Steel gate visual inspection robot positioning system and positioning method thereof

Abstract

The invention provides a steel gate visual inspection robot positioning system and a positioning method thereof. The system comprises a global positioning camera, an auxiliary laser device, a local positioning camera, an attitude sensor and a controller. The global positioning camera is used for shooting the whole working face of the steel gate and obtaining the position of the robot. The auxiliary laser device is located on one side of the working face of the steel gate and used for projecting laser beams to the working face. The local positioning camera is mounted on the robot and is used for acquiring an image of a laser beam on a working surface; the attitude sensor is installed on the robot and used for obtaining the attitude of the robot. According to the method, the problem that the precision is not enough during actual positioning in an existing positioning mode is solved in a coarse positioning and accurate positioning mode.

Description

Technical Field

[0001] The present invention relates to the technical field of water conservancy engineering anti-corrosion robot control, and in particular to a steel gate visual inspection robot positioning system and a positioning method thereof. Background Art

[0002] Due to long-term exposure to the atmosphere and water, the hydraulic steel gates of hydropower stations are damaged by the attachment of aquatic organisms and electrochemical corrosion, which affects the normal operation function and strength of the gates. In addition, due to the special structure and location of some steel gates, they are not suitable for removal and transportation. Therefore, the anti-corrosion work of such steel gates must be carried out locally. Currently, most of the work is done manually, and there are many problems with manual work: large dust and noise affect the health of construction workers. At the same time, the efficiency of manual anti-corrosion work is low, resulting in a long construction period, increasing construction costs and manpower investment. In addition, traditional anti-corrosion processes, such as sandblasting and rust removal, will produce a lot of dust and wastewater, pollute the environment, and increase the cost of environmental governance.

[0003] In view of the above reasons, it is imperative to use intelligent operation robots to replace manual operations, and the positioning and path planning of the operation robots during operation are the key to the robot's intelligentization. The water-facing surface of the hydraulic steel gate is usually a large flat structure with almost no attachments and a single environmental structure. The existing simultaneous positioning and mapping (SLAM) technology has been developed to maturity and has many commercial application cases, but this technology relies on a highly structural environment and is not suitable for situations where the environmental structure is not strong; and for ultra-wideband wireless carrier communication technology, not only does it require the layout of base stations and the provision of power supply systems in advance, but some scenes do not have the conditions for layout, and its positioning accuracy is about 0.1m, which is obviously not suitable for anti-corrosion operations such as spraying, welding and grinding that require millimeter-level positioning. Therefore, the present invention proposes a steel gate visual inspection robot positioning system and positioning method. Summary of the invention

[0004] In order to solve the current technical problems, the main purpose of the present invention is to provide a steel gate visual inspection robot positioning system and a positioning method thereof, which adopts a coarse positioning plus a precise positioning method to solve the problem that the existing positioning method has insufficient accuracy in actual positioning.

[0005] The technical solution adopted by the present invention is: a steel gate visual inspection robot positioning system, comprising: A global positioning camera, which is used to photograph the entire working surface of the steel gate and obtain the position of the robot; An auxiliary laser device, the auxiliary laser device is located on one side of the working surface of the steel gate, and the auxiliary laser device is used to project a laser beam onto the working surface; A local positioning camera, which is installed on the robot and is used to obtain an image of the laser beam on the working surface; A posture sensor, which is installed on the robot and is used to obtain the posture of the robot; A controller is used to analyze the image acquired by the global positioning camera and control the operating range and posture of the robot, to analyze the image acquired by the local positioning camera and control the robot to move in lanes on the steel gate so that the laser beam is located at a specified position in the field of view of the local positioning camera, to control the auxiliary laser device to project laser beams on the working surface of the steel gate in sequence, and to control the robot to move on the steel gate.

[0006] The global positioning camera is located at the center of the steel gate and faces the working surface of the steel gate.

[0007] The auxiliary laser device comprises a laser and a linear guide rail module, and the laser is mounted on a slide table of the linear guide rail module.

[0008] A magnetic seat is installed on the linear guide rail module, and the linear guide rail module can be detachably adsorbed on the side of the steel gate through the magnetic seat.

[0009] A positioning method for a steel gate visual inspection robot adopts the above-mentioned steel gate visual inspection robot positioning system, and the positioning method comprises the following steps: The working surface of the steel gate is photographed by a global positioning camera, and the working boundary and the robot's posture are obtained through controller analysis; Projecting laser beams at intervals on the working surface in sequence through an auxiliary laser device; The robot uses a local positioning camera to capture the image of the laser beam on the working surface, and uses a controller to extract line laser features so that the robot can work along the laser beam.

[0010] The steps to obtain the operation boundary through controller analysis are as follows: The global positioning camera is installed on one side of the steel gate. The global positioning camera is at a certain distance from the working surface and faces the working surface. The field of view of the global positioning camera covers the working surface of the steel gate. The global positioning camera shoots the working surface and transmits the shot image to the controller. The controller extracts features through a digital image processing algorithm and uses a contour extraction algorithm to obtain the contour of the working surface to obtain the working boundary of the working surface.

[0011] The steps to obtain the robot posture through controller analysis are as follows: After the controller performs feature extraction through the digital image processing algorithm, it obtains the ORB feature of the image, extracts the geometric center of the robot and the posture information of the posture sensor, and collects the rotation angle θ of the Z axis of the robot posture. The origin of the entire image coordinate system is located at the image origin in the upper left corner. The extracted coordinates of the robot's geometric center and the posture information of the posture sensor are expressed as (x, y, θ).

[0012] The method also includes the step of dilating the contour of the working surface, and using the expanded boundary as a new boundary.

[0013] The auxiliary laser device is installed on one side of the steel gate. The auxiliary laser device moves horizontally, and projects a laser beam onto the working surface every time it moves a certain distance.

[0014] The steps for the robot to work along the laser beam are as follows: The robot is operated so that the first laser beam is located within the field of view of the local positioning camera. The local positioning camera recognizes the laser beam and the position and posture of the robot are adjusted through the controller so that the laser beam is located at a specified position in the field of view of the local positioning camera. The robot moves along the laser beam and works on the steel gate; When the robot moves to the working boundary, the laser beam of the auxiliary laser device moves a certain distance to form the next laser beam; The robot adjusts its posture according to the translation direction of the laser beam, drives to the next laser beam, and places this laser beam at the specified position of the field of view of the local positioning camera; The robot moves in the opposite direction along this laser beam and works on the steel gate; When the robot moves to the working boundary, the laser beam of the auxiliary laser device will move a certain distance to form the next laser beam, and so on, thus completing the operation of the entire working surface of the steel gate.

[0015] The present invention has the following beneficial effects: The global positioning camera of the present invention is used to photograph the entire working surface of the steel gate and obtain the position of the robot; the auxiliary laser device is located on one side of the working surface of the steel gate, and the auxiliary laser device is used to project a laser beam to the working surface; the local positioning camera is installed on the robot, and is used to obtain the image of the laser beam on the working surface; the posture sensor is installed on the robot, and is used to obtain the posture of the robot; the controller is used to analyze the image obtained by the global positioning camera, and control the operating range and posture of the robot, to analyze the image obtained by the local positioning camera, and control the robot to move in lanes on the steel gate, the laser beam is located at the designated position of the field of view of the local positioning camera, to control the auxiliary laser device to sequentially project the laser beam on the working surface of the steel gate, and to control the robot to move on the steel gate. The present invention realizes the robot to perform high-precision positioning and maintenance operations on the surface of the steel gate by coarse positioning and precise positioning, ensures the comprehensiveness and stability of robot maintenance on the surface of the steel gate, and ensures the maintenance quality of the steel gate. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific implementation of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation or the prior art description are briefly introduced below. Obviously, the drawings in the following description are some implementations of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work: Figure 1 This is a schematic diagram of obtaining the boundary of a work surface through a global positioning camera in the present invention; Figure 2 A schematic diagram of a robot acquiring a laser beam image through a local positioning camera; Figure 3 is a flow chart of the positioning method of the present invention; Figure 4 This is a diagram of the robot's operation trajectory projected by laser beams in the present invention.

[0017] Reference numerals: Steel gate 10, global positioning camera 11, laser 12, linear guide module 13; Laser beam 21 , local positioning camera 22 , local positioning camera field of view 23 , working tool 24 , robot 25 , posture sensor 26 . DETAILED DESCRIPTION

[0018] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] Embodiment 1: See also Figure 1 , 2 , a steel gate visual inspection robot positioning system, comprising: A global positioning camera 11, an auxiliary laser device, a local positioning camera 22, a posture sensor 26 and a controller.

[0020] The global positioning camera 11 is used to photograph the entire working surface of the steel gate 10 and obtain the position of the robot 25; The auxiliary laser device is located on one side of the working surface of the steel gate 10, and the auxiliary laser device is used to project a laser beam 21 onto the working surface; The local positioning camera 22 is installed on the robot 25 and is used to obtain an image of the laser beam 21 on the working surface; The posture sensor 26 is installed on the robot 25 and is used to obtain the posture of the robot 25; The controller is used to analyze the image acquired by the global positioning camera 11 and control the operating range and posture of the robot 25; to analyze the image acquired by the local positioning camera 22 and control the robot 25 to move in lanes on the steel gate 10 so that the laser beam 21 is located at a specified position in the field of view of the local positioning camera 22; to control the auxiliary laser device to project the laser beam 21 sequentially on the working surface of the steel gate 10; and to control the robot 25 to move on the steel gate 10.

[0021] The controller may be installed on the robot or located outside the robot, and the controller may be connected to the robot, the global positioning camera 11, the auxiliary laser device, the local positioning camera 22, and the posture sensor 26 by wired or wireless communication. The global positioning camera and the posture sensor are used for rough positioning, and the auxiliary laser device and the local positioning camera are used for precise positioning.

[0022] For details, see Figure 1 The global positioning camera 11 is located at the center of the steel gate 10 and faces the working surface of the steel gate 10.

[0023] In this embodiment, see Figure 1 The auxiliary laser device includes a laser 12 and a linear guide module 13. The laser 12 is mounted on a slide of the linear guide module 13. The linear guide module 13 is driven by a servo motor, so that the laser 12 can be controlled to move along the linear guide module 13. The laser beam 21 emitted by the laser 12 is irradiated on the working surface, forming a visible light on the working surface, such as Figure 2 as shown in .

[0024] Furthermore, in order to facilitate the installation and fixation of the linear guide module 13, a magnetic seat is installed on the linear guide module 13, and the linear guide module 13 is detachably adsorbed on the side of the steel gate 10 through the magnetic seat. The magnetic seat is a prior art, and there is a knob on the magnetic seat, and the magnetic seat can be adsorbed and separated from the steel gate by turning the knob.

[0025] Embodiment 2: See also Figure 3 , 4 A positioning method for a steel gate visual inspection robot adopts the above-mentioned steel gate visual inspection robot positioning system, and the positioning method comprises the following steps: Step 1: Use the global positioning camera 11 to shoot the working surface of the steel gate 10, and use the controller to analyze and obtain the working boundary and the posture of the robot; Step 2: Projecting laser beams 21 at intervals on the working surface in sequence through an auxiliary laser device; Step three: the robot captures the image of the laser beam 21 on the working surface through the local positioning camera 22 , and extracts the line laser feature through the controller, so that the robot 25 can work along the laser beam 21 .

[0026] In this embodiment, the steps of obtaining the operation boundary through controller analysis are as follows: The global positioning camera 11 is installed on one side of the steel gate 10. The global positioning camera 11 is at a certain distance from the working surface and faces the working surface. The field of view of the global positioning camera 11 covers the working surface of the steel gate 10. The global positioning camera 11 photographs the working surface and transmits the photographed image to the controller. The controller performs feature extraction through a digital image processing algorithm and uses a contour extraction algorithm to obtain the contour of the working surface to obtain the working boundary of the working surface.

[0027] In this embodiment, the steps of obtaining the robot posture through controller analysis are as follows: After the controller performs feature extraction through a digital image processing algorithm, it obtains the ORB feature of the image, extracts the geometric center of the robot and the posture information of the posture sensor 26, and collects the rotation angle θ of the robot posture Z axis. The origin of the entire image coordinate system is located at the image origin in the upper left corner. The extracted coordinates of the robot's geometric center and the posture information of the posture sensor 26 are expressed as (x, y, θ).

[0028] Furthermore, the method also includes the step of expanding the contour of the working surface, and the expanded boundary is used as a new boundary to limit the movement of the robot on the working surface to prevent the robot from crossing the boundary.

[0029] See also Figure 1The auxiliary laser device is installed on one side of the steel gate 10. The auxiliary laser device moves horizontally, and projects a laser beam 21 onto the working surface every time it moves a certain distance.

[0030] In this embodiment, the robot 25 performs operations along the laser beam 21 as follows: The robot 25 is operated so that the first laser beam 21 is located within the field of view of the local positioning camera 22. The local positioning camera 22 recognizes the laser beam 21, and the position and posture of the robot 25 are adjusted by the controller so that the laser beam 21 is located at a specified position in the field of view of the local positioning camera 22; The robot 25 moves along the laser beam 21 to operate on the steel gate 10; When the robot 25 moves to the working boundary, the laser beam 21 of the auxiliary laser device is translated for a distance to form the next laser beam 21; The robot 25 adjusts its posture according to the translation direction of the laser beam 21, moves to the next laser beam 21, and places this laser beam 21 at a designated position in the field of view of the local positioning camera 22; The robot 25 moves in the opposite direction along the laser beam 21 to operate on the steel gate 10; When the robot 25 moves to the working boundary, the laser beam 21 of the auxiliary laser device moves a certain distance. Figure 4 , forming the next laser beam 21, and so on, thereby completing the operation of the entire working surface of the steel gate 10.

[0031] Specifically, see Figure 3 The positioning of the robot during use includes two stages. First, in the first stage, the global positioning camera 11 is installed at a certain distance in front of the steel gate 10 so that the entire steel gate 10 can be photographed by the global positioning camera 11. The robot 25 is adsorbed on the gate surface. The global positioning camera 11 collects the image at this time, and extracts features through the digital image processing algorithm to obtain its ORB features, and extracts the geometric center of the robot 25 and the posture information of the posture sensor 26. Here, only the rotation angle θ of the Z axis closely related to the robot posture is collected. The origin of the entire image coordinate system is at the image origin in the upper left corner. The extracted geometric center coordinates of the working robot and the posture information of the posture sensor 26 can be expressed as (x, y, θ); in addition, the boundary of the gate surface is also obtained when the global positioning camera 11 takes the first shot. The contour extraction algorithm is used to obtain the contour, and it is expanded. The expanded boundary is used as the new working boundary to limit the movement of the robot on the working surface and prevent the robot from crossing the boundary.

[0032] The second stage is the precise positioning stage: since the robot position and posture obtained by the global positioning camera 11 have large errors and cannot be directly used for the operation of the robot 25, the actual operation still depends on the precise positioning data. First, a linear guide module 13 is installed along the vertical or horizontal boundary of the steel gate 10. The installation direction of the linear guide module 13 is related to the actual working direction. A laser 12 is installed on the slider of the linear guide module 13. The lighting direction of the laser 12 is related to the actual working direction. If the main direction of the actual operation is in the horizontal direction, the linear guide module 13 can be installed in the vertical direction. The light direction of the laser 12 is from left to right or from right to left in the horizontal direction. After the laser beam 21 hits the surface of the steel gate 10, that is, the working surface, the line of the laser beam 21 projected on the surface of the steel gate 10 can be seen in the local positioning camera field of view 23 of the local positioning camera 22. Since the laser beam 21 is along the main direction of the robot's operation, the robot can achieve precise walking along the direction of the laser beam 21 to complete the corresponding operation task. After a horizontal process is completed, the laser 12 moves a width in the up and down directions driven by the slider. After the robot moves to the initial position of the next process, it can perform the next horizontal operation. The whole process is as follows Figure 3 As shown in Figure 4 shown.

[0033] Specifically, the operation process is as follows: After the robot 25 is adsorbed onto the surface of the steel gate 10 , the global positioning camera 11 collects images of the working surface of the steel gate 10 .

[0034] The controller acquires an image of the work surface and extracts the geometric center of the robot 25 and the posture information of the posture sensor 26 .

[0035] Operate the robot 25 so that the laser beam 21 is within the field of view of the local positioning camera 22. The local positioning camera 22 recognizes the laser beam 21 and adjusts the position and posture of the robot 25 through the controller so that the laser beam 21 is located at the specified position in the field of view of the local positioning camera 22.

[0036] The robot 25 moves along the laser beam 21 and operates on the steel gate 10 through the working tool 24 .

[0037] When the robot 25 moves to the working boundary, the laser beam 21 of the auxiliary laser device is translated for a distance to form the next laser beam 21 .

[0038] The robot 25 adjusts its posture according to the translation direction of the laser beam 21 , moves to the next laser beam 21 , and places this laser beam 21 at a designated position in the field of view of the local positioning camera 22 .

[0039] The robot 25 moves in the opposite direction along the laser beam 21 to operate on the steel gate 10 .

[0040] When the robot 25 moves to the working boundary, the laser beam 21 of the auxiliary laser device is translated for a distance to form the next laser beam 21, and so on, thereby completing the operation of the entire working surface of the steel gate 10.

[0041] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0042] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A steel gate visual inspection robot positioning system, characterized in that: include: A global positioning camera (11), the global positioning camera (11) being used to photograph the entire working surface of the steel gate (10) and to obtain the position of the robot (25); An auxiliary laser device, the auxiliary laser device being located on one side of the working surface of the steel gate (10), and the auxiliary laser device being used to project a laser beam (21) onto the working surface; A local positioning camera (22), the local positioning camera (22) being mounted on the robot (25) and used to acquire an image of the laser beam (21) on the working surface; A posture sensor (26), wherein the posture sensor (26) is installed on the robot (25) and is used to obtain the posture of the robot (25); A controller, the controller is used to analyze the image acquired by the global positioning camera (11) and control the operating range and posture of the robot (25), to analyze the image acquired by the local positioning camera (22) and control the robot (25) to move in lanes on the steel gate (10) so that the laser beam (21) is located at a specified position in the field of view of the local positioning camera (22), to control the auxiliary laser device to sequentially project the laser beam (21) on the working surface of the steel gate (10), and to control the robot (25) to move on the steel gate (10).

2. A steel gate visual inspection robot positioning system according to claim 1, characterized in that: The global positioning camera (11) is located at the center of the steel gate (10) and faces the working surface of the steel gate (10).

3. A steel gate visual inspection robot positioning system according to claim 1, characterized in that: The auxiliary laser device comprises a laser (12) and a linear guide rail module (13), and the laser (12) is mounted on a slide table of the linear guide rail module (13).

4. A steel gate visual inspection robot positioning system according to claim 3, characterized in that: A magnetic seat is installed on the linear guide rail module (13), and the linear guide rail module (13) is detachably adsorbed on the side of the steel gate (10) through the magnetic seat.

5. A positioning method for a steel gate visual inspection robot, characterized in that: A steel gate visual inspection robot positioning system according to any one of claims 1 to 4 is adopted, and the positioning method comprises the following steps: The working surface of the steel gate (10) is photographed by a global positioning camera (11), and the working boundary and the posture of the robot are obtained by analysis by a controller; Projecting laser beams (21) at intervals on the working surface in sequence by means of an auxiliary laser device; The robot captures an image of the laser beam (21) on the working surface through a local positioning camera (22), and extracts line laser features through a controller, so that the robot (25) performs work along the laser beam (21).

6. The positioning method of a steel gate visual inspection robot according to claim 5 is characterized in that: The steps to obtain the operation boundary through controller analysis are as follows: A global positioning camera (11) is installed on one side of the steel gate (10). The global positioning camera (11) is at a certain distance from the working surface and faces the working surface. The field of view of the global positioning camera (11) covers the working surface of the steel gate (10). The global positioning camera (11) photographs the working surface and transmits the photographed image to a controller. The controller extracts features through a digital image processing algorithm and uses a contour extraction algorithm to obtain the contour of the working surface to obtain the working boundary of the working surface.

7. The positioning method of a steel gate visual inspection robot according to claim 5 is characterized in that: The steps to obtain the robot posture through controller analysis are as follows: After the controller performs feature extraction through a digital image processing algorithm, the ORB feature of the image is obtained, the geometric center of the robot and the posture information of the posture sensor (26) are extracted, and the rotation angle θ with respect to the Z axis of the robot posture is collected. The origin of the entire image coordinate system is located at the image origin in the upper left corner. The extracted coordinates of the geometric center of the robot and the posture information of the posture sensor (26) are expressed as (x, y, θ).

8. The positioning method of a steel gate visual inspection robot according to claim 6 is characterized in that: The method also includes the step of dilating the contour of the working surface, and using the expanded boundary as a new boundary.

9. The positioning method of a steel gate visual inspection robot according to claim 5 is characterized in that: The auxiliary laser device is installed on one side of the steel gate (10). The auxiliary laser device moves in translation and projects a laser beam (21) onto the working surface every time it moves a certain distance.

10. The positioning method of a steel gate visual inspection robot according to claim 5, characterized in that: The steps of the robot (25) operating along the laser beam (21) are as follows: The robot (25) is operated so that the first laser beam (21) is located within the field of view of the local positioning camera (22), the local positioning camera (22) recognizes the laser beam (21), and the position and posture of the robot (25) are adjusted by a controller so that the laser beam (21) is located at a specified position in the field of view of the local positioning camera (22); The robot (25) moves along the laser beam (21) to operate the steel gate (10); When the robot (25) moves to the working boundary, the laser beam (21) of the auxiliary laser device is translated for a certain distance to form the next laser beam (21); The robot (25) adjusts its posture according to the translation direction of the laser beam (21), moves to the next laser beam (21), and places the laser beam (21) at a designated position in the field of view of the local positioning camera (22); The robot (25) moves in the opposite direction along the laser beam (21) to operate on the steel gate (10); When the robot (25) moves to the working boundary, the laser beam (21) of the auxiliary laser device is further translated for a distance to form the next laser beam (21), and so on, thereby completing the work on the entire working surface of the steel gate (10).

Images