Based on the above device embodiments, in some possible implementation manners, the processing unit 403 is specifically configured to:

[0139] Calculate the difference between the corresponding minimum safety distance and the actual distance, and determine the reciprocal of the difference as the dynamic weight factor of the waypoint corresponding to the key inspection point.

[0140] Based on the above device embodiments, in some possible implementation manners, the optimization unit 404 is specifically configured to:

[0141] Calculate the distances between adjacent waypoints in the first flight path, and determine the waypoints with distances less than or equal to the preset distance as redundant points;

[0142] Remove the redundant points in the first flight path to obtain the target flight path.

[0143] Based on the above device embodiments, in some possible implementation manners, the recognition unit 401 is specifically configured to:

[0144] Input the three-dimensional space model of the target substation into a preset recognition model for recognition processing to obtain key inspection points, and construct a key node list based on the key inspection points; wherein, the preset recognition model is a pre-trained deep learning model for recognizing the three-dimensional space model of the target substation to determine key inspection points.

[0145] Based on the above device embodiments, in some possible implementation manners, the recognition unit 401 is further configured to:

[0146] Before recognizing the three-dimensional space model of the target substation and obtaining the key node list, obtain the real construction drawings of the target substation from multiple different shooting perspectives;

[0147] Input the real construction drawings into data visualization software to construct the three-dimensional space model of the target substation.

[0148] The device provided in this embodiment can be used to execute the method in the above embodiment, and its implementation principle and technical effects are similar, which will not be elaborated here.

[0149] It should be noted that it should be understood that the division of each module of the above device is only a logical function division. In actual implementation, it can be fully or partially integrated into a physical entity, or physically separated. And these modules can all be implemented in the form of software called by a processing element; they can also all be implemented in the form of hardware; or some modules can be implemented in the form of software called by a processing element, and some modules can be implemented in the form of hardware. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a certain processing element of the above device to perform the functions of the above data processing modules. The implementation of other modules is similar. In addition, all or part of these modules can be integrated together or can be independently implemented. Here, the processing element can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed by the integrated logic circuit in the processor element or the instruction in the form of software.

[0150] Figure 5 This is a schematic structural diagram of an electronic device provided in an embodiment of the present application. As Figure 5 shown, the electronic device 50 provided in this embodiment includes: at least one processor 501 and a memory 502. Optionally, the device 50 further includes a communication component 503. Among them, the processor 501, the memory 502, and the communication component 503 are connected through a bus 504.

[0151] In the specific implementation process, at least one processor 501 executes the computer execution instructions stored in the memory 502, so that at least one processor 501 executes the above method.

[0152] For the specific implementation process of the processor 501, reference can be made to the above method embodiments. Their implementation principles and technical effects are similar, and thus will not be elaborated herein.

[0153] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU for short), or other general-purpose processors, digital signal processors (DSP for short), application specific integrated circuits (ASIC for short), etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in combination with the invention can be directly implemented by the execution of the hardware processor, or implemented by the combination of the hardware and software modules in the processor.

[0154] The memory may include a high-speed random access memory (RAM), and may also include a non-volatile memory (NVM), such as at least one disk memory.

[0155] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, the buses in the drawings of this application are not limited to only one bus or one type of bus.

[0156] This application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0157] This application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When the processor executes the computer-executable instructions, the above method is implemented.

[0158] The above-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0159] An exemplary readable storage medium is coupled to the processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in a device.

[0160] The division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of devices or units can be in electrical, mechanical or other forms.

[0161] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0162] In addition, in each embodiment of the present invention, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0163] If a function 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 technical solution of the present invention, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, etc., various media that can store program codes.

[0164] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When this program is executed, it executes the steps including the above method embodiments; and the aforementioned storage medium includes: ROMs, RAMs, magnetic disks, or optical discs, etc., various media that can store program codes.

[0165] Finally, it should be noted that: After considering the specification and practicing the invention disclosed herein, those skilled in the art will easily think of other implementation manners of the present invention. The present invention is intended to cover any variations, uses, or adaptive changes of the present invention. These variations, uses, or adaptive changes follow the general principles of the present invention and include common general knowledge or conventional technical means in the technical field of the present invention that are not disclosed in the present invention. It is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

Claims

1. A method for generating an inspection route of an unmanned aerial vehicle, characterized in that Including: Identifying a three-dimensional spatial model of a target substation and obtaining a list of key nodes; The list of key nodes includes N key inspection points, and the key inspection points represent equipment points in the target substation that need to be inspected; Obtaining a list of obstacles; the list of obstacles includes M obstacle nodes, and the obstacle nodes represent waypoints corresponding to obstacles that the UAV needs to avoid; Using the A* algorithm and a preset evaluation function, generating a first flight path according to the starting point, ending point, the list of key nodes, and the list of obstacles of the UAV; The preset evaluation function is used to describe the total cost of each waypoint in the first flight path, and the preset evaluation function includes a dynamic weight factor, and the dynamic weight factor is used to balance the total cost of the waypoint based on the actual distance between the key inspection point and the UAV and the corresponding minimum safety distance; Optimizing the first flight path to obtain a target flight path.

2. The method according to claim 1, wherein The step of using the A* algorithm and a preset evaluation function to generate a first flight path according to the starting point, ending point, the list of key nodes, and the list of obstacles of the UAV includes: Obtaining waypoints corresponding to each key inspection point in the list of key nodes, and optimizing the waypoints corresponding to the key inspection points according to the obstacle nodes in the list of obstacles, so that the waypoints corresponding to the key inspection points avoid the obstacle nodes; Using the A* algorithm and a preset evaluation function to determine the priority of the waypoints corresponding to each key inspection point in the list of key nodes according to the starting point and ending point of the UAV; Generating a first flight path based on the priority.

3. The method according to claim 2, wherein The step of using the A* algorithm and a preset evaluation function to determine the priority of the waypoints corresponding to each key inspection point in the list of key nodes according to the starting point and ending point of the UAV includes: Calculating the actual distance between each key inspection point in the list of key nodes and the waypoint corresponding to the key inspection point, and determining the dynamic weight factor of the waypoint corresponding to the key inspection point according to the actual distance and the corresponding minimum safety distance; Using the A* algorithm and a preset evaluation function to calculate the total cost of the waypoint corresponding to the key inspection point based on the dynamic weight factor of the waypoint corresponding to the key inspection point, the starting point and ending point of the UAV; Determining the priority of the waypoints corresponding to each key inspection point according to the total cost.

4. The method according to claim 3, characterized in that, The step of determining the dynamic weight factor of the waypoint corresponding to the key inspection point according to the actual distance and the corresponding minimum safety distance includes: Calculating the difference between the corresponding minimum safety distance and the actual distance, and determining the reciprocal of the difference as the dynamic weight factor of the waypoint corresponding to the key inspection point.

5. The method according to claim 1, characterized in that The step of optimizing the first flight path to obtain a target flight path includes: Calculating the distance between adjacent two waypoints in the first flight path, and determining the waypoints with the distance less than or equal to the preset distance as redundant points; Removing the redundant points in the first flight path to obtain a target flight path.

6. The method according to claim 1, characterized in that, The step of identifying a three-dimensional spatial model of a target substation and obtaining a list of key nodes includes: Input the three-dimensional space model of the target substation into a preset recognition model for recognition processing to obtain key inspection points, and construct a key node list based on the key inspection points; wherein, the preset recognition model is a pre-trained deep learning model for recognizing the three-dimensional space model of the target substation to determine key inspection points.

7. The method according to any one of claims 1-6, characterized in that, Before recognizing the three-dimensional space model of the target substation and obtaining the key node list, the method further includes: Obtain the actual construction drawings of the target substation from multiple different shooting perspectives; Input the actual construction drawings into data visualization software to construct the three-dimensional space model of the target substation.

8. An unmanned aerial vehicle patrol route generation device, characterized in that, It includes: An identification unit for identifying the three-dimensional space model of the target substation and obtaining a key node list; The key node list includes N key inspection points, and the key inspection points represent the equipment points that need to be inspected in the target substation; An acquisition unit for acquiring an obstacle list; the obstacle list includes M obstacle nodes, and the obstacle nodes represent the waypoints corresponding to the obstacles that the unmanned aerial vehicle needs to avoid; A processing unit for using the A* algorithm and a preset evaluation function to generate a first flight path according to the starting point, the ending point, the key node list and the obstacle list of the unmanned aerial vehicle; The preset evaluation function is used to describe the total cost of each waypoint in the first flight path, and the preset evaluation function includes a dynamic weight factor, and the dynamic weight factor is used to balance the total cost of the waypoint based on the actual distance between the key inspection point and the unmanned aerial vehicle and the corresponding minimum safety distance; An optimization unit for optimizing the first flight path to obtain a target flight path.

9. An electronic device, characterized in that, It includes: A memory and a processor; The memory stores computer execution instructions; The processor executes the computer execution instructions stored in the memory, so that the processor executes the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer execution instructions, and when the computer execution instructions are executed by a processor, they are used to implement the method according to any one of claims 1-7.

Images