Inspection robot operation control method and device, electronic equipment and program product

Abstract

The invention discloses an inspection robot operation control method and device, electronic equipment and a program product, the inspection robot is applied to a road guardrail, and the method comprises the following steps: acquiring GNSS positioning information of the inspection robot; acquiring inertial measurement data of the inspection robot; acquiring coded driving data of the inspection robot; fusing the GNSS positioning information, the inertial measurement data and the coded driving data to determine continuously updated first position information of the inspection robot; detecting stake mark identification information of the road guardrail to determine whether the road stake mark is close or not according to a detection result; when it is determined that the inspection robot is close to the road stake mark, second position information of the stake mark is obtained, and the first position information is corrected based on the second position information to obtain the corrected first position information; and controlling the inspection robot to run along the road guardrail based on the first position information. According to the inspection robot operation control method, continuous and accurate positioning of the inspection robot can be realized.

Description

Technical Field

[0001] This invention relates to the field of highway guardrail inspection robots, specifically to an inspection robot operation control method and device, electronic equipment and program products. Background Technology

[0002] Currently, highway patrol methods mainly include manual inspection, fixed roadside patrols, and mobile robot inspections. Manual inspections are time-consuming, labor-intensive, and inefficient, while fixed roadside robots have limited coverage. With technological advancements, using mobile inspection robots to replace manual labor in high-risk tasks is becoming a trend.

[0003] Several proposals have been put forward regarding road inspection robots.

[0004] CN110497379A discloses a highway inspection robot that travels along a guardrail. The highway inspection robot includes a traveling device, a limiting device, a power generation device, and an inspection device.

[0005] CN109514577A discloses an inspection robot that uses a tracked walking mechanism to move on the ground.

[0006] Current road inspection robot solutions cannot achieve high-precision, low-cumulative-error long-distance road inspection.

[0007] The background description is provided for the purpose of understanding the relevant technologies in this field and is not intended as an admission of prior art. Summary of the Invention

[0008] Therefore, the objective of this invention is to provide a method and apparatus for controlling the operation of an inspection robot, as well as electronic equipment and program products, which can at least partially solve the above-mentioned problems.

[0009] In a first aspect, a method for controlling the operation of an inspection robot is provided, wherein the inspection robot is applied to a road guardrail, and the method for controlling the operation of the inspection robot includes:

[0010] Obtain the GNSS positioning information of the inspection robot;

[0011] Acquire the inertial measurement data of the inspection robot;

[0012] Obtain the coded driving data of the inspection robot;

[0013] The GNSS positioning information, the inertial measurement data, and the coded driving data are fused to determine the first position information of the continuously updated inspection robot;

[0014] The station marker information of the road guardrail is detected to determine whether it is adjacent to a road station based on the detection results;

[0015] When it is determined that the inspection robot is close to a road marker, the second location information of the marker is obtained, and the first location information is corrected based on the second location information to obtain the corrected first location information.

[0016] The inspection robot is controlled to run along the road guardrail based on the first location information.

[0017] In some embodiments, fusing the GNSS positioning information, the inertial measurement data, and the coded driving data to determine the continuously updated first position information of the inspection robot includes:

[0018] When GNSS positioning information is updated, the current first position information is determined based on the GNSS positioning information and used as the position reference for track estimation;

[0019] During the time interval when the GNSS positioning information is not updated, the trajectory is calculated based on the inertial measurement data and coded driving data, starting from the position reference, to obtain the trajectory calculation position and determine the current first position information.

[0020] When new GNSS positioning information is received, the new GNSS positioning information is used as the new position reference to reset the cumulative error of the trajectory calculation.

[0021] In some embodiments, the inertial measurement data includes angular velocity data and acceleration data. In these embodiments, the step of calculating a trajectory based on the inertial measurement data and coded driving data to obtain a calculated position includes:

[0022] The travel distance data of the inspection robot is determined based on the coded travel data;

[0023] The heading angle of the inspection robot is calculated based on the angular velocity data in the inertial measurement data;

[0024] Based on the acceleration data in the inertial measurement data and the heading angle, the acceleration components in the navigation coordinate system are determined through coordinate transformation;

[0025] Integrating the acceleration components in the navigation coordinate system yields the first displacement increment;

[0026] The second displacement increment is determined based on the heading angle and the travel distance data;

[0027] The first displacement increment and the second displacement increment are merged to obtain the merged third displacement increment;

[0028] The estimated position of the trajectory is determined based on the position reference and the third displacement increment.

[0029] In some embodiments, detecting the post marker information of the road guardrail to determine whether it is adjacent to a road post marker based on the detection result includes:

[0030] As the inspection robot travels along the road guardrail, it captures images along the road guardrail.

[0031] The acquired images are processed using image recognition algorithms to identify the station number identification information in the images;

[0032] Based on the identified station number information, it is determined whether the inspection robot is near a road station number.

[0033] In some embodiments, determining whether the inspection robot is near a road marker based on the identified marker information includes:

[0034] Extract the image region corresponding to the road station number from the image;

[0035] Obtain the geometric features of the image region;

[0036] Based on the comparison between the geometric features of the image region and the preset geometric features, it is determined whether the inspection robot is near a road marker.

[0037] In some embodiments, determining whether the inspection robot is near a road marker based on a comparison between the geometric features of the image region and preset geometric features includes:

[0038] When the geometric features of the image region meet the preset conditions when compared with the preset geometric features, the inspection robot is determined to be located at the first calibration position at a preset distance from the road station number;

[0039] Obtain coded driving data starting from the first calibrated position;

[0040] When the coded driving data reaches a preset calibration threshold, it is determined that the inspection robot has reached the second calibration position;

[0041] When the inspection robot reaches the second designated position, it is determined that the inspection robot is close to the road marker.

[0042] In some embodiments, controlling the inspection robot to run along the road guardrail based on the first location information includes:

[0043] Obtain the relative position information of multiple target areas with respect to road station numbers, wherein the target areas correspond to the post areas and / or connection parts of the road guardrail;

[0044] The distance between the inspection robot and the target area is determined based on the first location information;

[0045] When the inspection robot reaches the target area and the distance is less than or equal to a first preset distance threshold, the inspection robot is controlled to reduce its operating speed from a first operating speed to a second operating speed and passes through the target area at the second operating speed.

[0046] When the inspection robot passes through the target area and the distance is greater than or equal to the second preset distance threshold, the inspection robot is allowed to increase from the second operating speed to the third operating speed.

[0047] In a second aspect, a control device for the operation of an inspection robot is provided. The inspection robot is applied to a road guardrail. The control device for the operation of the inspection robot includes:

[0048] The GNSS receiving module is configured to acquire the GNSS positioning information of the inspection robot.

[0049] An inertial measurement unit is configured to acquire inertial measurement data of the inspection robot;

[0050] The encoder is configured to acquire the coded driving data of the inspection robot;

[0051] The data fusion module is configured to fuse the GNSS positioning information, the inertial measurement data, and the coded driving data to determine the first position information of the continuously updated inspection robot.

[0052] The station number detection module is configured to detect the station number identification information of the road guardrail, so as to determine whether it is adjacent to the road station number based on the detection result;

[0053] The position correction module is configured to, when it is determined that the inspection robot is near a road marker, obtain the second position information of the marker, and correct the first position information based on the second position information to obtain the corrected first position information;

[0054] The operation control module is configured to control the inspection robot to run along the road guardrail based on the first location information.

[0055] In a third aspect, an electronic device is provided, including a processor and a memory storing a computer program, the processor being configured to implement the method of the first aspect when the computer program is executed.

[0056] In a fourth aspect, a program product is provided, comprising a computer program, wherein the computer program, when executed by a processor, implements the method described in the first aspect.

[0057] The inspection robot operation control method provided in this embodiment of the invention not only achieves continuous and accurate positioning of the inspection robot by integrating GNSS positioning information, inertial measurement data and coded driving data, but also utilizes the station numbers set along the road guardrail as precise position reference points. When the inspection robot approaches a station number, it obtains the precise position information of the station number to correct the first position information.

[0058] In a further embodiment, the inspection robot operation control method can also extract the geometric features of the station number in the image to initially determine the relative distance between the inspection robot and the station number, thus determining a first calibration position. Then, starting from the first calibration position, precise distance measurement is performed using coded travel data. When the coded travel data reaches a preset calibration threshold, a second calibration position is determined, thereby achieving high-precision proximity judgment of the station number. This solution is particularly suitable for inspection robots operating along highway guardrail paths. On the one hand, it fully utilizes image recognition to determine a generally consistent distance to the guardrail; on the other hand, it can fully utilize the encoder for precise distance difference compensation.

[0059] Other optional features and technical effects of the embodiments of the present invention are partly described below and partly apparent from reading this document. Attached Figure Description

[0060] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. The elements shown are not limited to the scale shown in the drawings, and the same or similar reference numerals in the drawings denote the same or similar elements, wherein:

[0061] Figure 1 This is an exemplary flowchart of an inspection robot operation control method according to an embodiment of the present invention;

[0062] Figure 2 This is an example of a highway guardrail inspection robot that can be applied to the inspection robot operation control method according to embodiments of the present invention;

[0063] Figure 3 This is an exemplary flowchart of an inspection robot operation control method according to an embodiment of the present invention;

[0064] Figure 4 This is an exemplary flowchart of an inspection robot operation control method according to an embodiment of the present invention;

[0065] Figure 5 This is a schematic control diagram for trajectory estimation according to an embodiment of the present invention;

[0066] Figure 6 This is an exemplary flowchart of an inspection robot operation control method according to an embodiment of the present invention;

[0067] Figure 7This is an exemplary flowchart of an inspection robot operation control method according to an embodiment of the present invention;

[0068] Figure 8 This is an exemplary flowchart of an inspection robot operation control method according to an embodiment of the present invention;

[0069] Figure 9 This is an exemplary flowchart of an inspection robot operation control method according to an embodiment of the present invention;

[0070] Figure 10 This is an exemplary block diagram of an inspection robot operation control device according to an embodiment of the present invention; and

[0071] Figure 11 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention.

[0072] In embodiments of the present invention, the same or similar reference numerals are used to denote the same or similar features or components. Detailed Implementation

[0073] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments and accompanying drawings. Here, the illustrative embodiments and descriptions of this invention are used to explain the invention, but are not intended to limit the invention.

[0074] The term "comprising" and its variations as used herein signify open inclusion, i.e., "including but not limited to". Unless otherwise stated, the term "or" means "and / or". The term "based on" means "at least partially based on". The terms "one example embodiment" and "one embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0075] The present invention will be further described below with reference to embodiments and accompanying drawings. Specific embodiments are only used to further illustrate the present invention and do not limit the scope of protection of the claims.

[0076] In practice, there is a need for road guardrail inspection robots, especially highway guardrail inspection robots, to autonomously travel long distances along guardrails for inspection operations. However, current highway inspection robot solutions cannot achieve long-distance highway inspection.

[0077] Here, the inventors recognized that accurate positioning and navigation are crucial for ensuring the quality of inspections. They noted that while GPS positioning can provide a location reference, the accuracy of civilian GPS is only about 10-20 meters, which is insufficient for the accuracy requirements of guardrail inspections. Inertial navigation can calculate position by measuring acceleration and angular velocity, offering high short-term accuracy, but it suffers from cumulative error, resulting in a significant decrease in positioning accuracy over long periods of operation.

[0078] In response, the inventors noted the inherently present mileage markers along highways and innovatively utilized the precise known locations of these mileage markers to periodically correct the robot's positioning results. For illustrative purposes, and not limitingly, mileage markers are fixed markers used in highway maintenance and management, typically placed every 100 meters. The location of each mileage marker is fixed and can be pre-obtained with precise GPS coordinates using high-precision GPS measurements or total station measurements, achieving centimeter-level accuracy. Specifically, in the embodiment of this invention, firstly, multi-source information fusion is performed using GNSS (such as GPS) data, inertial measurement data, and coded driving data to obtain first position information. When the robot moves to a mileage marker, the precise location of the mileage marker is used as second position information. The positioning error between the first and second position information is calculated, and the robot's position estimate is corrected based on this error to obtain corrected position information. The robot's movement is then controlled based on this corrected position information. In this way, error correction is performed at each mileage marker, effectively providing the robot with a periodically high-precision position reference, eliminating the cumulative errors of GPS positioning and inertial navigation. By transforming the long-distance continuous positioning problem into a short-distance positioning problem with multiple station intervals, the infinite accumulation of errors is prevented, ensuring the positioning accuracy and stability of long-distance inspection operations.

[0079] like Figure 1 As shown, this embodiment of the invention provides a method for controlling the operation of an inspection robot. This method is primarily applied to highway guardrail inspection scenarios. By way of explanation and not limitation, Figure 2The diagram shows a portion of a highway guardrail and an inspection robot 1 mounted on it. In a specific scenario, the highway guardrail extends along one or both sides of the highway, and the inspection robot 1 can autonomously travel along the guardrail L to detect and record its condition. In some embodiments, the highway guardrail L is provided with station markers (not shown), which are typically set at preset intervals (e.g., every 100 meters) to mark the mileage of the highway. The positions of these station markers can be pre-measured and recorded precisely on a station map, with an accuracy, for example, down to the centimeter level. In some embodiments, the highway guardrail may include connecting parts, such as joints near guardrail posts P or expansion joints, but the invention is not limited to these. These connecting parts typically have structural features such as height differences and gaps, which impose certain requirements on the mobility of the inspection robot.

[0080] like Figure 2 The diagram shows a schematic representation of an inspection robot according to an embodiment of the present invention. Figure 2 In the illustrated embodiment, the inspection robot 1 may include: a waveform guide wheel mechanism, a drive wheel mechanism, and a housing 50; the waveform guide wheel mechanism is used for guiding along the waveform structure of the waveform guardrail L; the drive wheel mechanism is used for providing walking drive force; and the housing 50 is used for mounting and protecting various mechanisms and sensors. In some embodiments, the waveform guide wheel mechanism may include at least one set of waveform guide wheels, each waveform guide wheel having a waveform profile matching the waveform structure of the waveform guardrail L, capable of rolling along one waveform structure of the waveform guardrail to achieve the guiding function of the robot. Figure 2 As shown, for a waveform guardrail with multiple waveform structures (such as a three-wave guardrail), the waveform guide wheel mechanism may include multiple sets of waveform guide wheels, respectively matching the upper waveform structure, the middle waveform structure, and the lower waveform structure. In some embodiments, the drive wheel mechanism may include multiple support wheels for supporting the robot body and providing walking drive. Figure 2 As shown, the drive wheel mechanism may include a plurality of lower support wheels that contact the lower edge of the wave-shaped guardrail L, wherein at least one lower support wheel is a walking drive wheel driven by a driver to propel the robot along the guardrail. In some embodiments, the inspection robot 1 may be mounted to the wave-shaped guardrail L at intervals from its upper edge.

[0081] In some embodiments, the inspection robot 1 may further include an inspection mechanism 60. The inspection mechanism 60 may include a support frame and detection equipment such as an image acquisition device 63 mounted at the end of the support frame. The support frame may include multiple support segments, such as support segments 61 and 62, which are pivotally connected, thereby allowing support segment 62 to form a cantilever. The image acquisition device 63 can be used to acquire relevant image information of the surrounding environment (as described below for detecting station numbers). Figure 2As shown, the inspection mechanism 60 may be pivotable, for example, it may be rotated to a given direction in order to detect station information (as described below).

[0082] In this embodiment of the invention, the inspection robot applicable to the method of this embodiment can adopt various structural forms, and no limitation is made thereto without conflicting with the solution of this invention.

[0083] For example, in some embodiments, the inspection robot used in the embodiments of the present invention can be a bottom-supported inspection robot with back-side support wheels, for example... Figure 2 As shown in the figure (not shown), the drive wheel mechanism may include multiple first lower support wheels configured to contact the front rolling surface of the lower edge of the corrugated guardrail L, multiple second lower support wheels configured to contact the back rolling surface of the lower edge of the corrugated guardrail L, and multiple third lower support wheels configured to contact the side rolling line of the lower edge of the corrugated guardrail L. Through the three-sided support structure of the first, second, and third lower support wheels, the inspection robot can be clamped and held at the lower edge of the corrugated guardrail, achieving stable support and movement.

[0084] For example, in some embodiments, the inspection robot used in the embodiments of the present invention can be a magnetically guided inspection robot with external single-sided support. In this structural form, the waveform guide wheel mechanism can include at least two sets of waveform guide magnetic wheels. The waveform guide magnetic wheels have a waveform profile that matches the waveform structure of the waveform guardrail, and each set of waveform guide magnetic wheels is configured to roll along a waveform structure of the waveform guardrail. In some embodiments, the waveform guide magnetic wheel can include a magnetic wheel body and a wheel axle. The magnetic wheel body can be provided with magnetic strips radially spaced along both sides of the waveform profile. In some embodiments, the waveform guide wheel mechanism can also include at least one retaining magnet facing the waveform structure of the waveform guardrail and spaced apart from the waveform structure. This can eliminate the need for any back clamping structure for retaining the inspection robot and can enable the inspection robot to be installed in a manner that does not extend beyond the lower edge of the waveform guardrail.

[0085] For example, in some embodiments, the inspection robot that can be used in the embodiments of the present invention can be a ground-supported wheel inspection robot, which may also include a ground-supported wheel mechanism, which includes multiple ground-supported wheels that roll on the road surface and bear the main weight of the robot.

[0086] The above-mentioned exemplary highway guardrail inspection robots and their components and structures can be referenced in Chinese invention patents CN118478338B, CN118596114B, CN118528229B, and Chinese utility model patent CN222290175U, the contents of which are incorporated herein by reference.

[0087] Continue to refer to Figure 1 The inspection robot operation control method according to embodiments of the present invention may include the following steps S110 to S170:

[0088] S110: Obtain GNSS positioning information of the inspection robot.

[0089] In this embodiment of the invention, GNSS positioning information of the inspection robot can be acquired. Accordingly, in some embodiments, the inspection robot may be equipped with a GNSS (Global Navigation Satellite System) receiver module. By way of explanation and not limitation, GNSS positioning information includes, but is not limited to, signals from navigation satellite systems such as GPS, BeiDou, GLONASS, and Galileo, and the robot's position coordinates are calculated. In some embodiments, GNSS positioning information typically includes longitude, latitude, and altitude. In some embodiments, it may also include auxiliary information such as positioning time, number of satellites, and signal strength.

[0090] In some embodiments, the update frequency of GNSS positioning information can be adjusted according to the robot's operating speed and positioning accuracy requirements.

[0091] S120: Acquire inertial measurement data of the inspection robot.

[0092] In this embodiment of the invention, inertial measurement data of the inspection robot can be acquired. In some embodiments, the inspection robot may be equipped with an inertial measurement unit (IMU), which may include a three-axis gyroscope and a three-axis accelerometer. By way of explanation and not limitation, the gyroscope is capable of measuring the angular velocity of the robot about three axes, and the accelerometer is capable of measuring the acceleration of the robot in three axes.

[0093] In some embodiments, inertial measurement data may include angular velocity data and acceleration data. In some embodiments, angular velocity data may include angular velocity components ω about the X-axis, Y-axis, and Z-axis. x ω y ω z Acceleration data can include acceleration components a in the X, Y, and Z axes. x a y a z .

[0094] In some embodiments, the robot's attitude changes (including yaw, pitch, and roll angles) can be calculated by integrating the angular velocity data; and the robot's velocity and displacement changes can be calculated by integrating the acceleration data (as further described below).

[0095] S130: Acquire the coded driving data of the inspection robot.

[0096] In some embodiments, encoders can be mounted on the wheels of the inspection robot, and these encoders can measure the rotation angle or number of rotations of the drive wheels. The data measured by the encoders can be used to calculate the distance the robot travels along the highway guardrail.

[0097] In some embodiments, the encoded travel data may include the number of encoder pulses, rotation angle, number of rotations, etc. In some embodiments, the robot's travel distance can be calculated by multiplying the rotation angle or number of rotations by the circumference parameter of the drive wheel.

[0098] In this embodiment of the invention, the encoder's installation position can be flexibly selected as needed. In some embodiments, the encoder (or encoder disk) can preferably be integrated onto the wave-shaped guide wheel. The wave-shaped guide wheel rolls along the wave-shaped contour of the guardrail, and its rotation has a definite correspondence with the robot's forward distance. By installing the encoder on the wave-shaped guide wheel, the rotation angle of the guide wheel can be accurately measured, thereby accurately calculating the robot's travel distance. In some embodiments, the encoder can also be integrated onto the drive wheel of the drive mechanism. In some embodiments using ground support wheels, the encoder can also be integrated onto the support wheels of the ground walking section. The ground support wheels roll on the road surface, and their rotation also reflects the robot's travel distance. Furthermore, it is conceivable to install the encoder onto other wheels of the robot.

[0099] S140: Fusion of GNSS positioning information, inertial measurement data, and coded driving data to determine the first position information of the continuously updated inspection robot.

[0100] In this embodiment of the invention, the first position information of the continuously updated inspection robot can be determined by fusing data from three different sources. In some embodiments, the first position information may include the robot's two-dimensional planar position coordinates (X, Y), and in some embodiments, it may also include elevation information Z, heading angle θ, velocity v, and other state information.

[0101] refer to Figure 3 A detailed flowchart illustrating the determination of first location information through data fusion according to an embodiment of the present invention is shown. Figure 3 As shown, step S140 may include the following sub-steps S310 to S330:

[0102] S310: When GNSS positioning information is updated, determine the current first position information based on the GNSS positioning information and use it as the position reference for track estimation.

[0103] In some embodiments, the GNSS receiving module receives updated GNSS positioning information at a certain frequency. In some embodiments, the received GNSS positioning information can be directly used as the current first location information. For example, if the GNSS positioning information shows that the robot is located at (Xg, Yg), then the current first location information can be set to (Xg, Yg).

[0104] Simultaneously, the GNSS positioning information is saved as a position reference for track estimation. In some embodiments, the position reference may include position coordinates, a timestamp, and optional information such as heading angle and velocity. This position reference will be used as a starting point in subsequent track estimation.

[0105] S320: During the time interval when GNSS positioning information is not updated, starting from the position reference, the trajectory is calculated based on inertial measurement data and coded driving data to obtain the trajectory calculation position, so as to determine the current first position information.

[0106] In this embodiment of the invention, the robot's position can be determined by track estimation during the time interval between two GNSS updates.

[0107] As an explanation, and not a limitation, the basic principle of trajectory estimation is that the current position can be calculated based on the known starting position and the displacement increment during the motion. Specifically, if the robot is located at the position reference (X0, Y0) at time t0, and the displacement increment from t0 to the current time t is measured to be (Δx, Δy), then the current position can be estimated as (X0+Δx, Y0+Δy).

[0108] In some embodiments of the present invention, the calculation of displacement increment can be achieved by fusing inertial measurement data and coded travel data. Inertial measurement data provides the robot's heading angle and acceleration information, while coded travel data provides travel distance information. By combining the heading angle and travel distance, the direction and magnitude of the displacement can be calculated, thereby obtaining the displacement increment.

[0109] Figure 4 A detailed flowchart of trajectory estimation according to an embodiment of the present invention is shown. Figure 4 As shown, the trajectory calculation in step S320 may include the following sub-steps S410 to S470:

[0110] S410: Determine the travel distance data of the inspection robot based on the coded travel data.

[0111] In some embodiments, as described above, an encoder may be mounted on the wheels of the inspection robot to measure the rotation of the drive wheels; for example, the encoded travel data may include the number of pulses output by the encoder, the rotation angle, or the number of rotations; thereby, the travel distance data of the inspection robot, such as the travel distance data from the position reference, can be determined based on the encoded travel data.

[0112] In some embodiments, the travel distance can be calculated based on the following formula:

[0113] d=(θ / 360°)×C

[0114] Where d is the travel distance (including absolute or relative travel distance), θ is the angle of rotation of the drive wheel, and C is the circumference of the drive wheel.

[0115] In some embodiments, if the encoder outputs the number of rotations n, the travel distance can be simplified as follows:

[0116] d=n×C

[0117] In some embodiments, the encoder reading of the previous trajectory calculation can be recorded, and the increase in travel distance within the current trajectory calculation cycle can be obtained by calculating the difference between the current encoder reading and the previous reading.

[0118] S420: Calculates the heading angle of the inspection robot based on the angular velocity data in the inertial measurement data.

[0119] In some embodiments, the heading angle has a conventional meaning in the art, such as representing the angle between the robot's forward direction and a reference direction (e.g., true north). Figure 5 As shown, a gyroscope (such as a three-axis gyroscope) can be used to obtain the angular velocity ω of the robot in multiple (e.g., three) directions. x ω y ω z Furthermore, multiple angular velocities ω can be processed through the attitude vector calculation module. x ω y ω zTo obtain the heading angle, in some embodiments, the heading angle can be calculated by integrating angular velocity data. In some embodiments, the integration can employ numerical integration methods such as the rectangular method, trapezoidal method, or Simpson's method. In some cases, the gyroscope may exhibit zero bias, meaning it outputs a non-zero angular velocity value even when stationary. In some embodiments, to improve the accuracy of the heading angle calculation, angular velocity data can be collected for a period of time when the robot starts or is stationary, and its average value can be calculated as a zero bias estimate, which is then subtracted during the heading angle calculation. In some embodiments, the initial value of the heading angle can be obtained using a magnetometer, GNSS heading, or other methods. In highway guardrail inspection scenarios, since the robot travels along the guardrail, the heading angle is usually consistent with the direction of the guardrail's extension. The initial heading angle can be set based on the map information of the guardrail (or the map information of the highway).

[0120] As an explanation and not a limitation, the coordinate transformation described below can be achieved by a rotation matrix, which is determined by the robot's posture (including heading angle, pitch angle, and roll angle). In the simplified scenario of highway guardrail inspection, if it is assumed that the robot mainly operates on the horizontal plane and the pitch and roll angles are small, then the influence of the heading angle can be mainly considered.

[0121] S430: Based on acceleration data and heading angle from inertial measurement data, the acceleration components in the navigation coordinate system are determined through coordinate transformation.

[0122] In some embodiments, in conjunction with reference Figure 5 Accelerometers (such as triaxial accelerometers) can be used to measure acceleration in the robot coordinate system. However, in order to calculate the robot's displacement in the navigation coordinate system (such as the N-H coordinate system or the local horizontal coordinate system), the acceleration in the robot coordinate system can be transformed to the navigation coordinate system.

[0123] As mentioned earlier, in some embodiments, coordinate transformation can be achieved using a rotation matrix, which is determined by the robot's posture (including heading, pitch, and roll angles). In the simplified scenario of road guardrail inspection, if it is assumed that the robot mainly operates on a horizontal plane with small pitch and roll angles, then the influence of the heading angle can be mainly considered.

[0124] Accordingly, such as Figure 5 In the example shown, let the acceleration in the carrier coordinate system be (a x , a y , a z Assuming the heading angle is θ, then the acceleration (a) in the navigation coordinate system x_n , a y_n , a z_n It can be determined through appropriate coordinate transformation.

[0125] S440: Integrate the acceleration components in the navigation coordinate system to obtain the first displacement increment.

[0126] In embodiments of the present invention, for example Figure 5 As shown, the acceleration components in the navigation coordinate system can be integrated using appropriate inertial navigation equations to obtain the first displacement increment. In some embodiments, such as... Figure 5 As shown, the velocity can also be obtained through the same integral operation. In some embodiments, the aforementioned first displacement increment and optional velocity can be determined using well-known inertial navigation equations, which will not be elaborated here.

[0127] S450: Determine the second displacement increment based on heading angle and travel distance data.

[0128] In some embodiments, the second displacement increment can be determined based on the travel distance determined by the encoder-measured coded data and the heading angle calculated by the IMU. By way of explanation and not limitation, the second displacement increment can serve as a correction to the first displacement increment.

[0129] S460: Merge the first displacement increment with the second displacement increment to obtain the merged displacement increment.

[0130] In some embodiments, the first displacement increment and the second displacement increment can be fused using weighted fusion, Kalman filtering, or other fusion algorithms.

[0131] In some embodiments, weighted fusion can dynamically adjust the weights based on the confidence levels of the two displacement increments.

[0132] In some alternative embodiments, anomalies can be detected by comparing the consistency of the first displacement increment and the second displacement increment.

[0133] S470: Determine the estimated position of the track based on the position reference and the fused displacement increment.

[0134] In some embodiments, the position can be calculated by overlaying the fused displacement increment onto a position reference.

[0135] In some embodiments, the estimated position can be determined according to the following formula:

[0136] Estimated position = Position reference + Fusion displacement increment

[0137] In some embodiments, trajectory estimation can estimate not only position, but also state variables such as speed and heading angle, which can be used for subsequent operational control.

[0138] In some alternative embodiments, GNSS positioning information and inertial measurement data can be fused to determine the first position information of the continuously updated inspection robot, which falls within the broad scope of the embodiments of the present invention. Accordingly, as a supplementary alternative to S140, the method of the embodiments of the present invention may include step S140' (not shown): fusing at least GNSS positioning information and inertial measurement data to determine the first position information of the continuously updated inspection robot. Accordingly, in some alternative embodiments, the calculation of the displacement increment can be determined based on the inertial measurement data.

[0139] In some alternative embodiments, step S140' may include steps A1 to A4 (not shown): A1: Calculate the heading angle of the inspection robot based on the angular velocity data in the inertial measurement data; A2: Determine the acceleration component in the navigation coordinate system through coordinate transformation based on the acceleration data and heading angle in the inertial measurement data; A3: Perform integration on the acceleration component in the navigation coordinate system to obtain the first displacement increment; A4: Determine the trajectory and calculate the position based on the position reference and the first displacement increment.

[0140] S330: When new GNSS positioning information is received, the new GNSS positioning information is used as the new position reference to reset the cumulative error of the track calculation.

[0141] As an explanation rather than a limitation, trajectory estimation inevitably produces cumulative errors due to its reliance on sensor measurements and numerical integration; these errors gradually increase over time.

[0142] Accordingly, in some embodiments, when new GNSS positioning information is received, the system resets the accumulated error of the track estimation while using the new GNSS positioning information as a new position reference.

[0143] In some specific embodiments, the new GNSS positioning information can be used as a new position reference while simultaneously calculating the deviation between the track-estimated position and the new GNSS positioning information. In this way, the accumulated error of the track estimation is cleared to zero each time the GNSS is updated.

[0144] S150: Detect the marker information of road guardrails to determine whether they are adjacent to highway markers based on the detection results.

[0145] In some embodiments, station number detection can be achieved by combining a visual sensor (such as visual sensor 63 described above) with an image recognition algorithm. As the robot moves along the highway guardrail, it can continuously collect images along the guardrail and search for station number markers in the images using an image recognition algorithm.

[0146] In some embodiments, the station number has a conventional meaning in the art, such as having specific appearance characteristics, such as a specific color (e.g., green background with white lettering), a specific shape (e.g., a circular sign or an inverted trapezoidal sign), or a specific content format (e.g., the lower number "148" represents the kilometer (e.g., 148 km), the upper number "9" represents the hemian (e.g., 900 m), i.e., 148 km + 900 m). In embodiments of the present invention, the identified station number can cover various types of station numbers, preferably including hemian-level station numbers. In some embodiments, step S150 can detect the station number alone or detect the combination of the station number with other road signs or markings (e.g., mileage markers or road signs). In the preferred embodiments described below, image recognition is performed on the station number itself and its various information, such as optical character recognition for both the kilometer and hemian numbers of the station number, but only the geometric feature comparison of the station number as a whole is performed (but it is not limited to geometric feature comparison or combination of the numbers within the station number), which will be further described below. In other embodiments, optical character recognition can be performed on both the station number and other road signs or markings (such as mile markers or road signs). For example, optical character recognition can be performed on mile markers at the kilometer level, while optical character recognition can also be performed on 100-meter station numbers at the 100-meter level.

[0147] In some embodiments, in addition to visual (image) recognition, other methods can be used to detect station numbers, such as reading the RFID tag installed on the station number using an RFID reader or scanning the QR code on the station number using a scanning device. These alternative methods can serve as supplements or alternatives to visual recognition, but the numerous embodiments of the present invention will be described below using visual (image) recognition as an example only.

[0148] In embodiments of the present invention, the determination of "whether it is near a highway marker" can be based on various other criteria. In an alternative embodiment, a marker can be considered near as long as it is detected in the image. In some preferred embodiments, the distance between the robot and the marker can be estimated by analyzing the geometric features such as the size and position of the marker in the image, thereby more accurately determining whether they are near.

[0149] The following will refer to Figure 6 , Figure 7 and Figure 8 Several preferred embodiments based on visual (image) recognition are further described.

[0150] Figure 6 A flowchart for station number detection according to an embodiment of the present invention is shown. Figure 6 As shown, the station number detection in step S150 may include the following sub-steps S610 to S630:

[0151] S610: When the inspection robot is running along the road guardrail, it collects images along the road guardrail.

[0152] In some embodiments, the inspection robot may be equipped with a vision sensor (such as the vision sensor 63 described above), such as a camera, CCD camera, or CMOS camera. In some embodiments, the vision sensor may be rotatably mounted on top of the robot to acquire images along the highway guardrail.

[0153] In some embodiments, images may preferably be acquired in sequence (e.g., at given time intervals).

[0154] In other embodiments, image acquisition can also be triggered. For example, the system can estimate the distance between the robot and the next station based on the robot's position information. When the distance is less than a certain threshold, the vision sensor is triggered to start acquiring images; when the robot passes the station and moves away from it by a certain distance, image acquisition stops.

[0155] In some other embodiments, image acquisition can be performed continuously.

[0156] In some embodiments, the acquired image may be a color image or a grayscale image, and the present invention does not limit this.

[0157] In some embodiments, the camera parameters can be adjusted as needed during image acquisition, and the present invention does not limit this.

[0158] S620: Processes the acquired images using an image recognition algorithm to identify the station number identification information in the images.

[0159] In some embodiments, the image recognition algorithm selects any suitable image algorithm in order to accurately identify the station marker from the image.

[0160] In some embodiments, the image recognition algorithm used may include a variety of image recognition algorithms or a collection thereof, such as preferably an image segmentation algorithm and an optical character recognition (OCR) algorithm, or a combination of the two. The image segmentation algorithm may be, for example, the YOLO algorithm, and this invention is not limited thereto. In a preferred embodiment, the image recognition algorithm, such as the image segmentation algorithm, may also be used in subsequent embodiments to extract, determine, or form geometric features, as further described below.

[0161] In some embodiments, image recognition may include image preprocessing, such as, but not limited to, denoising, enhancement, and correction, which are not limited by the present invention.

[0162] In some embodiments, image recognition may include station number-related region detection, which may be implemented, for example, through an image segmentation module of an image segmentation algorithm or an ensemble algorithm. In some embodiments, the station number identification information identified during image recognition, such as station number-related region detection, may include not only the station number but also, as needed, information such as the station number's position (e.g., pixel coordinates), size (e.g., the width and height of the envelope rectangle), and orientation in the image, as further described below.

[0163] In some embodiments, image recognition may include optical character recognition, such as recognizing characters on station markers, such as the character content on station markers, for example, recognizing characters for the kilometers and hectares mentioned above respectively. In other embodiments, character recognition may be performed on the kilometers on the mileage markers and on the hectares on the station markers, which falls within the scope of this invention.

[0164] S630: Based on the identified station marker information, determine whether the inspection robot is near a road station.

[0165] In some embodiments, determining whether a road marker is adjacent can be based on a variety of criteria.

[0166] In one embodiment, a station marker can be identified in the image, indicating that the robot is near a highway station. In this case, if the judgment result of step S630 is "yes", the position correction in step S160 can be executed, at which point the current position of the inspection robot will be approximated by the station location.

[0167] In some preferred embodiments, the proximity of a station number can be determined based on image geometric features. For example... Figure 7 As shown, step S630 may further include the following sub-steps S710 to S730:

[0168] S710: Extract the image region corresponding to the road station number from the image.

[0169] S720: Acquire the geometric features of the image region.

[0170] S730: Based on the comparison between the geometric features of the image area and the preset geometric features, determine whether the inspection robot is near a road marker.

[0171] In a more preferred embodiment, step S730 may include S730' (not shown): comparing the geometric features of the image region with preset geometric features, and determining that the inspection robot is located at a first calibration position when the comparison result meets preset conditions. In some embodiments, when the inspection robot is determined to be located at the first calibration position, the current position of the inspection robot is approximated by the station position. In the preferred embodiment described below, when the inspection robot is determined to be located at the first calibration position, a second calibration position "closer" to the station is further determined based on coded driving data, thereby more accurately determining the current position of the inspection robot.

[0172] In different embodiments of the present invention, the image region corresponding to the highway mileage can encompass various forms. In some embodiments, the image region corresponding to the highway mileage includes an image region whose shape is approximately consistent with that of the mileage in the image. For example, the image region corresponding to the highway mileage is a relatively precise mileage region in the image determined by an image segmentation algorithm. In some embodiments, the image region corresponding to the highway mileage includes an image region surrounding the mileage in the image, such as the envelope region of the mileage in the image. In a preferred embodiment, for example, the image region corresponding to the highway mileage is a predicted bounding box (such as a rectangular predicted bounding box) surrounding the mileage formed by an image segmentation algorithm (such as YOLO). In some embodiments, the image region can be represented by a rectangular envelope. The parameters of the rectangular envelope may include: the coordinates of the upper left corner (x, y, y). min , y min ); lower right corner coordinates (x max , y max ); or center coordinates (x c , y c The image region has a width w and a height h. In an alternative embodiment, as described above, the image region may be an area roughly corresponding to one or more characters within the station number, and the present invention does not limit this.

[0173] In different embodiments of the present invention, geometric features may encompass a variety of forms or combinations thereof, including but not limited to pixel features or their equivalents, area features, size features, shape features, position features, or combinations thereof.

[0174] In some embodiments, the geometric features include pixel features of the image region.

[0175] In a further embodiment, step S730, such as step S730', may include: counting the number of pixels in the image region; comparing the number of pixels with a preset reference number of pixels; and determining a first calibration position when the difference between the number of pixels and the reference number of pixels falls within a preset range.

[0176] As an alternative further embodiment, step S730, such as step S730', may include: counting the number of pixels in the image region; calculating the ratio of the number of pixels to the number of preset reference pixels; and determining the first calibration position when the ratio falls within the preset ratio range.

[0177] In some embodiments, the geometric features include area features of the image region.

[0178] In a further embodiment, step S730, such as step S730', may include: calculating the area of ​​the image region; comparing the area with a preset reference area; and determining a first calibration position when the difference between the area and the reference area falls within a preset range. In an even further embodiment, step S730, such as step S730', may include: identifying the actual pixel region of the station number through image segmentation; calculating the area of ​​the actual pixel region; comparing the area with a preset reference area; and determining a first calibration position when the difference between the area and the reference area falls within a preset range. As an alternative, even further embodiment, step S730, such as step S730', may include: determining an envelope region surrounding the station number; calculating the area of ​​the envelope region; comparing the area with a preset reference area; and determining a first calibration position when the difference between the area and the reference area falls within a preset range.

[0179] As an alternative further embodiment, step S730, such as step S730', may include: calculating the area of ​​the image region; calculating the ratio of the area to a preset reference area; and determining the first calibration position when the ratio falls within the preset ratio range. Similarly, the image region may be the actual pixel region or the envelope region of the station number.

[0180] In some embodiments, the geometric features include the size features of the image region.

[0181] In a further embodiment, step S730, such as step S730', may include: obtaining one or more side length dimensions of the image region; comparing the one or more side length dimensions with one or more preset reference side lengths; and determining a first calibration position when the absolute difference between the side length dimension and the reference side length is less than a preset threshold.

[0182] As an alternative further embodiment, step S730, such as step S730', may include: obtaining one or more side length dimensions of the image region; calculating the ratio of the one or more side length dimensions to one or more preset reference side lengths; and determining a first calibration position when the ratio falls within the preset ratio range.

[0183] In some embodiments, the side length may include length and / or width. In alternative embodiments, the diagonal may be used as an alternative to or supplement to the side length.

[0184] In some embodiments, the geometric features include multiple combinations of pixel features, area features, and (one-dimensional) size features of the image region. In some embodiments, the geometric features include one or more of pixel features, area features, and (one-dimensional) size features of the image region, combined with shape features and / or position features; this invention is not limited thereto.

[0185] As mentioned above, in some preferred embodiments, precise localization can be achieved through a two-stage approach based on image geometric features and an encoder. Figure 8 The diagram illustrates a two-stage localization flowchart based on image geometric features and an encoder, according to an embodiment of the present invention. Specifically, steps S730 and S730' may include sub-steps S810 to S840:

[0186] S810: When the geometric features of the image region meet the preset conditions when compared with the preset geometric features, the inspection robot is determined to be located at the first calibration position at a preset distance from the road station number.

[0187] As mentioned above, the above comparison can be achieved through different means and various preset conditions can be set.

[0188] As an explanation and not a limitation, in these embodiments, the determination of the first calibration location does not determine the robot's current location, but can generally characterize that the robot has entered the area around the station (greater than the area of ​​the adjacent highway station).

[0189] S820: Acquire coded driving data starting from the first calibration position.

[0190] In some embodiments, starting from a first calibration position, encoder data can be continuously recorded, and the incremental travel distance starting from the first calibration position can be determined based on the coded travel data.

[0191] S830: When the coded driving data reaches the preset calibration threshold, the inspection robot is determined to have reached the second calibration position.

[0192] In some embodiments, the preset calibration threshold is a pre-defined distance value. In some embodiments, the preset calibration threshold may be determined, for example, through experimentation.

[0193] S840: When the inspection robot reaches the second calibration position, determine the nearest road marker.

[0194] In some embodiments, the second calibration position is the position of the "nearest highway station" determined by the system; when the robot reaches the second calibration position, the highway station position will be used as the robot's current position (more accurately, as the second position for correction).

[0195] As an explanation rather than a limitation, the two-stage localization method enables the system to trigger position correction when the robot reaches a position at a precise distance from the station (e.g., at the centimeter level), which can significantly improve the accuracy of localization triggering.

[0196] In some embodiments, the setting of the second calibration position may also take into account the robot's operating speed and the system's response time.

[0197] By way of explanation and not limitation, the two-stage positioning method of the present invention combines the advantages of visual ranging and encoder ranging, thereby achieving centimeter-level proximity accuracy. It also achieves the complementary advantages of vision and encoder. Specifically, the first stage utilizes the long-distance detection capability of vision, and the second stage utilizes the high-precision ranging capability of encoder, especially taking advantage of the characteristic of the highway inspection robot traveling in one direction along the highway guardrail, to obtain this high-precision corrected position information.

[0198] When it is determined that the inspection robot is near the highway marker, the following step S160 can be performed.

[0199] S160: When it is determined that the inspection robot is close to a road marker, the second position information of the marker is obtained, and the first position information is corrected based on the second position information to obtain the corrected first position information.

[0200] In some embodiments, correcting the first location information based on the second location information may include calculating the positioning error between the first location information before correction and the second location information.

[0201] In some embodiments, the second position can be directly replaced by the first position.

[0202] As an explanation rather than a limitation, position correction eliminates the errors accumulated between two station points by GNSS and inertial navigation, bringing the robot's position estimation back to a high-precision state. The periodic error correction mechanism ensures that the robot maintains high positioning accuracy throughout long-distance inspections.

[0203] S170: Based on the first location information, control the inspection robot to run along the road guardrail.

[0204] For illustrative purposes, and not as a limitation, the first position information is continuously updated throughout the operation. Between two station numbers, the first position information is continuously updated through data fusion in step S140; when a station number is reached, the first position information is calibrated through correction in step S160. Therefore, the first position information used for operation control is always the latest and most accurate position estimate.

[0205] In some embodiments, operation control based on the first location information may include path planning, trajectory tracking, speed control, attitude control, etc.

[0206] In some embodiments, the robot can also determine whether it is approaching a specific area (such as a connecting point, a dangerous section of road, etc.) based on the first location information, and adjust its operating parameters accordingly. For example, when the robot approaches a connecting point, its operating speed can be reduced and the sensor sampling frequency increased to pass through the connecting point more safely. In particular, highway guardrails are usually composed of multiple sections spliced ​​together, and gaps, height differences, or protrusions exist at the connecting points of the guardrails (such as expansion joints, bolted connections, and the connection between bridges and road sections), posing a challenge to the robot's passage. If the robot cannot accurately identify these connecting points and adjust its operating status accordingly, it may lead to passage failure, jamming, or even equipment damage.

[0207] Accordingly, refer to Figure 9 Step S170 may include sub-steps S910 to S940:

[0208] S910: Obtain the relative position information of multiple target areas with respect to road station numbers;

[0209] The target area corresponds to the post area and / or connection part of the highway guardrail;

[0210] In this embodiment, the location information of the target area, especially the relative location information with respect to the station number, can be pre-stored in the location map.

[0211] In a preferred embodiment, the position of the column can be roughly corresponding to the connection part.

[0212] S920: Determines the distance between the inspection robot and the target area based on the first location information;

[0213] S930: When the inspection robot reaches the target area and the distance is less than or equal to the first preset distance threshold, control the inspection robot to reduce from the first running speed to the second running speed, and pass through the target area at the second running speed;

[0214] S940: When the inspection robot passes through the target area and the distance is greater than or equal to the second preset distance threshold, the inspection robot is allowed to increase from the second operating speed to the third operating speed.

[0215] In some embodiments, the first operating speed and / or the third operating speed may be the normal operating speed; the second operating speed may be the decelerated operating speed.

[0216] In some embodiments, the third operating speed may be equal to or different from the first operating speed.

[0217] By switching between the aforementioned operating states, the robot has a stronger ability to adapt when passing through connection points.

[0218] In an embodiment of the present invention, reference is made to Figure 10 The invention also provides an inspection robot operation control device 1000, wherein the inspection robot is applied to highway guardrails, and the inspection robot operation control device 1000 may include a GNSS receiving module 1010, an inertial measurement unit (IMU) 1020, an encoder 1030, a data fusion module 1040, a station detection module 1050, a position correction module 1060, and an operation control module 1070.

[0219] In some embodiments, the GNSS receiving module 1010 is configured to acquire the GNSS positioning information of the inspection robot.

[0220] In some embodiments, the inertial measurement unit 1020 is configured to acquire inertial measurement data of the inspection robot.

[0221] In some embodiments, encoder 1030 is configured to acquire coded driving data of the inspection robot.

[0222] In some embodiments, the data fusion module 1040 is configured to fuse the GNSS positioning information, the inertial measurement data, and the coded driving data to determine the first position information of the continuously updated inspection robot.

[0223] In some embodiments, the station detection module 1050 is configured to detect the station identification information of the road guardrail to determine whether it is adjacent to a road station based on the detection result.

[0224] In some embodiments, the position correction module 1060 is configured to, when it is determined that the inspection robot is near a road marker, acquire second position information of the marker, and correct the first position information based on the second position information to obtain corrected first position information.

[0225] In some embodiments, the operation control module 1070 is configured to control the inspection robot to run along the road guardrail based on the first location information.

[0226] The apparatus, components, modules, units, and features described in the embodiments of the present invention can be incorporated into the methods of the embodiments of the present invention in a non-contradictory manner, and the methods, steps, sub-steps, and features described in the embodiments of the present invention can also be incorporated into the apparatus of the embodiments of the present invention in a non-contradictory manner.

[0227] In embodiments of the present invention, an electronic device may also be provided, including: a processor and a memory storing a computer program, the processor being configured to perform the method of any embodiment of the present invention when running the computer program.

[0228] Figure 11 The diagram illustrates a method for implementing embodiments of the present invention or an electronic device 1100 for implementing embodiments of the present invention. In some embodiments, more or fewer electronic devices may be included than illustrated. In some embodiments, implementation may be carried out using a single or multiple electronic devices. In some embodiments, implementation may be carried out using cloud-based or distributed electronic devices.

[0229] like Figure 11 As shown, electronic device 1100 includes processor 1101, which can perform various appropriate operations and processes based on programs and / or data stored in read-only memory (ROM) 1102 or programs and / or data loaded from storage portion 1108 into random access memory (RAM) 1103. Processor 1101 may be a multi-core processor or may contain multiple processors. In some embodiments, processor 1101 may include a general-purpose main processor and one or more special coprocessors, such as a graphics processing unit (GPU), a neural network processor (NPU), a digital signal processor (DSP), etc. Various programs and data required for the operation of electronic device 1100 are also stored in RAM 1103. Processor 1101, ROM 1102, and RAM 1103 are interconnected via bus 1104. Input / output (I / O) interface 1105 is also connected to bus 1104.

[0230] The processor and memory described above are used together to execute a program stored in the memory. When the program is executed by a computer, it can implement the steps or functions of the methods described in the above embodiments.

[0231] The following components are connected to I / O interface 1105: an input section 1106 including a keyboard, mouse, touchscreen, etc.; an output section 1107 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1108 including a hard disk, etc.; and a communication section 1109 including a network interface card such as a LAN card, modem, etc. The communication section 1109 performs communication processing via a network such as the Internet. A drive 1110 is also connected to I / O interface 1105 as needed. Removable media 1111, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 1110 as needed so that computer programs read from them can be installed into storage section 1108 as needed. Figure 11 The diagram only shows a portion of the components and does not imply that the computer system 1100 includes only these components. Figure 11 The components shown.

[0232] In some embodiments, the electronic device refers to a mobile terminal or computer, including mobile phones, vehicle terminals, smart TVs, etc. Taking a mobile phone as an example, the electronic device also includes a touch screen, external speaker, gyroscope, camera, 4G / 5G antenna, and other device modules.

[0233] The systems, devices, modules, or units described in the above embodiments can be implemented by a computer or its associated components. The computer may be, for example, a mobile terminal, a personal computer, an in-vehicle human-machine interface device, a personal digital assistant, a navigation device, a tablet computer, an Internet of Things system, an industrial computer, a server, or a combination thereof.

[0234] Although not shown, in embodiments of the invention, a program product is provided, the program product comprising a computer program configured to be run to implement the methods of any embodiment of the invention.

[0235] Although not shown, in embodiments of the invention, a storage medium is provided storing a computer program configured to be run to implement the methods of any embodiment of the invention.

[0236] Storage media in embodiments of the present invention include articles that are permanent or non-permanent, removable or non-removable, and can store information by any method or technology. Examples of storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information that can be accessed by a computing device.

[0237] The methods, programs, systems, apparatuses, etc., in embodiments of the present invention can be executed or implemented in one or more networked computers, or practiced in a distributed computing environment. In the embodiments of this specification, in these distributed computing environments, tasks can be performed by remote processing devices connected via a communication network.

[0238] Those skilled in the art will understand that the embodiments described in this specification can be provided as methods, systems, or computer program products. Therefore, those skilled in the art will realize that the functional modules / units or controllers and related method steps described in the above embodiments can be implemented in software, hardware, or a combination of both.

[0239] Unless explicitly stated otherwise, the actions or steps of the methods and procedures described in the embodiments of the present invention do not necessarily have to be performed in a specific order and can still achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0240] This document describes several embodiments of the present invention; however, for the sake of brevity, the descriptions of the embodiments are not exhaustive, and identical or similar features or parts between the embodiments may be omitted. In this document, "one embodiment," "some embodiments," "example," "specific example," or "some examples" refers to embodiments applicable to at least one, but not all, of the present invention. The above terms do not necessarily refer to the same embodiments or examples. Without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described herein, as well as the features of the different embodiments or examples.

[0241] The exemplary systems and methods of the present invention have been specifically shown and described with reference to the above embodiments, which are merely examples of the best mode for implementing the systems and methods. Those skilled in the art will understand that various changes can be made to the embodiments of the systems and methods described herein without departing from the spirit and scope of the invention as defined in the appended claims when implementing the systems and / or methods.

Claims

1. A method for controlling the operation of an inspection robot, characterized in that, The inspection robot is applied to road guardrails, and the operation control method of the inspection robot includes: Obtain the GNSS positioning information of the inspection robot; Acquire the inertial measurement data of the inspection robot; Obtain the coded driving data of the inspection robot; The GNSS positioning information, the inertial measurement data, and the coded driving data are fused to determine the first position information of the continuously updated inspection robot; The marker information of the road guardrail is detected to determine whether it is adjacent to a road marker based on the detection results; When it is determined that the inspection robot is close to a road marker, the second location information of the marker is obtained, and the first location information is corrected based on the second location information to obtain the corrected first location information. The inspection robot is controlled to run along the road guardrail based on the first location information.

2. The inspection robot operation control method according to claim 1, characterized in that, The process of fusing the GNSS positioning information, the inertial measurement data, and the coded driving data to determine the continuously updated first position information of the inspection robot includes: When GNSS positioning information is updated, the current first position information is determined based on the GNSS positioning information and used as the position reference for track estimation; During the time interval when the GNSS positioning information is not updated, the trajectory is calculated based on the inertial measurement data and coded driving data, starting from the position reference, to obtain the trajectory calculation position and determine the current first position information. When new GNSS positioning information is received, the new GNSS positioning information is used as the new position reference to reset the cumulative error of the trajectory calculation.

3. The inspection robot operation control method according to claim 2, characterized in that, The inertial measurement data includes angular velocity data and acceleration data; The step of calculating the trajectory based on the inertial measurement data and coded driving data to obtain the estimated position includes: The travel distance data of the inspection robot is determined based on the coded travel data; The heading angle of the inspection robot is calculated based on the angular velocity data in the inertial measurement data; Based on the acceleration data in the inertial measurement data and the heading angle, the acceleration components in the navigation coordinate system are determined through coordinate transformation; Integrating the acceleration components in the navigation coordinate system yields the first displacement increment; The second displacement increment is determined based on the heading angle and the travel distance data; The first displacement increment and the second displacement increment are merged to obtain the merged third displacement increment; The estimated position of the trajectory is determined based on the position reference and the third displacement increment.

4. The inspection robot operation control method according to any one of claims 1 to 3, characterized in that, The detection of the road guardrail's marker information, to determine whether it is adjacent to a road marker based on the detection results, includes: As the inspection robot travels along the road guardrail, it captures images along the road guardrail. The acquired images are processed using image recognition algorithms to identify the station number identification information in the images; Based on the identified station number information, it is determined whether the inspection robot is near a road station number.

5. The inspection robot operation control method according to claim 4, characterized in that, The step of determining whether the inspection robot is near a road marker based on the identified marker information includes: Extract the image region corresponding to the road station number from the image; Obtain the geometric features of the image region; Based on the comparison between the geometric features of the image region and the preset geometric features, it is determined whether the inspection robot is near a road marker.

6. The inspection robot operation control method according to claim 5, characterized in that, The step of determining whether the inspection robot is near a road marker by comparing the geometric features of the image region with preset geometric features includes: When the geometric features of the image region meet the preset conditions when compared with the preset geometric features, the inspection robot is determined to be located at the first calibration position at a preset distance from the road station number; Obtain coded driving data starting from the first calibrated position; When the coded driving data reaches a preset calibration threshold, it is determined that the inspection robot has reached the second calibration position; When the inspection robot reaches the second designated position, it is determined that the inspection robot is close to the road marker.

7. The inspection robot operation control method according to any one of claims 1 to 3, characterized in that, The step of controlling the inspection robot to run along the road guardrail based on the first location information includes: Obtain the relative position information of multiple target areas with respect to road station numbers, wherein the target areas correspond to the post areas and / or connection parts of the road guardrail; The distance between the inspection robot and the target area is determined based on the first location information; When the inspection robot reaches the target area and the distance is less than or equal to a first preset distance threshold, the inspection robot is controlled to reduce its operating speed from a first operating speed to a second operating speed and passes through the target area at the second operating speed. When the inspection robot passes through the target area and the distance is greater than or equal to the second preset distance threshold, the inspection robot is allowed to increase from the second operating speed to the third operating speed.

8. A control device for the operation of an inspection robot, characterized in that, The inspection robot is used on road guardrails, and the inspection robot's operation control device includes: The GNSS receiving module is configured to acquire the GNSS positioning information of the inspection robot. An inertial measurement unit is configured to acquire inertial measurement data of the inspection robot; The encoder is configured to acquire the coded driving data of the inspection robot; The data fusion module is configured to fuse the GNSS positioning information, the inertial measurement data, and the coded driving data to determine the first position information of the continuously updated inspection robot. The station number detection module is configured to detect the station number identification information of the road guardrail, so as to determine whether it is adjacent to the road station number based on the detection result; The position correction module is configured to, when it is determined that the inspection robot is near a road marker, obtain the second position information of the marker, and correct the first position information based on the second position information to obtain the corrected first position information; The operation control module is configured to control the inspection robot to run along the road guardrail based on the first location information.

9. An electronic device, characterized in that, It includes a processor and a memory storing a computer program, the processor being configured to implement the method as described in any one of claims 1 to 7 when the computer program is executed.

10. A program product comprising a computer program, wherein, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 7.

Images