Autonomous operation method and system of underground coal mine roadway repairing robot

Abstract

The invention provides an autonomous operation method and system for a coal mine underground roadway repair robot, and the method comprises the steps: positioning a deformation region based on roadway three-dimensional point cloud data collected by a plurality of laser radars, and planning a navigation path according to the position information of the deformation region; detecting whether an exposed anchor rod exists in the deformation area or not through a first camera, if yes, cooperatively positioning the exposed anchor rod through a plurality of laser radars and the first camera, and controlling an auxiliary arm and a shearing clamp to shear; an operation mechanical arm and a breaking hammer are controlled to break the deformation area, float coal on a roadway bottom plate is recognized through a plurality of laser radars, and the operation mechanical arm and a bucket are controlled to gradually clean the float coal; and the repairing robot is controlled to run forwards to clean the step pitch, the anchor rod missing position is detected through a second camera, and the anchor rod drilling machine is controlled to drive an anchor rod to the anchor rod missing position. According to the method, accurate control over the whole process of roadway repairing operation is achieved, and the intelligence, the high efficiency and the safety of roadway repairing are improved.

Description

Technical Field

[0001] The present application relates to the technical field of underground tunnel repair, and in particular to an autonomous operation method and system of a coal mine underground tunnel repair robot. Background Art

[0002] At present, various operations in coal mines may cause deformation of the tunnels, affecting the safety of underground work and requiring repair.

[0003] In related technologies, underground tunnel repair primarily relies on manual labor. Most deformed tunnels are repaired using manually operated mechanical equipment such as pneumatic picks, excavators, and conventional excavators. However, these manual repair methods are extremely labor-intensive and lack a systematic approach, resulting in long repair cycles, low repair efficiency, and high repair costs. Furthermore, during the manual repair process, workers must handle anchor bolts and broken surrounding rock at close range within the deformation risk zone, posing significant safety risks.

[0004] Therefore, how to control the tunnel repair equipment to perform intelligent and autonomous repair operations has become an urgent problem that needs to be solved. Summary of the Invention

[0005] The present application aims to solve one of the technical problems in the related art at least to a certain extent.

[0006] To this end, the first objective of this application is to propose an autonomous operation method for a coal mine tunnel repair robot. This method, through autonomous sensing using multiple detection devices on the repair robot, enables precise control of the entire tunnel repair process, improving the intelligence, efficiency, and safety of tunnel repair. This method addresses issues such as the high manual dependency of tunnel repair equipment and the low level of automation and intelligence in some functions.

[0007] The second purpose of this application is to propose an autonomous operation system for a coal mine underground tunnel repair robot.

[0008] A third object of the present application is to provide a non-transitory computer-readable storage medium.

[0009] To achieve the above objectives, the first aspect of the present application is to provide an autonomous operation method for a coal mine tunnel repair robot, wherein the cleaning robot includes: multiple laser radars, a first camera, a second camera, an operating robot arm, an auxiliary arm, a shear clamp, a breaker hammer, a bucket, and an airborne anchor drill. The method includes the following steps:

[0010] Based on the three-dimensional point cloud data of the roadway collected by the multiple laser radars, the deformed area to be repaired is located and the position information of the deformed area is obtained, and a navigation path is planned according to the position information, and the repair robot is controlled to travel to the working position along the navigation path;

[0011] detecting, by the first camera, whether there is an exposed anchor rod in the deformation area; if there is an exposed anchor rod, collaboratively locating the exposed anchor rod by the multiple laser radars and the first camera; and controlling the auxiliary arm and the shearing clamp to shear the exposed anchor rod based on the anchor rod locating result;

[0012] Controlling the operating robot arm and the breaker hammer to crush the deformed area without exposed anchor rods, and identifying floating coal on the roadway floor through the multiple laser radars, and controlling the operating robot arm and the bucket to gradually clean the floating coal based on the floating coal identification results;

[0013] After the floating coal is cleaned, the repair robot is controlled to move forward a preset cleaning step, and the second camera is used to detect the missing anchor position on the coal wall surface, and the airborne anchor drill is controlled to drive the anchor to the missing anchor position.

[0014] Optionally, in one embodiment of the present application, after locating the deformed area to be repaired and obtaining the position information of the deformed area, it also includes: detecting the deformation degree of the deformed area, and determining whether the deformation degree exceeds the safety threshold; when the deformation degree exceeds the safety threshold, controlling the repair robot to suspend operation and report warning information.

[0015] Optionally, in one embodiment of the present application, the collaborative positioning of the exposed anchor rod by the multiple laser radars and the first camera includes: performing point cloud registration processing on the point cloud data of the exposed anchor rod collected by the multiple laser radars and the first camera to obtain three-dimensional posture information of the exposed anchor rod; controlling the auxiliary arm and the shear clamp to shear the exposed anchor rod based on the anchor rod positioning result includes: planning the motion trajectory of the auxiliary arm through an inverse kinematics algorithm based on the three-dimensional posture information, and according to the motion trajectory, the auxiliary arm drives the shear clamp to move to the target working point to shear the exposed anchor rod; in the case that there are remaining exposed anchor rods in the deformation area, repeating the anchor rod positioning and autonomous shearing until there are no exposed anchor rods in the deformation area.

[0016] Optionally, in one embodiment of the present application, the controlling of the operating robot arm and the breaker hammer to crush the deformed area without exposed anchor rods includes: based on a force-position hybrid control strategy, controlling the operating robot arm to dynamically adjust the impact frequency and impact angle of the breaker hammer to drive the breaker hammer to perform crushing operations.

[0017] Optionally, in one embodiment of the present application, the identifying of floating coal on the tunnel floor by the multiple laser radars includes: identifying a floating coal accumulation area and determining the floating coal position coordinates from the tunnel floor point cloud data collected by the multiple laser radars through a density clustering algorithm; controlling the operating robot arm and the bucket to gradually clean the floating coal based on the floating coal identification result includes: planning the motion trajectory of the operating robot arm according to the floating coal position coordinates, and driving the bucket to shovel the floating coal to the side belt conveyor according to the motion trajectory by the operating robot arm; after each round of shoveling, evaluating the remaining coal amount in the floating coal accumulation area, and if the remaining coal amount does not meet the standard, re-determining the floating coal position coordinates and planning the motion trajectory of this round of shoveling task.

[0018] Optionally, in one embodiment of the present application, the repair robot also includes a chassis and multiple detection devices, and controlling the repair robot to move forward a preset cleaning step includes: combining the feedback data of the multiple laser radars and the multiple detection devices to correct the travel direction of the repair robot in real time, wherein the repair robot is driven by the chassis; and avoiding obstacles encountered during driving through a dynamic avoidance algorithm.

[0019] Optionally, in one embodiment of the present application, the detecting of the missing anchor position on the coal wall surface by the second camera includes: locating the position coordinates of the anchor tray on the coal wall surface by the second camera, and determining the coordinates of the missing anchor position based on the position coordinates of the anchor tray and the missing area position; before controlling the airborne anchor drill to drive the anchor toward the missing anchor position, it also includes: adjusting the posture of the airborne anchor drill according to the coordinates of the missing anchor position.

[0020] To achieve the above objectives, the second aspect of the present application further proposes an autonomous operation system for a coal mine tunnel repair robot, wherein the repair robot comprises: multiple laser radars, a first camera, a second camera, an operating manipulator arm, an auxiliary arm, a shear clamp, a breaker hammer, a bucket, and an airborne anchor drill. The system comprises the following modules:

[0021] a positioning module, configured to locate the deformed area to be repaired and obtain position information of the deformed area based on the three-dimensional point cloud data of the roadway collected by the multiple laser radars, plan a navigation path according to the position information, and control the repair robot to travel to a working position;

[0022] a shearing module, configured to detect whether there is an exposed anchor rod in the deformation area by using the first camera; if an exposed anchor rod is present, collaboratively locate the exposed anchor rod by using the multiple laser radars and the first camera; and control the auxiliary arm and the shearing clamp to shear the exposed anchor rod based on the anchor rod positioning result;

[0023] A crushing and coal shoveling module is used to control the operating robot arm and the breaker hammer to crush the deformed area without exposed anchor bolts, identify floating coal on the roadway floor through the multiple laser radars, and control the operating robot arm and the bucket to gradually remove the floating coal based on the floating coal identification results;

[0024] The anchoring module is used to control the repair robot to move forward a preset cleaning step after the floating coal is cleaned, and to detect the missing anchor position on the coal wall surface through the second camera, and control the airborne anchor drill to drive the anchor to the missing anchor position.

[0025] In order to implement the above embodiments, the third aspect embodiment of the present application also proposes a non-temporary computer-readable storage medium, on which a computer program is stored. When the computer program is executed by the processor, the autonomous operation method of the coal mine underground tunnel repair robot in the above first aspect is implemented.

[0026] The technical solutions provided by the embodiments of this application provide at least the following beneficial effects: This application first locates the deformed area using point cloud data collected by a laser radar, then uses the front camera's recognition results to shear the exposed anchor bolts, then crushes the deformed area, then removes the loose coal using the laser radar's recognition results, and finally installs the anchor bolts using the rear camera's recognition results. Thus, based on a multi-sensor fusion system consisting of multiple laser radars, multiple cameras, and an IMU, this application can achieve full-process autonomous and intelligent operation of the tunnel repair robot. Autonomous operation by the repair robot reduces labor intensity, while precise control through fully automated equipment improves tunnel repair efficiency and ensures the accuracy of repair operations. Furthermore, the unmanned repair method reduces the risk of tunnel repair operations and ensures the safety of workers. The tunnel cleaning robot in this application makes operational decisions based entirely on environmental perception information, improving tunnel repair efficiency, enhancing the intelligence level of underground tunnel repair equipment, and promoting safety upgrades in underground operations. As a result, this application improves the intelligence, efficiency, and safety of tunnel repair.

[0027] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0029] Figure 1 This is a flow chart of an autonomous operation method of a coal mine tunnel repair robot proposed in an embodiment of the present application;

[0030] Figure 2 This is the structural intention of a tunnel repair robot proposed in an embodiment of the present application;

[0031] Figure 3 A schematic diagram of a specific laneway repair process proposed in an embodiment of the present application;

[0032] Figure 4 This is a schematic structural diagram of an autonomous operation system of a coal mine underground tunnel repair robot proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0033] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and are not to be construed as limiting the present invention.

[0034] It should be noted that the manual repair methods used in related technologies lack a systematic approach to the repair process, making it impossible to simultaneously complete deformation monitoring, precise cleaning, and support reinforcement, resulting in low repair efficiency. Although some automated equipment has been employed for repair in some relevant embodiments, the following issues remain: First, the repair equipment's functionality is limited and its adaptability is insufficient. Some automated systems only provide basic crushing and loading functions, requiring manual operation to clean floating coal from the floor. This makes it impossible to shear anchor bolts from the sidewalls, identify deformed areas, or maintain surrounding rock stability. Furthermore, the equipment design is not adapted to the complex geological conditions found underground, and its high cost makes it difficult to implement on a large scale. Second, the equipment's automation level is low. Current roadway cleaning machines focus on floor cleaning and rely on manual assistance to complete sidewall anchor bolt processing and repair of deformed areas. The equipment lacks autonomous perception and decision-making capabilities, and key processes such as deformation monitoring, target identification and positioning, path planning and obstacle avoidance, and surrounding rock stability maintenance have yet to be intelligently implemented, limiting operational accuracy and efficiency.

[0035] To this end, this application proposes an autonomous operation method and system for a coal mine underground tunnel repair robot, which breaks through core technologies such as autonomous perception, precise operation and full-process closed-loop control, and can achieve unmanned, efficient and safe upgrades to tunnel repair.

[0036] The following describes an autonomous operation method and system of a coal mine underground tunnel repair robot proposed in an embodiment of the present application with reference to the accompanying drawings.

[0037] Figure 1 This is a flow chart of an autonomous operation method of a coal mine tunnel repair robot proposed in an embodiment of the present application, such as Figure 1 As shown, the method includes the following steps:

[0038] In step S101, based on the three-dimensional point cloud data of the tunnel collected by multiple laser radars, the deformed area to be repaired is located and the position information of the deformed area is obtained. A navigation path is planned according to the position information, and the repair robot is controlled to travel to the working position along the navigation path.

[0039] Specifically, when a deformed area in an underground tunnel needs to be repaired, the tunnel repair robot is first activated and the robot's multiple laser radars are used to perform dynamic scanning to detect the deformed area in the tunnel. The repair robot targeted by this application includes at least: multiple laser radars, a first camera, a second camera, an operating manipulator arm, an auxiliary arm, shears, a breaker hammer, a bucket, and an airborne anchor drill.

[0040] In one embodiment of the present application, Figure 2 As shown, the tunnel repair robot targeted by this application includes: a first laser radar 1, a second laser radar 2, a first camera 3, a second camera 4, an operating robot arm 5, an auxiliary arm 6, a shearing clamp 7, a breaker hammer 8, a bucket 9, an airborne anchor drill 10, a standing platform 11, a chassis 12 and a power system 13. This embodiment uses two laser radars and two cameras as an example. In actual applications, the number of laser radars and cameras can be determined as needed, and each laser radar and camera can be installed in a position convenient for scanning. Among them, as Figure 2 As shown, the first camera 3 is a camera set in front of the robot for photographing the front area, and the second camera 4 is a rear camera for identifying the rear area of ​​the robot.

[0041] In order to more clearly describe the specific process of the lane repair robot of the present application for lane repair, the following is combined with the examples proposed in the present application. Figure 3 The operation process shown in FIG is exemplified. Specifically, Figure 3 As shown in the figure, when the repair robot operates autonomously, it first powers on the entire robot. After powering on, each module in the robot is initialized synchronously, automatically completing hardware self-tests and sensor calibration. This includes initializing the lidar, vision camera, and robotic arm drive modules, putting each subsystem into standby mode.

[0042] Furthermore, the robot conducts lane scanning modeling and environmental perception. Multiple laser radars onboard the robot scan the lane ahead in real time, generating centimeter-level precision 3D point cloud data. This collected point cloud data is then analyzed to construct a lane point cloud map.

[0043] As a possible implementation approach, a simultaneous localization and mapping SLAM algorithm is first combined to construct a real-time roadway geometry model. This is then synchronized with feedback from the robot's inertial measurement unit (IMU) to correct for offsets in point cloud acquisition and data calculations. This dynamically updated global map ensures that the roadway global map is consistent with the actual environment, providing an environmental benchmark for subsequent operations.

[0044] Specifically, the laser radar of this embodiment continuously scans at different angles to obtain scanning frames at different times. The SLAM algorithm is then used to match and fuse the scanning frames with different time stamps, eliminate motion distortion, and construct a high-precision global point cloud map of the alley. Then, by repairing the feedback data of multiple detection devices in the robot, the posture of the cleaning robot is corrected, including: dynamically correcting the posture offset of the cleaning robot based on the data fed back by the odometer and inertial measurement unit (IMU) of the cleaning robot. Then, based on the posture correction result, the alley point cloud map is recalculated and updated to generate an accurate global map of the alley.

[0045] Furthermore, deformation area extraction and positioning are performed. Based on the obtained global map data of the tunnel, the plane extraction algorithm is used to identify the maximum deformation area of ​​the tunnel wall (i.e., the local collapse area), and the position information of the deformation area, such as the boundary coordinates of the deformation area, is extracted.

[0046] As a possible implementation method, the RANSAC algorithm can be used to segment the preprocessed roadway point cloud model into multiple planar regions that make up the roadway. The geometric structures of these planar regions are then clustered using a clustering algorithm. The largest cluster is selected from the resulting clusters, and the plane corresponding to the largest cluster is used as the region with the largest deformation. The contour of the detected deformed region and its boundary coordinates are then extracted. For example, the deformed region can be projected onto a two-dimensional plane, and a convex hull fit is performed on the point set on the two-dimensional plane to obtain multiple convex polygons. The smallest convex polygon is then used as the contour of the deformed region. The mid-coordinates of the contour in two-dimensional planes and three-dimensional space are then analyzed to obtain the boundary coordinates of the deformed region.

[0047] Furthermore, the navigation path of the repair robot can be planned according to the coordinate position information of the deformation area, and the repair robot can be controlled to travel along the navigation path to the working position for subsequent repair operations.

[0048] As one possible implementation, the coordinates of the location where the repair work will be performed are determined based on the coordinates of the deformed area. These coordinates serve as the target coordinates for the robot's navigation endpoint. Real-time path planning is then performed based on the robot's starting and target coordinates, along with actual factors such as the underground tunnel's geographic information and equipment information. The repair robot is then navigated to the target coordinates along the optimal planned path.

[0049] Based on the above embodiments, to ensure the safety of the repair robot during repair operations, it is also possible to determine whether the deformed area of ​​the roadway supports autonomous robot operation. In one embodiment of the present application, after locating the deformed area to be repaired and obtaining the position information of the deformed area, the following further comprises: detecting the degree of deformation of the deformed area and determining whether the deformation exceeds a safety threshold; if the deformation exceeds the safety threshold, controlling the repair robot to suspend operations and reporting a warning message.

[0050] Specifically, in this embodiment, the degree of deformation of a deformed area can be detected by various methods, such as calculating the difference between the real-time coordinates of the deformed area's boundary and the coordinates of the area's boundary before the deformation occurred. If the degree of deformation exceeds a preset safety threshold, it indicates that the roadway currently poses a significant safety hazard and is unsuitable for repair work. The repair robot is then controlled to suspend operations, and an alert is sent to a remote control center via the robot's communication system, indicating that the roadway is currently dangerous so that relevant safety measures can be taken promptly.

[0051] Step S102: Use the first camera to detect whether there are exposed anchor rods in the deformation area. If there are exposed anchor rods, multiple laser radars and the first camera are used to collaboratively locate the exposed anchor rods, and based on the anchor rod positioning results, the auxiliary arm and the shear clamp are controlled to shear the exposed anchor rods.

[0052] Specifically, when the repair robot performs a repair operation, it first detects exposed anchors and autonomously cuts them. The first camera detects whether there are exposed anchors within the deformation area. If no exposed anchors are present, the robot proceeds directly to step S103. If exposed anchors are present, the robot uses multiple laser radars and the first camera to collaboratively locate the exposed anchors.

[0053] In one embodiment of the present application, the exposed anchor rod is collaboratively located by multiple laser radars and a first camera, including: performing point cloud registration processing on the point cloud data of the exposed anchor rod collected by the multiple laser radars and the first camera to obtain three-dimensional position information of the exposed anchor rod.

[0054] Specifically, multiple laser radars and the first camera 3 each collect point cloud data from the deformation area. Because these laser radars and the first camera 3 each have different acquisition angles and point cloud data processing procedures, this embodiment processes the data collected by multiple detection devices using point cloud registration technology to obtain accurate three-dimensional pose information of the exposed anchor. The obtained three-dimensional pose information includes information such as the position coordinates and tilt angle of the exposed anchor.

[0055] As a possible implementation method, when obtaining three-dimensional pose data through point cloud registration technology, different point cloud data are first preprocessed to improve the efficiency and accuracy of registration, including downsampling the data, removing noise, and extracting feature points. Then, a coarse registration is performed to find an approximate rotation and translation matrix between the two point clouds collected by multiple lidars and the first camera 3, so that their relative positions are roughly aligned. Then, a fine registration is performed. Based on the coarse registration, the rotation and translation matrices are further optimized to achieve more accurate alignment. For example, the ICP (Iterative Closest Point) algorithm can be used. Finally, based on the rotation matrix and translation vector obtained by point cloud registration, the three-dimensional pose information of the exposed anchor can be obtained.

[0056] Furthermore, in this embodiment, the auxiliary arm and the shearing clamp are controlled to cut the exposed anchor rods based on the anchor rod positioning results, including: based on the three-dimensional posture information, the motion trajectory of the auxiliary arm is planned by the inverse kinematics algorithm, and according to the motion trajectory, the auxiliary arm drives the shearing clamp to move to the target working point to cut the exposed anchor rods; in the case that there are remaining exposed anchor rods in the deformation area, the anchor rod positioning and autonomous shearing are repeated until there are no exposed anchor rods in the deformation area.

[0057] Specifically, if Figure 3 As shown, this embodiment autonomously plans the motion trajectory of the auxiliary arm 6 based on the three-dimensional position information of the anchor rod. Specifically, the inverse kinematics algorithm is used to plan a collision-free trajectory, and the current attachment (i.e., the shear clamp 7) is driven to move accurately to the target point. The final target coordinates of the auxiliary arm 6 after stopping can be determined based on the coordinates of the exposed anchor rod, so as to drive the shear clamp 7 to a position suitable for cutting the exposed anchor rod.

[0058] As a possible implementation method, when using an inverse kinematics algorithm to plan a collision-free trajectory, the inverse kinematics solution is first performed to calculate the joint angles of the robot auxiliary arm 6 so that the end can reach the target coordinates and the corresponding posture. Trajectory planning is then performed. Based on the inverse kinematics solution, a collision-free trajectory is planned from the initial position to the target coordinates. This process can adopt common trajectory planning methods, such as trajectory planning based on time parameterization or trajectory planning based on convex optimization. To ensure that the trajectory is collision-free, collision detection and optimization are finally required. For example, collision detection is the real-time detection of whether points on the trajectory collide with obstacles in the environment during the planning process. Space partitioning methods (such as octrees and VDBs) can be used to accelerate collision detection. When performing path optimization, convex optimization methods (such as GCS, Graphs of Convex Sets) can be used to optimize the trajectory. The GCS method generates a collision-free trajectory by dividing the configuration space into convex safe regions and finding the shortest path between these regions.

[0059] Furthermore, after the shearing clamp 7 has completed shearing the current exposed anchor rods, the remaining exposed anchor rods are subjected to a secondary inspection, and the anchor rod positioning, autonomous trajectory planning and autonomous shearing in the above embodiment are cyclically executed until there are no exposed anchor rods in the deformation area, and subsequent cleaning operations can be carried out.

[0060] Step S103: Control the operating robot arm and the breaker hammer to crush the deformed area without exposed anchor rods, identify the floating coal on the roadway floor through multiple laser radars, and control the operating robot arm and the bucket to gradually clean the floating coal based on the floating coal identification results.

[0061] Specifically, after the residual anchor bolts are cleaned, a crushing and brushing operation is performed. In this operation step, the attachment is switched to a hydraulic breaker hammer 8 to crush the deformed area.

[0062] In one embodiment of the present application, the operating robot arm and the breaker hammer are controlled to crush the deformed area without exposed anchor rods, including: based on the force-position hybrid control strategy, the operating robot arm is controlled to dynamically adjust the impact frequency and impact angle of the breaker hammer to drive the breaker hammer to perform the crushing operation.

[0063] Specifically, in this embodiment, the robot arm dynamically adjusts the impact frequency and angle based on the force-position hybrid control strategy to avoid excessive damage to the tunnel structure. As a possible implementation method, the adjustment of the impact frequency can be achieved through mechanical adjustment and hydraulic adjustment of the operating robot arm 5. For example, the stroke of the piston can be changed by adjusting the adjustment screws on the top or side of the cylinder of the hydraulic breaker, thereby adjusting the impact frequency. The working pressure and flow of the hydraulic system can also be adjusted to change the impact frequency of the breaker. The adjustment of the impact angle can be achieved by the installation position of the breaker and the angle of the operating robot arm 5. Among them, in the above-mentioned adjustment process, accurate impact frequency and angle control can be achieved by debugging the force-position hybrid control parameters. For example, the force-position hybrid control parameters such as inertia parameters, stiffness parameters and damping parameters can be adjusted one by one.

[0064] Furthermore, the floating coal on the roadway floor is detected and shoveled and unloaded. First, the roadway floor is scanned by multiple laser radars, and the location information of the floating coal is identified based on the collected floor point cloud data. Then, the detected floating coal is shoveled and unloaded to other areas by the bucket 9.

[0065] In one embodiment of the present application, multiple laser radars are used to identify floating coal on the roadway floor, including: using a density clustering algorithm to identify the floating coal accumulation area and determine the floating coal position coordinates from the roadway floor point cloud data collected by the multiple laser radars.

[0066] Specifically, this embodiment uses a density clustering algorithm to identify areas of floating coal accumulation. For example, a density clustering algorithm such as DBSCAN, OPTICS, or HDBSCAN can be used. The parameters of the selected algorithm are adjusted based on the density distribution of point cloud data collected by multiple lidar sensors. The adjusted density clustering algorithm is then run to perform clustering processing, identifying floating coal accumulation areas in the point cloud. The clustering results can also be analyzed to extract the coordinate information of the clustered floating coal accumulation areas. Furthermore, based on the clustering results of the floating coal accumulation areas, a heat map of the floating coal distribution can be output to clearly and intuitively display the floating coal at different locations on the floor.

[0067] Furthermore, this embodiment controls the operating robot arm and bucket to gradually clean the floating coal based on the floating coal identification results, including: planning the motion trajectory of the operating robot arm according to the floating coal position coordinates, and driving the bucket to shovel the floating coal to the side conveyor according to the motion trajectory; after each round of shoveling, evaluating the remaining coal amount in the floating coal accumulation area, and re-determining the floating coal position coordinates and planning the motion trajectory of this round of shoveling task if the remaining coal amount does not meet the standard.

[0068] Specifically, in this embodiment, the attachment of the working robot arm 5 is first switched to the bucket 9, and the shoveling trajectory of the working robot arm 5 is planned according to the volume and position coordinates of the coal pile to be cleaned. A step-by-step shoveling strategy is adopted to shovel the floating coal onto the belt conveyor on the side of the robot. Figure 3 As shown, after each shoveling operation, the remaining floating coal amount is re-scanned and assessed using the floating coal detection method described in the above embodiment. If the remaining floating coal amount does not meet the standard, for example, if the remaining floating coal amount is greater than the allowable residual coal amount, it indicates that the floating coal has not been completely cleared, and the next round of shoveling operation is carried out. The motion trajectory planning method for the working robot arm 5 described in the above embodiment is then used to re-plan the operation path for this round of shoveling floating coal.

[0069] Therefore, this embodiment can avoid the impact of floating coal position change caused by each shoveling of floating coal by distributing the strategy of shoveling floating coal. Each round of shoveling task shovels floating coal with the most reasonable motion trajectory, thereby further improving the operating efficiency of the repair robot.

[0070] Step S104, after the floating coal is cleaned, the repair robot is controlled to move forward a preset cleaning step, and the second camera is used to detect the missing anchor position on the coal wall surface, and the airborne anchor drill is controlled to drive the anchor to the missing anchor position.

[0071] Specifically, after the floating coal is cleaned, the entire repair robot is controlled to move forward, and the forward movement is controlled by a preset step distance.

[0072] In one embodiment of the present application, the repair robot also includes a chassis and multiple detection devices, which control the repair robot to move forward at a preset cleaning step, including: combining feedback data from multiple laser radars and multiple detection devices to correct the direction of travel of the repair robot in real time, wherein the repair robot is driven by the chassis; and avoiding obstacles encountered during driving through a dynamic avoidance algorithm.

[0073] Specifically, this embodiment utilizes a crawler chassis 12 to drive the repair robot to autonomously advance a preset cleaning step (e.g., 0.5 meters), wherein the cleaning step can be determined based on the cleaning position of the floating coal and the position of the anchor area on the coal wall surface, and the specific step length is calculated based on the actual situation. During the forward movement, in order to avoid deviation in the driving direction and collision with unexpected obstacles, this embodiment also integrates the navigation system with data from multiple laser radars and detection equipment such as a visual odometer preset on the robot, and corrects the direction of travel in real time to ensure that the direction of travel is consistent with the planned direction. When encountering an obstacle during the movement, the dynamic obstacle avoidance algorithm is triggered, and the robot returns to the original planned path after detouring.

[0074] One possible implementation involves fusing LiDAR and visual odometry data to overcome the limitations of single sensors and improve the accuracy and robustness of robot positioning. Specifically, various coupling methods, such as tightly coupled and loosely coupled fusion, can be employed to fuse the corresponding robot pose estimates from the LiDAR and visual odometry to obtain the robot's global pose. Based on this fused pose, the robot's forward path is then planned to ensure it follows the intended trajectory. During driving, control commands are generated in real time based on the path planning results to adjust the robot's direction.

[0075] When encountering an obstacle during driving, the robot first predicts the obstacle's trajectory, then uses algorithms such as the Dynamic Window Algorithm (DWA) to plan an obstacle avoidance path. It then develops an obstacle avoidance strategy, including speed adjustment and maintaining a safe distance, to ensure the robot can circumvent the obstacle. Finally, through real-time feedback updates, the robot returns to its original path after confirming it has circumvented the obstacle.

[0076] Furthermore, after the repair robot completes the cleaning step, it automatically performs anchor bolting and support repair. A second camera 4 located behind the repair robot scans the coal wall surface at its current location, identifies the missing anchor locations in the anchor tray, and then controls the onboard anchor drill to drive anchor bolts to the missing locations.

[0077] In one embodiment of the present application, the missing anchor position on the coal wall surface is detected by a second camera, including: locating the position coordinates of the anchor tray on the coal wall surface by the second camera, and determining the coordinates of the missing anchor position based on the position coordinates of the anchor tray and the missing area position; before controlling the airborne anchor drill to drive the anchor toward the missing anchor position, it also includes: adjusting the posture of the airborne anchor drill according to the coordinates of the missing anchor position.

[0078] Specifically, this embodiment first analyzes the data scanned by the second camera 4, and uses various target detection algorithms, such as the YOLO (You Only Look Once) model, to first determine the position of the anchor tray on the coal wall surface and the coordinates of each part of the tray, and then determine the coordinates of the area where the anchor is missing, thereby obtaining the coordinates of the missing anchor position. The airborne anchor drill 10 is then controlled to automatically adjust its position according to the coordinates of the missing anchor position, for example, adjusting the position and angle of the airborne anchor drill 10 so that it is aligned with the coordinates of the missing anchor position. After starting the "one-click anchoring" program, the secondary reinforcement support is completed. If there are multiple missing anchor positions, the above scheme can be repeated for multiple rounds of anchoring.

[0079] Therefore, this application completes a single autonomous operation cycle of the repair robot, and the tunnel cleaning robot can also wait for continuous operation instructions to achieve full-process closed-loop autonomous operation and autonomously repair different deformation areas in different tunnels.

[0080] In summary, the tunnel deformation detection method based on the coal mine underground cleaning robot in the embodiment of the present application first performs a dynamic scanning of the tunnel by the laser radar on the cleaning robot to collect the three-dimensional point cloud data of the tunnel in real time; then aligns the point cloud data of different time frames to construct a tunnel point cloud map, corrects the posture of the cleaning robot and updates the tunnel point cloud map to generate a tunnel point cloud model; then, multiple plane areas are segmented from the pre-processed tunnel point cloud model, and the geometric structures in the multiple plane areas are clustered to obtain the deformation area; finally, the contour of the deformation area is extracted to determine the multiple state information of the deformation area. Therefore, this method utilizes the autonomous perception and calculation of the tunnel cleaning robot before operation, and performs deformation detection by scanning the tunnel perception point cloud data. It can automatically detect the deformation area in the tunnel, obtain multiple accurate information of the deformation area, accurately quantify the degree of deformation, and improve the accuracy and real-time performance of the deformation area detection. Furthermore, this method requires no human intervention throughout the entire detection process, reducing staff workload, making deformation area detection more convenient, ensuring staff safety, reducing the complexity of deformation area detection, and improving its efficiency. Furthermore, the automatically detected deformation information can be used for subsequent autonomous control of the robotic arm, achieving a closed-loop, full-process operation from perception to decision-making to execution, which is beneficial for improving the operating efficiency and intelligent control level of the roadway cleaning robot.

[0081] In order to implement the above embodiment, the present application also proposes an autonomous operation system of a coal mine tunnel repair robot. Figure 4 This is a structural diagram of an autonomous operation system of a coal mine tunnel repair robot proposed in an embodiment of the present application, such as Figure 4 As shown, the system includes: a positioning module 100, a shearing module 200, a crushing and coal shoveling module 300 and an anchoring module 400.

[0082] Among them, the positioning module 100 is used to locate the deformed area to be repaired and obtain the position information of the deformed area based on the three-dimensional point cloud data of the tunnel collected by multiple laser radars, and plan the navigation path according to the position information to control the repair robot to travel to the working position.

[0083] The shearing module 200 is used to detect whether there are exposed anchor rods in the deformation area through the first camera. If there are exposed anchor rods, the exposed anchor rods are collaboratively located by multiple laser radars and the first camera, and the auxiliary arm and shearing clamp are controlled to shear the exposed anchor rods based on the anchor rod positioning results.

[0084] The crushing and coal shoveling module 300 is used to control the operating robot arm and the breaker hammer to crush the deformed area without exposed anchor rods, and identify the floating coal on the tunnel floor through multiple laser radars. Based on the floating coal identification results, the operating robot arm and the bucket are controlled to gradually clean the floating coal.

[0085] The anchoring module 400 is used to control the repair robot to move forward a preset cleaning step after the floating coal is cleaned, and to detect the missing anchor position on the coal wall surface through the second camera, and to control the airborne anchor drill to drive the anchor to the missing anchor position.

[0086] Optionally, in one embodiment of the present application, the system also includes an early warning module, which is specifically used to: detect the degree of deformation of the deformation area and determine whether the degree of deformation exceeds a safety threshold; if the safety threshold is exceeded, control the repair robot to suspend operation and report early warning information.

[0087] Optionally, in one embodiment of the present application, the shearing module 200 is specifically used to: perform point cloud registration processing on the point cloud data of the exposed anchor rods collected by multiple laser radars and the first camera to obtain three-dimensional pose information of the exposed anchor rods; based on the three-dimensional pose information, plan the motion trajectory of the auxiliary arm through an inverse kinematics algorithm, and according to the motion trajectory, the auxiliary arm drives the shear clamp to move to the target working point to shear the exposed anchor rods; in the case that there are remaining exposed anchor rods in the deformation area, repeat the anchor rod positioning and autonomous shearing until there are no exposed anchor rods in the deformation area.

[0088] Optionally, in one embodiment of the present application, the crushing and coal shoveling module 300 is specifically used to: based on the force-position hybrid control strategy, control the operating robot arm to dynamically adjust the impact frequency and impact angle of the breaker hammer to drive the breaker hammer to perform crushing operations.

[0089] Optionally, in one embodiment of the present application, the crushing and coal shoveling module 300 is specifically used to: identify the floating coal accumulation area and determine the floating coal position coordinates from the tunnel floor point cloud data collected by multiple lidars through a density clustering algorithm; plan the motion trajectory of the operating robot arm according to the floating coal position coordinates, and according to the motion trajectory, the operating robot arm drives the bucket to shovel the floating coal to the side belt conveyor; after each round of shoveling, evaluate the remaining coal amount in the floating coal accumulation area, and if the remaining coal amount does not meet the standard, re-determine the floating coal position coordinates and plan the motion trajectory of this round of shoveling task.

[0090] Optionally, in one embodiment of the present application, the anchoring module 400 is specifically used to: combine feedback data from multiple laser radars and multiple detection devices to correct the travel direction of the repair robot in real time, wherein the repair robot is driven by the chassis; and avoid obstacles encountered during driving through a dynamic avoidance algorithm.

[0091] Optionally, in one embodiment of the present application, the anchoring module 400 is specifically used to: locate the position coordinates of the anchor tray on the coal wall surface through a second camera, and determine the anchor missing position coordinates based on the position coordinates of the anchor tray and the missing area position; adjust the posture of the airborne anchor drilling rig according to the anchor missing position coordinates.

[0092] It should be noted that the aforementioned explanation of the embodiment of the autonomous operation method of the coal mine underground tunnel repair robot is also applicable to the system of this embodiment and will not be repeated here.

[0093] To sum up, the autonomous operation system of the coal mine underground tunnel repair robot in the embodiment of the present application uses the automatically detected deformation information to perform subsequent autonomous control of the robotic arm, realizing a closed-loop full-process operation from perception to decision-making to execution, which is conducive to improving the operating efficiency and intelligent control level of the tunnel cleaning robot.

[0094] In order to implement the above embodiments, the present application also proposes a non-temporary computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements the autonomous operation method of the coal mine underground tunnel repair robot as described in any one of the above-mentioned first aspect embodiments.

[0095] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0096] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. Throughout the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0097] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0098] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0099] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0100] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0101] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0102] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. An autonomous operation method of a coal mine tunnel repair robot, characterized in that: The repair robot includes: multiple laser radars, a first camera, a second camera, an operating robot arm, an auxiliary arm, a shearing pliers, a breaker hammer, a bucket, and an airborne anchor drill. The method includes the following steps: Based on the three-dimensional point cloud data of the roadway collected by the multiple laser radars, the deformed area to be repaired is located and the position information of the deformed area is obtained, and a navigation path is planned according to the position information, and the repair robot is controlled to travel to the working position along the navigation path; detecting, by the first camera, whether there is an exposed anchor rod in the deformation area; if there is an exposed anchor rod, collaboratively locating the exposed anchor rod by the multiple laser radars and the first camera; and controlling the auxiliary arm and the shearing clamp to shear the exposed anchor rod based on the anchor rod locating result; Controlling the operating robot arm and the breaker hammer to crush the deformed area without exposed anchor rods, and identifying floating coal on the roadway floor through the multiple laser radars, and controlling the operating robot arm and the bucket to gradually clean the floating coal based on the floating coal identification results; After the floating coal is cleaned, the repair robot is controlled to move forward a preset cleaning step, and the second camera is used to detect the missing anchor position on the coal wall surface, and the airborne anchor drill is controlled to drive the anchor to the missing anchor position.

2. The method according to claim 1, characterized in that After locating the deformed area to be repaired and obtaining the position information of the deformed area, the method further includes: detecting a degree of deformation of the deformation region, and determining whether the degree of deformation exceeds a safety threshold; When the degree of deformation exceeds the safety threshold, the repair robot is controlled to suspend operation and report warning information.

3. The method according to claim 1, characterized in that The method of collaboratively locating the exposed anchor rod by using the multiple laser radars and the first camera includes: Performing point cloud registration processing on the point cloud data of the exposed anchor rod collected by the multiple laser radars and the first camera to obtain three-dimensional pose information of the exposed anchor rod; The controlling the auxiliary arm and the shearing pliers to shear the exposed anchor rod based on the anchor rod positioning result includes: Based on the three-dimensional posture information, a motion trajectory of the auxiliary arm is planned by an inverse kinematics algorithm, and according to the motion trajectory, the auxiliary arm drives the shear clamp to move to a target working point to shear the exposed anchor rod; In the case where there are remaining exposed anchor rods in the deformation area, anchor rod positioning and autonomous shearing are repeated until there are no exposed anchor rods in the deformation area.

4. The method according to claim 1, wherein The controlling of the operating mechanical arm and the breaker hammer to break the deformed area without exposed anchor rods includes: Based on the force-position hybrid control strategy, the operating mechanical arm is controlled to dynamically adjust the impact frequency and impact angle of the breaker hammer to drive the breaker hammer to perform the crushing operation.

5. The method according to claim 1, characterized in that The identifying floating coal on the roadway floor by using the multiple laser radars includes: Using a density clustering algorithm, identifying floating coal accumulation areas and determining the floating coal location coordinates from the roadway floor point cloud data collected by the multiple lidars; The step of controlling the operating robot arm and the bucket to gradually clean the floating coal based on the floating coal identification result includes: Planning a motion trajectory of the operating robot arm according to the floating coal position coordinates, and driving the bucket to shovel the floating coal onto the side conveyor by the operating robot arm according to the motion trajectory; After each round of shoveling is completed, the amount of remaining coal in the floating coal accumulation area is evaluated. If the remaining coal amount does not meet the standard, the floating coal position coordinates are re-determined and the motion trajectory of this round of shoveling is planned.

6. The method according to claim 1, characterized in that The repair robot further includes a chassis and a plurality of detection devices, and the control of the repair robot to move forward a preset cleaning step distance includes: Combining feedback data from the multiple laser radars and the multiple detection devices, correcting the travel direction of the repair robot in real time, wherein the repair robot is driven by the chassis; Obstacles encountered during driving are avoided through dynamic avoidance algorithms.

7. The method according to claim 1, characterized in that The detecting the missing position of the anchor rod on the surface of the coal wall by the second camera includes: Locating the position coordinates of the anchor tray on the surface of the coal wall by the second camera, and determining the coordinates of the missing position of the anchor according to the position coordinates of the anchor tray and the position of the missing area; Before controlling the airborne anchor drill to drive the anchor toward the anchor missing position, the method further includes: The posture of the airborne anchor drilling rig is adjusted according to the coordinates of the anchor missing position.

8. An autonomous operation system of a coal mine tunnel repair robot, characterized in that: The repair robot includes: multiple laser radars, a first camera, a second camera, an operating robot arm, an auxiliary arm, a shearing pliers, a breaker hammer, a bucket and an airborne anchor drill. The system includes the following modules: a positioning module, configured to locate the deformed area to be repaired and obtain position information of the deformed area based on the three-dimensional point cloud data of the roadway collected by the multiple laser radars, plan a navigation path according to the position information, and control the repair robot to travel to a working position; a shearing module, configured to detect whether there is an exposed anchor rod in the deformation area by using the first camera; if an exposed anchor rod is present, collaboratively locate the exposed anchor rod by using the multiple laser radars and the first camera; and control the auxiliary arm and the shearing clamp to shear the exposed anchor rod based on the anchor rod positioning result; A crushing and coal shoveling module is used to control the operating robot arm and the breaker hammer to crush the deformed area without exposed anchor bolts, identify floating coal on the roadway floor through the multiple laser radars, and control the operating robot arm and the bucket to gradually remove the floating coal based on the floating coal identification results; The anchoring module is used to control the repair robot to move forward a preset cleaning step after the floating coal is cleaned, and to detect the missing anchor position on the coal wall surface through the second camera, and control the airborne anchor drill to drive the anchor to the missing anchor position.

9. The system according to claim 8, characterized in that It also includes an early warning module, which is specifically used to: detecting a degree of deformation of the deformation region, and determining whether the degree of deformation exceeds a safety threshold; When the safety threshold is exceeded, the repair robot is controlled to suspend operation and report warning information.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the autonomous operation method of the coal mine underground tunnel repair robot is implemented as described in any one of claims 1 to 7.

Images