Vehicle-mounted intelligent laser obstacle clearing device and obstacle clearing method

Abstract

The present invention provides a vehicle-mounted intelligent laser obstacle clearer, comprising a vehicle body, a controller and an image acquisition module connected to the controller, a mechanical arm and a laser transmitter installed on the vehicle body, and the laser transmitter is installed at the end of the mechanical arm; the image acquisition module is used to obtain image information of the overhead line, and the controller identifies and locates obstacles on the overhead line according to the acquired image information, and controls the movement of the mechanical arm according to the position information of the obstacle, so that the laser transmitter aims at the obstacle to perform obstacle clearance. The present invention automatically obtains image information of the overhead line through the image acquisition module, automatically identifies and locates obstacles on the overhead line according to the image information, and controls the mechanical arm to move the laser transmitter to realize automatic aiming and obstacle clearance operations for the obstacles; there is no need for manual observation and aiming of obstacles with the naked eye, which improves the efficiency and accuracy of laser obstacle clearance and reduces the intensity of manual labor.

Description

Technical Field

[0001] The present application relates to the field of laser obstacle removal technology, and in particular to a vehicle-mounted intelligent laser obstacle removal device and an obstacle removal method. Background Art

[0002] Overhead lines mainly refer to overhead open lines, which are erected above the ground. They use insulators to fix the transmission wires on the towers erected on the ground to transmit electric energy. Because the overhead lines are directly exposed to the air, kites, plastic sheets, plastic bags, kite lines and other floating objects are easily blown onto the overhead lines. Once such floating foreign objects are soaked by rain, snow, and dew, it is very easy to cause metal conductor phase-to-phase short circuit, single-phase grounding and other faults, thereby causing the tripping of the transmission and distribution lines or line damage. Even foreign objects that fall to the position where people and animals can touch may cause casualties to people and animals. Therefore, timely cleaning of foreign objects on the transmission lines is very important for power supply safety. However, due to the restrictions of the installation ground being irregular and the overhead lines being far away from the ground, it is very difficult to remove foreign objects. The traditional obstacle removal method is that workers install crawling devices on the overhead lines by climbing the towers. The crawling devices move on the overhead lines to remove foreign objects. However, due to many defects such as greater climbing dangers, long operation time, complex operation, high cost, and poor results, this obstacle removal method is gradually being eliminated.

[0003] In order to solve the above-mentioned defects of manual obstacle removal, lasers are used for obstacle removal. The staff only need to turn on and move the laser on the ground, aim the laser at the obstacle on the overhead line, and wait for a long enough time for the obstacle to burn or vaporize, thereby removing the obstacle. The operation is very simple and quick.

[0004] However, when using the existing laser obstacle remover, the human eye needs to judge the obstacle and aim it. It is inconvenient for the human eye to watch for a long time, there is a large deviation, and it is difficult to manually move the laser to aim at the obstacle, the positioning is not accurate, and the manual labor intensity is high. Summary of the invention

[0005] The present application provides a vehicle-mounted intelligent laser obstacle clearer and an obstacle clearing method, which solves the problems of inaccurate positioning, high manual labor intensity, etc. in existing laser obstacle clearers, which require human eyes to aim at obstacles and manually move the laser to aim at obstacles when in use.

[0006] A first aspect of the present application provides a vehicle-mounted intelligent laser obstacle clearer, including a vehicle body, on which is mounted a controller and an image acquisition module, a mechanical arm and a laser emitter connected to the controller, wherein the laser emitter is mounted at the end of the mechanical arm; the image acquisition module is used to acquire image information of the overhead line, the controller identifies and locates obstacles on the overhead line according to the acquired image information, and controls the movement of the mechanical arm according to the position information of the obstacle, so that the laser emitter aims at the obstacle to perform obstacle clearance operations.

[0007] In the technical solution provided in the present application, image information of the overhead line is automatically acquired through an image acquisition module, obstacles on the overhead line are automatically identified and located based on the image information, and the robotic arm is controlled to move the laser transmitter to achieve automatic aiming and obstacle clearance operations for the obstacles; there is no need for manual observation and aiming of obstacles with the naked eye, which improves the efficiency and accuracy of laser obstacle clearance and reduces manual labor intensity.

[0008] In some embodiments, the laser transmitter includes a laser, a laser head and a focusing assembly. The laser is installed on a vehicle body, and the laser head and the focusing assembly are installed at the end of a robotic arm. The output end of the laser is connected to the input end of the focusing assembly via an optical fiber, and the output end of the focusing assembly is connected to the input end of the laser head; the focusing assembly is connected to a controller, and the controller controls the focusing assembly to adaptively adjust the focal length of the laser according to the distance between the obstacle and the laser head; by installing the laser and the laser head separately, the load on the end of the robotic arm can be reduced, and the accuracy and stability of the aiming of the robotic arm's moving laser head can be improved; by arranging the focusing assembly at the front end of the laser head, the focal length of the laser can be automatically adjusted according to the distance between the obstacle and the laser head, so that the laser spot is focused on the obstacle, thereby improving the accuracy and efficiency of laser obstacle removal.

[0009] In some embodiments, the focusing assembly includes a collimating lens group, a focusing lens group and a diverging lens group arranged in sequence along the optical axis, the collimating lens group is fixedly installed at the input end of the focusing assembly, and the focusing lens group and / or the diverging lens group are slidably installed at the output end of the focusing assembly, and the focusing assembly also includes a driving component, and the driving component is used to drive the focusing lens group and / or the diverging lens group to slide straight along the optical axis, thereby changing the distance between the focusing lens group and the diverging lens group, thereby realizing the focal length adjustment of the emitted laser beam.

[0010] In some embodiments, the robotic arm includes a base, a first joint arm, a second joint arm and a third joint arm connected in sequence, one end of the first joint arm is rotationally connected to the base via an azimuth joint, the first joint arm, the second joint arm and the third joint arm are rotationally connected via a pitch joint respectively, and the laser transmitter is installed at the end of the third joint arm.

[0011] In some embodiments, the vehicle body is an unmanned vehicle, and obstacle avoidance sensors are arranged on all sides of the vehicle body; the controller controls the vehicle body to automatically travel along the laying direction of the overhead line according to the image information of the overhead line acquired by the image acquisition module; by arranging obstacle avoidance sensors around the vehicle body, the vehicle body can automatically avoid obstacles on the inspection path; according to the acquired image information of the overhead line, the vehicle body can be controlled to automatically travel along the laying direction of the overhead line, realizing truly intelligent inspection and obstacle clearance operations, without the need for staff to follow the vehicle body for inspection and obstacle clearance, reducing the intensity of manual labor and improving the intelligence of the vehicle-mounted laser obstacle clearer.

[0012] In some embodiments, a rotating component is installed at the end of the robotic arm, a turntable is installed at the output end of the rotating component, the image acquisition module and the laser emitter are installed on the turntable, and the optical axis of the image acquisition module coincides with the rotation path of the optical axis of the laser emitter on the turntable; when the image captured by the image acquisition module contains an obstacle, the controller controls the robotic arm to move so that the optical axis of the image acquisition module is aligned with the obstacle, and then controls the rotating component to drive the turntable to rotate a certain angle, so that the laser emitter rotates to the position of the image acquisition module, thereby realizing rapid aiming of the laser emitter and improving the aiming efficiency of the laser emitter.

[0013] In some embodiments, a communication module is also installed on the vehicle body, and the communication module is connected to the background monitoring center via wireless communication. The communication module is used to send the image information acquired by the image acquisition module and the operating status data of the vehicle body to the background monitoring center in real time, so as to facilitate the background monitoring center to monitor the operating status and obstacle removal effect of the laser obstacle remover in real time; when the operating status of the laser obstacle remover is abnormal or the obstacle removal effect is not good, the background monitoring center can also send control instructions to the controller through the communication module to adjust the operating status of the laser obstacle remover or repeat the obstacle removal operation; the vehicle body can also be remotely controlled by the background monitoring center to patrol along the laying direction of the overhead line. When an obstacle is detected on the overhead line, the laser transmitter can be moved by remotely controlling the robotic arm to perform the obstacle removal operation.

[0014] The second aspect of the present application provides a method for clearing obstacles, comprising the following steps:

[0015] Acquire image information of overhead lines through an image acquisition module;

[0016] Identify the position of obstacles based on the acquired image information;

[0017] According to the direction of the obstacle, the robot arm is controlled to move the laser transmitter so that the laser transmitter is aimed at the obstacle;

[0018] Control the laser transmitter to emit laser beam to clear obstacles.

[0019] In certain embodiments, when an obstacle is identified in an image, the distance from the obstacle to the image acquisition module is calculated based on the pixel distance between the two wires in the image and the distance between the two wires in actual space using the principle of similar triangles; the laser emitter is then moved to the position of the image acquisition module by a robotic arm, and the focal length of the laser emitted by the laser emitter is adjusted based on the calculated distance so that the laser beam emitted by the laser emitter is focused on the obstacle, thereby improving the efficiency and accuracy of laser obstacle removal.

[0020] In some embodiments, when an obstacle is identified in the image, an optimal obstacle removal path is planned for the obstacle in the image through a pre-trained neural network model, and the controller controls the robotic arm to move the laser transmitter according to the planned optimal obstacle removal path to perform obstacle removal operations;

[0021] The training process of the neural network model is as follows:

[0022] Collect a large amount of image data of overhead lines containing different obstacles to build a training set, and pre-process the images in the training set;

[0023] Mark the optimal obstacle-clearing path in the preprocessed image. The optimal obstacle-clearing path is the shortest obstacle-clearing path, and the optimal obstacle-clearing path needs to avoid the wires on the overhead lines.

[0024] The convolutional neural network is iteratively trained using the labeled training set to obtain the optimal obstacle clearance path planning model.

[0025] This application plans the optimal obstacle clearance path based on the shortest obstacle clearance path while training a neural network model, while avoiding the wires on overhead lines. This can not only avoid damage to the wires during laser obstacle clearance, but also shorten the laser obstacle clearance path to the maximum extent, thereby improving obstacle clearance efficiency and reducing laser energy consumption.

[0026] In certain embodiments, when it is recognized that the image of the overhead line does not contain an obstacle, the controller controls the vehicle body to automatically travel along the laying direction of the overhead line; automatically identifies whether the vehicle body deviates from the laying direction of the overhead line based on the position information of the wires in the image, and when the driving direction of the vehicle body is consistent with the laying direction of the overhead line, the two wires in the image are distributed in the central position; by calculating the distance between the two wires and the center line of the image, the offset of the driving direction of the vehicle body is obtained, and when the offset exceeds the set offset threshold, the vehicle body is controlled to automatically correct the driving direction.

[0027] 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

[0028] The drawings in this application are used to illustrate preferred embodiments, so that those skilled in the art can clearly understand various other advantages and benefits, and should not be considered as limitations of this application. In addition, the same reference numerals are used throughout the drawings to represent the same or similar components.

[0029] Figure 1 This is a structural schematic diagram of a vehicle-mounted intelligent laser obstacle remover in one embodiment of the present application;

[0030] Figure 2 This is a schematic diagram of the effect of adjusting different focal lengths by a focusing assembly in one embodiment of the present application;

[0031] Figure 3 This is a schematic diagram of the effect of planning an optimal obstacle-clearing path in an image in one embodiment of the present application;

[0032] Figure 4 This is a schematic diagram of the effect of correcting the driving direction of a vehicle body according to the distance between the wire in the image and the center line of the image in one embodiment of the present application;

[0033] Icons: 1. Vehicle body; 2. Image acquisition module; 3. Laser emitter; 4. Collimating lens group; 5. Focusing lens group; 6. Diverging lens group; 7. Base; 8. First joint arm; 9. Second joint arm; 10. Third joint arm; 11. Obstacle avoidance sensor; 12. Rotating part; 13. Turntable. DETAILED DESCRIPTION

[0034] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with specific embodiments. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0035] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0036] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two (including two), unless otherwise clearly and specifically defined.

[0037] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0038] In the description of the embodiments of the present application, the technical terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, which are only for the convenience of describing the embodiments of the present application and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the embodiments of the present application.

[0039] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0040] See also Figure 1-Figure 4 In a first aspect, an embodiment of the present application provides a vehicle-mounted intelligent laser obstacle clearer, comprising a vehicle body 1, on which is mounted a controller and an image acquisition module 2 connected to the controller, a mechanical arm and a laser emitter 3, wherein the laser emitter 3 is mounted at the end of the mechanical arm; the image acquisition module 2 is used to acquire image information of the overhead line, the controller identifies and locates obstacles on the overhead line according to the acquired image information, and controls the movement of the mechanical arm according to the position information of the obstacle, so that the laser emitter 3 aims at the obstacle to perform obstacle clearance operations.

[0041] In the technical solution provided in the present application, the image information of the overhead line is automatically acquired through the image acquisition module 2, the obstacles on the overhead line are automatically identified and located according to the image information, and the robotic arm is controlled to move the laser transmitter 3 to realize automatic aiming and obstacle clearance operations for the obstacles; there is no need for manual observation and aiming of obstacles with the naked eye, which improves the efficiency and accuracy of laser obstacle clearance and reduces the intensity of manual labor.

[0042] In some embodiments, the laser transmitter 3 includes a laser, a laser head and a focusing assembly. The laser is mounted on the vehicle body 1, and the laser head and the focusing assembly are mounted at the end of the robotic arm. The output end of the laser is connected to the input end of the focusing assembly through an optical fiber, and the output end of the focusing assembly is connected to the input end of the laser head; the focusing assembly is connected to a controller, and the controller controls the focusing assembly to adaptively adjust the focal length of the laser according to the distance between the obstacle and the laser head; by installing the laser and the laser head separately, the load on the end of the robotic arm can be reduced, and the accuracy and stability of the aiming of the robotic arm's moving laser head can be improved; by arranging the focusing assembly at the front end of the laser head, the focal length of the laser can be automatically adjusted according to the distance between the obstacle and the laser head, so that the laser spot is focused on the obstacle, thereby improving the accuracy and efficiency of laser obstacle removal.

[0043] Please continue reading Figure 2 In some embodiments, the focusing assembly includes a collimating lens group 4, a focusing lens group 5 (a convex lens may be used) and a diverging lens group 6 (a concave lens may be used) which are sequentially arranged along the optical axis. The collimating lens group 4 is fixedly installed at the input end of the focusing assembly, and the focusing lens group 5 and / or the diverging lens group 6 are slidably installed at the output end of the focusing assembly. The focusing assembly also includes a driving component, and the driving component is used to drive the focusing lens group 5 and / or the diverging lens group 6 to slide along the optical axis straight line, thereby changing the distance between the focusing lens group 5 and the diverging lens group 6 to achieve focal length adjustment of the emitted laser beam; the collimating lens group 4 is used to collimate the diverging light output from the output coupling end of the optical fiber into a parallel light beam, the focusing lens group 5 is used to focus the collimated parallel light beam, and the diverging lens group 6 is used to diverge the focused light beam, so as to adjust the focal length of the laser beam so that the laser can be focused farther, and at the same time, it is convenient to adjust the focal length of the laser to a large extent by fine-tuning the distance between the focusing lens group 5 and the diverging lens group 6, thereby reducing the volume of the focusing assembly.

[0044] In a specific embodiment, the focusing lens group 5 and the diverging lens group 6 are respectively installed in two lens barrels, and the two lens barrels can be slidably connected or threadedly connected. The driving component can adopt a telescopic motor or a rotating motor, and the spacing between the focusing lens group 5 and the diverging lens group 6 can be adjusted by driving the two lens barrels to slide axially or rotate in / out circumferentially.

[0045] like Figure 2As shown in (a) to (c), in a specific embodiment, the farther the distance between the focusing lens group 5 and the diverging lens group 6 is, the closer the distance between the laser spot and the laser head is. There is a linear correlation between the distance between the focusing lens group 5 and the diverging lens group 6 and the laser focal length. By adjusting the distance between the focusing lens group 5 and the diverging lens group 6, the laser focal length can be adjusted to match the distance from the obstacle to the laser head.

[0046] Please continue reading Figure 1 In some embodiments, the robotic arm includes a base 7, a first joint arm 8, a second joint arm 9 and a third joint arm 10 connected in sequence, one end of the first joint arm 8 is rotationally connected to the base 7 through an azimuth joint, and the first joint arm 8, the second joint arm 9 and the third joint arm 10 are rotationally connected through a pitch joint respectively, and the laser emitter 3 is installed at the end of the third joint arm 10.

[0047] Please continue reading Figure 1 In some embodiments, the vehicle body 1 is an unmanned vehicle, and obstacle avoidance sensors 11 are arranged around the vehicle body 1 (sensors with ranging function such as ultrasonic ranging probes, infrared ranging probes or laser ranging probes can be used); the controller controls the vehicle body 1 to automatically travel along the laying direction of the overhead line according to the image information of the overhead line obtained by the image acquisition module 2; by arranging obstacle avoidance sensors 11 around the vehicle body 1, automatic obstacle avoidance of the vehicle body 1 on the inspection path can be achieved; according to the acquired image information of the overhead line, the vehicle body 1 can be controlled to automatically travel along the laying direction of the overhead line, realizing truly intelligent inspection and obstacle removal operations, without the need for staff to follow the vehicle body 1 for inspection and obstacle removal, reducing the intensity of manual labor and improving the intelligence of the vehicle-mounted laser obstacle remover.

[0048] Please continue reading Figure 1 In some embodiments, a rotating component 12 (a rotating motor may be used) is installed at the end of the robotic arm, a turntable 13 is installed at the output end of the rotating component 12, the image acquisition module 2 and the laser emitter 3 are installed on the turntable 13, and the optical axis of the image acquisition module 2 coincides with the rotation path of the optical axis of the laser emitter 3 on the turntable 13; when the image captured by the image acquisition module 2 contains an obstacle, the controller controls the robotic arm to move so that the optical axis of the image acquisition module 2 is aligned with the obstacle, and then controls the rotating component 12 to drive the turntable 13 to rotate a certain angle, so that the laser emitter 3 rotates to the position of the image acquisition module 2, thereby realizing rapid aiming of the laser emitter 3 and improving the aiming efficiency of the laser emitter 3.

[0049] In some embodiments, a communication module is also installed on the vehicle body 1, and the communication module is connected to the background monitoring center through wireless communication. The communication module is used to send the image information obtained by the image acquisition module 2 and the operating status data of the vehicle body 1 to the background monitoring center in real time, so as to facilitate the background monitoring center to monitor the operating status and obstacle removal effect of the laser obstacle remover in real time; when the operating status of the laser obstacle remover is abnormal or the obstacle removal effect is not good, the background monitoring center can also send control instructions to the controller through the communication module to adjust the operating status of the laser obstacle remover or repeat the obstacle removal operation; the vehicle body 1 can also be remotely controlled by the background monitoring center to patrol along the laying direction of the overhead line. When an obstacle is detected on the overhead line, the laser emitter 3 can be moved by remotely controlling the robotic arm to perform the obstacle removal operation.

[0050] In a specific embodiment, an alarm (which may be an audible and visual alarm) is also installed on the vehicle body 1. When the laser transmitter 3 is performing an obstacle removal operation, the controller controls the alarm to respond to the audible and visual alarm to prompt nearby people or animals to stay away.

[0051] In a specific implementation, the image acquisition module 2 may use a high-definition camera.

[0052] A second aspect of the embodiment of the present application provides an obstacle removal method, comprising the following steps:

[0053] Acquire image information of the overhead line through the image acquisition module 2;

[0054] Identify the position of obstacles based on the acquired image information;

[0055] According to the position of the obstacle, the robot arm is controlled to move the laser emitter 3 so that the laser emitter 3 is aimed at the obstacle;

[0056] The laser transmitter 3 is controlled to emit a laser beam to clear obstacles.

[0057] In some embodiments, when an obstacle is identified in the image, the distance from the obstacle to the image acquisition module 2 is calculated based on the pixel distance between the two wires in the image and the distance between the two wires in the actual space using the principle of similar triangles; the laser emitter 3 is then moved to the position of the image acquisition module 2 by a robotic arm, and the focal length of the laser emitted by the laser emitter 3 is adjusted according to the calculated distance so that the laser beam emitted by the laser emitter 3 is focused on the obstacle, thereby improving the efficiency and accuracy of laser obstacle removal.

[0058] In a specific implementation, the distance from the obstacle to the image acquisition module 2 is calculated based on the pixel distance between the two wires in the image and the distance between the two wires in the actual space using the principle of similar triangles. This distance is actually the distance from the wires on the overhead line to the image acquisition module 2. In general, this distance is assumed to be equal to the distance from the obstacle to the image acquisition module 2. However, when there is an "obstruction" between the image acquisition module and the wires or there is a "background object" above the wires, the "obstruction" or "background object" is easily misidentified as an obstacle, and the misidentified obstacle cannot be removed. At this time, the distance calculated using the above-mentioned principle of similar triangles is not equal to the actual distance from the "obstruction" or "background object" to the image acquisition module 2. The actual distance between the "obstruction" and the image acquisition module 2 should be less than the calculated distance, and the "background object" The actual distance between the "background object" and the image acquisition module 2 should be greater than the calculated distance; based on this, after identifying the obstacle, this embodiment can also determine whether the obstacle is a misjudgment. The judgment method is: adjust the wavelength emitted by the laser to the visible light range, reduce the emission power of the laser, adjust the focal length of the laser according to the calculated distance between the wire and the image acquisition module, irradiate the laser onto the obstacle, and then obtain the image of the obstacle through the image acquisition module 2. According to the size of the light spot in the image, it is determined whether the laser is focused on the obstacle. If the diameter of the light spot is within the preset range, it means that the laser is focused on the obstacle, and it can be determined that the obstacle is located on the wire of the overhead line; if the diameter of the light spot exceeds the preset range, it means that the laser is not focused on the obstacle, and it can be determined that the obstacle is an "obstruction" or "background object", and there is no need to perform obstacle clearance operations.

[0059] In some embodiments, when an obstacle is identified in the image, an optimal obstacle removal path is planned for the obstacle in the image through a pre-trained neural network model, and the controller controls the robotic arm to move the laser transmitter 3 according to the planned optimal obstacle removal path to perform obstacle removal operations;

[0060] The training process of the neural network model is as follows:

[0061] Collect a large amount of image data of overhead lines containing different obstacles to build a training set, and preprocess the images in the training set, including image magnification, cropping, rotation, resolution adjustment, color optimization and other operations;

[0062] The optimal obstacle-clearing path is marked in the preprocessed image. The optimal obstacle-clearing path is the shortest obstacle-clearing path, and the optimal obstacle-clearing path needs to avoid the wires on the overhead lines; Figure 3 As shown, Figure 3 The two black “thick lines” in the middle are electric wires, the irregular area between the two wires represents an obstacle, and the dotted line in the middle of the obstacle is the optimal obstacle-clearing path;

[0063] The convolutional neural network is iteratively trained using the labeled training set to obtain the optimal obstacle clearance path planning model.

[0064] This application plans the optimal obstacle clearance path based on the shortest obstacle clearance path while training a neural network model, while avoiding the wires on overhead lines. This can not only avoid damage to the wires during laser obstacle clearance, but also shorten the laser obstacle clearance path to the maximum extent, thereby improving obstacle clearance efficiency and reducing laser energy consumption.

[0065] In some embodiments, when an obstacle is detected in an image, the optimal obstacle-clearing path can be planned by the following method:

[0066] The contour extraction algorithm is used to obtain the contour information of the obstacle, and the contour information of the upper and lower edges adjacent to the obstacle and the wire is obtained. The coordinate information of each point on the upper and lower edges in the image coordinate system is determined, and the contours on the upper and lower edges whose distance from the wire is less than the set safety distance are eliminated (to prevent accidental damage to the wire during laser obstacle removal). Then, a pixel point on one of the edges is selected as the starting point, and a pixel point on the other edge is selected as the end point, and the distance from the starting point to the end point is calculated; the distances from all starting points to the end points on the upper and lower edges are traversed, and the start-end point path with the shortest distance is selected as the optimal obstacle removal path; this method can also automatically plan the optimal obstacle removal path with the shortest obstacle removal path and no damage to the wire.

[0067] In a specific embodiment, after the controller obtains the optimal obstacle clearance path, the controller controls the robotic arm to move the image acquisition module 2 so that the center point of the image coincides with the starting point of the optimal obstacle clearance path; then the rotating component 12 is controlled to rotate a corresponding angle so that the laser head rotates to the position of the image acquisition module 2. At this time, the light spot of the laser emitted by the laser head coincides with the starting point of the optimal obstacle clearance path, and then the focal length of the laser is adjusted according to the distance between the obstacle and the laser head so that the laser is focused on the starting point of the optimal obstacle clearance path. Then, the robotic arm is controlled to move the laser head according to the optimal obstacle clearance path so that the laser emitted by the laser head clears the obstacle along the optimal obstacle clearance path.

[0068] In some embodiments, when it is recognized that the image of the overhead line does not contain obstacles, the controller controls the vehicle body 1 to automatically travel along the laying direction of the overhead line (the azimuth of the image acquisition module 2 is always consistent with the azimuth of the vehicle body 1); automatically identify whether the vehicle body 1 deviates from the laying direction of the overhead line according to the position information of the wire in the image. When the driving direction of the vehicle body 1 is consistent with the laying direction of the overhead line, the two wires in the image are distributed in the central position; by calculating the distance between the two wires and the center line of the image (i.e. Figure 4 The distance between the vehicle body 1 and the dashed line is obtained to obtain the offset of the driving direction of the vehicle body 1. When the offset exceeds the set offset threshold d, the vehicle body 1 is controlled to automatically correct the driving direction.

[0069] Please continue to refer to Figure 4 , in a specific embodiment, the distance between the left wire and the center line of the image in the image is a, and the distance between the right wire and the center line of the image is b. When |a - b| ≤ d, it indicates that the driving direction of the vehicle body 1 does not deviate from the laying direction of the overhead line, as shown in Figure 4 (b) in; when |a - b| > d and a > b, it indicates that the driving direction of the vehicle body 1 deviates to the right from the laying direction of the overhead line, as shown in Figure 4 (a) in, and it is necessary to control the vehicle body 1 to turn left by a certain angle; when |a - b| > d and a < b, it indicates that the driving direction of the vehicle body 1 deviates to the left from the laying direction of the overhead line, as shown in Figure 4 (c) in, and it is necessary to control the vehicle body 1 to turn right by a certain angle.

[0070] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and they should all be covered by the scope of the claims and the description of the present application. In particular, as long as there is no conflict, the technical features mentioned in each embodiment can be combined in any way. The present application is not limited to the specific embodiments disclosed in the text, but includes all technical solutions falling within the scope of the claims.

Claims

1. An obstacle removal method, applied to a vehicle-mounted intelligent laser obstacle removal device, characterized in that: The intelligent laser obstacle remover comprises a vehicle body (1), on which a controller and an image acquisition module (2) connected to the controller, a mechanical arm and a laser emitter (3) are mounted, wherein the laser emitter (3) is mounted at the end of the mechanical arm; the image acquisition module (2) is used to acquire image information of the overhead line, the controller identifies and locates obstacles on the overhead line according to the acquired image information, and controls the movement of the mechanical arm according to the position information of the obstacle, so that the laser emitter (3) is aimed at the obstacle to perform an obstacle removal operation; The obstacle removal method comprises the following steps: Acquiring image information of the overhead line through an image acquisition module (2); Identify the position of obstacles based on the acquired image information; Controlling the mechanical arm to move the laser emitter (3) according to the direction of the obstacle so that the laser emitter (3) is aimed at the obstacle; Controlling the laser transmitter (3) to emit a laser beam to clear obstacles; When an obstacle is detected in the image, the following method is used to determine whether the obstacle is a false positive: The wavelength emitted by the laser is adjusted to be within the visible light range, the emission power of the laser is reduced, the focal length of the laser is adjusted according to the calculated distance between the electric wire and the image acquisition module, the laser is irradiated onto the obstacle, and the image of the obstacle is acquired through the image acquisition module (2), and the size of the light spot in the image is used to determine whether the laser is focused on the obstacle. If the diameter of the light spot is within a preset range, it indicates that the laser is focused on the obstacle, and it is determined that the obstacle is located on the electric wire of the overhead line; if the diameter of the light spot exceeds the preset range, it indicates that the laser is not focused on the obstacle, and it is determined that the obstacle is an "obstruction" or a "background object", and no obstacle clearance operation is required; When an obstacle is detected in the image, the optimal obstacle-clearing path is planned using the following methods: The contour extraction algorithm is used to obtain the contour information of the obstacle, and the contour information of the upper and lower sides of the obstacle intercepted by the two wires is obtained. The coordinate information of each point on the upper and lower sides in the image coordinate system is determined, and the contours on the upper and lower sides whose distance from the wires is less than the set safety distance are eliminated. Then, a pixel point on one of the edges is selected as the starting point, and a pixel point on the other edge is selected as the end point, and the distance from the starting point to the end point is calculated; the distances from all starting points to the end points on the upper and lower edges are traversed, and the start-end point path with the shortest distance is selected as the optimal obstacle clearance path.

2. The obstacle removal method according to claim 1, characterized in that: The laser transmitter (3) comprises a laser, a laser head and a focusing assembly. The laser is mounted on a vehicle body (1). The laser head and the focusing assembly are mounted at the end of a mechanical arm. The output end of the laser is connected to the input end of the focusing assembly via an optical fiber. The output end of the focusing assembly is connected to the input end of the laser head. The focusing assembly is connected to a controller. The controller controls the focusing assembly to adaptively adjust the focal length of the laser according to the distance between the obstacle and the laser head.

3. The obstacle removal method according to claim 2, characterized in that: The focusing assembly comprises a collimating lens group (4), a focusing lens group (5) and a diverging lens group (6) which are sequentially arranged along the optical axis; the collimating lens group (4) is fixedly mounted on the input end of the focusing assembly; the focusing lens group (5) and / or the diverging lens group (6) are slidably mounted on the output end of the focusing assembly; the focusing assembly further comprises a driving component, which is used to drive the focusing lens group (5) and / or the diverging lens group (6) to slide linearly along the optical axis.

4. The obstacle removal method according to claim 1, characterized in that: The mechanical arm comprises a base (7), a first joint arm (8), a second joint arm (9) and a third joint arm (10) which are connected in sequence, one end of the first joint arm (8) is rotationally connected to the base (7) via an azimuth joint, the first joint arm (8) and the second joint arm (9) are rotationally connected via a pitch joint, and the second joint arm (9) and the third joint arm (10) are rotationally connected via a pitch joint.

5. The obstacle removal method according to claim 1, characterized in that: The vehicle body (1) is an unmanned vehicle, and obstacle avoidance sensors (11) are arranged on all four sides of the vehicle body (1); the controller controls the vehicle body (1) to automatically travel along the laying direction of the overhead line based on image information of the overhead line acquired by the image acquisition module (2).

6. The obstacle removal method according to claim 1, characterized in that: A rotating component (12) is installed at the end of the mechanical arm, a turntable (13) is installed at the output end of the rotating component (12), the image acquisition module (2) and the laser emitter (3) are installed on the turntable (13), and the optical axis of the image acquisition module (2) and the optical axis of the laser emitter (3) coincide with the rotation path of the turntable (13).

7. The obstacle removal method according to claim 1, characterized in that: When an obstacle is identified in the image, the distance from the obstacle to the image acquisition module (2) is calculated using the principle of similar triangles based on the pixel distance between the two wires in the image and the distance between the two wires in real space; the laser emitter (3) is then moved to the position of the image acquisition module (2) by a mechanical arm, and the focal length of the laser emitted by the laser emitter (3) is adjusted based on the calculated distance.

8. The obstacle removal method according to claim 1, characterized in that: When it is identified that the image of the overhead line does not contain an obstacle, the controller controls the vehicle body (1) to automatically travel along the laying direction of the overhead line; automatically identifies whether the vehicle body (1) deviates from the laying direction of the overhead line based on the position information of the wire in the image; when the driving direction of the vehicle body (1) is consistent with the laying direction of the overhead line, the overhead line including the two wires is set at the center of the image; by calculating the distance between the two wires and the center line of the image, the offset of the driving direction of the vehicle body (1) is obtained; when the offset exceeds a set offset threshold, the vehicle body (1) is controlled to automatically correct the driving direction.

Images