A navigation and positioning method, system, equipment and storage medium for a substation inspection robot.

Abstract

This invention discloses a navigation and positioning method, system, device, and storage medium for a substation inspection robot. The method includes: deploying RFID tags with known global coordinates at key locations along the substation inspection path, and simultaneously acquiring environmental images and RFID tag information during the robot's movement; calculating the robot's relative position based on environmental image features and camera calibration parameters, and fusing odometer data to generate a preliminary pose; when an RFID tag is detected, performing absolute correction on the current pose using its global coordinates as a reference; generating an obstacle avoidance path based on the corrected high-precision pose and the task objective, driving the robot to perform the inspection, and uploading the positioning results and trajectory information to a monitoring center to achieve closed-loop control. This invention enables intelligent, autonomous, and precise operation of the inspection robot within the substation.

Description

Technical Field

[0001] This invention relates to the technical field of robot navigation and positioning, and in particular to a navigation and positioning method, system, equipment and storage medium for a substation inspection robot. Background Technology

[0002] Currently, while navigation and positioning technologies for substation inspection robots have achieved a certain degree of autonomy and intelligence, they still face several limitations and shortcomings in complex power environments. Existing inspection robots mostly employ path navigation based on magnetic strips or lidar. Their path planning relies on fixed markers or reflective features. If the magnetic strip falls off, the surface becomes contaminated, or the reflective environment changes, the robot's positioning error will increase, potentially even causing it to deviate from its trajectory. Especially in substations, environments with dense metal equipment and strong electromagnetic interference, traditional single-sensor positioning methods struggle to maintain long-term stable operation. Secondly, positioning accuracy is insufficient, and error accumulation is significant. Conventional robots often rely on odometers or monocular vision for relative positioning, but due to wheel slippage, uneven ground, or changes in lighting conditions, distance and mileage data often drift and accumulate errors. After prolonged operation, these errors lead to increased positioning deviations, failing to meet the requirements of high-precision inspection tasks, especially when precise comparison and identification of equipment status are needed.

[0003] Traditional systems often only achieve one-way data acquisition and transmission, lacking a fusion mechanism for multi-source data such as visual information and RFID, and thus cannot achieve self-correction and dynamic correction of positioning errors. In addition, the information interaction delay between the monitoring terminal and the robot is relatively high, making it difficult to form a stable closed-loop control system, resulting in untimely task response. Summary of the Invention

[0004] In view of the aforementioned existing problems, this invention is proposed. Therefore, this invention provides a navigation and positioning method, system, device, and storage medium for a substation inspection robot, addressing the problems of insufficient navigation accuracy, accumulated positioning errors, poor environmental adaptability, and weak information fusion capabilities of existing substation inspection robots in complex operating environments.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, embodiments of the present invention provide a navigation and positioning method for a substation inspection robot, comprising: deploying radio frequency identification (RFID) tags with known global coordinates at key locations along the substation inspection path, and simultaneously collecting environmental images and RFID tag information during the robot's movement. The robot's relative position is calculated based on the environmental image features and camera calibration parameters, and preliminary pose is generated by fusing odometry data. When an RFID tag is read, its global coordinates are used as a reference to perform absolute correction on the current pose. Based on the corrected high-precision pose and task objective, an obstacle avoidance path is generated, and the robot is driven to perform inspection. The positioning results and trajectory information are then uploaded to the monitoring center to achieve closed-loop control.

[0006] As a preferred embodiment of the substation inspection robot navigation and positioning method of the present invention, the step of deploying radio frequency identification tags with known global coordinates at key locations along the substation inspection path includes: The area where the power equipment is located is divided into one or more rectangular areas, and further divided into several subspaces according to the equipment attributes. The gap between adjacent rectangular areas is used as the travel path of the inspection robot. Radio frequency identification (RFID) tags are deployed along the edges of the rectangular area and on both sides of the travel channel. The position of each RFID tag has known global coordinates in a pre-established ground coordinate system.

[0007] As a preferred embodiment of the substation inspection robot navigation and positioning method of the present invention, the calculation of the robot's relative position based on the environmental image features and camera calibration parameters includes: the camera calibration parameters include camera intrinsic parameters, extrinsic parameters, installation height and pitch angle; A monocular camera is mounted on the inspection robot at a fixed pitch angle, and its intrinsic parameters and extrinsic parameters relative to the ground coordinate system are obtained through calibration; the extrinsic parameters are determined by the camera's mounting height and pitch angle. During the inspection process, environmental images containing ground feature points are collected, and the pixel coordinates of the ground feature points are extracted. Based on the pinhole camera model, and combining the camera's intrinsic and extrinsic parameters, installation height and pitch angle, horizontal and vertical field of view, and image size, a geometric mapping relationship between image pixel coordinates and the ground coordinate system is established. Based on the geometric mapping relationship, the pixel coordinates are converted into two-dimensional coordinates in the ground coordinate system, and the relative position of the robot with respect to the environment is calculated.

[0008] In a preferred embodiment of the substation inspection robot navigation and positioning method of the present invention, the geometric mapping relationship between the image pixel coordinates and the ground coordinate system is expressed as follows: in, Let P be the coordinates of the target point P in the ground coordinate system. Let P be the pixel coordinates in the image plane. As a scale factor, This is the intrinsic parameter matrix of the camera. and These are the rotation matrix and translation vector of the camera relative to the ground coordinate system, respectively. These are the coordinates of the image center.

[0009] As a preferred embodiment of the substation inspection robot navigation and positioning method described in this invention, the method for generating a preliminary pose by fusing odometer data includes: calculating the current odometer-based pose based on the pose estimate from the previous moment, the current odometer-output travel distance, and the turning angle. in, The coordinates of the previous time step. The distance traveled. This refers to the steering angle; Obtain real-time coordinates of the ground coordinate system Pose error in computational vision and odometry: Weighted fusion correction is applied to the current pose estimate: in, and For fusion weighting coefficients.

[0010] As a preferred embodiment of the substation inspection robot navigation and positioning method described in this invention, when an RFID tag is read, the current pose is absolutely corrected based on its global coordinates, including: obtaining the coordinates of the RFID tag in its local coordinate system. And transform it to the ground coordinate system: in, The translation amount, It represents the rotation angle.

[0011] Calculate the robot's current position With label position The Euclidean distance between them; when the Euclidean distance is less than a preset threshold, the current pose will be forcibly corrected to be equal to the Euclidean distance between them. The high-confidence pose centered on the subject.

[0012] As a preferred embodiment of the substation inspection robot navigation and positioning method described in this invention, the obstacle avoidance path is generated based on the corrected high-precision pose and the task objective, including: if the target equipment is located within an unobstructed line of sight, the travel direction angle is calculated and the robot is controlled to travel straight along that direction; otherwise, based on the environmental map and robot kinematic constraints, the A* algorithm is used to plan the obstacle avoidance path and drive the robot to follow the path to perform the inspection.

[0013] Secondly, the present invention provides a navigation and positioning system for a substation inspection robot, comprising: The perception module is used to deploy RFID tags with known global coordinates at key locations along the substation inspection path, and simultaneously collect environmental images and RFID tag information during the movement of the inspection robot. The pose estimation module is used to calculate the robot's relative position based on the environmental image features and camera calibration parameters, and to generate a preliminary pose by fusing odometry data. The pose correction module is used to perform absolute correction of the current pose based on the global coordinates of the RFID tag when it is read. The path planning module is used to generate obstacle avoidance paths based on the corrected high-precision pose and task objectives, drive the robot to perform inspections, and upload the positioning results and trajectory information to the monitoring center to achieve closed-loop control.

[0014] Thirdly, the present invention provides an electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the steps of the navigation and positioning method for the substation inspection robot.

[0015] Fourthly, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the substation inspection robot navigation and positioning method.

[0016] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention introduces a collaborative fusion mechanism of machine vision and radio frequency identification (RFID) technologies into a substation inspection robot. Visual recognition enables environmental feature extraction and obstacle detection, while RFID nodes are used for global positioning and equipment identification. A composite navigation model combining visual relative positioning and RFID absolute correction is constructed, improving the robot's positioning accuracy and path stability in complex electromagnetic environments. Furthermore, by establishing a geometric mapping relationship between image plane coordinates and the robot's coordinate system, rapid spatial positioning of target points is achieved. Compared with traditional stereo vision methods, this algorithm has lower computational complexity, stronger real-time performance, can run efficiently on resource-constrained embedded platforms, and possesses good resistance to light interference. Based on visual positioning, RFID signal coordinate information is integrated, and a joint correction model is established through time series and spatial geometric relationships to achieve dynamic calibration of the robot's pose. This overcomes the problem of monocular vision ranging error accumulation and reduces the overall deviation of the inspection path. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein: Figure 1 This is a schematic diagram of a navigation and positioning method for a substation inspection robot according to an embodiment of the present invention; Figure 2 This is a flowchart illustrating the overall information transmission and control process of a navigation and positioning system for a substation inspection robot, as described in one embodiment of the present invention. Figure 3 This is an example diagram illustrating the inspection positioning of a substation inspection robot navigation and positioning method according to an embodiment of the present invention. Detailed Implementation

[0018] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0019] Example 1, referring to Figures 1-3 As one embodiment of the present invention, this embodiment provides a navigation and positioning method for a substation inspection robot, such as... Figure 1 As shown, it includes: S100: Deploy RFID tags with known global coordinates at key locations along the substation inspection path, and simultaneously collect environmental images and RFID tag information during the inspection robot's movement. S200: Calculate the robot's relative position based on the environmental image features and camera calibration parameters, and generate a preliminary pose by fusing odometry data; S300: When an RFID tag is read, the current pose is absolutely corrected based on its global coordinates. S400: Generates obstacle avoidance path based on the corrected high-precision pose and task objective, drives the robot to perform inspection, and uploads the positioning results and trajectory information to the monitoring center to achieve closed-loop control.

[0020] It should be noted that existing robots mostly rely on magnetic strips or single sensors for navigation, which can easily lose guidance when the magnetic strip is damaged or the signal is interfered with; traditional odometers or monocular vision positioning suffer from error accumulation and cannot achieve high-precision path tracking; barcode or QR code recognition is sensitive to light and dirt, making it difficult to reliably identify in substation environments. This invention integrates RFID nodes and visual guidance into the inspection path to achieve multi-source information complementarity, improving the robustness and environmental adaptability of path recognition; by combining visual ranging algorithms with RFID coordinate matching mechanisms, a mapping relationship between the world coordinate system and the imaging coordinate system is established, forming a joint visual and RFID correction mechanism that effectively suppresses positioning drift; and by employing RFID non-contact identification technology, high-precision reading of equipment number and location information is achieved, which is then fused and matched with visual feature point data to realize automatic identification and positioning.

[0021] Furthermore, the substation intelligent inspection robot proposed in this invention adopts a composite navigation and positioning scheme integrating machine vision and radio frequency identification (RFID) technologies. Magnetic strips are pre-laid within the inspection area to serve as the signal guidance basis for the robot's path, providing directional information for trajectory planning. The monitoring center is equipped with a real-time visualization interface to dynamically monitor the robot's deviation from the preset route and identify potential obstacles in the path, determining whether they will affect the safety of power equipment for timely avoidance. RFID technology, with its non-contact identification and high reliability advantages, can effectively replace traditional barcode methods, providing a new technological path for future power grid status perception and monitoring. The RFID reader / writer device configured on the inspection robot consists of wireless transmitting and receiving antennas, a data communication unit, and control circuitry. The read information is processed by the system and transmitted back to the intelligent inspection platform to achieve high-precision determination of the robot's position.

[0022] The basic idea behind navigation and positioning is to set up guide markers along the travel path within the substation area. The inspection robot collects equipment information via RFID according to a pre-programmed sequence and uses a combination of technologies to achieve its own positioning. In practice, the accuracy of environmental identification and data reading is crucial; that is, the predicted information from fixed-point monitoring should be as consistent as possible with the actual situation. The specific process is as follows: Figure 2 As shown, the central controller, as the system core, is responsible for task planning and command issuance, transmitting scheduling commands at high speed to the wireless communication layer via a fiber optic network. Subsequently, the wireless Wi-Fi module acts as a signal relay and forwarder, transmitting task information and control commands to the robot communication module. After receiving the data, the communication module interacts with the internal control system of the inspection robot to complete the parsing and execution of task commands. During the robot's movement within the park, it uses preset RFID guidance tags and environmental perception information to achieve path recognition and positioning correction, while simultaneously feeding back real-time inspection data to the central controller via the wireless network. This forms a closed-loop working mechanism of "perception—transmission—control—execution—feedback," ensuring the efficient and reliable operation of the inspection task.

[0023] In this embodiment of the invention, step S100, which involves deploying radio frequency identification (RFID) tags with known global coordinates at key locations along the substation inspection path, includes: The area where the power equipment is located is divided into one or more rectangular areas, and further divided into several subspaces according to the equipment attributes. The gap between adjacent rectangular areas is used as the travel path of the inspection robot. Radio frequency identification (RFID) tags are deployed along the edges of the rectangular area and on both sides of the travel channel. The position of each RFID tag has known global coordinates in a pre-established ground coordinate system.

[0024] Furthermore, assuming a rectangular area as the pre-defined layout area for power equipment, this area is divided into several smaller spaces based on equipment attributes. The gaps between the rectangular areas serve as the movement channels for the inspection robot. Solid black dots on the edges of the rectangular areas and along the channels represent RFID tags, used for rough robot positioning. Energy transfer and data exchange occur in a time-series manner within the coupling channel. The system first determines the robot's initial starting position and establishes a corresponding coordinate system, mapping important equipment within the rectangular area to coordinate points in this system. In practice, when the robot moves to a specific location, it scans the RFID tags to determine its position. After receiving the data uploaded by the robot, the monitoring center can obtain the equipment number and its corresponding path information in the visualization system.

[0025] In one feasible approach, the inspection robot employs monocular vision ranging. Its basic principle is to use images captured by a camera and mathematical algorithms to calculate the target distance. Considering the system's real-time requirements, the ranging algorithm is typically designed to be relatively simple, and a noise reduction mechanism is introduced during the calculation process. The optimized target distance formula based on noise reduction is as follows: in, Indicates the focal length of the camera. Indicates the actual physical size of the target. This refers to the filtered pixel size after taking into account fluctuations in image pixel size due to lighting, motion blur, etc. in real-world scenarios.

[0026] Based on this requirement, the mathematical correspondence between the object's position in the world coordinate system and its projection point in the image coordinate system is determined through geometric relationships; that is, a camera imaging geometric model is established. Among these, the pinhole camera model is the most widely used linear camera model. A point in the world coordinate system corresponds to the coordinates of a feature point on the camera's imaging plane. The purpose of distance measurement is to convert the coordinates of the target feature point on the image plane into its three-dimensional coordinates in the robot coordinate system, thereby realizing spatial distance calculation.

[0027] In this embodiment of the invention, step S200, which calculates the robot's relative position based on the environmental image features and camera calibration parameters, includes: the camera calibration parameters include camera intrinsic parameters, extrinsic parameters, installation height, and pitch angle; A monocular camera is mounted on the inspection robot at a fixed pitch angle, and its intrinsic parameters and extrinsic parameters relative to the ground coordinate system are obtained through calibration; the extrinsic parameters are determined by the camera's mounting height and pitch angle. During the inspection process, environmental images containing ground feature points are collected, and the pixel coordinates of the ground feature points are extracted. Based on the pinhole camera model, and combining the camera's intrinsic and extrinsic parameters, installation height and pitch angle, horizontal and vertical field of view, and image size, a geometric mapping relationship between image pixel coordinates and the ground coordinate system is established. Based on the geometric mapping relationship, the pixel coordinates are converted into two-dimensional coordinates in the ground coordinate system, and the relative position of the robot with respect to the environment is calculated.

[0028] In this embodiment of the invention, the geometric mapping relationship between the image pixel coordinates and the ground coordinate system in step S200 is expressed as follows: in, Let P be the coordinates of the target point P in the ground coordinate system. Let P be the pixel coordinates in the image plane. As a scale factor, This is the intrinsic parameter matrix of the camera. and These are the rotation matrix and translation vector of the camera relative to the ground coordinate system, respectively. These are the coordinates of the image center.

[0029] Specifically, when the robot locates the device, the monocular camera first tilts at a specific angle to establish a target ranging algorithm model. The specific process is as follows: Step 1: Calibrate the monocular camera tilted at a specific angle to obtain the camera's focal length. Image center coordinates Rotation matrix of the camera relative to the ground coordinate system after tilting Translation vector ; Step 2: Obtain the projection relationship based on the pinhole camera model; Step 3: During long-term, large-scale inspection tasks, the system needs to be calibrated periodically. Let the target point on the ground plane be P, and its coordinates in the ground coordinate system be... The corresponding coordinates of the image plane projection point are also The ordinate of point P in the ground coordinate system is... The calculation relationship is as follows: The parameters and UG are defined as follows: in, Indicates the image height. Indicates the image width. Installation height of the camera, For horizontal field of view, For vertical field of view, The pitch angle is UG, which is the vertical coordinate of the ground reference pixel and is a key intermediate parameter connecting the image pixel coordinates and the ground coordinate system.

[0030] Based on the perspective projection geometry model of a monocular camera, the following was obtained. The mapping relationship between the axes can be further derived. The formula for calculating coordinates is: It should be noted that this model can effectively achieve spatial ranging and target localization using a monocular camera, providing accurate positional information support for the autonomous navigation of inspection robots.

[0031] Furthermore, refer to Figure 3After completing visual localization, the scanned images acquired by the robot are processed using a specific algorithm combining visual feature processing and path synthesis to filter out data noise. By connecting feature points in the image plane, a roadside curve can be formed, which is then used to determine the path center point. Simultaneously, the RFID coordinates are mapped to a unified coordinate system, establishing a one-to-one correspondence with the aforementioned rectangular device area. In this way, the spatial correspondence between the tag and the robot's position can be further determined.

[0032] In this embodiment of the invention, step S200, which involves fusing odometer data to generate a preliminary pose, includes: calculating the current odometer-based pose based on the pose estimate from the previous moment, the current odometer-output travel distance, and the steering angle. in, The coordinates of the previous time step. The distance traveled. This refers to the steering angle; Obtain real-time coordinates of the ground coordinate system Pose error in computational vision and odometry: Weighted fusion correction is applied to the current pose estimate: in, and For fusion weighting coefficients.

[0033] In this embodiment of the invention, step S300, when an RFID tag is read, performs absolute correction on the current pose based on its global coordinates, including: obtaining the coordinates of the RFID tag in its local coordinate system. And transform it to the ground coordinate system: in, The translation amount, It represents the rotation angle.

[0034] Calculate the robot's current position With label position The Euclidean distance between them; when the Euclidean distance is less than a preset threshold, the current pose will be forcibly corrected to be equal to the Euclidean distance between them. The high-confidence pose centered on the subject.

[0035] In this embodiment of the invention, step S400 generates an obstacle avoidance path based on the corrected high-precision pose and the task objective, including: if the target device is within the unobstructed line of sight, then calculate the travel direction angle and control the robot to travel straight along that direction; otherwise, based on the environmental map and robot kinematic constraints, use the A* algorithm to plan the obstacle avoidance path and drive the robot to follow the path to perform inspection.

[0036] Specifically, the precise positioning steps include: Step 1: Determine the mapping relationship between the landmark plane and the camera imaging plane using the homography matrix; Step 2: Perform coordinate transformation based on the spatial orientation of the device and map it to the specified coordinate system; Step 3: Calculate the distance between the RFID tag and the robot, estimate the robot's actual travel path, and plot the trajectory. The calculation process is as follows: Obtain the robot's current coordinates in the ground coordinate system. and RFID coordinate system coordinates .

[0037] The formula for transforming the coordinates of an RFID tag to a ground coordinate system is: in, The translation amount, It represents the rotation angle.

[0038] Calculate the distance between the tag and the robot: Based on the robot's motion constraints, plan the travel path, with the travel direction angle as follows: When the distance is close, proceed straight according to the direction angle; otherwise, plan the obstacle avoidance path according to the traditional A* algorithm.

[0039] Update the odometer reading to correct for accumulated errors; the specific process is as follows: Retrieve data from each module: including current travel distance Steering angle Real-time coordinates of the ground coordinate system and RFID ground coordinates .

[0040] The current coordinates are calculated as follows: in, The coordinates are from the previous time step.

[0041] Coordinate errors between vision and odometer: Odometry data correction based on weighted fusion method: Step 5: Determine the positioning relationship between the final coordinates and the actual rectangular area, and display it graphically in the visualization interface of the monitoring center.

[0042] It should be noted that this invention introduces a collaborative fusion mechanism of machine vision and radio frequency identification (RFID) technologies into the substation inspection robot. Visual recognition enables environmental feature extraction and obstacle detection, while RFID nodes are used for global positioning and equipment identification. A composite navigation model combining visual relative positioning and RFID absolute correction is constructed, improving the robot's positioning accuracy and path stability in complex electromagnetic environments. Furthermore, by establishing a geometric mapping relationship between image plane coordinates and the robot's coordinate system, rapid spatial positioning of target points is achieved. Compared to traditional stereo vision methods, this algorithm has lower computational complexity, stronger real-time performance, can run efficiently on resource-constrained embedded platforms, and possesses good resistance to light interference. Based on visual positioning, RFID signal coordinate information is integrated, and a joint correction model is established through time series and spatial geometric relationships to achieve dynamic calibration of the robot's pose. This overcomes the problem of monocular vision ranging error accumulation, reduces the overall deviation of the inspection path, and realizes the entire process of the inspection robot from coarse positioning to high-precision positioning, ensuring high stability and high accuracy in its autonomous inspection in the substation environment.

[0043] Example 2: The above example is an illustrative scheme of a navigation and positioning method for a substation inspection robot. It should be noted that the technical solution of this substation inspection robot navigation and positioning system belongs to the same concept as the technical solution of the above-described substation inspection robot navigation and positioning method. Details not described in detail in this example can be found in the description of the above-described substation inspection robot navigation and positioning method.

[0044] This embodiment provides a substation inspection robot navigation and positioning system, comprising: The perception module is used to deploy RFID tags with known global coordinates at key locations along the substation inspection path, and simultaneously collect environmental images and RFID tag information during the movement of the inspection robot. The pose estimation module is used to calculate the robot's relative position based on the environmental image features and camera calibration parameters, and to generate a preliminary pose by fusing odometry data. The pose correction module is used to perform absolute correction of the current pose based on the global coordinates of the RFID tag when it is read. The path planning module is used to generate obstacle avoidance paths based on the corrected high-precision pose and task objectives, drive the robot to perform inspections, and upload the positioning results and trajectory information to the monitoring center to achieve closed-loop control.

[0045] This embodiment also provides an electronic device applicable to the navigation and positioning method for substation inspection robots, including: The system includes a memory and a processor. The memory stores computer-executable instructions, and the processor executes these instructions to implement the navigation and positioning method for a substation inspection robot as described in the above embodiments.

[0046] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, it implements the navigation and positioning method for a substation inspection robot as proposed in the above embodiments.

[0047] The storage medium proposed in this embodiment belongs to the same inventive concept as the navigation and positioning method for substation inspection robots proposed in the above embodiments. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0048] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0049] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A navigation and positioning method for a substation inspection robot, characterized in that, include: Radio frequency identification (RFID) tags with known global coordinates are deployed at key locations along the substation inspection path, and environmental images and RFID tag information are collected simultaneously during the inspection robot's movement. The robot's relative position is calculated based on the environmental image features and camera calibration parameters, and preliminary pose is generated by fusing odometry data. When an RFID tag is read, its global coordinates are used as a reference to perform absolute correction on the current pose. Based on the corrected high-precision pose and task objective, an obstacle avoidance path is generated, and the robot is driven to perform inspection. The positioning results and trajectory information are then uploaded to the monitoring center to achieve closed-loop control.

2. The navigation and positioning method for a substation inspection robot as described in claim 1, characterized in that, The deployment of RFID tags with known global coordinates at key locations along the substation inspection route includes: The area where the power equipment is located is divided into one or more rectangular areas, and further divided into several subspaces according to the equipment attributes. The gap between adjacent rectangular areas is used as the travel path of the inspection robot. Radio frequency identification (RFID) tags are deployed along the edges of the rectangular area and on both sides of the travel channel. The position of each RFID tag has known global coordinates in a pre-established ground coordinate system.

3. The substation inspection robot navigation and positioning method as described in claim 2, characterized in that, Calculating the robot's relative position based on the environmental image features and camera calibration parameters includes: the camera calibration parameters include camera intrinsic parameters, extrinsic parameters, installation height, and pitch angle; A monocular camera is mounted on the inspection robot at a fixed pitch angle, and its intrinsic parameters and extrinsic parameters relative to the ground coordinate system are obtained through calibration; the extrinsic parameters are determined by the camera's mounting height and pitch angle. During the inspection process, environmental images containing ground feature points are collected, and the pixel coordinates of the ground feature points are extracted. Based on the pinhole camera model, and combining the camera's intrinsic and extrinsic parameters, installation height and pitch angle, horizontal and vertical field of view, and image size, a geometric mapping relationship between image pixel coordinates and the ground coordinate system is established. Based on the geometric mapping relationship, the pixel coordinates are converted into two-dimensional coordinates in the ground coordinate system, and the relative position of the robot with respect to the environment is calculated.

4. The substation inspection robot navigation and positioning method as described in claim 3, characterized in that, The geometric mapping relationship between the image pixel coordinates and the ground coordinate system is expressed as follows: in, Let P be the coordinates of the target point P in the ground coordinate system. Let P be the pixel coordinates in the image plane. As a scale factor, This is the intrinsic parameter matrix of the camera. and These are the rotation matrix and translation vector of the camera relative to the ground coordinate system, respectively. These are the coordinates of the image center.

5. The substation inspection robot navigation and positioning method as described in claim 4, characterized in that, The initial pose is generated by fusing odometry data, including: calculating the current odometry-based pose based on the pose estimate from the previous moment, the current travel distance output by the odometry, and the steering angle. in, The coordinates of the previous time step. The distance traveled. This refers to the steering angle; Obtain real-time coordinates of the ground coordinate system Pose error in computational vision and odometry: Weighted fusion correction is applied to the current pose estimate: in, and For fusion weighting coefficients.

6. The substation inspection robot navigation and positioning method as described in claim 5, characterized in that, When an RFID tag is read, its global coordinates are used as a reference to perform absolute correction on the current pose, including: obtaining the coordinates of the RFID tag in its local coordinate system. And transform it to the ground coordinate system: in, The translation amount, It is the rotation angle. Calculate the robot's current position With label position The Euclidean distance between them; when the Euclidean distance is less than a preset threshold, the current pose will be forcibly corrected to be equal to the Euclidean distance between them. The high-confidence pose centered on the subject.

7. The substation inspection robot navigation and positioning method as described in claim 6, characterized in that, Based on the corrected high-precision pose and task objective, an obstacle avoidance path is generated, including: if the target device is within the unobstructed line of sight, the travel direction angle is calculated and the robot is controlled to travel straight along that direction; otherwise, based on the environmental map and robot kinematic constraints, the A* algorithm is used to plan the obstacle avoidance path and drive the robot to follow the path to perform inspection.

8. A navigation and positioning system for a substation inspection robot, applied to the method described in any one of claims 1-7, characterized in that, include: The sensing module is used to deploy RFID tags with known global coordinates at key locations along the substation inspection path, and simultaneously collect environmental images and RFID tag information during the inspection robot's movement. The pose estimation module is used to calculate the robot's relative position based on the environmental image features and camera calibration parameters, and to generate a preliminary pose by fusing odometry data. The pose correction module is used to perform absolute correction of the current pose based on the global coordinates of the RFID tag when it is read. The path planning module is used to generate obstacle avoidance paths based on the corrected high-precision pose and task objectives, drive the robot to perform inspections, and upload the positioning results and trajectory information to the monitoring center to achieve closed-loop control.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the steps of the substation inspection robot navigation and positioning method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the substation inspection robot navigation and positioning method according to any one of claims 1 to 7.

Images