Climbing method and device of power distribution network robot, computer equipment and storage medium

Abstract

The invention relates to a climbing method and device of a power distribution network robot, computer equipment and a storage medium. The method comprises the steps that a camera image corresponding to a power transmission line component and distance information of the power distribution network robot and the power transmission line component are acquired; determining a current angle between the power transmission line component and the power distribution network robot according to the camera image; under the condition that the current angle is within the preset inclination angle range, the power distribution network robot is controlled to rotate based on the current angle and the inclination angle range, so that the power distribution network robot climbs at a non-inclination angle; determining a climbing speed corresponding to the distance information based on a preset speed-distance relationship, and controlling the power distribution network robot to climb at the climbing speed, so that the climbing speed of the power distribution network robot is reduced when the distance information is smaller than a preset distance threshold value; and under the condition that the climbing speed is reduced to the target speed, the power distribution network robot is controlled to climb to a preset target climbing position. Therefore, the climbing stability of the power distribution network robot can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of robots, and particularly to a climbing method, device, computer device and storage medium for a distribution network robot. Background Art

[0002] With the wider coverage of power distribution network lines, more connection points and branch lines, the maintenance and renovation of power distribution networks have also increased accordingly. The maintenance and renovation are mainly completed through manual operation of insulating rods and insulating boom trucks. Such operation methods have high labor intensity, low efficiency and high risk factors, and it is difficult to ensure personal safety. Therefore, using a distribution network operation robot to maintain and renovate the distribution network can effectively improve the safety and efficiency of the operation.

[0003] At present, distribution network operation robots mainly adopt manual remote control operation and control the climbing of the robot according to the visual measurement of the operation height by human eyes. To a certain extent, it avoids the risks of manual operation, but relying on remote control operation, the efficiency is still low, and the efficiency can be improved by the way of the robot's autonomous climbing.

[0004] However, the applicant found during the implementation process that there is at least a problem of too low stability in the process of the robot's autonomous climbing in the related technology. Summary of the Invention

[0005] Based on this, the purpose of the present application aims to solve at least one of the above technical defects, especially the technical defect of too low stability in autonomous climbing in the prior art. The present application provides a climbing method, device, computer device and storage medium for a distribution network robot.

[0006] In a first aspect, the present application provides a climbing method for a distribution network robot. The distribution network robot includes a camera device and a ranging device. The method includes:

[0007] Obtain the camera image corresponding to the transmission line component obtained by the camera device, and obtain the distance information between the distribution network robot and the transmission line component obtained by the ranging device;

[0008] Determine the current angle between the transmission line component and the distribution network robot according to the camera image;

[0009] When the current angle is within the preset inclination angle range, based on the current angle and the inclination angle range, control the distribution network robot to rotate so that the distribution network robot climbs at an un-inclined angle;

[0010] Based on the preset speed-distance relationship, determine the climbing speed corresponding to the distance information, and control the distribution network robot to climb at the climbing speed, so that when the distance information is less than the preset distance threshold, reduce the climbing speed of the distribution network robot;

[0011] When the climbing speed drops to the target speed, control the distribution network robot to climb to a preset target climbing position.

[0012] In one embodiment, the ranging device includes a first ranging device and a second ranging device, wherein the ranging accuracy of the second ranging device is greater than that of the first ranging device;

[0013] Determining the climbing speed corresponding to the distance information based on a preset speed-distance relationship includes:

[0014] Determine the climbing speed according to the first distance information obtained by the first ranging device and the speed-distance relationship;

[0015] When the climbing speed drops to the target speed, controlling the distribution network robot to climb to a preset target climbing position includes:

[0016] When the climbing speed drops to the target speed, based on the second distance information obtained by the second ranging device, control the distribution network robot to climb to the target climbing position.

[0017] In one embodiment, determining the climbing speed according to the first distance information obtained by the first ranging device and the speed-distance relationship includes:

[0018] If the first distance information is greater than a preset first distance threshold, determine that the climbing speed is a preset high speed;

[0019] If the first distance information is greater than a preset second distance threshold and less than the first distance threshold, determine that the climbing speed is a preset medium speed;

[0020] If the first distance information is less than the second distance threshold, determine that the climbing speed is the target speed;

[0021] Wherein, the preset high speed is greater than the preset medium speed, and the preset medium speed is greater than the target speed.

[0022] In one embodiment, controlling the distribution network robot to climb to the target climbing position based on the second distance information obtained by the second ranging device includes:

[0023] If the second distance information is less than or equal to a preset third distance threshold, control the distribution network robot to adjust and climb to the target climbing position.

[0024] In one embodiment, the second ranging device is a line laser device; the transmission line component is a conductor of the distribution network;

[0025] Obtaining the distance information between the distribution network robot and the transmission line component obtained by the ranging device includes:

[0026] Obtain the line laser data collected by the line laser device;

[0027] Based on the line laser data, fit to obtain the first straight line data of the wire;

[0028] According to the first straight line data, obtain the second distance information.

[0029] In one embodiment, based on the line laser data, fitting to obtain the first straight line data of the wire includes:

[0030] Obtain the candidate direction vector between the first data point and the second data point included in the line laser data;

[0031] Determine the degree of difference between the candidate direction vector and other direction vectors; the other direction vectors are obtained according to the line laser data;

[0032] If the degree of difference is less than the preset difference degree threshold, then based on the first data point and the second data point, obtain the first straight line data of the wire.

[0033] In one embodiment, the first ranging device is a lidar device; the transmission line component is the wire of the distribution network;

[0034] Obtain the distance information between the distribution network robot and the transmission line component obtained by the ranging device, including:

[0035] Obtain the lidar point cloud data obtained by the lidar device, and the external transformation parameters between the lidar device and the camera device;

[0036] Use the external transformation parameters to transform the lidar point cloud data to obtain the projection data in the camera coordinate system;

[0037] According to the projection data, fit to obtain the second straight line data of the wire;

[0038] According to the second straight line data, obtain the first distance information.

[0039] In a second aspect, the present application provides a climbing device for a distribution network robot. The distribution network robot includes a camera device and a ranging device; the device includes:

[0040] An information acquisition module, configured to obtain the camera image corresponding to the transmission line component obtained by the camera device, and obtain the distance information between the distribution network robot and the transmission line component obtained by the ranging device;

[0041] An angle determination module, configured to determine the current angle between the transmission line component and the distribution network robot according to the camera image;

[0042] An angle correction module, configured to control the rotation of the distribution network robot based on the current angle and the preset inclination angle range when the current angle is within the preset inclination angle range, so that the distribution network robot climbs at an un-inclined angle;

[0043] A speed control module, configured to determine the climbing speed corresponding to the distance information based on a preset speed-distance relationship, and control the distribution network robot to climb at the climbing speed, so that when the distance information is less than a preset distance threshold, the climbing speed of the distribution network robot is reduced;

[0044] A position control module, configured to control the distribution network robot to climb to a preset target climbing position when the climbing speed drops to the target speed.

[0045] In a third aspect, the present application provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above method are implemented.

[0046] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0047] As can be seen from the above technical solutions, the embodiments of the present application have the following advantages:

[0048] The climbing method, device, computer device and storage medium of the distribution network robot provided by the present application determine the current angle between the transmission line component and the distribution network robot through the camera image; thus, it can be judged whether the current angle is inclined relative to the preset climbing angle. If there is an inclination, the rotation of the distribution network robot can be controlled so that the distribution network robot climbs at an un-inclined angle, thereby avoiding the risk that the distribution network robot shakes and deviates from the initial climbing angle during the autonomous climbing process and improving the climbing stability. And in the present application, when the distance information is less than the preset distance threshold, the climbing speed of the distribution network robot can be reduced, and when it drops to the target speed, the distribution network robot is controlled to climb to the preset target climbing position. In this way, it can be ensured that before climbing to the target climbing position, the risk of being unable to stop climbing in time due to too high a speed can be avoided, thereby improving the climbing stability. Based on this, the present application can improve the climbing stability of the distribution network robot from the overall solution. Description of the Drawings

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0050] Figure 1 Schematic flow of the climbing method of the distribution network robot provided by the embodiment of the present application Figure 1 ;

[0051] Figure 2 Schematic diagram of the current angle of the wire in the camera image provided by the embodiment of the present application;

[0052] Figure 3 Schematic flow of the climbing method of the distribution network robot provided by the embodiment of the present application Figure 2 ;

[0053] Figure 4 Schematic flow of the climbing method of the distribution network robot provided by the embodiment of the present application Figure 3 ;

[0054] Figure 5 Schematic flow of the climbing method of the distribution network robot provided by the embodiment of the present application Figure 3 ;

[0055] Figure 6 Schematic flow of the climbing method of the distribution network robot provided by the embodiment of the present application Figure 4 ;

[0056] Figure 7 Schematic structural diagram of a climbing device of a distribution network robot provided by the embodiment of the present application;

[0057] Figure 8 Schematic internal structure diagram of a computer device provided by the embodiment of the present application. Detailed implementation manners

[0058] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0059] The distribution network lines have a wide coverage range, many connection points and branch lines, and the maintenance and transformation of the distribution network also increase accordingly. The maintenance and transformation are mainly completed through manual operation of insulating rods and insulating boom trucks. Such operation methods have high labor intensity, low efficiency, and high risk coefficients, and it is difficult to ensure personal safety. Therefore, using a distribution network robot to perform maintenance and transformation on the distribution network lines can effectively improve the safety and efficiency of the operation.

[0060] At present, distribution network robots mainly adopt manual remote control operation, and the climbing of the robot is controlled according to the visual measurement of the operation height by human eyes. To a certain extent, this avoids the risks of manual operation. However, relying on remote control operation, its perception accuracy is low and unstable, the efficiency is still low, and it is extremely easy to have misoperations and cause danger.

[0061] Based on this, the present application provides a climbing method, device, computer device and storage medium for a distribution network robot. The present application determines whether the current angle is inclined relative to a preset climbing angle through a camera image. If there is an inclination, the distribution network robot can be controlled to rotate so that the distribution network robot climbs at an un-inclined angle. And when the distance information is less than a preset distance threshold, the climbing speed of the distribution network robot can be reduced. When the target speed is reached, the distribution network robot is controlled to climb to a preset target climbing position. In this way, the risk of shaking and deviation of the distribution network robot during autonomous climbing can be avoided, and the risk of being unable to stop climbing in time due to too fast a speed can be avoided before climbing to the target climbing position, thereby improving the stability of the autonomous climbing of the distribution network robot.

[0062] In an exemplary embodiment, Figure 1 is a flowchart of the climbing method for a distribution network robot provided by an embodiment of the present application Figure 1 , as Figure 1 shown, a climbing method for a distribution network robot is provided. The distribution network robot includes a camera device and a ranging device. In this embodiment, it is exemplified that the method is applied to the edge end set in the robot. It can be understood that the method can also be applied to a server or the cloud, and can also be applied to a system including an edge end and a server / cloud, and is realized through the interaction between the edge end and the server / cloud. The method includes the following S101 to S105. Among them:

[0063] S101. Obtain the camera image corresponding to the transmission line component obtained through the camera device, and obtain the distance information between the distribution network robot and the transmission line component obtained through the ranging device.

[0064] Among them, the edge end of the robot can refer to the on-board edge end of the robot, that is, the edge computing of the distribution network robot can be deployed in the distribution network robot to realize real-time climbing analysis. The camera device can be a device installed on the distribution network robot to obtain collected images, and can be a monocular camera; the ranging device can be a device installed on the distribution network robot to realize ranging, and can be a lidar, a line laser, etc. that can realize ranging; for example, both the camera device and the ranging device can be installed on the top of the distribution network robot so that the distribution network robot can collect images above the climbing during the operation climbing process and realize ranging.

[0065] The transmission line components can refer to power target components such as transmission wires, insulators, porcelain cross-arms, etc. The camera image can refer to the two-dimensional image obtained by the camera. The distance information can refer to the distance between the distribution network robot and the transmission line components.

[0066] Exemplarily, the edge end of the robot can collect an image of the transmission line components of the distribution network through a camera device to obtain a camera image. And the edge end can obtain the distance information between the distribution network robot and the transmission line components through a ranging device. For example, the edge end can obtain this distance information through a lidar.

[0067] S102. Determine the current angle between the transmission line component and the distribution network robot according to the camera image.

[0068] Among them, the current angle can refer to the included angle between the transmission line component and the vision of the distribution network robot. For example, it can be the included angle between the wire of the distribution network and the vision of the distribution network robot.

[0069] Exemplarily, the edge end of the robot can determine the position of the wire captured by the camera device in the camera image through the camera image. And the current angle of the wire in the camera coordinate system of the camera image can be determined.

[0070] Optionally, Figure 2 is a schematic diagram of the current angle of a wire in the camera image provided by an embodiment of the present application; as Figure 2 shown, the edge end of the robot can obtain the wire target in the image through a pre-set target recognition algorithm , where is the wire target, , are the coordinates of the upper left corner point and the lower right corner point of the wire target respectively. Figure 2 In, θ is the current angle, that is, the included angle between the wire and the distribution network robot, and the inclination angle between the distribution network robot and the apology.

[0071] Schematically, the inclination angle of the wire in the image is obtained according to trigonometric functions , that is, the following expression (1):

[0072]

[0073] S103. When the current angle is within the preset inclination angle range, control the distribution network robot to rotate based on the current angle and the inclination angle range, so that the distribution network robot climbs at an un-inclined angle.

[0074] Among them, the inclination angle range can refer to the pre-set angle range. If it is within this range, it can be considered that the distribution network robot is inclined relative to the wire.

[0075] Exemplarily, the edge device can determine whether the current angle is within a preset tilt angle range. For example, if the current angle is greater than the preset angle, it can indicate that the distribution network robot is in a state of rotational tilt. If the current angle is within the preset tilt angle range, the angle when the distribution network robot has no rotational tilt can be determined based on the current angle and the tilt angle range, and then the distribution network robot can be controlled to rotate to the angle when it has no rotational tilt, so that the distribution network robot climbs at an untilted angle.

[0076] Schematically, the distribution network robot can autonomously climb up the electric pole. During the autonomous climbing process, the distribution network robot may rotate, that is, the distribution network robot does not always climb autonomously at the initial climbing angle during the climbing process. Herein, the initial climbing angle can be obtained with reference to the wire.

[0077] Optionally, as Figure 2 shown, if the initial climbing angle of the distribution network robot is , then if the or of the current angle of the distribution network robot during the autonomous climbing process, it can be considered that the current angle is within the preset tilt angle range, and the distribution network robot can be controlled to rotate so that the distribution network robot climbs at .

[0078] In this way, at the initial climbing, it can start climbing at an angle without tilt. If it is determined that there is a tilt angle during the autonomous climbing process, the distribution network robot can be rotated during the climbing process to keep it consistent with the initial climbing angle, so as to ensure the stability of the distribution network robot during the entire climbing process, avoid the risk of the distribution network robot shaking and deviating from the initial climbing angle during the climbing process, and thus improve the climbing stability.

[0079] S104. Based on a preset speed-distance relationship, determine the climbing speed corresponding to the distance information, and control the distribution network robot to climb at the climbing speed, so that when the distance information is less than a preset distance threshold, the climbing speed of the distribution network robot is reduced.

[0080] Wherein, the speed-distance relationship can refer to the corresponding relationship between distance and speed. The distance refers to the distance between the distribution network robot and transmission line components such as wires. The climbing speed refers to the climbing speed of the distribution network robot. The preset distance threshold can be a threshold preset for the distance, and the climbing speed of the distribution network robot can be controlled to change through the preset distance threshold.

[0081] Exemplarily, the edge device can determine a pre-set speed-distance relationship, and based on this speed-distance relationship, determine the current distance information and the corresponding climbing speed that the distribution network robot should have, and control the distribution network robot to climb at this climbing speed. In this way, when the distribution network robot climbs to a distance less than the preset distance threshold, the climbing speed of the distribution network robot can be reduced, thereby ensuring the stable climbing of the distribution network robot.

[0082] Optionally, when the distance between the distribution network robot and the wire is far, the distribution network robot can be controlled to climb at a higher speed. When the distance between the distribution network robot and the wire is close, the distribution network robot can be controlled to climb at a lower speed. In this way, while avoiding the safety risks caused by the rapid climbing of the distribution network robot when the distance from transmission line components such as wires is close, it can ensure that the distribution network robot climbs relatively quickly when the distance is far, improving the climbing rate.

[0083] Among them, the distance is judged by the distance threshold. For example, when it is greater than the preset distance threshold, it can be considered that the distance is far; when it is less than the preset distance threshold, it can be considered that the distance is close. The higher speed and the lower speed can both be pre-set speeds, and the higher speed should be greater than the lower speed.

[0084] S105. When the climbing speed drops to the target speed, control the distribution network robot to climb to a preset target climbing position.

[0085] Among them, the target speed can refer to a pre-set low speed. The target climbing position can refer to a preset position that needs to be climbed. For example, when performing an inspection operation on the distribution network, the target climbing position can be the position of the transmission line component that needs to be inspected.

[0086] Exemplarily, when the climbing speed of the distribution network robot drops to the target speed, the edge device of the distribution network robot can control the distribution network robot to adjust and climb to a pre-set target climbing position. For example, the distribution network robot can be controlled to finely adjust to the operation height position at the target speed to complete the autonomous climbing of the distribution network robot.

[0087] In this embodiment, the current angle between the transmission line component and the distribution network robot is determined through the camera image. In this way, it can be judged whether the current angle is inclined relative to the preset climbing angle. If there is an inclination, the distribution network robot can be controlled to rotate so that the distribution network robot climbs at an un-inclined angle, thereby avoiding the risk that the distribution network robot shakes and deviates from the initial climbing angle during the autonomous climbing process and improving the climbing stability. And when the distance information is less than the preset distance threshold in this application, the climbing speed of the distribution network robot can be reduced. When the target speed is reached, the distribution network robot is controlled to climb to the preset target climbing position. In this way, it can be ensured that before climbing to the target climbing position, the risk of being unable to stop climbing in time due to too high a speed can be avoided, thereby improving the climbing stability. Based on this, this application can improve the climbing stability of the distribution network robot from the overall solution.

[0088] In an exemplary embodiment, Figure 3 is a schematic flow chart of the climbing method of the distribution network robot provided by the embodiment of the present application Figure 2 , as Figure 3 shown, on the basis of Figure 1 , the steps of the climbing method of the distribution network robot are described exemplarily. Among them, the ranging device includes a first ranging device and a second ranging device, and the ranging accuracy of the second ranging device is greater than that of the first ranging device; in the step of S104, based on the preset speed-distance relationship, the climbing speed corresponding to the distance information is determined, including S301; in the step of S105, when the climbing speed drops to the target speed, the distribution network robot is controlled to climb to the preset target climbing position, including S302; where:

[0089] S301. Determine the climbing speed according to the first distance information obtained by the first ranging device and the speed-distance relationship.

[0090] Among them, the first ranging device can be a lidar device, and the second ranging device can be a line laser device.

[0091] Exemplarily, the first distance information can be collected through the first ranging device, and the edge end can further determine the climbing speed corresponding to the first distance information according to the speed-distance relationship, that is, the edge end can determine the climbing speed that the distribution network robot should correspond to through the first distance information.

[0092] S302. When the climbing speed drops to the target speed, based on the second distance information obtained by the second ranging device, control the distribution network robot to climb to the target climbing position.

[0093] Exemplarily, the second distance information can be collected by the second ranging device, and the edge terminal can control the distribution network robot to finely adjust to the operating height position at the target speed through the second distance information with higher accuracy, so as to improve the accuracy of adjusting the target climbing position.

[0094] In this embodiment, the adjustment of the climbing speed is achieved through the first distance information obtained by the first ranging device, and the adjustment of the target climbing position is achieved through the second distance information obtained by the second ranging device. In this way, long-distance ranging can be achieved through the first ranging device with a longer ranging distance, and more accurate position adjustment can be achieved through the second ranging device with higher ranging accuracy, thereby improving the accuracy of speed adjustment and the accuracy of target climbing position adjustment.

[0095] In an exemplary embodiment, in step S301, according to the first distance information obtained by the first ranging device and the speed-distance relationship, determining the climbing speed includes:

[0096] If the first distance information is greater than the preset first distance threshold, determine the climbing speed as the preset high speed;

[0097] If the first distance information is greater than the preset second distance threshold and less than the first distance threshold, determine the climbing speed as the preset medium speed;

[0098] If the first distance information is less than the second distance threshold, determine the climbing speed as the target speed;

[0099] Wherein, the preset high speed is greater than the preset medium speed, and the preset medium speed is greater than the target speed.

[0100] Wherein, the first distance threshold can be the threshold for determining the preset high-speed climbing speed. The second distance threshold can be the distance threshold for controlling the medium speed to change to the low speed.

[0101] Exemplarily, the first distance information from the top of the distribution network robot to the wire obtained in real time can be , for climbing speed v adjustment. For example, the climbing speed can be determined according to the following expression (2):

[0102]

[0103] Wherein, is the first distance information; is the first distance threshold; is the second distance threshold; is the preset high speed; is the preset medium speed; is the preset low speed (target speed).

[0104] In this embodiment, through the above distance threshold judgment, the climbing speed can be effectively controlled. By dividing the preset high speed, preset medium speed, and preset low speed (target speed), while avoiding the safety risks caused by the close distance between the distribution network robot and transmission line components such as wires during rapid climbing, the climbing speed first decreases from high speed to medium speed and then to low speed, avoiding a direct drop from high speed to low speed, so that the climbing speed can transition smoothly, improving the stability of the speed, and further improving the autonomous climbing stability of the distribution network robot.

[0105] In an exemplary embodiment, based on the second distance information obtained by the second ranging device, controlling the distribution network robot to climb to the target climbing position includes:

[0106] If the second distance information is less than or equal to a preset third distance threshold, then control the distribution network robot to adjust and climb to the target climbing position.

[0107] Wherein, the third distance threshold can be a threshold preset for adjusting the target climbing position.

[0108] Exemplarily, the distance information can be collected by the second ranging device, and the second distance information from the top of the robot to the wire can be calculated in real time , if , then the distribution network robot can be finely controlled to climb to the specified working height position (target climbing position), and then the robot climbing is completed. Wherein, is the third distance threshold, if , then it can be determined again through expression (2) whether the requirements of the target speed and the second distance threshold are met. If not, the speed is adjusted again until the second distance threshold is met and until the second distance information can meet being less than or equal to the preset third distance threshold.

[0109] In this embodiment, through the third distance threshold, a higher-precision distance judgment can be achieved. When the distance is less than the third distance threshold, the distribution network robot is finely controlled to the target climbing position, thereby improving the climbing accuracy of the distribution network robot.

[0110] In an exemplary embodiment, Figure 4 is the flow schematic of the climbing method of the distribution network robot provided by the embodiment of the present application Figure 3 , as Figure 4 shown, on the basis of Figure 1 , the steps of the climbing method of the distribution network robot are described exemplarily. Among them, the second ranging device is a line laser device, the transmission line component is the wire of the distribution network. In step S101, obtaining the distance information between the distribution network robot and the transmission line component through the ranging device includes: S401 to S403, wherein:

[0111] S401. Obtain the line laser data collected by the line laser device.

[0112] S402. Based on the line laser data, fit to obtain the first straight line data of the wire.

[0113] S403. Obtain the second distance information according to the first straight line data.

[0114] Among them, the line laser data may refer to the data collected in real time by the line laser device.

[0115] Exemplarily, the line laser device can collect line laser data in real time. The edge side can, based on the line laser data, fit out the straight line data corresponding to the wire, that is, the first straight line data, and the edge side can, according to the first straight line data, calculate the second distance information between the distribution network robot and the wire.

[0116] In this embodiment, the first straight line data is fitted out through the line laser data collected by the line laser device, which is beneficial to determining the second distance information. In this way, the second distance information obtained by the line laser device with high ranging accuracy can improve the position accuracy of the autonomous climbing of the distribution network robot.

[0117] Optionally, in the step of S402, based on the line laser data, fitting to obtain the first straight line data of the wire may specifically include:

[0118] Obtain the candidate direction vector between the first data point and the second data point included in the line laser data.

[0119] Determine the difference degree between the candidate direction vector and other direction vectors; the other direction vectors are obtained according to the line laser data.

[0120] If the difference degree is less than the preset difference degree threshold, then based on the first data point and the second data point, obtain the first straight line data of the wire.

[0121] Among them, the first data point and the second data point can be any two data points. The candidate direction vector may refer to the undetermined straight line direction vector, and the accurate straight line direction vector can be determined from multiple candidate direction vectors. The difference degree threshold may refer to the threshold preset for the error between direction vectors.

[0122] Exemplarily, the edge side, according to the line laser data, takes two points among them and to fit the wire to obtain the direction vector of the wire , calculate The root mean square error of the distance from the remaining laser points (data points), that is, the root mean square error can be used as the degree of difference. For example, the root mean square error can be determined by the following expression (3):

[0123]

[0124] where is the root mean square error, is the number of laser points per frame; is any point in each frame.

[0125] Schematically, if is less than the pre-set difference degree threshold Q, then is considered as the wire direction vector, otherwise repeat the above steps until the wire direction vector is obtained.

[0126] Taking as the wire direction vector, then the straight line equation of the wire can be obtained according to and i.e., the following expression (4):

[0127]

[0128] In this embodiment, through the above steps, the first straight line data corresponding to the wire can be accurately determined, that is, wire data with higher accuracy can be obtained based on the line laser device, so that distance information with higher accuracy can be obtained, and the climbing position accuracy of the distribution network robot can be improved.

[0129] In an exemplary embodiment, Figure 5 is the process schematic of the climbing method of the distribution network robot provided by the embodiment of the present application Figure 3 , as Figure 5 shown, on the basis of Figure 1 , the steps of the climbing method of the distribution network robot are illustrated exemplarily. Among them, the first distance measuring device is a lidar device, the transmission line component is the wire of the distribution network. In the step of S101, the distance information between the distribution network robot and the transmission line component obtained by the distance measuring device is obtained, including S501 to S504, where:

[0130] S501. Obtain the lidar point cloud data obtained by the lidar device, and the external transformation parameters between the lidar device and the camera device.

[0131] S502. Use the external transformation parameters to transform the lidar point cloud data to obtain the projection data in the camera coordinate system.

[0132] S503. Fit the projection data to obtain the second straight line data of the wire.

[0133] S504. Obtain the first distance information according to the second straight-line data.

[0134] Among them, the external transformation parameters can refer to the extrinsic parameters between the camera and the lidar. The projection data can refer to the point cloud projection. For example, it can be the projection coordinate data. The second straight-line data refers to the wire straight-line data obtained by the lidar.

[0135] Exemplarily, the edge device can use the extrinsic parameters between the camera and the lidar to transform the point cloud in the lidar coordinate system to the camera coordinate system. For example, through expression (5):

[0136]

[0137] Among them, is the point cloud data in the lidar coordinate system; is the point cloud data in the camera coordinate system, is the lidar extrinsic parameter.

[0138] The edge device can use the pre-determined camera intrinsic parameters to project the laser point cloud data in the camera coordinate system onto the image, that is, through expression (6):

[0139]

[0140] Among them, and are the camera focal lengths; and are the central coordinates of the image; is the point cloud projection in the camera coordinate system, that is, the depth map.

[0141] As an example, from the wire recognition result shown in Figure 2 , it can be seen that the area where the wire is located , so that the edge device can extract of the wire point cloud data, denoted as .

[0142] The edge device can use the RANSAC algorithm to fit the wire point cloud to obtain the wire equation. In this way, the closest distance from the wire to the top of the distribution network robot can be obtained, that is, the first distance information .

[0143] In this embodiment, the laser point cloud data obtained by the lidar device can use the external transformation parameters to transform the laser point cloud data to obtain the projection data in the camera coordinate system. Further, according to the projection data, the second straight-line data of the wire can be fitted. In this way, the first distance information can be accurately and effectively determined, so that the climbing speed of the distribution network robot can be controlled more precisely.

[0144] In some specific embodiments, Figure 6 is a schematic flow chart of the climbing method of the distribution network robot provided by the embodiment of the present application Figure 4 , as Figure 6 shown, on the basis of Figures 1 to 5 , an exemplary description is made of the steps of the climbing method of the distribution network robot. The climbing method of the distribution network robot may include the following steps: S601 to S615, where:

[0145] S601. The distribution network robot perception system (camera, lidar, line laser) collects data; where: in the operation scenario of the distribution network, the multi-source perception system can be fixedly installed on the robot. The distribution network operation scenario contains power targets such as insulators, porcelain cross arms, and conductors. The multi-source perception system includes a monocular camera, lidar, line laser, etc.

[0146] S602. Conductive target recognition, where: according to the camera and lidar, images and point cloud data containing conductors are obtained, and target recognition and distance perception are performed on the conductors above the climbing direction of the robot.

[0147] S603. Real-time calculation of the inclination angle of the conductor in the image ;

[0148] S604. Determine whether the conductor is vertically centered; if not, execute S605, if so, execute S606;

[0149] S605. Control the rotation of the distribution network robot; where: according to the inclination angle value, control the rotation of the robot , to achieve vertical centering of the conductor, that is, it can be achieved through the following expression (7):

[0150]

[0151] where, a positive value is counterclockwise rotation, a negative value is clockwise rotation.

[0152] S606. Real-time calculation of the first distance information from the top of the robot to the conductor ; where: according to the closest distance d 1 from the top of the robot to the conductor obtained in real time, the climbing speed v is adjusted, that is, the climbing speed v can be determined through expression (2) in the above text.

[0153] S607. Determine whether d 1 is less than , if not, execute S608, if so, execute S609.

[0154] S608. Control the distribution network robot to climb at a climbing speed v fast Climb.

[0155] S609. Control the distribution network robot to climb at a climbing speed v low Climb; wherein: Repeat steps S601 to S608 until the climbing speed drops to .

[0156] S610. Extract the second straight line data of the wire according to the line laser data.

[0157] S611. Obtain the second distance information d between the wire and the distribution network robot 2 . Wherein: The second distance information d can be determined in the implementation manners such as S501 to S504 2 .

[0158] S612. Judge whether d 2 is greater than the third distance threshold M of the point. If so, execute S608; if not, execute S613;

[0159] S613. Judge whether the distribution network robot has reached the predetermined position; if not, execute S614; if so, execute S615;

[0160] S614. Slowly and finely adjust the distance between the distribution network robot and the wire;

[0161] S615. Control the distribution network robot to complete the climb.

[0162] Schematically, the steps of S601 to S615 can be limited by referring to the steps of the climbing method of the distribution network robot in the above various embodiments, and will not be elaborated here.

[0163] In this embodiment, an autonomous climbing method for a distribution network robot based on the collaborative perception of a camera and multiple lidars is adopted. The distribution network robot is quickly centered on the wire position by using image recognition, and then the lidar and line laser are used to perform rough positioning and fine positioning on the wire at different distances, so as to realize the dynamic climbing of the robot to the target position.

[0164] The embodiment of the present application provides an autonomous climbing method for a distribution network robot based on the collaborative perception of a camera and multiple lidars. The robot is quickly centered on the wire position by using image recognition, and according to the lidar and line laser, the obstacles and wires during the climbing process can be target-recognized and distance-perceived. At the same time, an adaptive speed adjustment method based on distance is adopted to realize the collaborative perception and precise and compliant climbing of the robot.

[0165] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown in the direction of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, there is no strict order limit for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0166] The climbing device of the distribution network robot provided by the embodiments of the present application will be described below. The climbing device of the distribution network robot has the same inventive concept as the above-described climbing method of the distribution network robot. The implementation solution provided by this device to solve the problem is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more embodiments of the climbing device of the distribution network robot provided below can refer to the limitations on the climbing method of the distribution network robot in the above text. The climbing device of the distribution network robot described below and the climbing method of the distribution network robot described above can be correspondingly referred to each other, and will not be repeated here.

[0167] In an exemplary embodiment, Figure 7 is a schematic structural diagram of a climbing device of a distribution network robot provided by an embodiment of the present application. As Figure 7 shown, the climbing device 70 of the distribution network robot includes: an information acquisition module 710, an angle determination module 720, an angle correction module 730, a speed control module 740, and a position control module 750, where:

[0168] The information acquisition module 710 is configured to obtain a camera image corresponding to a transmission line component obtained through a camera device, and obtain distance information between the distribution network robot and the transmission line component obtained through a ranging device.

[0169] The angle determination module 720 is configured to determine a current angle between the transmission line component and the distribution network robot according to the camera image.

[0170] The angle correction module 730 is configured to, when the current angle is within a preset inclination angle range, control the rotation of the distribution network robot based on the current angle and the inclination angle range, so that the distribution network robot climbs at an un-inclined angle.

[0171] A speed control module 740 is configured to determine a climbing speed corresponding to the distance information based on a preset speed-distance relationship, and control the distribution network robot to climb at the climbing speed, so as to reduce the climbing speed of the distribution network robot when the distance information is less than a preset distance threshold.

[0172] A position control module 750 is configured to control the distribution network robot to climb to a preset target climbing position when the climbing speed drops to a target speed.

[0173] In an exemplary embodiment, the ranging device includes a first ranging device and a second ranging device, wherein the ranging accuracy of the second ranging device is greater than that of the first ranging device. The speed control module is configured to determine the climbing speed according to the first distance information obtained by the first ranging device and the speed-distance relationship. The position control module is configured to control the distribution network robot to climb to the target climbing position based on the second distance information obtained by the second ranging device when the climbing speed drops to the target speed.

[0174] In an exemplary embodiment, the speed control module is configured to determine the climbing speed as a preset high speed if the first distance information is greater than a preset first distance threshold; determine the climbing speed as a preset medium speed if the first distance information is greater than a preset second distance threshold and less than the first distance threshold; determine the climbing speed as the target speed if the first distance information is less than the second distance threshold; wherein the preset high speed is greater than the preset medium speed, and the preset medium speed is greater than the target speed.

[0175] In an exemplary embodiment, the position control module is configured to control the distribution network robot to adjust and climb to the target climbing position if the second distance information is less than or equal to a preset third distance threshold.

[0176] In an exemplary embodiment, the information acquisition module is configured to use the second ranging device as a line laser device. Obtain line laser data collected by the line laser device; based on the line laser data, fit to obtain first straight line data of the wire; according to the first straight line data, obtain the second distance information.

[0177] In an exemplary embodiment, the information acquisition module is configured to obtain a candidate direction vector between a first data point and a second data point included in the line laser data; determine the degree of difference between the candidate direction vector and other direction vectors; the other direction vectors are obtained according to the line laser data; if the degree of difference is less than a preset degree of difference threshold, then based on the first data point and the second data point, obtain the first straight line data of the wire.

[0178] In an exemplary embodiment, the first ranging device is a lidar device. The information acquisition module is configured to obtain the lidar point cloud data obtained by the lidar device, as well as the external transformation parameters between the lidar device and the camera device; use the external transformation parameters to transform the lidar point cloud data to obtain the projection data in the camera coordinate system; fit the projection data to obtain the second straight line data of the wire; and obtain the first distance information according to the second straight line data.

[0179] In an exemplary embodiment, the present application further provides a computer-readable storage medium storing a computer program, which when executed by one or more processors, causes the one or more processors to execute the steps of the climbing method of the distribution network robot in any one of the above embodiments.

[0180] In an exemplary embodiment, the present application further provides a computer device storing a computer program, which when the computer-readable instructions are executed by one or more processors, causes the one or more processors to execute the steps of the climbing method of the distribution network robot in any one of the above embodiments.

[0181] In an exemplary embodiment, the present application further provides a computer program product including a computer program, which when executed by a processor, implements the steps of the climbing method of the distribution network robot in any one of the above embodiments.

[0182] Schematically, as Figure 8 shown, Figure 8 is an internal structural diagram of a computer device provided by an embodiment of the present application. The computer device 800 can be provided as a server. Referring to Figure 8 , the computer device 800 includes a processing component 802, which further includes one or more processors, and memory resources represented by a memory 801 for storing instructions executable by the processing component 802, such as application programs. The application programs stored in the memory 801 can include one or more modules each corresponding to a set of instructions. In addition, the processing component 802 is configured to execute instructions to perform the text recognition method of any of the above embodiments.

[0183] The computer device 800 may further include a power supply component 803 configured to perform power management of the computer device 800, a wired or wireless network interface 804 configured to connect the computer device 800 to a network, and an input / output (I / O) interface 805. The computer device 800 can operate based on an operating system stored in the memory 801, such as WindowsServer TM, Mac OS XTM, Unix TM, Linux TM, Free BSDTM or the like.

[0184] Those skilled in the art can understand that Figure 8 The structure shown in [the figure] is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0185] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0186] Finally, it should also be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the said element.

[0187] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referred to each other.

[0188] The above description of the disclosed embodiments enables those skilled in the art to implement or use this application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application will not be limited to these embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A climbing method for a distribution network robot, characterized in that: The distribution network robot includes a camera device and a distance measuring device; the method includes: Acquire a camera image corresponding to a power transmission line component obtained by the camera device, and acquire distance information between the power distribution network robot and the power transmission line component obtained by the distance measuring device; determining a current angle between the power transmission line component and the power distribution network robot based on the camera image; In the case where the current angle is within a preset tilt angle range, based on the current angle and the tilt angle range, controlling the distribution network robot to rotate so that the distribution network robot climbs at a non-tilted angle; Based on a preset speed-distance relationship, determine a climbing speed corresponding to the distance information, and control the distribution network robot to climb at the climbing speed, so that when the distance information is less than a preset distance threshold, the climbing speed of the distribution network robot is reduced; When the climbing speed drops to the target speed, the distribution network robot is controlled to climb to a preset target climbing position.

2. The method according to claim 1, characterized in that The distance measuring device comprises a first distance measuring device and a second distance measuring device, wherein the distance measuring accuracy of the second distance measuring device is greater than the distance measuring accuracy of the first distance measuring device; The determining the climbing speed corresponding to the distance information based on a preset speed-distance relationship includes: Determine the climbing speed according to the first distance information obtained by the first distance measuring device and the speed-distance relationship; When the climbing speed drops to the target speed, controlling the distribution network robot to climb to a preset target climbing position includes: When the climbing speed drops to the target speed, the distribution network robot is controlled to climb to the target climbing position based on the second distance information obtained by the second distance measuring device.

3. The method according to claim 2, characterized in that The step of determining the climbing speed according to the first distance information obtained by the first distance measuring device and the speed-distance relationship includes: If the first distance information is greater than a preset first distance threshold, determining that the climbing speed is a preset high speed; If the first distance information is greater than a preset second distance threshold and less than the first distance threshold, determining that the climbing speed is a preset medium speed; If the first distance information is less than the second distance threshold, determining the climbing speed to be the target speed; The preset high speed is greater than the preset medium speed, and the preset medium speed is greater than the target speed.

4. The method according to claim 2, characterized in that: The step of controlling the distribution network robot to climb to the target climbing position based on the second distance information obtained by the second distance measuring device includes: If the second distance information is less than or equal to a preset third distance threshold, the distribution network robot is controlled to adjust and climb to the target climbing position.

5. The method according to claim 2 or 4, characterized in that: The second distance measuring device is a line laser device; the power transmission line component is a conductor of a power distribution network; The obtaining of the distance information between the distribution network robot and the transmission line component obtained by the distance measuring device includes: Acquiring line laser data collected by the line laser device; Based on the line laser data, fitting to obtain first straight line data of the conductor; The second distance information is obtained according to the first straight line data.

6. The method according to claim 5, characterized in that The fitting to obtain first straight line data of the conductor based on the line laser data includes: Acquire a candidate direction vector between a first data point and a second data point included in the line laser data; Determine the degree of difference between the candidate direction vector and other direction vectors; the other direction vectors are obtained based on the line laser data; If the difference degree is less than a preset difference degree threshold, first straight line data of the conductive line is obtained based on the first data point and the second data point.

7. The method according to claim 2, characterized in that The first distance measuring device is a laser radar device; the power transmission line component is a conductor of a power distribution network; The obtaining of the distance information between the distribution network robot and the transmission line component obtained by the distance measuring device includes: Acquire laser point cloud data obtained by the laser radar device, and external transformation parameters of the laser radar device and the camera device; Using the external transformation parameters, transforming the laser point cloud data to obtain projection data in a camera coordinate system; According to the projection data, fitting obtains second straight line data of the guide wire; The first distance information is obtained according to the second straight line data.

8. A climbing device for a distribution network robot, characterized in that: The distribution network robot includes a camera device and a distance measuring device; the device includes: An information acquisition module, used to obtain a camera image corresponding to a power transmission line component obtained by the camera device, and to obtain distance information between the power distribution network robot and the power transmission line component obtained by the distance measuring device; an angle determination module, for determining a current angle between the power transmission line component and the power distribution network robot based on the camera image; An angle correction module, used for controlling the distribution network robot to rotate based on the current angle and the tilt angle range when the current angle is within a preset tilt angle range, so that the distribution network robot climbs at a non-tilted angle; A speed control module, used to determine a climbing speed corresponding to the distance information based on a preset speed-distance relationship, and control the distribution network robot to climb at the climbing speed, so that when the distance information is less than a preset distance threshold, the climbing speed of the distribution network robot is reduced; The position control module is used to control the distribution network robot to climb to a preset target climbing position when the climbing speed drops to the target speed.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images