Calibration Method, Device, Electronic Device and Storage Medium for Robot Patrol Point

Abstract

The present application provides a calibration method, device, electronic device and storage medium for robot patrol points, relating to the technical field of patrol robots. The calibration method for robot patrol points includes: based on a virtual simulation scenario, receiving an information collection task and determining a collection image according to the information collection task; determining the target point cloud coordinates of the patrol target corresponding to the information collection task according to the collection image; determining the shooting parameters of the pan-tilt shooting device corresponding to the virtual patrol robot according to the target point cloud coordinates and the current docking position of the virtual patrol robot; and verifying the patrol points corresponding to the information collection task based on the shooting parameters, the current docking position, the target patrol path corresponding to the current docking position, and the patrol verification task. The present application sends an information collection task to the virtual patrol robot, realizes the calibration process of the patrol points in the virtual simulation scenario and adjusts the shooting parameters, ensuring the accuracy of the calibration of the patrol points.

Description

Technical Field

[0001] This application relates to the technical field of inspection robots, for example, to a method, device, electronic device, and storage medium for calibrating inspection points of a robot. Background Art

[0002] Inspection robots are increasingly widely used in the power field. They can perform inspection tasks autonomously or semi-autonomously, equipped with various sensors, cameras, and other detection devices, which can improve work efficiency, reduce costs, reduce dependence on manual inspections, and improve the accuracy and reliability of task execution. In the power field, especially in substations or converter stations, power inspection robots mainly inspect primary equipment or meters in the station. Before being put into use, the inspection points of the inspection robot need to be calibrated, including the positions of the inspection points, the docking positions of the inspection robot, and the parameter settings of the pan-tilt device during inspection, etc., so that the inspection robot can perform task inspections on primary equipment according to the calibrated information of the inspection points after being put into use.

[0003] Currently, the calibration method of inspection points mainly relies on on-site manual inspection and manual calibration. In related technologies, in some substations or converter stations, staff can control the robot to move to the required position, then adjust the relevant parameters of the shooting device carried by the robot to take pictures, and continuously correct. Affected by work tickets and meteorological conditions, the workload of the current inspection point calibration process is large and time-consuming, resulting in a low calibration efficiency of the current inspection points. Summary of the Invention

[0004] This application aims to provide a method, device, electronic device, and storage medium for calibrating inspection points of a robot.

[0005] According to one aspect of this application, a method for calibrating inspection points of a robot is proposed, including: based on a virtual simulation scenario, receiving a data collection task, and determining a data collection image according to the data collection task; wherein, the data collection image is an image taken by a virtual inspection robot according to the data collection task and multiple pre-planned inspection paths; determining the target point cloud coordinates of the inspection target corresponding to the data collection task according to the data collection image; determining the shooting parameters of the pan-tilt shooting device corresponding to the virtual inspection robot according to the target point cloud coordinates and the current docking position of the virtual inspection robot; verifying the inspection points corresponding to the data collection task based on the shooting parameters, the current docking position, the target inspection path corresponding to the current docking position, and the inspection verification task; wherein, the target inspection path is the path where the current docking position is located.

[0006] According to one aspect of the present application, a calibration device for robot inspection points is provided, including: a data collection image determination module, configured to receive a data collection task based on a virtual simulation scenario and determine a data collection image according to the data collection task; wherein, the data collection image is an image captured by a virtual inspection robot according to the data collection task and multiple pre-planned inspection paths; a coordinate determination module, configured to determine the target point cloud coordinates of the inspection target corresponding to the data collection task according to the data collection image; a shooting parameter determination module, configured to determine the shooting parameters of the pan-tilt shooting device corresponding to the virtual inspection robot according to the target point cloud coordinates and the current docking position of the virtual inspection robot; a verification module, configured to verify the inspection points corresponding to the data collection task based on the shooting parameters, the current docking position, the target inspection path corresponding to the current docking position, and the inspection verification task; wherein, the target inspection path is the path where the current docking position is located.

[0007] According to one aspect of the present application, an electronic device is provided, which includes: a processor; a memory storing a computer program, and when the computer program is executed by the processor, the processor is caused to execute the calibration method for robot inspection points as described above.

[0008] According to one aspect of the present application, a non-transitory computer-readable medium is provided, on which readable instructions are stored, and when the instructions are executed by the processor, the processor is caused to execute the calibration method for robot inspection points as described above.

[0009] It should be understood that the above general description and the following detailed description are only exemplary and do not limit the present application.

[0010] Beneficial effects:

[0011] Through the above embodiments provided by this application, based on the data collection task, the virtual inspection robot is controlled to perform data collection in the virtual simulation scenario, and automatically receives the collected images, target point cloud coordinates, shooting parameters, current docking positions, and target inspection paths after the data collection is completed. The automation of the inspection process is realized in the virtual simulation scenario, which not only reduces manual participation and labor costs, but also significantly improves the efficiency and coverage of the inspection, ensuring a comprehensive inspection of the inspection targets. Based on the collected images, the target point cloud coordinates of the inspection targets can be accurately determined, which helps to achieve the precise identification and positioning of the inspection targets. According to the target point cloud coordinates and the current docking position of the virtual inspection robot, the optimal shooting parameters of the pan-tilt shooting device are determined, which not only optimizes the shooting effect, reduces redundant data, but also improves the quality and efficiency of data acquisition, providing more accurate and useful information for subsequent data analysis and processing. Based on the shooting parameters, current docking position, target inspection path, and inspection verification task, the inspection points corresponding to the data collection task are verified in real time, ensuring the accuracy and reliability of the final inspection results, effectively avoiding potential safety hazards caused by missed or incorrect inspections, and improving the overall quality and reliability of the inspection work. By performing the inspection task through the virtual simulation scenario, various risks and other uncertainties including manual factors in the actual environment are avoided, such as bad weather, equipment failures, etc. At the same time, the virtual inspection can be repeated without restrictions on time and number, further reducing the costs and risks of the inspection work. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of this application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of this application. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings without exceeding the scope of protection required by this application.

[0013] Figure 1 It is a flowchart of the calibration method for the inspection points of the robot provided by the embodiment of this application;

[0014] Figure 2 It is a schematic diagram of the specific implementation process of step S11 provided by the embodiment of this application;

[0015] Figure 3 It is a schematic diagram of the specific implementation process of step S12 provided by the embodiment of this application;

[0016] Figure 4 It is a schematic diagram of the specific implementation process of step S13 provided by the embodiment of this application;

[0017] Figure 5It is a schematic diagram of the specific implementation process of step S131 provided by the embodiment of the present application;

[0018] Figure 6 It is a schematic diagram of the specific implementation process of step S132 provided by the embodiment of the present application;

[0019] Figure 7 It is a block diagram of the calibration device for the robot inspection points provided by the embodiment of the present application;

[0020] Figure 8 It is a schematic diagram of the structure of the electronic device provided by the embodiment of the present application. Detailed implementation manners

[0021] Now, example embodiments will be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this application will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. Identical reference numerals in the figures denote identical or similar parts, and thus their repetitive description will be omitted.

[0022] In addition, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of the embodiments of the present application. However, those skilled in the art will realize that the technical solutions of the present application can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be used. In other cases, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the present application.

[0023] The block diagrams shown in the drawings are only functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0024] The flowcharts shown in the drawings are only illustrative and do not necessarily include all the contents and operations / steps, nor do they necessarily have to be executed in the described order. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to the actual situation.

[0025] The specific implementation manners can refer to the following embodiments.

[0026] Figure 1The flowchart of the calibration method for the robot inspection points provided by the embodiments of the present application. The method of this embodiment can be applied to an inspection point calibration server, and a virtual simulation scene can be built on the inspection point calibration server. As Figure 1 shown, the method includes: step S10, step S11, step S12, and step S13.

[0027] In step S10, based on the virtual simulation scene, a data collection task is received, and a data collection image is determined according to the data collection task; wherein, the data collection image is an image taken by a virtual inspection robot according to the data collection task and multiple pre-planned inspection paths.

[0028] In the present application, the data collection task can be a task that requires the inspection robot to collect data of each inspection point in the inspection site. This task can be sent by relevant staff in the inspection site to the inspection point calibration server through the background server, and the inspection point calibration server receives it correspondingly.

[0029] A virtual simulation scene corresponding to the inspection site can be established in advance, and a virtual inspection robot corresponding to an inspection robot can be established in the virtual simulation scene. The virtual simulation scene includes, but is not limited to, real-scene point cloud data corresponding to the inspection site in equal proportion. The real-scene point cloud data includes real-scene photos and point cloud information of the inspection site. In the process of modeling the virtual inspection robot, it includes the establishment of the physical model of the entity inspection robot, the setting of walking modes such as wheeled / quadruped, and the setting of at least three pan-tilt shooting devices such as front / left / right. In some implementation manners, the pan-tilt shooting device can be a dual-light pan-tilt camera, and the dual-light pan-tilt camera includes two cameras, namely visible light and infrared. Among them, taking the forward direction of the virtual inspection robot as the front, the left and right are distinguished based on the forward direction.

[0030] According to the exemplary embodiment, the staff sends a data collection task to the inspection point calibration server (which can be abbreviated as the calibration server) through the background server. The virtual inspection robot set in the calibration server can analyze the data collection task and determine the area to be inspected therefrom. The inspection path can be pre-planned. The inspection path can include edges connected by charging points, charging preparation points of the inspection robot, and path points on each road in the actual inspection site. Among them, the path points can be at least two points on each straight road, and the edges have one-way and two-way attributes. Therefore, each road corresponding to the inspection site can correspond to multiple edges in the virtual simulation scene, that is, multiple inspection paths. The data collection task can include the area to be collected.

[0031] The virtual inspection robot can be controlled to traverse multiple inspection paths within the area to be surveyed, and the shortest inspection path can be determined from these inspection paths. Then, the virtual inspection robot can be controlled to move along the shortest inspection path. During the movement, the pan-tilt camera device on the virtual inspection robot takes real-time images, and the calibration server determines the captured images as the surveyed images.

[0032] In some implementation manners, methods such as the "method of working on an odd-even point graph" and the "Edmonds-Johnson method" can be used to determine the shortest inspection path among multiple inspection paths. Taking the method of working on an odd-even point graph as an example, in the specific implementation process, it can be first determined which nodes (the intersection points of each edge in the scene) in the virtual simulation scene have an odd degree and are used as odd points. For the paths between each pair of odd points, all their edges are added to the virtual simulation scene as repeated edges (i.e., the edges that the virtual inspection robot needs to pass through again) to ensure that the degrees of all nodes become even. The selection of the repeated edges is adjusted to minimize the total weight (or total length) of the repeated edges, so as to obtain the shortest traversal path. In some other implementation manners, according to a preset judgment criterion, such as there is at most one repeated edge on each edge and the total weight of the repeated edges on each loop is not greater than half of the total weight of the loop, it can be verified whether the obtained path is the shortest inspection path.

[0033] In step S11, according to the surveyed images, the target point cloud coordinates of the inspection target corresponding to the survey task are determined.

[0034] In this application, the survey task may include certain devices in certain areas that need to be photographed by the virtual inspection robot. Images of multiple devices at various angles and distances can be used as samples to pre-train an inspection target determination model.

[0035] According to the exemplary embodiment, the received surveyed images can be input into the above-mentioned inspection target determination model to directly output the inspection target. Then, based on the moment when each surveyed image is taken, it is determined where the virtual inspection robot takes the photo, and then the target point cloud coordinates of the inspection target in the virtual simulation scene are obtained.

[0036] In step S12, according to the target point cloud coordinates and the current docking position of the virtual inspection robot, the shooting parameters of the pan-tilt camera device corresponding to the virtual inspection robot are determined.

[0037] Since this application pre-sets a virtual simulation scene, the point cloud data of each position can be obtained in real time. The current docking position can be used to represent the point cloud data of the position where the virtual inspection robot is located at the moment when the target point cloud coordinates are obtained. The shooting parameters may include parameters such as the horizontal rotation angle, pitch angle of the pan-tilt, as well as the camera magnification and focal length.

[0038] According to an exemplary embodiment, the current docking position of the virtual inspection robot can be obtained, a model for determining shooting parameters is preset, the target point cloud coordinates and the current docking position are input into the shooting parameter determination model, and the shooting parameters of the pan-tilt shooting device are directly output.

[0039] According to some embodiments, the angular difference between the inspection target and the virtual inspection robot can also be determined based on the coordinate difference between the target point cloud coordinates and the current docking position, and the shooting parameters of the pan-tilt shooting device are adjusted based on this angular difference.

[0040] In step S13, based on the shooting parameters, the current docking position, the target inspection path corresponding to the current docking position, and the inspection verification task, the inspection points corresponding to the data collection task are verified; wherein, the target inspection path is the path where the current docking position is located.

[0041] In this application, the target inspection path is used to represent the path edge where the virtual inspection robot is located when the inspection target is photographed. This path edge is used as the target inspection path, and this target inspection path is a part of the shortest inspection path. The inspection verification task can be used to be sent by the calibration server to the virtual inspection robot, and this task can be used to guide the virtual inspection robot to re-photograph and verify the inspection points according to the determined shooting parameters, the current docking position, and the target inspection path.

[0042] According to an exemplary embodiment, the inspection verification task is sent to the virtual inspection robot. After receiving the task, the virtual inspection robot can go to the current docking position corresponding to each target inspection path, and adjust the pan-tilt shooting device to take pictures according to the corresponding shooting parameters, and obtain new images for verification to analyze whether the inspection points corresponding to the data collection task are appropriate.

[0043] In some implementation manners, if the position of the inspection target corresponding to the inspection point in the image does not meet the preset conditions, it means that the inspection point is inappropriate and the shooting parameters need to be adjusted again, etc. If the preset conditions are met, it means that the inspection point is appropriate and can be stored, and then used for the actual inspection process of the inspection robot.

[0044] This application realizes the automation of the inspection process in a virtual simulation scenario by sending data collection tasks to a virtual inspection robot and automatically receiving the collected images, target point cloud coordinates, shooting parameters, current docking positions, and target inspection paths after the data collection is completed. This not only reduces manual participation and labor costs but also significantly improves the inspection efficiency and coverage, ensuring a comprehensive inspection of the inspection targets. Based on the collected images, the target point cloud coordinates of the inspection targets can be accurately determined, which helps to achieve accurate identification and positioning of the inspection targets. According to the target point cloud coordinates and the current docking position of the virtual inspection robot, the optimal shooting parameters of the pan-tilt shooting device are determined, which not only optimizes the shooting effect, reduces redundant data, but also improves the quality and efficiency of data acquisition, providing more accurate and useful information for subsequent data analysis and processing. Based on the shooting parameters, current docking position, target inspection path, and inspection verification task, the inspection points corresponding to the data collection task are verified in real time, ensuring the accuracy and reliability of the final inspection results, effectively avoiding potential safety hazards caused by missed or incorrect inspections, and improving the overall quality and reliability of the inspection work. By performing inspection tasks through a virtual simulation scenario, various risks and other uncertainties involving humans in the actual environment, such as bad weather and equipment failures, are avoided. At the same time, virtual inspections can be repeated without restrictions on time and frequency, further reducing the costs and risks of inspection work.

[0045] According to some embodiments, a virtual simulation scenario, a virtual inspection robot, and an inspection point template database can be established in advance. Specifically, a real-world point cloud map can be established based on the inspection point information of the target inspection site, and a virtual simulation scenario can be established based on the real-world point cloud map; a virtual inspection robot can be established in the virtual simulation scenario according to the physical attributes of the target inspection robot; and an inspection point template database can be established according to the inspection requirements of the target inspection site.

[0046] In this application, an inspection point template database, that is, a preset inspection point template database, can be established in advance. The database can include the names of the inspection sites such as various substations or converter stations, for example, the substation names, and can also include voltage levels, equipment types, area IDs, bay IDs, main equipment IDs, component IDs, equipment point IDs, etc.

[0047] According to an exemplary embodiment, a high-precision laser scanner, such as lidar, and possibly auxiliary devices, such as binocular cameras, can be used to scan a target inspection site. The inspection site is scanned omnidirectionally by the laser scanner to collect point cloud data. This data contains the three-dimensional spatial information of the inspection site. According to the collected point cloud data, the coordinate transformation of the point cloud data is completed by calculating the coordinates of each point in the world coordinate system, and the collected point cloud data is preprocessed, including removing noise, filtering redundant data, and removing overlapping data, to improve the accuracy and efficiency of subsequent modeling.

[0048] Then, three-dimensional reconstruction algorithms (such as Poisson surface reconstruction, octree, etc.) can be used to process the preprocessed point cloud data to generate a real-world point cloud map. The generated real-world point cloud map is imported into a virtual simulation platform as the basis of the virtual simulation scene. According to the real-world point cloud map, a virtual environment of the inspection site is constructed in the virtual simulation platform, including buildings, equipment, roads, etc. The physical properties of the virtual environment, such as lighting, materials, etc., are set to improve the realism and immersion of the virtual environment.

[0049] According to the physical properties of the target inspection robot (such as size, shape, sensor configuration, etc.), a model of the virtual inspection robot is designed in the virtual simulation platform. Corresponding function simulations, such as mobility, sensor perception ability, data processing ability, etc., are added to the virtual inspection robot. The behavior logic of the virtual inspection robot is set to ensure that it can perform inspections in the virtual simulation scene according to the predetermined inspection path and tasks.

[0050] The inspection point information of the target inspection site is sorted out, including the type of the points, inspection requirements, etc. According to the inspection point information, an inspection point template is designed, including the identification of the points, inspection content, inspection standards, etc. The inspection point template is stored in a database to form an inspection point template database.

[0051] This application provides a high-precision three-dimensional model of the inspection site through the establishment of a real-world point cloud map, enabling the virtual inspection robot to perform rehearsals and planning in the virtual environment, improving the efficiency and accuracy of inspections. The virtual inspection robot in the virtual simulation scene can simulate the real inspection process, discover obstacles and potential hazards in the inspection path in advance, and reduce the repetitive labor and omissions in actual inspections. The virtual simulation scene and the virtual inspection robot can be flexibly configured and adjusted according to different inspection requirements to adapt to different inspection scenarios and tasks. The establishment of the inspection point template database standardizes and streamlines the inspection process, facilitating replication and expansion, and improving the repeatability and consistency of inspection work.

[0052] According to some embodiments, referring to Figure 2, step S11 can be specifically implemented through step S110, step S111, and step S112.

[0053] In step S110, the collection image is recognized to determine the inspection target.

[0054] In this application, there are multiple collection images. Some collection images may have inspection targets, while others may not.

[0055] According to the exemplary embodiment, image analysis, such as feature extraction, is performed on each collection image, and the extracted features are compared with the pre-stored feature images to further determine whether there is an inspection target in each collection image and what kind of inspection target it is.

[0056] In step S111, according to the real-scene point cloud map and the target area selection method, the area point cloud coordinates of the target area corresponding to the inspection target are determined.

[0057] In this application, the target area selection method can be set according to the attributes of different devices, and these attributes can include physical size, usually set height, etc. In some implementation manners, the size of the image selected by the target area selection method needs to ensure that the edges of the inspection target can be clearly selected. The target area is generally a rectangle, and the corresponding area point cloud coordinates at least include the point cloud coordinates of four vertices.

[0058] According to the exemplary embodiment, based on the target area selection method, the target area corresponding to the inspection target can be selected in the real-scene point cloud map. Then the area point cloud coordinates of the entire target area are obtained.

[0059] In step S112, based on the area point cloud coordinates and the positional relationship between the inspection target and the target area, the target point cloud coordinates of the inspection target are determined.

[0060] According to the exemplary embodiment, a target point cloud coordinate determination model can be preset, and by inputting the area point cloud coordinates and the positional relationship between the inspection target and the target area into the target point cloud coordinate determination model, the target point cloud coordinates of the inspection target are directly output.

[0061] In this application, by automatically identifying the inspection targets in the collection images, the time cost of manual identification and marking is reduced, making the inspection process faster and more efficient, and improving the overall efficiency of the inspection work. By using the real-scene point cloud map and the target area selection method, the target area where the inspection target is located can be accurately positioned, and based on the area point cloud coordinates of this area, the specific point cloud coordinates of the inspection target can be further determined. Compared with traditional two-dimensional images or simple coordinate positioning, the accuracy and reliability of target positioning are greatly improved. By comprehensively considering the positional relationship between the inspection target and the target area, the specific position of the inspection target can be determined more accurately, ensuring the effectiveness and pertinence of the inspection work.

[0062] According to some embodiments, referring to Figure 3 , step S12 can be specifically implemented through step S120, step S121, and step S122.

[0063] In step S120, obtain the current docking point cloud coordinates corresponding to the current docking point.

[0064] Since the virtual inspection robot works in a virtual simulation scenario, and the virtual simulation scenario is set based on the real-scene point cloud map, the point cloud coordinates of the required equipment can be obtained.

[0065] According to the exemplary embodiments, directly obtain the current docking point cloud coordinates corresponding to the current docking point in the virtual simulation scenario.

[0066] In step S121, according to the target point cloud coordinates and the current docking point cloud coordinates, determine the positional relationship between the virtual inspection robot and the inspection target.

[0067] According to the exemplary embodiments, calculate the relative distance, direction angle, pitch angle, etc. between the target point cloud coordinates and the current docking point cloud coordinates through spatial geometry, and take the determined relative distance, direction angle, and pitch angle as a whole as the positional relationship.

[0068] In some implementation manners, a positional relationship determination model can be established in advance, and by inputting the target point cloud coordinates and the current docking point cloud coordinates into this model, directly output the positional relationship between the virtual inspection robot and the inspection target.

[0069] In step S122, based on the positional relationship and the performance parameters of the pan-tilt shooting device, determine the shooting parameters of the pan-tilt shooting device.

[0070] The performance parameters of the pan-tilt shooting device can be used to represent the shooting settings of the pan-tilt shooting device itself before it is produced and put into use, and can include the zoom range, maximum / minimum shooting angle, resolution, etc.

[0071] According to an exemplary embodiment, a shooting parameter determination model can be preset. By inputting the positional relationship and performance parameters into the shooting parameter determination model, the shooting parameters of the pan-tilt shooting device can be directly output.

[0072] In this application, by accurately calculating the positional relationship between the virtual inspection robot and the inspection target, it is possible to ensure that the pan-tilt shooting device accurately aims at the target point cloud coordinates. This method of determining shooting parameters based on three-dimensional spatial position information significantly improves the accuracy and precision of shooting compared to traditional methods based on two-dimensional images or rough estimations. Determining shooting parameters based on the positional relationship and performance parameters of the pan-tilt shooting device (such as zoom range, maximum / minimum shooting angle, resolution, etc.) can make full use of the performance advantages of the device and avoid problems such as blurring, overexposure, and underexposure during shooting. At the same time, by adjusting parameters such as the focal length and shooting angle, it is possible to ensure the best quality of the captured images or videos. By automatically determining the shooting parameters, the time cost of manual intervention and adjustment is reduced, making the inspection process faster and more efficient. The virtual inspection robot can quickly adjust the state of the pan-tilt shooting device, aim at the target for shooting, without waiting for manual instructions or manual adjustment, thereby improving the overall efficiency of the inspection operation.

[0073] According to some embodiments, with reference to Figure 4 , step S13 can be specifically implemented through step S130, step S131, and step S132.

[0074] In step S130, according to the shooting parameters, the current docking point, and the target inspection path, determine the information of the collection point corresponding to the collection task; extract the primary equipment information from the collection task.

[0075] In this application, the collection task may include primary equipment information, and the primary equipment information may include relevant information such as the equipment model, serial number, and operating status of different equipment.

[0076] According to an exemplary embodiment, take the shooting parameters, the current docking point, and the target inspection path as a whole as the information of the collection point corresponding to the collection task. Extract the primary equipment information from the collection task.

[0077] In step S131, according to the primary equipment information, the preset electrical interval, the preset equipment model corresponding to the primary equipment information, the collection point information, and the inspection point template database, determine the alternative point configuration information.

[0078] In the power system, for safety and maintenance needs, devices or combinations of devices with different functions are divided into different areas, and the spatial distance between these areas is the electrical interval. The preset electrical interval can be set in advance according to design specifications, safety requirements, and the actual situation of the target inspection site.

[0079] In some implementations, the historical points obtained can be verified after the execution of the historical inspection tasks. After passing the verification, an inspection point template generated based on the historical points and the historical inspection tasks is stored in the inspection point template database.

[0080] In this application, to facilitate the simulation and management of primary equipment in a virtual simulation scenario, a preset model can be created in advance for each type of equipment, and this model contains information such as the geometric shape, physical properties, and electrical characteristics of the equipment.

[0081] According to the exemplary embodiment, information such as the model number and serial number of the equipment to be inspected corresponding to the current data collection task is extracted from the primary equipment information. Then, the preset equipment models corresponding to these equipment are searched for and loaded from multiple preset equipment models set in advance. Using the preset electrical interval, preset equipment model, and data collection point information as labels, the configuration information corresponding to the matching alternative points is found in the inspection point template database, which is the alternative point configuration information. Among them, the alternative point configuration information can be used to represent the information of the inspection points calibrated at the current moment, and can include the order during inspection, etc.

[0082] In step S132, according to the inspection verification task and the alternative point configuration information, the inspection images captured by the virtual inspection robot are determined, so as to judge whether it is necessary to recalibrate the inspection points based on the inspection images, and generate the target point configuration information for the actual inspection process.

[0083] In this application, the inspection verification task can be used to guide the virtual inspection robot to verify the rationality of the inspection point configuration and the inspection effect. This inspection verification task can be sent by the staff to the calibration server through the background server, and then verified by the calibration server. In some implementations, the staff can send the inspection verification task to the calibration server through the background server to instruct the calibration server to send relevant information such as inspection images or inspection points to the background server for verification, and can also send the verification results to the calibration server.

[0084] According to the exemplary embodiment, according to the received inspection verification task, the virtual inspection robot can perform automatic inspection according to the alternative point configuration information, and capture and upload inspection images during the inspection process. By performing image analysis on the inspection images, it is judged whether the equipment captured in the inspection images meets the preset requirements, such as no deformation, the equipment is displayed in the middle of the inspection image, and the clarity is relatively high, etc. If a certain inspection image does not meet the preset requirements, it means that it is necessary to recalibrate the inspection points of the equipment corresponding to this inspection image. The recalibrated inspection points and the inspection points that meet the preset requirements can be used as the target point configuration information for the virtual inspection robot to perform actual inspection in the target inspection site.

[0085] By comprehensively considering multiple factors such as shooting parameters, current docking points, target inspection paths, and primary equipment information, this application can more accurately determine the positions and shooting requirements of inspection points, ensure that key equipment or areas are not missed during the inspection process, reduce unnecessary repeated shooting at the same time, and improve the inspection efficiency. In the inspection verification task, the virtual inspection robot conducts simulated inspections according to the alternative point configuration information and uploads the inspection images. These images serve as important bases for judging the rationality of the inspection point configuration, and their quality and reliability directly affect subsequent judgments and decisions. By optimizing the shooting parameters and point configuration, the clarity and accuracy of the inspection images can be significantly improved. Verifying and optimizing the inspection points in a virtual environment can avoid frequent adjustments due to improper point configuration during the actual inspection process. This can not only save labor and material costs, but also reduce the inspection time delay caused by adjustments and improve the overall efficiency of the inspection work.

[0086] According to some embodiments, referring to Figure 5 , step S131 can be specifically implemented through step S1310 and step S1311.

[0087] In step S1310, according to the primary equipment information, the preset electrical interval, and the preset equipment model corresponding to the primary equipment information, the data collection order of the virtual inspection robot is determined.

[0088] In this application, the placement positions and working modes of the equipment in the target inspection site basically do not change. The primary equipment information can include information such as the placement positions and working modes of the equipment, and the working mode can include the operation associations between the equipment, etc. Based on the primary equipment information, the preset electrical interval, and the corresponding preset equipment model, the data collection order of the virtual inspection robot can be obtained.

[0089] In some implementation manners, a data collection order determination model can be established in advance. This model can be associated with the preset equipment model. By inputting the primary equipment information and the preset electrical interval into this model, the data collection order can be directly output.

[0090] In step S1311, according to the data collection order, the data collection point information is associated with the preset inspection point template database to form alternative point configuration information.

[0091] According to the exemplary embodiments, the templates related to the equipment corresponding to the current data collection task are obtained from the preset inspection point template database, which can include the layout of the inspection points, shooting requirements, etc. According to the data collection order, the shooting parameters, current docking points, and target inspection paths corresponding to each inspection point in the data collection point information are associated with the corresponding inspection point templates to generate alternative point configuration information.

[0092] By comprehensively considering primary equipment information, electrical bays, and preset equipment models, this application can more accurately determine the data collection order of virtual inspection robots, reducing unnecessary movement and waiting time, thereby improving the overall efficiency and accuracy of inspections. Associating the data collection point information with the inspection point template database enables the point configuration to be no longer limited to fixed templates, but to be flexibly adjusted according to specific primary equipment information and electrical bays. This flexibility helps to adapt to inspection requirements in different scenarios and improves the adaptability and effectiveness of inspections. During the process of determining the data collection order, factors such as electrical bays and equipment layout are considered to optimize the inspection path. This helps to reduce duplicate paths and ineffective movements during inspections and improves the efficiency and safety of inspections.

[0093] According to some embodiments, referring to Figure 6 , in the case where step S132 determines whether it is necessary to recalibrate the inspection points based on the inspection image to generate the target point configuration information for the actual inspection process, it can be specifically implemented through step S1320 and step S1321.

[0094] In step S1320, based on the inspection image, determine the image position of the inspection target in the inspection image; based on the image position and preset recalibration conditions, determine whether it is necessary to recalibrate the inspection points.

[0095] In this application, the preset recalibration conditions can be set based on inspection requirements and inspection targets, such as the attributes of equipment, components, etc.

[0096] According to the exemplary embodiment, in the case where the calibration server performs a verification operation, the inspection image captured by the virtual inspection server can be analyzed, and image processing techniques, such as edge detection, feature recognition, etc., can be used to determine the specific position of the inspection target (such as equipment, components, etc.) in the image. This includes determining key information such as the center point coordinates and bounding boxes of the target.

[0097] Compare the analyzed specific position with the recalibration conditions to determine whether the recalibration conditions are met. If they are met, there is no need to recalibrate; if not, it means that recalibration is required.

[0098] In step S1321, in the case where there is no need to recalibrate the inspection points, determine the alternative point configuration information as the target point configuration information; in the case where it is necessary to recalibrate the inspection points, receive externally input calibration point data to determine the target point configuration information based on the calibration point data and the alternative point configuration information.

[0099] In this application, the calibration point data can be the adjustment of the shooting parameters of the pan-tilt shooting device in the virtual simulation scenario by relevant staff after receiving a prompt for recalibration.

[0100] According to the exemplary embodiment, when it is not necessary to recalibrate the inspection points, the alternative point configuration information is determined as the target point configuration information. When it is necessary to recalibrate the inspection points, calibration point data input by relevant staff is received, and then the calibration point data is used to replace the configuration information that needs to be recalibrated. The calibration point data and the alternative point configuration information that does not need to be recalibrated are used as the target point configuration information as a whole.

[0101] Through the precise analysis of the positions of inspection targets in the inspection images and in combination with preset recalibration conditions, this application can promptly detect and correct possible deviations in the inspection points. When it is necessary to recalibrate the inspection points, external input calibration point data can be received, and the alternative point configuration information can be adjusted according to these data. This flexible adjustment mechanism enables the inspection process to respond quickly and be optimized according to the actual situation, improving the adaptability and flexibility of the inspection work.

[0102] The device embodiments of this application are described below, which can be used to execute the method embodiments of this application. For details not disclosed in the device embodiments of this application, reference can be made to the method embodiments of this application.

[0103] Figure 7 It is a block diagram of a calibration device for inspection points of a robot provided in an embodiment of this application. As Figure 7 shown, the calibration device 700 for inspection points of a robot includes a data collection image determination module 701, a coordinate determination module 702, a shooting parameter determination module 703, and a verification module 704.

[0104] The data collection image determination module 701 can receive a data collection task based on a virtual simulation scenario and determine a data collection image according to the data collection task; wherein, the data collection image is an image captured by a virtual inspection robot according to the data collection task and a plurality of pre-planned inspection paths.

[0105] The coordinate determination module 702 can determine the target point cloud coordinates of the inspection target corresponding to the data collection task according to the data collection image.

[0106] The shooting parameter determination module 703 can determine the shooting parameters of the pan-tilt shooting device corresponding to the virtual inspection robot according to the target point cloud coordinates and the current docking position of the virtual inspection robot.

[0107] The verification module 704 can verify the inspection points corresponding to the data collection task based on the shooting parameters, the current docking position, the target inspection path corresponding to the current docking position, and the inspection verification task; wherein, the target inspection path is the path where the current docking position is located.

[0108] Optionally, the calibration device 700 for the robot patrol points further includes a scene construction module 705, which can establish a real - point cloud map according to the patrol point information of the target patrol site, and establish a virtual simulation scene based on the real - point cloud map; establish a virtual patrol robot in the virtual simulation scene according to the physical attributes of the target patrol robot; and establish a patrol point template database according to the patrol requirements of the target patrol site.

[0109] Optionally, the coordinate determination module 702 can specifically identify the information - collection image, determine the patrol target; determine the regional point - cloud coordinates of the target area corresponding to the patrol target according to the real - point cloud map and the target area selection method; and determine the target point - cloud coordinates of the patrol target based on the regional point - cloud coordinates, the positional relationship between the patrol target and the target area.

[0110] Optionally, the shooting parameter determination module 703 can specifically obtain the current docking point - cloud coordinates corresponding to the current docking position; determine the positional relationship between the virtual patrol robot and the patrol target according to the target point - cloud coordinates and the current docking point - cloud coordinates; and determine the shooting parameters of the pan - tilt shooting device based on the positional relationship and the performance parameters of the pan - tilt shooting device.

[0111] Optionally, the verification module 704 can specifically determine the information - collection point - position information corresponding to the information - collection task according to the shooting parameters, the current docking position, and the target patrol path; extract the primary equipment information from the information - collection task; determine the alternative point - position configuration information according to the primary equipment information, the preset electrical interval, the preset equipment model corresponding to the primary equipment information, the information - collection point - position information, and the patrol point template database; and determine the patrol images captured by the virtual patrol robot according to the patrol verification task and the alternative point - position configuration information, so as to judge whether it is necessary to recalibrate the patrol points according to the patrol images, and generate the target point - position configuration information for the actual patrol process.

[0112] Optionally, when the verification module 704 determines the alternative point - position configuration information according to the primary equipment information, the preset electrical interval, the preset equipment model corresponding to the primary equipment information, the information - collection point - position information, and the patrol point template database, it can specifically determine the information - collection sequence of the virtual patrol robot according to the primary equipment information, the preset electrical interval, and the preset equipment model corresponding to the primary equipment information; and associate the information - collection point - position information with the preset patrol point template database according to the information - collection sequence to form the alternative point - position configuration information.

[0113] Optionally, when the verification module 704 determines whether it is necessary to recalibrate the inspection points based on the inspection image to generate the target point configuration information for the actual inspection process, it can specifically determine the image position of the inspection target in the inspection image according to the inspection image; determine whether it is necessary to recalibrate the inspection points based on the image position and the preset recalibration conditions; when it is not necessary to recalibrate the inspection points, determine the alternative point configuration information as the target point configuration information; when it is necessary to recalibrate the inspection points, receive the externally input calibration point data to determine the target point configuration information according to the calibration point data and the alternative point configuration information.

[0114] The device performs functions similar to the methods provided above. For other functions, please refer to the previous description and will not be elaborated here.

[0115] Figure 8 The following is a schematic structural diagram of the electronic device provided by the embodiment of the present application. As Figure 8 shown, the electronic device 800 in this embodiment may include: a memory 801 and a processor 802.

[0116] A computer program is stored on the memory 801. When the computer program is executed by the processor 802, the processor 802 is caused to execute the method in the above embodiment.

[0117] Among them, the processor 802 and the memory 801 are connected, such as through a bus.

[0118] Optionally, the electronic device 800 may further include a transceiver. It should be noted that in practical applications, there may be more than one transceiver, and the structure of the electronic device 800 does not limit the embodiments of the present application.

[0119] The processor 802 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logical blocks, modules, and circuits described in combination with the disclosure of the present application. The processor 802 may also be a combination that realizes computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0120] The bus may include a path for transmitting information between the above components. The bus can be a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity of representation, only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0121] The memory 801 can be a ROM (Read Only Memory), or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory), or other types of dynamic storage devices that can store information and instructions. It can also be an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0122] The memory 801 is used to store the application program code for implementing the solution of this application, and is controlled by the processor 802 for execution. The processor 802 is used to execute the application program code stored in the memory 801 to implement the content shown in the foregoing method embodiments.

[0123] Among them, the electronic device includes but is not limited to: mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 8 The electronic device shown is only an example and should not impose any limitations on the functions and usage scope of the embodiments of this application.

[0124] The electronic device of this embodiment can be used to execute the method of any of the foregoing embodiments, and its implementation principle and technical effects are similar and will not be elaborated here.

[0125] The present application also provides a non-transitory computer-readable storage medium, on which computer-readable instructions are stored. When the foregoing instructions are executed by a processor, the processor is caused to execute the method in the above embodiments.

[0126] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a non-transitory computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the foregoing storage medium includes: various media such as ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0127] The above has introduced the embodiments of the present application in detail. Specific examples are used herein to elaborate on the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application. At the same time, changes or deformations made by those skilled in the art based on the idea of the present application, in terms of the specific implementation manners and application scope of the present application, all belong to the protection scope of the present application. In summary, the content of this specification should not be construed as a limitation on the present application.

Claims

1. A calibration method for robot inspection points, characterized in that, Including: Based on a virtual simulation scenario, receiving an information collection task and determining an information collection image according to the information collection task; wherein, the information collection image is an image captured by a virtual inspection robot according to the information collection task and multiple pre-planned inspection paths. Determining the target point cloud coordinates of the inspection target corresponding to the information collection task according to the information collection image. Determining the shooting parameters of the pan-tilt shooting device corresponding to the virtual inspection robot according to the target point cloud coordinates and the current docking position of the virtual inspection robot. Verifying the inspection points corresponding to the information collection task based on the shooting parameters, the current docking position, the target inspection path corresponding to the current docking position, and the inspection verification task; wherein, the target inspection path is the path where the current docking position is located. Establishing a real-scene point cloud map according to the inspection point information of the target inspection site, and establishing the virtual simulation scenario based on the real-scene point cloud map. Establishing the virtual inspection robot in the virtual simulation scenario according to the physical attributes of the target inspection robot. Establishing an inspection point template database according to the inspection requirements of the target inspection site. Wherein, the verifying the inspection points corresponding to the information collection task based on the shooting parameters, the current docking position, the target inspection path corresponding to the current docking position, and the inspection verification task includes: Determining the information collection point information corresponding to the information collection task according to the shooting parameters, the current docking position, and the target inspection path. Extracting primary equipment information from the information collection task. Determining alternative point configuration information according to the primary equipment information, a preset electrical interval, a preset equipment model corresponding to the primary equipment information, the information collection point information, and the inspection point template database. Determining the inspection image captured by the virtual inspection robot according to the inspection verification task and the alternative point configuration information, so as to judge whether it is necessary to re-calibrate the inspection points according to the inspection image, and generate target point configuration information for the actual inspection process. Wherein, the judging whether it is necessary to re-calibrate the inspection points according to the inspection image to generate target point configuration information for the actual inspection process includes: Determining the image position of the inspection target in the inspection image according to the inspection image. Determining whether it is necessary to re-calibrate the inspection points based on the image position and a preset re-calibration condition. When it is not necessary to re-calibrate the inspection points, determining the alternative point configuration information as the target point configuration information. When it is necessary to re-calibrate the inspection points, receiving externally input calibration point data, and determining the target point configuration information according to the calibration point data and the alternative point configuration information.

2. The method according to claim 1, wherein The determining the target point cloud coordinates of the inspection target corresponding to the information collection task according to the information collection image includes: Identifying the information collection image to determine the inspection target. Determining the regional point cloud coordinates of the target area corresponding to the inspection target according to the real-scene point cloud map and the target area selection method. Determine the target point cloud coordinates of the inspection target based on the regional point cloud coordinates, the positional relationship between the inspection target and the target area.

3. The method according to claim 1, wherein Determine the shooting parameters of the pan-tilt shooting device corresponding to the virtual inspection robot according to the target point cloud coordinates and the current docking position of the virtual inspection robot, including: Obtain the current docking point cloud coordinates corresponding to the current docking position; Determine the positional relationship between the virtual inspection robot and the inspection target according to the target point cloud coordinates and the current docking point cloud coordinates; Determine the shooting parameters of the pan-tilt shooting device based on the positional relationship and the performance parameters of the pan-tilt shooting device.

4. The method according to claim 1, characterized in that, Determine the alternative point configuration information according to the primary equipment information, the preset electrical interval, the preset equipment model corresponding to the primary equipment information, the information collection point position information, and the inspection point template database, including: Determine the information collection sequence of the virtual inspection robot according to the primary equipment information, the preset electrical interval, and the preset equipment model corresponding to the primary equipment information; Associate the information collection point position information with the preset inspection point template database according to the information collection sequence to form alternative point configuration information.

5. A calibration device for robot patrol points, characterized in that, Include: An information collection image determination module, configured to receive an information collection task based on a virtual simulation scenario and determine an information collection image according to the information collection task; wherein, the information collection image is an image captured by the virtual inspection robot according to the information collection task and multiple pre-planned inspection paths; A coordinate determination module, configured to determine the target point cloud coordinates of the inspection target corresponding to the information collection task according to the information collection image; A shooting parameter determination module, configured to determine the shooting parameters of the pan-tilt shooting device corresponding to the virtual inspection robot according to the target point cloud coordinates and the current docking position of the virtual inspection robot; A verification module, configured to verify the inspection point corresponding to the information collection task based on the shooting parameters, the current docking position, the target inspection path corresponding to the current docking position, and the inspection verification task; wherein, the target inspection path is the path where the current docking position is located; A scene construction module, configured to establish a real-world point cloud map according to the inspection point information of the target inspection site, and establish the virtual simulation scenario based on the real-world point cloud map; Wherein, the scene construction module is further configured to establish the virtual inspection robot in the virtual simulation scenario according to the physical attributes of the target inspection robot; The scene construction module is further configured to establish an inspection point template database according to the inspection requirements of the target inspection site; The verification module is further configured to: Determine the information collection point position information corresponding to the information collection task according to the shooting parameters, the current docking position, and the target inspection path; Extract the primary equipment information from the information collection task; Determine the alternative point configuration information according to the primary equipment information, the preset electrical interval, the preset equipment model corresponding to the primary equipment information, the information collection point position information, and the inspection point template database; Determine the inspection images captured by the virtual inspection robot according to the inspection verification task and the alternative point configuration information, so as to judge whether it is necessary to recalibrate the inspection points according to the inspection images, and generate the target point configuration information for the actual inspection process; Among them, when the verification module judges whether it is necessary to recalibrate the inspection points to generate the target point configuration information for the actual inspection process according to the inspection images, it is specifically used for: Determine the image position of the inspection target in the inspection image according to the inspection image; Based on the image position and the preset recalibration condition, determine whether it is necessary to recalibrate the inspection points; When it is not necessary to recalibrate the inspection points, determine the alternative point configuration information as the target point configuration information; When it is necessary to recalibrate the inspection points, receive the calibration point data input from the outside, and determine the target point configuration information according to the calibration point data and the alternative point configuration information.

6. An electronic device, characterized in that, Including: A processor; A memory storing a computer program, when the computer program is executed by the processor, the processor is caused to execute the calibration method of the robot inspection points according to any one of claims 1-4.

7. A non-transitory computer-readable storage medium, characterized in that, Stored thereon are computer-readable instructions, when the instructions are executed by the processor, the processor is caused to execute the calibration method of the robot inspection points according to any one of claims 1-4.

Images