An automatic monitoring correction method based on a mobile robot inspection platform

Abstract

The application discloses an automatic monitoring correction method based on a mobile robot inspection platform and belongs to the technical field of intelligent traffic. In order to solve the problems of intelligent road facility pose calibration and correction, the mobile robot inspection platform is constructed, the mobile robot is connected with roadside equipment and an online platform respectively, and the road testing equipment is connected with the online platform. The mobile robot collects the world pose of the mobile robot at different sampling points and sampling angles based on high-precision positioning and navigation, collects the distance and azimuth angle between the mobile robot and the road testing equipment based on laser radar detection, collects the angle between the orientation of the road testing equipment and the line of sight of the mobile robot based on visual sensing, and obtains basic data. The mobile robot pose calibration method is constructed to adjust the mobile robot. The roadside equipment pose verification method is constructed, the online platform calculates the deviation degree of the roadside equipment based on the roadside equipment pose verification method, selects all roadside equipment needing correction or restoration, and notifies the maintenance personnel to restore at the designated point.

Description

Technical Field

[0001] This invention belongs to the field of intelligent transportation technology, specifically relating to an automatic monitoring and correction method based on a mobile robot inspection platform. Background Technology

[0002] Traditional roadside sensor (such as camera and radar) pose calibration mainly relies on manual inspection. This is susceptible to issues such as operator experience and fatigue, making it difficult to guarantee calibration consistency. Furthermore, manual inspection poses significant safety risks in complex traffic environments or inclement weather, and suffers from slow response times in large-scale sensor networks. Because it cannot dynamically adapt to roadside equipment displacement or environmental changes, sensor data is prone to drift or failure, leading to biases in subsequent analysis. This results in low efficiency, high cost, unstable accuracy, and insufficient real-time performance. These limitations restrict the reliability and maintainability of roadside sensing systems, necessitating automation technologies to improve inspection efficiency. Summary of the Invention

[0003] The problem to be solved by this invention is to realize the pose calibration and correction of intelligent road facilities, and to propose an automatic monitoring and correction method based on a mobile robot inspection platform.

[0004] To achieve the above objectives, the present invention provides the following technical solution:

[0005] An automatic monitoring and correction method based on a mobile robot inspection platform includes the following steps:

[0006] S1. Construct a mobile robot inspection platform, which includes mobile robots, roadside equipment, and an online platform. The mobile robots are connected to the roadside equipment and the online platform, and the roadside equipment is connected to the online platform.

[0007] The mobile robot integrates high-precision positioning and navigation, lidar detection, visual sensing detection, pose edge calculation and communication functions. The roadside equipment is pre-set with ArUco codes or reflective markers as targets for the mobile robot to identify the orientation of the roadside equipment.

[0008] S2. The mobile robot moves near the roadside equipment. Based on high-precision positioning and navigation, the world pose of the mobile robot is collected from different sampling points and sampling angles. Based on lidar detection, the distance and azimuth between the mobile robot and the roadside equipment are collected. Based on visual sensing, the angle between the orientation of the roadside equipment and the orientation of the mobile robot's line of sight is detected to obtain basic data.

[0009] S3. Considering the distance, occlusion, and angle difference between the mobile robot and the roadside equipment, a mobile robot pose calibration method is constructed. The pose edge calculation is based on the constructed mobile robot pose calibration method and the basic data obtained in step S2 to calculate the optimal observation pose of the mobile robot and adjust the mobile robot accordingly.

[0010] S4. Construct a roadside equipment pose verification method. Based on the best observation pose of the mobile robot obtained in step S3, the online platform calculates the deviation of the roadside equipment based on the roadside equipment pose verification method, and filters out all roadside equipment that needs to be corrected or restored, and notifies maintenance personnel to restore it at the correct location.

[0011] Furthermore, in step S1, the roadside equipment is pre-set with ArUco codes or reflective markers as targets, thus obtaining the standard world pose pre-set by the roadside equipment. ,in , , These are the preset lateral distance, longitudinal distance, and line-of-sight orientation of the roadside equipment t relative to the world origin.

[0012] Furthermore, the basic data for step S2 includes the following specific content:

[0013] The world pose of the mobile robot at sampling point i and sampling angle j ,in , , These represent the lateral distance, longitudinal distance, and line-of-sight orientation of the mobile robot relative to the world origin at sampling point i and sampling angle j, respectively.

[0014] At sampling point i and sampling angle j, the mobile robot uses lidar to detect the distance between itself and the roadside equipment. and the position of the roadside equipment relative to the mobile robot. ;

[0015] At sampling point i and sampling angle j, the mobile robot uses visual sensing to detect and identify the angle between the orientation of the road test equipment and the orientation of the mobile robot's line of sight. .

[0016] Furthermore, the specific implementation method of step S3 includes the following steps:

[0017] S3.1. The standard world pose based on roadside equipment is The mobile robot moves to the vicinity of the target area and continuously monitors whether it can detect the ArUco code of the roadside equipment during the movement.

[0018] Based on the gaze orientation of the mobile robot Assuming on the extension of the line of sight Direction deviation In the angular direction, the mobile robot observes a distance of If a roadside device exists at a certain location, then the lateral and longitudinal distances of the roadside device monitored by the robot are:

[0019] ;

[0020] S3.2. Define the sampling range for the mobile robot's position as the nearest and farthest distances from the roadside observation equipment. Inside, that is, the distance between the mobile robot sampling point i and the roadside equipment. satisfy:

[0021]

[0022] The mobile robot samples angles by dividing the 360-degree direction into N equal segments. The mathematical expression for the sampling angle j is:

[0023]

[0024] S3.3. Considering the distance, occlusion, and angle difference between the mobile robot and roadside equipment, use a weighted evaluation function. The mathematical expression for evaluating the observation pose quality of a mobile robot is:

[0025]

[0026] in, , , These are the distance score, angle score, and occlusion score within the sampling angle, respectively. These are the weights corresponding to the distance score, angle score, and occlusion score within the sampling angle, respectively.

[0027] Then, the optimal pose of the mobile robot facing the roadside equipment is the sampling point i and sampling angle j that maximizes the weighted evaluation function, and its expression is:

[0028]

[0029] in, The optimal observation pose for the mobile robot;

[0030] S3.4. Based on the optimal observed pose of the mobile robot, adjust the current pose of the mobile robot in the translation direction and orientation angle. The adjustment amount is:

[0031]

[0032] in, This is the adjustment amount for the lateral distance. This is the adjustment amount for the longitudinal distance. This is the amount of adjustment for the direction of the line of sight.

[0033] Furthermore, the specific implementation method of step S4 includes the following steps:

[0034] S4.1. After the mobile robot adjusts to the optimal pose, calculate the current line of sight of the roadside equipment relative to the world origin. The mathematical expression is:

[0035] ;

[0036] S4.2. The online platform, based on the lateral and longitudinal distances of the roadside equipment monitored by the mobile robot and the current line of sight of the roadside equipment relative to the world origin, compares the preset standard world pose of the roadside equipment to calculate the absolute translation error and absolute angular error, quantifying the degree of deviation of the roadside equipment. The absolute translation error is:

[0037]

[0038] The absolute angle error is:

[0039]

[0040] The rap function is a modulo operation used to normalize the angle difference to the standard range of -180 to 180.

[0041] S4.3. Let the position threshold be... Angle threshold is The evaluation criteria for whether or not roadside equipment needs to be repaired are as follows:

[0042] like Then the roadside equipment does not need to be modified;

[0043] like To correct the position of roadside equipment;

[0044] like To correct the steering of roadside equipment;

[0045] If both the absolute translation error and the absolute angle error exceed the set threshold, the position and orientation of the roadside equipment will be calibrated simultaneously.

[0046] The beneficial effects of this invention are:

[0047] The present invention discloses an automatic monitoring and correction method based on a mobile robot inspection platform, which completes the method of intelligent road facility pose calibration and correction, and solves the problems of automation requirements for online calibration of roadside equipment and inefficiency of traditional manual inspection. Attached Figure Description

[0048] Figure 1 This is a flowchart of an automatic monitoring and correction method based on a mobile robot inspection platform according to the present invention;

[0049] Figure 2This is a structural block diagram of an automatic monitoring and correction method based on a mobile robot inspection platform according to the present invention.

[0050] Figure 3 This is a schematic diagram of the pose parameters of the present invention. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only for explaining the invention and are not intended to limit the invention; that is, the described specific embodiments are merely a part of the embodiments of the invention, and not all of them. The components of the specific embodiments of the invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations, and the invention may also have other embodiments.

[0052] Therefore, the following detailed description of specific embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected specific embodiments of the invention. All other specific embodiments obtained by those skilled in the art based on these specific embodiments without inventive effort are within the scope of protection of this invention.

[0053] To further understand the invention's content, features, and effects, the following specific embodiments are provided, along with accompanying drawings. Figure 1 - Appendix Figure 3 Detailed explanation is as follows:

[0054] Example 1:

[0055] An automatic monitoring and correction method based on a mobile robot inspection platform includes the following steps:

[0056] S1. Construct a mobile robot inspection platform, which includes mobile robots, roadside equipment, and an online platform. The mobile robots are connected to the roadside equipment and the online platform, and the roadside equipment is connected to the online platform.

[0057] The mobile robot integrates high-precision positioning and navigation, lidar detection, visual sensing detection, pose edge calculation and communication functions. The roadside equipment is pre-set with ArUco codes or reflective markers as targets for the mobile robot to identify the orientation of the roadside equipment.

[0058] Furthermore, in step S1, the roadside equipment is pre-set with ArUco codes or reflective markers as targets, thus obtaining the standard world pose pre-set by the roadside equipment. ,in , , These are the preset lateral distance, longitudinal distance, and line-of-sight orientation of the roadside equipment t relative to the world origin;

[0059] Furthermore, the high-precision positioning and navigation function is mainly used for the mobile robot's field inspection navigation and collision avoidance. It is used to determine positioning information. LiDAR is used for distance monitoring of roadside equipment and the orientation of the roadside equipment relative to the mobile robot. Visual sensing is used to detect and identify the angle between the orientation of the roadside equipment and the orientation of the mobile robot. Edge computing is used to calculate the distance, angle, and occlusion of the roadside equipment observed by the mobile robot, so that the mobile robot can calculate and adjust its own orientation to obtain the optimal observation sampling point. The communication module enables the mobile robot to communicate with the roadside equipment monitoring platform and submit the observation poses of all roadside equipment during the inspection process to the platform.

[0060] The roadside equipment module pre-embeds ArUco codes or reflective markers into the roadside equipment as targets so that the mobile robot can detect and identify the current orientation of the roadside equipment through visual sensing.

[0061] The online platform module receives the observed poses of roadside equipment uploaded by the mobile robot. The platform uniformly calculates and registers the correction amounts for different roadside equipment in batches, and automatically associates the corresponding maintenance personnel to carry out fixed-point restoration.

[0062] S2. The mobile robot moves near the roadside equipment. Based on high-precision positioning and navigation, the world pose of the mobile robot is collected from different sampling points and sampling angles. Based on lidar detection, the distance and azimuth between the mobile robot and the roadside equipment are collected. Based on visual sensing, the angle between the orientation of the roadside equipment and the orientation of the mobile robot's line of sight is detected to obtain basic data.

[0063] Furthermore, the basic data for step S2 includes the following specific content:

[0064] The world pose of the mobile robot at sampling point i and sampling angle j ,in , , These represent the lateral distance, longitudinal distance, and line-of-sight orientation of the mobile robot relative to the world origin at sampling point i and sampling angle j, respectively.

[0065] At sampling point i and sampling angle j, the mobile robot uses lidar to detect the distance between itself and the roadside equipment. and the position of the roadside equipment relative to the mobile robot. ;

[0066] At sampling point i and sampling angle j, the mobile robot uses visual sensing to detect and identify the angle between the orientation of the road test equipment and the orientation of the mobile robot's line of sight. .

[0067] Furthermore, to simplify the calculation, the world coordinates are assumed to be a two-dimensional plane. The world pose of the mobile robot is determined based on the mobile robot's built-in GNSS+SLAM navigation system. The technology originates from mobile robot localization and navigation technology based on GNSS+visual SLAM and the development and application of graph-optimized GNSS / binocular vision / inertial SLAM systems. The core of this embodiment lies in comparing the pose of the roadside equipment observed by the mobile robot. Standard position of roadside equipment pre-embedded This quantifies the angle and position of roadside equipment deviating from its standard state, helping road maintenance personnel to accurately locate and restore the roadside equipment's condition. Once the mobile robot detects the ArUco code target, it will continuously change its sampling position around the target, adjust its posture, optimize the observation angle, and calculate the optimal observation position and posture, taking into account factors such as distance from the target, occlusion, and angle difference.

[0068] S3. Considering the distance, occlusion, and angle difference between the mobile robot and the roadside equipment, a mobile robot pose calibration method is constructed. The pose edge calculation is based on the constructed mobile robot pose calibration method and the basic data obtained in step S2 to calculate the optimal observation pose of the mobile robot and adjust the mobile robot accordingly.

[0069] Furthermore, the specific implementation method of step S3 includes the following steps:

[0070] S3.1. The standard world pose based on roadside equipment is The mobile robot moves to the vicinity of the target area and continuously monitors whether it can detect the ArUco code of the roadside equipment during the movement.

[0071] Based on the gaze orientation of the mobile robot Assuming on the extension of the line of sight Direction deviation In the angular direction, the mobile robot observes a distance of If a roadside device exists at a certain location, then the lateral and longitudinal distances of the roadside device monitored by the robot are:

[0072] ;

[0073] S3.2. Define the sampling range for the mobile robot's position as the nearest and farthest distances from the roadside observation equipment. Inside, that is, the distance between the mobile robot sampling point i and the roadside equipment. satisfy:

[0074]

[0075] The mobile robot samples angles by dividing the 360-degree direction into N equal segments. The mathematical expression for the sampling angle j is:

[0076]

[0077] S3.3. Considering the distance, occlusion, and angle difference between the mobile robot and roadside equipment, use a weighted evaluation function. The mathematical expression for evaluating the observation pose quality of a mobile robot is:

[0078]

[0079] in, , , These are the distance score, angle score, and occlusion score within the sampling angle, respectively. These are the weights corresponding to the distance score, angle score, and occlusion score within the sampling angle, respectively.

[0080] Then, the optimal pose of the mobile robot facing the roadside equipment is the sampling point i and sampling angle j that maximizes the weighted evaluation function, and its expression is:

[0081]

[0082] in, The optimal observation pose for the mobile robot;

[0083] S3.4. Based on the optimal observed pose of the mobile robot, adjust the current pose of the mobile robot in the translation direction and orientation angle. The adjustment amount is:

[0084]

[0085] in, This is the adjustment amount for the lateral distance. This is the adjustment amount for the longitudinal distance. This is the amount of adjustment for the direction of the line of sight.

[0086] Furthermore, The evaluation criteria are whether the distance is within the band and whether the distance exceeds the tolerance limit for distance adjustment. The calculation expression is:

[0087] ;

[0088] in, The upper limit of distance tolerance is known.

[0089] The roadside equipment itself also has orientation information. The positive orientation of the target ArUco code represents the positive orientation of the roadside equipment. express. Angle points are used to measure the angle between the mobile robot's line of sight and the roadside equipment's forward orientation, i.e., the orientation of the roadside equipment. With mobile robots The included angle , It is obtained by the mobile robot's vision camera based on the detected ArUco code shape. A value of 180 degrees indicates that the mobile robot's line of sight is directly facing the roadside equipment, which is the ideal state; a value of 0 or 360 degrees indicates that the mobile robot's line of sight is consistent with the roadside equipment, and observation conditions are not available. The value range is 0~360 degrees, and the mobile robot is dedicated to... Maintain a distance of around 180 degrees, i.e., face-to-face observation. The mathematical expression is:

[0090] ;

[0091] The evaluation criteria are the target's occlusion and visible area; if a detection returns an order... ;otherwise .

[0092] S4. Construct a roadside equipment pose verification method. Based on the best observation pose of the mobile robot obtained in step S3, the online platform calculates the deviation of the roadside equipment based on the roadside equipment pose verification method, and filters out all roadside equipment that needs to be corrected or restored, and notifies maintenance personnel to restore it at the correct location.

[0093] Furthermore, the specific implementation method of step S4 includes the following steps:

[0094] S4.1. After the mobile robot adjusts to the optimal pose, calculate the current line of sight of the roadside equipment relative to the world origin. The mathematical expression is:

[0095] ;

[0096] S4.2. The online platform, based on the lateral and longitudinal distances of the roadside equipment monitored by the mobile robot and the current line of sight of the roadside equipment relative to the world origin, compares the preset standard world pose of the roadside equipment to calculate the absolute translation error and absolute angular error, quantifying the degree of deviation of the roadside equipment. The absolute translation error is:

[0097]

[0098] The absolute angle error is:

[0099]

[0100] The rap function is a modulo operation used to normalize the angle difference to the standard range of -180 to 180.

[0101] S4.3. Let the position threshold be... Angle threshold is The evaluation criteria for whether or not roadside equipment needs to be repaired are as follows:

[0102] like Then the roadside equipment does not need to be modified;

[0103] like To correct the position of roadside equipment;

[0104] like To correct the steering of roadside equipment;

[0105] If both the absolute translation error and the absolute angle error exceed the set threshold, the position and orientation of the roadside equipment will be calibrated simultaneously.

[0106] Furthermore, in the mobile robot's recognition of target world coordinates and azimuth Subsequently, the observed world pose of the roadside equipment is uploaded to the online platform via the communication module. The platform then statistically calculates and registers the observed pose of the roadside equipment and the pre-embedded standard coordinates. and direction angle The system automatically identifies the degree of deviation between the two, and based on this degree of deviation, automatically filters out all roadside equipment that needs to be corrected or restored, and notifies maintenance personnel to restore them at the designated locations.

[0107] It should be noted that relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0108] Although this application has been described above with reference to specific embodiments, various modifications can be made and components can be replaced with equivalents without departing from the scope of this application. In particular, as long as there is no structural conflict, the features in the specific embodiments disclosed in this application can be combined with each other in any way. The lack of an exhaustive description of these combinations in this specification is merely for the sake of brevity and resource conservation. Therefore, this application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. An automatic monitoring and correction method based on a mobile robot inspection platform, characterized in that, Includes the following steps: S1. Construct a mobile robot inspection platform, which includes mobile robots, roadside equipment, and an online platform. The mobile robots are connected to the roadside equipment and the online platform, and the roadside equipment is connected to the online platform. The mobile robot integrates high-precision positioning and navigation, lidar detection, visual sensing detection, pose edge calculation and communication functions. The roadside equipment is pre-set with ArUco codes or reflective markers as targets for the mobile robot to identify the orientation of the roadside equipment. S2. The mobile robot moves near the roadside equipment. Based on high-precision positioning and navigation, the world pose of the mobile robot is collected from different sampling points and sampling angles. Based on lidar detection, the distance and azimuth between the mobile robot and the roadside equipment are collected. Based on visual sensing, the angle between the orientation of the roadside equipment and the orientation of the mobile robot's line of sight is detected to obtain basic data. S3. Considering the distance, occlusion, and angle difference between the mobile robot and the roadside equipment, a mobile robot pose calibration method is constructed. The pose edge calculation is based on the constructed mobile robot pose calibration method and the basic data obtained in step S2 to calculate the optimal observation pose of the mobile robot and adjust the mobile robot accordingly. S4. Construct a roadside equipment pose verification method. Based on the best observation pose of the mobile robot obtained in step S3, the online platform calculates the deviation of the roadside equipment based on the roadside equipment pose verification method, and filters out all roadside equipment that needs to be corrected or restored, and notifies maintenance personnel to restore it at the correct location.

2. The automatic monitoring and correction method based on a mobile robot inspection platform according to claim 1, characterized in that, In step S1, the roadside equipment is pre-set with ArUco codes or reflection markers as targets, and the standard world pose preset by the roadside equipment is obtained. ,in , , These are the preset lateral distance, longitudinal distance, and line-of-sight orientation of the roadside equipment t relative to the world origin.

3. The automatic monitoring and correction method based on a mobile robot inspection platform according to claim 2, characterized in that, The basic data for step S2 includes the following specific content: The world pose of the mobile robot at sampling point i and sampling angle j ,in , , These represent the lateral distance, longitudinal distance, and line-of-sight orientation of the mobile robot relative to the world origin at sampling point i and sampling angle j, respectively. At sampling point i and sampling angle j, the mobile robot uses lidar to detect the distance between itself and the roadside equipment. and the position of the roadside equipment relative to the mobile robot. ; At sampling point i and sampling angle j, the mobile robot uses visual sensing to detect and identify the angle between the orientation of the road test equipment and the orientation of the mobile robot's line of sight. .

4. The automatic monitoring and correction method based on a mobile robot inspection platform according to claim 3, characterized in that, The specific implementation method of step S3 includes the following steps: S3.

1. The standard world pose based on roadside equipment is The mobile robot moves to the vicinity of the target area and continuously monitors whether it can detect the ArUco code of the roadside equipment during the movement. Based on the gaze orientation of the mobile robot Assuming on the extension of the line of sight Direction deviation In the angular direction, the mobile robot observes a distance of If a roadside device exists at a certain location, then the lateral and longitudinal distances of the roadside device monitored by the robot are: ； S3.

2. Define the sampling range for the mobile robot's position as the nearest and farthest distances from the roadside observation equipment. Inside, that is, the distance between the mobile robot sampling point i and the roadside equipment. satisfy: ； The mobile robot samples angles by dividing the 360-degree direction into N equal segments. The mathematical expression for the sampling angle j is: ； S3.

3. Considering the distance, occlusion, and angle difference between the mobile robot and roadside equipment, use a weighted evaluation function. The mathematical expression for evaluating the observation pose quality of a mobile robot is: ； in, , , These are the distance score, angle score, and occlusion score within the sampling angle, respectively. These are the weights corresponding to the distance score, angle score, and occlusion score within the sampling angle, respectively. Then, the optimal pose of the mobile robot facing the roadside equipment is the sampling point i and sampling angle j that maximizes the weighted evaluation function, and its expression is: ； in, The optimal observation pose for the mobile robot; S3.

4. Based on the optimal observed pose of the mobile robot, adjust the current pose of the mobile robot in the translation direction and orientation angle. The adjustment amount is: ； in, This is the adjustment amount for the lateral distance. This is the adjustment amount for the longitudinal distance. This is the amount of adjustment for the direction of the line of sight.

5. The automatic monitoring and correction method based on a mobile robot inspection platform according to claim 4, characterized in that, The specific implementation method of step S4 includes the following steps: S4.

1. After the mobile robot adjusts to the optimal pose, calculate the current line of sight of the roadside equipment relative to the world origin. The mathematical expression is: ； S4.

2. The online platform, based on the lateral and longitudinal distances of the roadside equipment monitored by the mobile robot and the current line of sight of the roadside equipment relative to the world origin, compares the preset standard world pose of the roadside equipment to calculate the absolute translation error and absolute angular error, quantifying the degree of deviation of the roadside equipment. The absolute translation error is: ； The absolute angle error is: ； The rap function is a modulo operation used to normalize the angle difference to the standard range of -180 to 180. S4.

3. Let the position threshold be... Angle threshold is The evaluation criteria for whether or not roadside equipment needs to be repaired are as follows: like Then the roadside equipment does not need to be modified; like To correct the position of roadside equipment; like To correct the steering of roadside equipment; If both the absolute translation error and the absolute angle error exceed the set threshold, the position and orientation of the roadside equipment will be calibrated simultaneously.

Images