Gesture adjusting method of cable-type wall-climbing robot and cable-type wall-climbing robot

Abstract

The invention discloses a posture adjustment method of a cable-type wall-climbing robot and the cable-type wall-climbing robot. The method comprises the steps that a first image collected by an image collection device in the wall-climbing process of the cable-type wall-climbing robot is obtained; the first image comprises a parallel cable, and two ropes in the parallel cable are distributed on the two sides of the center line of the first image; determining slopes of two ropes in the parallel cable based on the first image; based on the slopes of the two ropes in the parallel cables, deviation information of the motion trail of the cable type wall-climbing robot is determined; and the posture of the cable type wall-climbing robot is adjusted based on the offset information. Therefore, when the cable-type wall-climbing robot moves along the two ropes of the parallel cable, the posture of the cable-type wall-climbing robot can be adjusted in real time, so that the cable-type wall-climbing robot walks along a linear track.

Description

Technical Field

[0001] The present application relates to the field of robots and automation technology, and in particular to a posture adjustment method of a rope-type wall-climbing robot and a rope-type wall-climbing robot. Background Art

[0002] With the development of computers, rope-type wall-climbing robots are gradually replacing manpower to clean the exterior surfaces of buildings.

[0003] At present, the rope-type wall-climbing robot uses two left and right moving devices to move along parallel ropes to drive the rope-type wall-climbing robot to move to complete the cleaning task. The use of parallel ropes can adjust the posture of the rope-type wall-climbing robot, and they can serve as safety ropes for each other, greatly improving the safety performance. However, during the operation of the rope-type wall-climbing robot, if it encounters an obstacle or the moving speed of the left and right moving devices deviates, the posture of the rope-type wall-climbing robot will change slightly, resulting in the route of the rope-type wall-climbing robot not being a straight line. Therefore, a solution is urgently needed to adjust the posture of the wall-climbing robot in real time so that its trajectory remains straight. Summary of the invention

[0004] In view of this, an embodiment of the present application provides a posture adjustment method of a rope-type wall-climbing robot and a rope-type wall-climbing robot.

[0005] According to the first aspect of the present application, an embodiment of the present application provides a posture adjustment method of a rope-type wall-climbing robot, comprising: Acquire a first image acquired by an image acquisition device during the wall climbing process of the rope-type wall-climbing robot; the first image includes a parallel rope, and two ropes in the parallel rope are distributed on both sides of the center line of the first image; determining the slopes of two ropes in the parallel cable based on the first image; Based on the slopes of the two ropes in the parallel rope, the offset information of the motion trajectory of the rope-type wall-climbing robot is determined; The posture of the rope-type wall-climbing robot is adjusted based on the offset information.

[0006] Optionally, based on the first image, determining the slopes of two ropes in the parallel cable comprises: Determine a key detection area in the first image, the key detection area including the parallel line; Identify each straight line in the key detection area; Based on the slope of each line, determine the slope of the two ropes in the parallel cable.

[0007] Optionally, determining a key detection area in the first image includes: determining a resolution of the first image; Based on the resolution of the first image and the corresponding relationship between the resolution and the key detection area, the key detection area in the first image is determined.

[0008] Optionally, identifying each straight line in the key detection area includes: Obtaining a first grayscale image corresponding to the key detection area; Performing edge detection on the first grayscale image; Based on the Hough line detection algorithm, line detection is performed on the first grayscale image after edge detection to obtain each straight line in the key detection area.

[0009] Optionally, obtaining a first grayscale image corresponding to the key detection area includes: Converting the first image into a second grayscale image; Based on the coordinates of the key detection area in the first image, forming a mask corresponding to the key detection area; The mask and the second grayscale image are subjected to a Boolean operation to obtain a first grayscale image corresponding to the key detection area.

[0010] Optionally, determining the slopes of two ropes in the parallel cable based on the slopes of the straight lines comprises: Based on the slope of each straight line, each straight line is divided into two groups; one group is a set of straight lines with positive slopes, and the other group is a set of straight lines with negative slopes; Fit the straight lines in the two groups respectively to obtain the fitting lines corresponding to the two groups; The slopes of the fitted lines corresponding to the two groups are taken as the slopes of the two ropes in the parallel cable.

[0011] Optionally, before fitting the straight lines in the two groups respectively, the posture adjustment method of the rope-type wall-climbing robot further includes: Based on the slopes of the lines within the two groups, determine the average slopes corresponding to the groups; Based on the slope of each straight line in each group and the average slope, the noise straight lines in each group are removed.

[0012] Optionally, based on the slopes of the two ropes in the parallel rope, the offset information of the motion trajectory of the rope-type wall-climbing robot is determined, including: If the slope or the sum of the slopes of the two ropes in the parallel rope is less than the corresponding slope threshold, it is determined that the motion trajectory of the rope-type wall-climbing robot is shifted to the right; If the slope of the two ropes in the parallel rope or the sum of the slopes is greater than the corresponding slope threshold, it is determined that the motion trajectory of the rope-type wall-climbing robot is shifted to the left; If the slope of the two ropes in the parallel cable or the sum of the slopes is equal to the corresponding slope threshold, it is determined that the motion trajectory of the rope-type wall-climbing robot has not deviated.

[0013] Optionally, adjusting the posture of the rope-type wall-climbing robot based on the offset information includes: Based on the offset information, the first moving speed of the first moving device and / or the second moving speed of the second moving device of the rope-type wall-climbing robot are adjusted to adjust the posture of the rope-type wall-climbing robot, wherein the first moving device and the second moving device are sleeved on two ropes of the parallel cable.

[0014] According to the second aspect of the present application, an embodiment of the present application provides a rope-type wall-climbing robot, comprising: A robot body, an image acquisition device, a first moving device and a second moving device; The image acquisition device is arranged on the robot body; The robot body is arranged on the first moving device and the second moving device; The first moving device and the second moving device are used to be sleeved on the two ropes of the parallel cable to drive the robot body to move along the two ropes of the parallel cable; The robot body is used to obtain a first image captured by an image acquisition device during the robot body climbing a wall; the first image includes a parallel cable, and two ropes in the parallel cable are distributed on both sides of a center line of the first image; based on the first image, the slopes of the two ropes in the parallel cable are determined; based on the slopes of the two ropes in the parallel cable, the offset information of the robot body's motion trajectory is determined; and the posture of the robot body is adjusted based on the offset information.

[0015] The posture adjustment method of the rope-type wall-climbing robot and the rope-type wall-climbing robot provided in the embodiment of the present application are as follows: a first image captured by an image acquisition device during the wall-climbing process of the rope-type wall-climbing robot is acquired; the first image includes a parallel rope, and two ropes in the parallel rope are distributed on both sides of the center line of the first image; based on the first image, the slopes of the two ropes in the parallel rope are determined; based on the slopes of the two ropes in the parallel rope, the offset information of the motion trajectory of the rope-type wall-climbing robot is determined; based on the offset information, the posture of the rope-type wall-climbing robot is adjusted; in this way, when the rope-type wall-climbing robot moves along the two ropes of the parallel rope, the rope-type wall-climbing robot can be adjusted in real time The posture of the wall-climbing robot makes the rope-type wall-climbing robot walk in a straight line; and, through the non-contact detection method of visual images, the changes in the motion trajectory of the rope-type wall-climbing robot are detected in real time. It has strong adaptability and convenient adjustment, reduces the use of posture sensors, and avoids the influence of factors such as posture sensor installation errors, data accumulation errors and temperature drift on the control of the rope-type wall-climbing robot. Moreover, through the non-contact detection method of visual images, the operating environment around the rope-type wall-climbing robot can also be observed in real time, assisting the operator of the rope-type wall-climbing robot to make reasonable decisions, which can improve the operator's work efficiency.

[0016] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic flow chart of a posture adjustment method of a rope-type wall-climbing robot in an embodiment of the present application; Figure 2 A schematic diagram of a rope-type wall-climbing robot moving along a parallel rope in an embodiment of the present application; Figure 3 It is a flow chart of another posture adjustment method of a rope-type wall-climbing robot in an embodiment of the present application; Figure 4 Schematic diagram of the process of obtaining the first grayscale image corresponding to the key detection area in the embodiment of the present application; Figure 5 This is a schematic diagram of edge detection in the first grayscale image in an embodiment of the present application; Figure 6 This is a schematic diagram of fitting straight lines in two groups in an embodiment of the present application; Figure 7 It is a flow chart of another posture adjustment method of a rope-type wall-climbing robot in an embodiment of the present application; Figure 8 This is a schematic diagram of the hardware structure of a rope-type wall-climbing robot in an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0019] The embodiment of the present application provides a posture adjustment method of a rope-type wall-climbing robot, such as Figure 1 As shown, including: S101, obtaining a first image captured by an image acquisition device during the wall climbing process of the rope-type wall-climbing robot; the first image includes a parallel rope, and two ropes in the parallel rope are distributed on both sides of the center line of the first image.

[0020] In this embodiment, if Figure 2As shown, the parallel cable includes two ropes 21 arranged in parallel. The rope-type wall-climbing robot includes a first moving device 22 and a second moving device 23, which are sleeved on the two ropes 21 on the parallel cable, and the rope-type wall-climbing robot moves through the first moving device 22 and the second moving device 23. In some embodiments, the first moving device and the second moving device may be winches.

[0021] In this embodiment, in the field of view of the image acquisition device, the two ropes in the parallel cable are distributed in an "eight" shape, and the two ropes are located on both sides of the center line of the field of view of the image acquisition device. In specific implementation, the position of the image acquisition device may need to be adjusted according to actual conditions. By adjusting the position of the image acquisition device, the two ropes can be distributed approximately symmetrically in the field of view of the image acquisition device.

[0022] In this embodiment, the image acquisition device can be arranged on the rope-type wall-climbing robot, such as Figure 2 As shown, an image acquisition device 24 can be provided at the head and the tail of the rope-type wall-climbing robot. When the rope-type wall-climbing robot moves forward along the parallel rope, the image acquisition device 24 at the head can be used to acquire a first image including the parallel rope. When the rope-type wall-climbing robot moves backward along the parallel rope, the image acquisition device 24 at the tail can be used to acquire a first image including the parallel rope. The installation positions of the image acquisition devices at the head and the tail can be determined based on the principle that the two ropes in the parallel rope are located on both sides of the center line of the field of view of the image acquisition device. In this way, the two ropes in the parallel rope in the first image acquired by the image acquisition device can be distributed on both sides of the center line of the first image, which is convenient for the subsequent determination of whether the motion trajectory of the rope-type wall-climbing robot is offset based on the slopes of the two ropes.

[0023] S102: Determine the slopes of two ropes in the parallel cable based on the first image.

[0024] In this embodiment, since the first image includes two ropes in the parallel cable, the slopes of the two ropes in the parallel cable can be determined by rope recognition or straight line recognition.

[0025] In some embodiments, the two ropes in the first image may be identified to determine the coordinates of the two ropes in the first image, and then the slopes of the two ropes in the parallel cable may be determined based on the coordinates of the two ropes in the first image.

[0026] In some embodiments, two straight lines corresponding to the two ropes may be determined by identifying the straight lines in the first image, and then the slopes of the two ropes in the parallel cable may be obtained based on the slopes of the two straight lines.

[0027] S103, determining the offset information of the motion trajectory of the rope-type wall-climbing robot based on the slopes of the two ropes in the parallel rope.

[0028] In this embodiment, when the motion trajectory of the rope-type wall-climbing robot has not deviated, the slope corresponding to each rope is a fixed value, so based on the slopes of the two ropes calculated in real time and the fixed value, it can be determined whether the motion trajectory of the rope-type wall-climbing robot has deviated.

[0029] In this embodiment, the offset information includes but is not limited to an offset direction and an offset distance.

[0030] In this embodiment, the slopes of the two ropes may be used as a control strategy, or the sum of the slopes of the two ropes may be used as a control strategy to determine the offset information of the motion trajectory of the rope-type wall-climbing robot.

[0031] S104, adjusting the posture of the rope-type wall-climbing robot based on the offset information.

[0032] In this embodiment, after the offset information is determined, the posture of the rope-type wall-climbing robot can be adjusted based on the offset information so that the rope-type wall-climbing robot walks on a straight track. The posture includes but is not limited to the moving speed, moving acceleration, and moving direction of the first moving device and / or the second moving device.

[0033] The posture adjustment method of the rope-type wall-climbing robot provided in the embodiment of the present application is by acquiring a first image acquired by an image acquisition device during the wall climbing process of the rope-type wall-climbing robot; the first image includes a parallel rope, and two ropes in the parallel rope are distributed on both sides of the center line of the first image; based on the first image, the slopes of the two ropes in the parallel rope are determined; based on the slopes of the two ropes in the parallel rope, the offset information of the motion trajectory of the rope-type wall-climbing robot is determined; based on the offset information, the posture of the rope-type wall-climbing robot is adjusted; in this way, when the rope-type wall-climbing robot moves along the two ropes of the parallel rope, the posture of the rope-type wall-climbing robot can be adjusted in real time so that the rope-type wall-climbing robot walks on a straight trajectory; and, through the non-contact detection method of visual images, the changes in the motion trajectory of the rope-type wall-climbing robot are detected in real time, the adaptive ability is strong, the adjustment is convenient, the use of posture sensors is reduced, and the influence of factors such as posture sensor installation errors, data accumulation errors and temperature drift on the control of the rope-type wall-climbing robot is avoided. Moreover, through the non-contact detection method of visual images, the operating environment around the rope-type wall-climbing robot can also be observed in real time, and the operator of the rope-type wall-climbing robot is assisted to make reasonable decisions, which can improve the work efficiency of the operator.

[0034] In an optional embodiment, step S102, based on the first image, determines the slopes of the two ropes in the parallel cable, such as Figure 3 As shown, including: S1021, determining a key detection area in the first image, where the key detection area includes a parallel line.

[0035] In this embodiment, since the first image includes not only parallel ropes but also some other objects, in order to improve the calculation time of image processing and eliminate the influence of irrelevant areas on the detection results, a key detection area can be selected in the first image, and image processing is performed on the key detection area. The key detection area includes the parallel rope.

[0036] In this embodiment, the key detection area may be a quadrilateral including the parallelogram, and the quadrilateral may be a rectangle or a trapezoid.

[0037] In some implementations, determining a key detection area in the first image includes: Determine the resolution of the first image; and determine the key detection area in the first image based on the resolution of the first image and the corresponding relationship between the resolution and the key detection area.

[0038] In this embodiment, after determining the installation position of the image acquisition device, image acquisition devices with different resolutions can be selected for image acquisition according to actual needs. Figure 2 As shown, the image acquisition device 24 at the head of the rope-type wall-climbing robot and the image acquisition device 24 at the tail can choose to use image acquisition devices with different resolutions, or the image acquisition device at the head can choose to use an image acquisition device with a first resolution, or can choose to use an image acquisition device with a second resolution. Since the resolutions of different image acquisition devices may be different, the resolutions of the images acquired by different image acquisition devices are different, and the sizes and coordinates of the key detection areas corresponding to the images with different resolutions are different. In order to quickly determine the key detection area in the first image acquired by the current image acquisition device, the key detection areas corresponding to the images with different resolutions can be calibrated in a pre-calibrated manner. For example, for the image acquisition device with a first resolution, the size of the key detection area is determined to be the first size and the coordinates are the first coordinates through calibration; for the image acquisition device with a second resolution, the size of the key detection area is determined to be the second size and the coordinates are the second coordinates through calibration, so that a corresponding relationship between the resolution and the key detection area can be formed. Therefore, after acquiring the first image acquired by the image acquisition device, the resolution of the first image can be acquired, and based on the resolution, the key detection area in the first image can be determined.

[0039] In this embodiment, by pre-establishing a corresponding relationship between the resolution and the key detection area, the key detection area in the first image can be quickly determined by determining the resolution of the first image.

[0040] S1022, identifying each straight line in the key detection area.

[0041] In this embodiment, after the key detection area in the first image is determined, the slopes of the two ropes in the parallel cable can be determined by identifying the straight lines in the key detection area.

[0042] In some implementations, identifying each straight line in the key detection area includes: Obtain a first grayscale image corresponding to the key detection area; perform edge detection on the first grayscale image; perform line detection on the first grayscale image after edge detection based on the Hough line detection algorithm to obtain each straight line in the key detection area.

[0043] In this embodiment, the first image can be converted into a second grayscale image, and then the second grayscale image can be cropped based on the coordinates of the key detection area in the first image to obtain the first grayscale image corresponding to the key detection area. Alternatively, the first image can be cropped based on the coordinates of the key detection area in the first image to obtain the image corresponding to the key detection area, and then the image corresponding to the key detection area can be converted into the first grayscale image.

[0044] In a specific implementation, obtaining a first grayscale image corresponding to the key detection area includes: The first image is converted into a second grayscale image; based on the coordinates of the key detection area in the first image, a mask corresponding to the key detection area is formed; and the mask and the second grayscale image are subjected to a Boolean operation to obtain a first grayscale image corresponding to the key detection area.

[0045] For example, Figure 4 As shown, the first image is converted into the second grayscale Figure 4 After that, based on the coordinates of the key detection area in the first image, a mask 5 corresponding to the key detection area is formed, and then the mask 5 is combined with the second grayscale image. Figure 4 By performing the AND operation in Boolean operation, the first grayscale corresponding to the key detection area can be obtained. Figure 6 .

[0046] In this embodiment, an edge detection algorithm can be used to extract the edge in the first grayscale image. In specific implementation, the edge in the first grayscale image can be extracted by calculating the gradient change of the pixel value in the horizontal direction and the vertical direction. Figure 5As shown, the horizontal direction is G direction, and the vertical direction is E direction. For pixel A, in the horizontal direction, due to the huge change in the gradient value of the pixel value from pixel B to pixel A and then to pixel C, the gradient value of the pixel value of pixel A in the horizontal direction is greater than the gradient threshold, then pixel A is considered to be at the edge of the image. For other pixels, searching along the horizontal and vertical directions in the same way can obtain all the edges in the image. The edge extraction algorithm needs to set the upper and lower thresholds of the gradient change. The upper and lower thresholds can be selected according to the actual situation. When selecting, the upper and lower thresholds are generally used as two variables, and then the appropriate upper and lower thresholds are selected by adjusting the parameter sliders corresponding to the upper and lower thresholds. The operation is simple and fast.

[0047] In this embodiment, the first grayscale image after edge detection is subjected to line detection based on the Hough line detection algorithm, so that each line in the key detection area can be accurately obtained. Figure 6 As shown, the first grayscale image after edge detection includes two ropes A and B in the parallel ropes. When the two ropes A and B are subjected to straight line detection based on the Hough line detection algorithm, multiple straight lines 61 and multiple straight lines 62 can be detected respectively, thereby obtaining the straight lines in the key detection area.

[0048] S1023, based on the slopes of the straight lines, determine the slopes of the two ropes in the parallel cable.

[0049] In this embodiment, all the straight lines identified in the key detection area include the straight lines corresponding to the two ropes in the parallel cable. After the straight lines in the key detection area are determined, since the slopes of the two ropes in the parallel cable are one positive and one negative, the slope of one straight line from a plurality of straight lines with positive slopes and similar slopes can be selected as the slope of one rope; the slope of one straight line from a plurality of straight lines with negative slopes and similar slopes can be selected as the slope of another rope.

[0050] In one embodiment, determining the slopes of two ropes in a parallel cable based on the slopes of the straight lines comprises: Based on the slope of each straight line, each straight line is divided into two groups; one group is a collection of straight lines with positive slopes, and the other group is a collection of straight lines with negative slopes; the straight lines in the two groups are fitted respectively to obtain the fitting lines corresponding to the two groups; the slopes of the fitting lines corresponding to the two groups are used as the slopes of the two ropes in the parallel cable.

[0051] In this embodiment, the least square method can be used to fit multiple straight lines in each group into a fitting line. Figure 6As shown, the first grayscale image after edge detection includes two ropes A and B in the parallel cable. When the first grayscale image after edge detection is subjected to line detection based on the Hough line detection algorithm, multiple straight lines 61 and multiple straight lines 62 corresponding to the two ropes A and B can be detected respectively. Since the slope corresponding to the multiple straight lines 61 is positive and the slope corresponding to the multiple straight lines 62 is negative, the multiple straight lines 61 are divided into one group and the multiple straight lines 62 are divided into another group. Then, the multiple straight lines 61 are fitted by the least squares method to obtain a corresponding fitting line 63. The multiple straight lines 62 are fitted by the least squares method to obtain a corresponding fitting line 64. Therefore, the slope corresponding to the fitting line 63 can be used as the slope of the rope A in the parallel cable; and the slope corresponding to the fitting line 64 can be used as the slope of the rope B in the parallel cable.

[0052] In this embodiment, the straight lines are divided into two groups based on the slope of each straight line; then the straight lines in the two groups are fitted respectively to obtain the fitting lines corresponding to the two groups; the slopes of the fitting lines corresponding to the two groups are used as the slopes of the two ropes in the parallel cable, which can largely avoid the influence of external factors on the calculation results, and can make the calculated slopes of the two ropes more accurate and closer to the true value.

[0053] In some embodiments, before fitting the straight lines in the two groups respectively, the posture adjustment method of the rope-type wall-climbing robot further includes: Based on the slopes of the straight lines in the two groups, the average slopes corresponding to the groups are determined; based on the slopes of the straight lines in the groups and the average slope, the noise straight lines in the groups are removed.

[0054] In this embodiment, the multiple straight lines in the two groups may include other straight lines besides the ropes, so that the average slope of each group can be calculated, the slope of each straight line in the group is compared with the average slope, a suitable threshold is set, and the outlier filtering method is used to eliminate the straight lines with a large difference from the average slope, that is, the noise straight lines.

[0055] When implementing it, Figure 7As shown, the image acquisition device, that is, the position of the camera, can be adjusted first, so that the two ropes corresponding to the rope-type wall-climbing robot are approximately symmetrically distributed in the field of view of the camera. Then the image collected by the camera is extracted and converted into a grayscale image, and the edge of the grayscale image is extracted using an edge detection algorithm. Then the key detection area is selected. Then all the straight lines in the key detection area are calculated by the Hough line detection algorithm, the slope of each straight line is calculated, and the straight lines are divided into two groups according to the positive and negative slopes. Based on the slopes of each straight line in the two groups, the average slope corresponding to each group is determined. Based on the slopes of each straight line in each group and the average slope, the outlier filtering method is used to eliminate irrelevant straight lines in each group, that is, noise straight lines. Then the straight lines of each group are fitted into a straight line by the least squares method. Based on the slopes of the fitted straight lines of the two groups, the slopes of the two ropes are determined. According to the slopes of the two ropes, the posture of the rope-type wall-climbing robot is adjusted in real time so that the rope-type wall-climbing robot walks a straight trajectory.

[0056] In this embodiment, by removing the noise straight lines in each group, the influence of external factors on the calculation results of the slopes of the two ropes can be avoided to a great extent.

[0057] In this embodiment, the selection of key detection areas improves the calculation time of image processing and can eliminate the influence of irrelevant areas on the detection results; by identifying the straight lines in the key detection areas and determining the slopes of the two ropes in the parallel cable based on the slopes of the straight lines, the slopes of the two ropes in the parallel cable can be obtained more accurately and the influence of external factors on the slope calculation results can be avoided to a large extent.

[0058] In an optional embodiment, step S103, determining the offset information of the motion trajectory of the rope-type wall-climbing robot based on the slopes of the two ropes in the parallel rope, includes: If the slope of the two ropes in the parallel cable or the sum of their slopes is less than the corresponding slope threshold, it is determined that the motion trajectory of the rope-type wall-climbing robot is deflected to the right; if the slope of the two ropes in the parallel cable or the sum of their slopes is greater than the corresponding slope threshold, it is determined that the motion trajectory of the rope-type wall-climbing robot is deflected to the left; if the slope of the two ropes in the parallel cable or the sum of their slopes is equal to the corresponding slope threshold, it is determined that the motion trajectory of the rope-type wall-climbing robot has not deflected.

[0059] In this embodiment, when the position of the image acquisition device is fixed, since the two ropes in the field of view of the image acquisition device are distributed in an "eight" shape, if the motion trajectory of the rope-type wall-climbing robot does not deviate, the slope corresponding to each rope remains unchanged and is a fixed value, so that the fixed value corresponding to the rope or the sum of the fixed values ​​corresponding to the two ropes can be set as the slope threshold, and the slopes of the two ropes calculated in real time are compared with the slope threshold to determine the deviation direction of the motion trajectory of the rope-type wall-climbing robot.

[0060] In some embodiments, the offset distance of the motion trajectory of the rope-type wall-climbing robot can also be calculated based on the slopes of the two ropes calculated in real time and the slope threshold.

[0061] In this embodiment, the deviation direction of the motion trajectory of the rope-type wall-climbing robot can be quickly determined by comparing the slopes of the two ropes calculated in real time with the slope threshold.

[0062] In an optional embodiment, step S104, adjusting the posture of the rope-type wall-climbing robot based on the offset information, includes: Based on the offset information, the first moving speed of the first moving device and / or the second moving speed of the second moving device of the rope-type wall-climbing robot are adjusted to adjust the posture of the rope-type wall-climbing robot, wherein the first moving device and the second moving device are sleeved on two ropes of the parallel cable.

[0063] In specific implementation, if the motion trajectory of the rope-type wall-climbing robot deviates to the left, the first moving speed of the first moving device of the rope-type wall-climbing robot can be increased, and / or the second moving speed of the second moving device can be decreased, so that the motion trajectory of the rope-type wall-climbing robot gradually deviates to the right, thereby making the rope-type wall-climbing robot maintain a straight walking trajectory, wherein the first moving device is the moving device on the left side of the rope-type wall-climbing robot, and the second moving device is the moving device on the right side of the rope-type wall-climbing robot. If the motion trajectory of the rope-type wall-climbing robot deviates to the right, the first moving speed of the first moving device of the rope-type wall-climbing robot can be decreased, and / or the second moving speed of the second moving device can be increased, so that the motion trajectory of the rope-type wall-climbing robot gradually deviates to the left, thereby making the rope-type wall-climbing robot maintain a straight walking trajectory. If the motion trajectory of the rope-type wall-climbing robot does not deviate, no processing is performed.

[0064] In this embodiment, by adjusting the first moving speed of the first moving device of the rope-type wall-climbing robot and / or the second moving speed of the second moving device, the posture of the rope-type wall-climbing robot can be adjusted so that the rope-type wall-climbing robot walks in a straight trajectory.

[0065] The present application also provides a rope-type wall-climbing robot, such as Figure 2 As shown, including: A robot body 25 , an image acquisition device 24 , a first moving device 22 and a second moving device 23 .

[0066] The image acquisition device 24 is disposed on the robot body 25 .

[0067] The robot body 25 is disposed on the first moving device 22 and the second moving device 23 .

[0068] The first moving device 22 and the second moving device 23 are used to be sleeved on the two ropes 21 of the parallel cable to drive the robot body 25 to move along the two ropes 21 of the parallel cable.

[0069] The robot body 25 is used to obtain the first image captured by the image acquisition device during the robot body climbing the wall; the first image includes a parallel cable, and the two ropes in the parallel cable are distributed on both sides of the center line of the first image; based on the first image, the slopes of the two ropes in the parallel cable are determined; based on the slopes of the two ropes in the parallel cable, the offset information of the robot body motion trajectory is determined; and the posture of the robot body is adjusted based on the offset information.

[0070] The rope-type wall-climbing robot provided in the embodiment of the present application obtains a first image captured by an image acquisition device during the wall-climbing process of the rope-type wall-climbing robot; the first image includes a parallel rope, and two ropes in the parallel rope are distributed on both sides of the center line of the first image; based on the first image, the slopes of the two ropes in the parallel rope are determined; based on the slopes of the two ropes in the parallel rope, the offset information of the motion trajectory of the rope-type wall-climbing robot is determined; based on the offset information, the posture of the rope-type wall-climbing robot is adjusted; in this way, when the rope-type wall-climbing robot moves along the two ropes of the parallel rope, the posture of the rope-type wall-climbing robot can be adjusted in real time, so that the rope-type wall-climbing robot walks on a straight trajectory; and, through the non-contact detection method of visual images, the changes in the motion trajectory of the rope-type wall-climbing robot are detected in real time, the adaptive ability is strong, the adjustment is convenient, the use of posture sensors is reduced, and the influence of factors such as posture sensor installation errors, data accumulation errors and temperature drift on the control of the rope-type wall-climbing robot is avoided. Moreover, through the non-contact detection method of visual images, the operating environment around the rope-type wall-climbing robot can also be observed in real time, and the operator of the rope-type wall-climbing robot is assisted to make reasonable decisions, which can improve the work efficiency of the operator.

[0071] In some embodiments, the rope-type wall-climbing robot is Figure 8 As shown, Figure 8 A schematic block diagram of an example rope-type wall-climbing robot 800 that can be used to implement embodiments of the present application is shown.

[0072] like Figure 8 As shown, the rope climbing robot 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 to a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the rope climbing robot 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other through a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0073] Multiple components in the rope-type wall-climbing robot 800 are connected to the I / O interface 805, including: an input unit 806, such as an image acquisition device; an output unit 807, such as a first mobile device, a second mobile device, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the rope-type wall-climbing robot 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0074] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as the posture adjustment method of the rope-type wall-climbing robot. For example, in some embodiments, the posture adjustment method of the rope-type wall-climbing robot may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the rope-type wall-climbing robot 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the posture adjustment method of the rope-type wall-climbing robot described above may be executed. Alternatively, in other embodiments, the computing unit 801 may be configured to execute the posture adjustment method of the rope-type wall-climbing robot in any other appropriate manner (for example, by means of firmware).

[0075] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0076] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0077] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0078] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0079] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0080] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0081] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. As long as the expected results of the technical solution disclosed in this application can be achieved, this document does not limit it here.

[0082] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0083] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for adjusting the posture of a rope-type wall-climbing robot, characterized in that: include: Acquire a first image captured by an image acquisition device during the wall climbing process of the rope-type wall-climbing robot; the first image includes a parallel rope, and two ropes in the parallel rope are distributed on both sides of the center line of the first image; determining the slopes of two ropes in the parallel cable based on the first image; Determining the offset information of the motion trajectory of the rope-type wall-climbing robot based on the slopes of the two ropes in the parallel rope; The posture of the rope-type wall-climbing robot is adjusted based on the offset information.

2. The posture adjustment method of the rope-type wall-climbing robot according to claim 1, characterized in that: Determining the slopes of two ropes in the parallel cable based on the first image comprises: Determine a key detection area in the first image, wherein the key detection area includes the parallel rope; Identifying each straight line in the key detection area; Based on the slope of each of the straight lines, the slopes of the two ropes in the parallel cable are determined.

3. The posture adjustment method of the rope-type wall-climbing robot according to claim 2, characterized in that: Determining a key detection area in the first image includes: determining a resolution of the first image; Based on the resolution of the first image and the corresponding relationship between the resolution and the key detection area, the key detection area in the first image is determined.

4. The posture adjustment method of the rope-type wall-climbing robot according to claim 2, characterized in that: Identifying each straight line in the key detection area includes: Obtaining a first grayscale image corresponding to the key detection area; Performing edge detection on the first grayscale image; Based on the Hough line detection algorithm, line detection is performed on the first grayscale image after edge detection to obtain each straight line in the key detection area.

5. The posture adjustment method of the rope-type wall-climbing robot according to claim 4, characterized in that: Acquiring a first grayscale image corresponding to the key detection area includes: Converting the first image into a second grayscale image; Based on the coordinates of the key detection area in the first image, forming a mask corresponding to the key detection area; A Boolean operation is performed on the mask and the second grayscale image to obtain a first grayscale image corresponding to the key detection area.

6. The posture adjustment method of the rope-type wall-climbing robot according to claim 2, characterized in that: Determining the slopes of two ropes in the parallel cable based on the slopes of the straight lines comprises: Based on the slopes of the straight lines, the straight lines are divided into two groups; one group is a set of straight lines with positive slopes, and the other group is a set of straight lines with negative slopes; Fit the straight lines in the two groups respectively to obtain the fitting lines corresponding to the two groups; The slopes of the fitting lines corresponding to the two groups are taken as the slopes of the two ropes in the parallel cable.

7. The posture adjustment method of the rope-type wall-climbing robot according to claim 6, characterized in that: Before fitting the straight lines in the two groups respectively, it also includes: Based on the slopes of the lines within the two groups, determine the average slopes corresponding to the groups; Based on the slopes of the straight lines in each group and the average slope, the noise straight lines in each group are removed.

8. The posture adjustment method of the rope-type wall-climbing robot according to claim 1, characterized in that: Determining the offset information of the motion trajectory of the rope-type wall-climbing robot based on the slopes of the two ropes in the parallel rope includes: If the slope or the sum of the slopes of the two ropes in the parallel rope is less than the corresponding slope threshold, it is determined that the motion trajectory of the rope-type wall-climbing robot is shifted to the right; If the slope of the two ropes in the parallel rope or the sum of the slopes is greater than the corresponding slope threshold, it is determined that the motion trajectory of the rope-type wall-climbing robot is shifted to the left; If the slope of the two ropes in the parallel rope or the sum of the slopes is equal to the corresponding slope threshold, it is determined that the motion trajectory of the rope-type wall-climbing robot has not deviated.

9. The posture adjustment method of the rope-type wall-climbing robot according to claim 1, characterized in that: Adjusting the posture of the rope-type wall-climbing robot based on the offset information includes: Based on the offset information, adjust the first moving speed of the first moving device of the rope-type wall-climbing robot and / or the second moving speed of the second moving device to adjust the posture of the rope-type wall-climbing robot, wherein the first moving device and the second moving device are sleeved on two ropes of the parallel cable.

10. A rope-type wall-climbing robot, characterized in that: include: A robot body, an image acquisition device, a first moving device and a second moving device; The image acquisition device is arranged on the robot body; The robot body is arranged on the first moving device and the second moving device; The first moving device and the second moving device are used to be sleeved on the two ropes of the parallel cable to drive the robot body to move along the two ropes of the parallel cable; The robot body is used to obtain a first image captured by an image acquisition device during the robot body climbing a wall; the first image includes a parallel cable, and two ropes in the parallel cable are distributed on both sides of a center line of the first image; based on the first image, the slopes of the two ropes in the parallel cable are determined; based on the slopes of the two ropes in the parallel cable, the offset information of the motion trajectory of the robot body is determined; and the posture of the robot body is adjusted based on the offset information.

Images