Intelligent path planning method and system for coal mining robot in mine

Abstract

The invention belongs to the technical field of intelligent path planning of coal mining robots, and particularly provides an intelligent path planning method and system for a coal mining robot in a mine, and the method mainly comprises the steps: obtaining and preprocessing an original image of a camera, geological data of a contact sensor and original attitude data of an inertial measurement unit; obtaining three-dimensional visual data, geological feature data and correction attitude data; acquiring historical working face data and equipment attitude information, and combining the three-dimensional visual data, the geological feature data and the corrected attitude data to perform environmental perception collaborative correction processing to obtain environmental model data; and acquiring the original walking distance of a motor encoder and the original displacement data of an external positioning system, and carrying out walking slip state monitoring processing to obtain a dynamic slip rate. According to the method, environment perception accurate correction and walking slip real-time compensation can be achieved, the deviation between the actual cutting track and the theoretical path is effectively controlled to be within the safety threshold value, and the coal mining efficiency and the operation safety are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent path planning for coal mining robots, and in particular relates to an intelligent path planning method and system for coal mining robots in mines. Background Art

[0002] In coal mining operations in mines, the path planning of coal mining robots relies on a variety of perception technologies. Visual sensors are often used to obtain working face images, combined with contact sensors to collect geological parameters, and the robot posture is monitored through inertial measurement units. Based on this, an environmental model is built and the operation path is planned. However, the mine environment is characterized by high dust, and coal dust easily adheres to the visual sensor lens, causing image information distortion and affecting the accuracy of environmental perception. When the walking mechanism of the coal mining robot operates on loose coal gangue layers, dynamic slippage is prone to occur, causing the deviation between the robot's actual operating trajectory and the theoretical path to exceed the safety range, affecting coal mining efficiency and operation safety. Summary of the Invention

[0003] This application provides an intelligent path planning method and system for coal mining robots in mines, which effectively solves the problem of environmental perception deviation caused by distortion of visual sensors in high dust environments in the existing technology, and dynamic slip of the walking mechanism in loose coal gangue layers. The existing methods are difficult to compensate for the two synchronously, causing trajectory deviation beyond the safe range. It realizes precise correction of environmental perception and real-time compensation of walking slip, effectively controls the deviation between the actual cutting trajectory and the theoretical path within the safety threshold, and improves coal mining efficiency and operation safety.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions: In a first aspect, the present application provides an intelligent path planning method for a coal mining robot in a mine, comprising: The original image of the camera, the geological data of the contact sensor and the original posture data of the inertial measurement unit are obtained and preprocessed to obtain three-dimensional visual data, geological feature data and corrected posture data.

[0005] Historical working face data and equipment posture information are acquired, and environmental perception collaborative correction processing is performed in combination with the three-dimensional visual data, the geological feature data and the correction posture data to obtain environmental model data.

[0006] The original walking distance of the motor encoder and the original displacement data of the external positioning system are obtained, and the walking slip state is monitored and processed to obtain the dynamic slip rate.

[0007] A preset cutting template is obtained, and the historical working face geological data, the correction posture data, the environmental model data and the dynamic slip rate in the historical working face data are combined to perform initial path planning and slip compensation processing to obtain optimized path data.

[0008] Safety conflict detection and path adjustment processing are performed based on the optimized path data to obtain path verification mark data and adjusted path data.

[0009] Based on the path verification mark data and the adjusted path data, path output and execution control processing are performed to obtain the actual path execution effect.

[0010] Further, preprocessing is performed to obtain three-dimensional visual data, geological feature data and corrected posture data, including: The original camera image is processed to remove the interference of coal dust attachment and obtain a preliminary clean image.

[0011] The preliminary cleaned image is subjected to edge sharpening and enhancement processing to obtain enhanced visual data.

[0012] The enhanced visual data is subjected to stereo depth reconstruction processing to obtain three-dimensional visual data.

[0013] The geological data of the contact sensor is processed for rock formation feature extraction, and the original attitude data of the inertial measurement unit is processed for zero drift correction to obtain geological feature data and corrected attitude data.

[0014] Furthermore, environmental perception collaborative correction processing is performed to obtain environmental model data, including: The three-dimensional visual data and the geological feature data are processed by three-dimensional point cloud reconstruction to obtain environmental point cloud data.

[0015] Coal-rock interface pattern recognition processing is performed based on the environmental point cloud data and historical working face data to obtain interface recognition data.

[0016] Performing posture collaborative registration processing on the corrected posture data and the interface recognition data to obtain compensated perception data.

[0017] A dynamic reference plane construction process is performed based on the compensated perception data and the device posture information to obtain environmental model data.

[0018] Furthermore, the walking slip state monitoring process is performed to obtain the dynamic slip rate, including: Perform cumulative error reset processing on the original travel distance of the motor encoder to obtain reset distance data.

[0019] The reset distance data is subjected to instantaneous speed deduction processing, and the original displacement data of the external positioning system is subjected to multipath effect suppression processing to obtain theoretical walking speed data and actual displacement data.

[0020] The theoretical walking speed data and the actual displacement data are subjected to dynamic slip rate estimation processing to obtain a dynamic slip rate.

[0021] Furthermore, initial path planning and slip compensation processing are performed to obtain optimized path data, including: An initial path generation process is performed based on the environmental model data and a preset cutting template to obtain theoretical cutting path data.

[0022] Based on the interface identification data and historical working face geological data, the geological characteristics of the working face are zoned to obtain geological zoning map data.

[0023] Slip influence domain segmentation processing is performed based on the dynamic slip rate and the geological partition map data to obtain regionalized slip parameter data.

[0024] Perform trend prediction processing on the regionalized slip parameter data to obtain slip prediction data.

[0025] The theoretical cutting path data and the slip prediction data are subjected to path point collaborative compensation processing to obtain compensated path data.

[0026] Dynamic posture constraint optimization processing is performed on the compensated path data and the corrected posture data to obtain optimized path data.

[0027] Furthermore, security conflict detection and path adjustment processing are performed based on the optimized path data to obtain path verification mark data and adjusted path data, including: The optimized path data is scanned for conflicts in a safe distance to obtain conflict marking data.

[0028] Performing local path replanning processing on the conflict mark data to obtain adjusted path data.

[0029] Efficiency evaluation is performed on the adjusted path data to obtain path score data.

[0030] The path scoring data is subjected to an executable threshold verification process to obtain path verification mark data.

[0031] Furthermore, based on the path verification flag data and the adjusted path data, path output and execution control processing are performed to obtain an actual path execution effect, including: An execution instruction conversion process is performed based on the path verification flag data and the adjusted path data to obtain control instruction data.

[0032] The control instruction data is subjected to time sequence scheduling and allocation processing to obtain time sequence instruction sequence data.

[0033] The timing instruction sequence data is subjected to actuator compatibility adaptation processing to obtain adaptation control data.

[0034] The actual path execution effect is obtained by sending the adaptive control data to the robot drive unit for processing.

[0035] Furthermore, the compensated path data and the corrected posture data are subjected to dynamic posture constraint optimization processing to obtain optimized path data, including: Perform dynamic posture constraint modeling and generate constraint rule data.

[0036] An iterative optimization calculation is performed on the compensated path data based on the constraint rule data to obtain optimized path data.

[0037] Furthermore, the reset distance data is subjected to instantaneous speed deduction processing, and the original displacement data of the external positioning system is subjected to multipath effect suppression processing to obtain theoretical walking speed data and actual displacement data, including: The reset distance data is subjected to instantaneous speed deduction processing to obtain theoretical walking speed data.

[0038] The original displacement data of the external positioning system is processed to suppress the multipath effect and obtain the actual displacement data.

[0039] In a second aspect, the present application also provides an intelligent path planning system for a coal mining robot in a mine, which comprises: Multi-source data preprocessing module: acquires the original camera image, contact sensor geological data and inertial measurement unit original posture data and preprocesses them to obtain 3D visual data, geological feature data and corrected posture data; Environmental perception, correction, and modeling module: This module obtains historical working face data and equipment posture information, combines 3D visual data, geological feature data, and correction posture data, performs environmental perception collaborative correction processing, and obtains environmental model data. Walking slip monitoring module: obtains the original walking distance of the motor encoder and the original displacement data of the external positioning system, performs walking slip status monitoring and processing, and obtains the dynamic slip rate; Path planning and slip compensation module: obtains the preset cutting template, combines the historical working face geological data, correction posture data, environmental model data and dynamic slip rate in the historical working face data, performs initial path planning and slip compensation processing, and obtains optimized path data; Safety conflict detection and path adjustment module: performs safety conflict detection and path adjustment based on optimized path data, and obtains path verification mark data and adjusted path data; Path output and execution control module: Based on the path verification mark data and the adjusted path data, the path output and execution control processing are performed to obtain the actual path execution effect.

[0040] In the third aspect, the present application provides an intelligent path planning device for a coal mining robot in a mine, which includes a memory and a processor; the memory is used to store computer programs; the processor is used to implement the steps of the intelligent path planning method for a coal mining robot in a mine as in the first aspect when executing the computer program.

[0041] In a fourth aspect, the present application provides a storage medium storing computer program instructions. When the computer program instructions are read and executed by a processor, the steps of the intelligent path planning method for a coal mining robot in a mine as in the first aspect are executed.

[0042] Beneficial effects of the present invention: This application adopts multi-sensor data fusion preprocessing, collaboratively corrects the environmental model, monitors the dynamic slip rate, combines historical data with preset templates to plan the path and compensate for the slip, and outputs the execution plan after safety detection and adjustment. It effectively solves the problem of environmental perception deviation caused by distortion of visual sensors in high dust environments in the existing technology, and dynamic slip of the walking mechanism in loose coal gangue layers. The existing method is difficult to compensate for the two synchronously, causing the trajectory deviation to exceed the safety range. It realizes precise correction of environmental perception and real-time compensation of walking slip, effectively controls the deviation between the actual cutting trajectory and the theoretical path within the safety threshold, and improves coal mining efficiency and operation safety.

[0043] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0045] Figure 1 A schematic diagram showing the flow of the intelligent path planning method for a coal mining robot in a mine according to the present invention is shown; Figure 2The module schematic diagram of the intelligent path planning system for coal mining robots in mines of the present invention is shown. DETAILED DESCRIPTION

[0046] In order to solve the problems raised by the background technology, this application adopts multi-sensor data fusion preprocessing, collaboratively corrects the environmental model, monitors the dynamic slip rate, combines historical data with preset templates to plan the path and compensate for slip, and outputs the execution plan after safety detection and adjustment, thereby improving coal mining efficiency and operation safety.

[0047] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0048] In some embodiments, as Figure 1 As shown, the present application provides an intelligent path planning method for a coal mining robot in a mine, comprising: S1. Obtain the camera raw image, contact sensor geological data and inertial measurement unit raw posture data and preprocess them to obtain three-dimensional visual data, geological feature data and corrected posture data.

[0049] S2. Obtain historical working face data and equipment posture information, combine it with three-dimensional visual data, geological feature data and correction posture data, perform environmental perception collaborative correction processing, and obtain environmental model data.

[0050] S3. Obtain the original travel distance of the motor encoder and the original displacement data of the external positioning system, perform travel slip status monitoring and processing, and obtain the dynamic slip rate.

[0051] S4. Obtain a preset cutting template, combine historical working face geological data, correction posture data, environmental model data, and dynamic slip rate in the historical working face data, perform initial path planning and slip compensation processing, and obtain optimized path data.

[0052] S5. Perform safety conflict detection and path adjustment processing based on the optimized path data to obtain path verification mark data and adjusted path data.

[0053] S6. Based on the path verification mark data and the adjusted path data, perform path output and execution control processing to obtain the actual path execution effect.

[0054] In some embodiments, the camera raw image in S1 represents the visual information of the coal mining face directly collected by the mine explosion-proof camera, including the spatial distribution information of the coal wall, hydraulic support and conveyor.

[0055] The contact sensor geological data represents the mechanical signals collected by the piezoelectric sensor array installed on the coal mining machine pick. It includes the triaxial force values ​​(Fx, Fy, Fz) and the vibration spectrum characteristics. For example, when cutting sandstone layers, the peak force on the Z axis can reach 25kN±3kN, while it remains at 8-12kN when cutting coal seams.

[0056] The raw attitude data of the inertial measurement unit refers to the motion parameters directly output by the MEMS inertial sensor on the coal mining machine body, including the three-axis angular velocity ( ) and triaxial acceleration ( ).

[0057] Perform preprocessing to obtain 3D visual data, geological feature data, and corrected posture data, including: S11. Perform coal dust interference removal processing on the original camera image to obtain a preliminary clean image.

[0058] The dark channel prior model can be used to process the foggy blur of the original image and obtain a preliminary clean image.

[0059] S12. Perform edge sharpening and enhancement processing on the preliminary cleaned image to obtain enhanced visual data.

[0060] Aiming at the low illumination environment underground, Laplace pyramid fusion enhancement is adopted to obtain enhanced visual data, which is specifically a floating-point image matrix.

[0061] S13. Perform stereo depth reconstruction processing on the enhanced visual data to obtain three-dimensional visual data.

[0062] Depth calculation can be implemented based on the binocular parallax principle to obtain three-dimensional visual data, which is specifically a point cloud data set.

[0063] S14. Perform rock formation feature extraction processing on the geological data of the contact sensor, and perform zero drift correction processing on the original attitude data of the inertial measurement unit to obtain geological feature data and corrected attitude data.

[0064] The geological data of the contact sensor are subjected to time domain peak extraction and frequency domain energy analysis to obtain geological characteristic data.

[0065] For example, the cutting resistance peak is detected within a 50 millisecond window, and the hard rock layer is marked when the peak exceeds the hard rock judgment threshold. The energy proportion in the 200-800 Hz frequency band is calculated, and the sandstone layer is marked when the proportion exceeds the sandstone judgment threshold. The hard rock judgment threshold and the sandstone judgment threshold can be calibrated according to the sample destruction test.

[0066] In some embodiments, the historical working face data in S2 represents a set of geological characteristics and path execution records of completed working faces stored in the coal mining database, including coal seam thickness distribution, lithology zoning map, cutting path trajectory, equipment operating parameters, etc.

[0067] The equipment attitude information represents the real-time spatial attitude parameters of the coal mining machine body, including pitch angle, roll angle, and yaw angle.

[0068] Perform environmental perception collaborative correction processing to obtain environmental model data, including: S21. Perform three-dimensional point cloud reconstruction on the three-dimensional visual data and geological feature data to obtain environmental point cloud data.

[0069] The geological feature point cloud can be aligned with the visual point cloud through the ICP registration algorithm, and the environmental point cloud data can be generated by combining the RGB-D information.

[0070] S22. Perform coal-rock interface pattern recognition processing based on environmental point cloud data and historical working face data to obtain interface recognition data.

[0071] The ResNet-18 network can be trained based on historical data to identify the coal-rock boundary pattern. The environmental point cloud data and historical working face data are used as input. The network extracts point cloud features through transfer learning and outputs interface recognition data. Among them, the coal-rock boundary threshold can be determined by the grayscale gradient mean statistics of samples in the historical working face data.

[0072] S23. Perform posture collaborative registration processing on the corrected posture data and the interface recognition data to obtain compensated perception data.

[0073] The extended Kalman filter correction can be used to perform posture co-registration of posture data and interface recognition data to obtain compensated perception data, that is, a semantic environment model aligned in time and space.

[0074] S24. Perform dynamic reference plane construction based on the compensated perception data and device posture information to obtain environmental model data.

[0075] The least squares plane fitting can be used to construct a dynamic reference surface to obtain environmental model data.

[0076] In some embodiments, the original travel distance of the motor encoder in S3 represents the pulse count data directly output by the built-in encoder of the coal mining machine travel motor.

[0077] The raw displacement data of the external positioning system represents the absolute position data of the coal mining machine directly output by the mine positioning system.

[0078] Perform walking slip status monitoring and processing to obtain dynamic slip rate, including: S31. Perform cumulative error reset processing on the original travel distance of the motor encoder to obtain reset distance data.

[0079] The accumulated error reset process performs periodic calibration through the absolute position feedback of the external positioning system to obtain reset distance data.

[0080] S32. Perform instantaneous speed deduction processing on the reset distance data and multipath effect suppression processing on the original displacement data of the external positioning system to obtain theoretical walking speed data and actual displacement data, including: S321. Perform instantaneous speed deduction processing on the reset distance data to obtain theoretical walking speed data.

[0081] The instantaneous speed deduction process is specifically as follows: differential calculation is performed on the reset distance data to obtain the instantaneous speed, and the theoretical walking speed data is output as an instantaneous speed sequence with a timestamp.

[0082] S322. Perform multipath effect suppression processing on the original displacement data of the external positioning system to obtain actual displacement data.

[0083] The multipath effect suppression process is specifically as follows: Kalman filtering is used to eliminate the lane multipath interference of the original displacement data of the external positioning system to obtain the actual displacement data.

[0084] S33. Perform dynamic slip rate estimation processing on the theoretical walking speed data and the actual displacement data to obtain a dynamic slip rate.

[0085] Calculate the slip rate using the slip rate formula: ;in, represents the slip ratio, It is obtained by differentiating the actual displacement data. Represents theoretical walking speed data.

[0086] In some embodiments, the preset cutting template in S4 represents a reference cutting path set generated based on coal seam occurrence parameters, including a vector sequence of path point coordinates (X, Y, Z) and cutting drum height adjustment instructions.

[0087] For example, when the thickness of a coal seam is 2.1m±0.2m and the inclination is 15°, the template defines the roller center track as 1.0m away from the roof and the cutting depth as 0.8m.

[0088] Historical working face geological data represents the structural geological attribute characteristics of the mined working face extracted from historical working face data, including lithology distribution, structural characteristics, hydrological parameters, etc.

[0089] Perform initial path planning and slip compensation processing to obtain optimized path data, including: S41. Perform initial path generation processing based on the environmental model data and the preset cutting template to obtain theoretical cutting path data.

[0090] The reference path points of the preset cutting template are aligned with the spatial coordinates of the environmental model data through the cubic spline interpolation algorithm to generate smooth and continuous theoretical cutting path data.

[0091] For example, when the inclination angle of a coal seam is 18°, the preset template path points (X, Y, Z) are interpolated to generate continuous trajectory lines with a spacing of 0.1 meters.

[0092] S42. Based on the interface identification data and historical working face geological data, the geological characteristics of the working face are zoned to obtain geological zone map data.

[0093] The geological units are divided based on the coal-rock boundary line of the interface identification data as the threshold. The attribute annotation of the geological unit can refer to the lithologic parameters of similar geological conditions in the historical working face geological data (such as sandstone hardness 120MPa), and a gridded geological attribute map with lithologic coding is obtained, which is marked as geological zoning map data.

[0094] For example, a working face is divided into two geological zones: Zone 1: Coal seam proportion > 85%, cutting parameters [speed 80 rpm, feed 1.2 m / s].

[0095] Zone 2: Sandstone with gangue layer, cutting parameters [rotation speed 60 rpm, feed 0.8 m / s].

[0096] S43. Performing a segmentation process on the slip influence domain based on the dynamic slip rate and geological zoning map data to obtain regionalized slip parameter data.

[0097] The slip rate values ​​in the dynamic slip rate data are mapped to the grid cells of the geological zoning map data according to their spatial coordinates (X, Y), and a mapping relationship between slip rate and geological attributes is established.

[0098] If the slip ratio is greater than or equal to 0.2, it represents a high impact domain; if the slip ratio is less than or equal to 0.1, it represents a low impact threshold; the rest represent a medium impact threshold.

[0099] Regenerate the slip compensation coefficient: 1. Calculate the basic coefficient: ,in, 、 Represents the regression coefficient calibrated through mine field tests.

[0100] 2. If the geology is soft rock, the slip compensation coefficient Corrected to: ; If the geology is hard rock, the slip compensation coefficient Corrected to: .

[0101] The generated regionalized slip parameter data includes coordinates, geological codes, slip rates , influence domain registration, slip compensation coefficient .

[0102] S44. Perform trend prediction processing on the regionalized slip parameter data to obtain slip prediction data.

[0103] The regionalized slip parameter data can be input into the ARIMA time series model, and after model processing, the output slip prediction data is obtained, specifically the slip rate change curve within the future time window (such as 5 seconds).

[0104] For example, the current slip ratio It is 0.18, and it is predicted to rise to 0.22 in 2 seconds.

[0105] S45. Perform path point collaborative compensation processing on the theoretical cutting path data and the slip prediction data to obtain compensated path data.

[0106] Map the coordinates (X, Y) of the theoretical cutting path data to the grid coordinate system and calculate the normal offset of the path point : ; where v represents the theoretical walking speed, Represents the prediction time window.

[0107] According to the axial pitch angle of the drum, the normal direction of the cutting trajectory is determined, and the coordinate points of the theoretical cutting path data are translated along the normal direction. Distance, get the compensated path data, that is, the new trajectory after slip correction.

[0108] S46. Perform dynamic posture constraint optimization processing on the compensated path data and the corrected posture data to obtain optimized path data, including: S461. Perform dynamic posture constraint modeling and generate constraint rule data.

[0109] By correcting the real-time pitch angle θ and roll angle γ of the attitude data, a curvature safety constraint is constructed: ;in, represents the maximum curvature allowed, Represents the length of the coal mining robot, Represents the maximum pitch angle.

[0110] when hour, Attenuates to 0.85 times when the roll angle hour, Attenuated to 0.9 times.

[0111] Constraint rule data includes Structured parameter set for dynamic threshold and decay rules.

[0112] S462. Perform iterative optimization calculation on the compensated path data based on the constraint rule data to obtain optimized path data.

[0113] Detecting the curvature of compensated path data ,right The coordinates of the points are compressed along the curvature radius: ; Get optimized path data; Among them, Represents the optimized curvature radius.

[0114] In some embodiments, the security conflict detection and path adjustment processing based on the optimized path data in S5 to obtain path verification flag data and adjusted path data includes: S51. Perform safety distance conflict scanning on the optimized path data to obtain conflict mark data.

[0115] The distance field algorithm is used to detect and optimize the minimum distance between path data and static obstacles such as tunnel boundaries and hydraulic supports.

[0116] When the distance is less than a preset safety distance threshold (such as 0.5 meters), it is marked as a conflict and conflict marking data is output, including structured data such as the location, type, and level of the conflict. The safety distance threshold can be determined through analysis of collision accident data.

[0117] For example, if the minimum distance between a certain coal mining machine theoretical path point (35.6, 2.42) and a hydraulic support is 0.3 meters and less than 0.5 meters, the conflict mark data is recorded as "coordinates (35.6, 2.42), conflict type: equipment interference, level: high risk".

[0118] S52. Perform local path replanning processing on the conflict mark data to obtain adjusted path data.

[0119] Specifically, a fast exploration random tree algorithm can be used to perform local path correction: a replanning area of ​​a specified range (such as 1.5×1.5 meters) is established with the conflict point as the center, and an obstacle avoidance path is generated based on the lane constraints of the environmental model data. The new path must ensure that the distance from the obstacle is greater than the safety distance threshold. The generated adjusted path data is the continuous trajectory after obstacle avoidance optimization.

[0120] For example, for the conflict point (35.6, 2.42), a detour path point sequence (35.6, 2.62), (35.7, 2.58), and (35.7, 2.45) is generated.

[0121] S53. Perform efficiency evaluation on the adjusted path data to obtain path score data.

[0122] Increment the path length of the adjusted path data , curvature change rate , cutting time estimate These three key indicators are quantitatively analyzed, path length increment for: ; Curvature change rate for: ; Cutting time estimate for: ;in, Represents the total length of the adjusted path, Represents the total length of the original path, represents the curvature of the i-th path point, represents the average curvature of the path, n represents the total number of path points, Represents the preset average cutting speed.

[0123] S54. Perform executable threshold verification processing on the path scoring data to obtain path verification mark data.

[0124] Perform sub-item threshold verification to determine the path feasibility: the verification threshold of the path length increment ΔL can be set according to the minimum cutting efficiency requirement of the mine. When the path length increment ΔL is greater than the verification threshold, it is determined that the mining efficiency is affected; the curvature change rate The verification threshold can be determined based on the statistical results of the equipment stability test. If it is less than the verification threshold, it means that the equipment is in good stability; the verification threshold of the cutting time T is determined by the time distribution statistics of the cutting cycle in the historical working face data. When the cutting time T is greater than the verification threshold, the production rhythm will be disrupted.

[0125] The final generated path verification mark data is as follows: when the path length increment ΔL and curvature change rate When the three indicators of time T and cutting time T all meet the threshold, the output represents an executable status code. If any indicator exceeds the limit, the output represents the need to readjust the status code.

[0126] In some embodiments, the path output and execution control processing in S6 is performed based on the path verification flag data and the adjusted path data to obtain the actual path execution effect, including: S61. Perform execution instruction conversion processing based on the path verification flag data and the adjusted path data to obtain control instruction data.

[0127] When the status code indicates that it is executable, the coordinate points of the adjusted path data are converted into robot driving instructions, specifically including coordinate instructions and motion parameters, and the motion parameters specifically include speed and acceleration.

[0128] S62. Perform timing scheduling and allocation processing on the control instruction data to obtain timing instruction sequence data.

[0129] The time interval between each instruction is calculated based on the distance between the path points and the preset walking speed, and an absolute timestamp is assigned to the reference time slice according to the specified time (such as 0.1 second), and finally the time sequence instruction sequence data is output.

[0130] S63. Perform actuator compatibility adaptation processing on the timing instruction sequence data to obtain adaptation control data.

[0131] The timing instruction sequence data is converted into the electrical protocol supported by the robot drive unit, and the electrical characteristics are adapted at the same time, and the adapted control data is output, which represents the electrical signal sequence that can directly drive the actuator.

[0132] S64. The actual path execution effect is obtained by sending the adaptive control data to the robot drive unit for processing.

[0133] The adaptive control data is sent to the robot drive unit, and the execution effect is monitored in real time: the actual position (X', Y', Z') feedback from the motor encoder is sampled at a specified frequency (such as 1kHz), and the error value compared with the theoretical coordinates is calculated; when the error value exceeds the preset error threshold, real-time calibration is automatically triggered, and the actual path execution effect is output as a structured log containing the theoretical coordinates, actual coordinates, error value, and timestamp.

[0134] In some embodiments, as Figure 2 As shown, the present application also provides an intelligent path planning system for a coal mining robot in a mine, which includes: Multi-source data preprocessing module: acquires the original camera image, contact sensor geological data and inertial measurement unit original posture data and preprocesses them to obtain 3D visual data, geological feature data and corrected posture data; Environmental perception, correction, and modeling module: This module obtains historical working face data and equipment posture information, combines 3D visual data, geological feature data, and correction posture data, performs environmental perception collaborative correction processing, and obtains environmental model data. Walking slip monitoring module: obtains the original walking distance of the motor encoder and the original displacement data of the external positioning system, performs walking slip status monitoring and processing, and obtains the dynamic slip rate; Path planning and slip compensation module: obtains the preset cutting template, combines the historical working face geological data, correction posture data, environmental model data and dynamic slip rate in the historical working face data, performs initial path planning and slip compensation processing, and obtains optimized path data; Safety conflict detection and path adjustment module: performs safety conflict detection and path adjustment based on optimized path data, and obtains path verification mark data and adjusted path data; Path output and execution control module: Based on the path verification mark data and the adjusted path data, the path output and execution control processing are performed to obtain the actual path execution effect.

[0135] In some embodiments, the present application provides an intelligent path planning device for a coal mining robot in a mine, which includes a memory and a processor; the memory is used to store computer programs; and the processor is used to implement the steps of an intelligent path planning method for a coal mining robot in a mine when executing the computer program.

[0136] In some embodiments, the present application provides a storage medium storing computer program instructions. When the computer program instructions are read and executed by a processor, the steps of the intelligent path planning method for a coal mining robot in a mine are executed.

[0137] Any reference to memory, storage, database, or other media used in the embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory.

[0138] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or elements that are inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device that includes the element.

[0139] Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent path planning method for a coal mining robot in a mine, characterized in that: include: Obtain camera raw images, contact sensor geological data, and inertial measurement unit raw attitude data and preprocess them to obtain three-dimensional visual data, geological feature data, and corrected attitude data; Acquire historical working face data and equipment posture information, combine the three-dimensional visual data, the geological feature data and the corrected posture data, perform environmental perception collaborative correction processing, and obtain environmental model data; Obtain the original travel distance of the motor encoder and the original displacement data of the external positioning system, perform travel slip status monitoring and processing, and obtain the dynamic slip rate; Obtaining a preset cutting template, combining historical working face geological data in the historical working face data, the corrected posture data, the environmental model data, and the dynamic slip rate, performing initial path planning and slip compensation processing to obtain optimized path data; Performing safety conflict detection and path adjustment processing based on the optimized path data to obtain path verification mark data and adjusted path data; Based on the path verification mark data and the adjusted path data, path output and execution control processing are performed to obtain the actual path execution effect.

2. The intelligent path planning method for a coal mining robot in a mine according to claim 1, characterized in that: Perform preprocessing to obtain 3D visual data, geological feature data, and corrected posture data, including: The original camera image is processed to remove the interference of coal dust adhesion and obtain a preliminary clean image; performing edge sharpening and enhancement processing on the preliminary cleaned image to obtain enhanced visual data; Performing stereo depth reconstruction processing on the enhanced visual data to obtain three-dimensional visual data; The geological data of the contact sensor is processed for rock formation feature extraction, and the original attitude data of the inertial measurement unit is processed for zero drift correction to obtain geological feature data and corrected attitude data.

3. The intelligent path planning method for a coal mining robot in a mine according to claim 1, characterized in that: Perform environmental perception collaborative correction processing to obtain environmental model data, including: Performing three-dimensional point cloud reconstruction processing on the three-dimensional visual data and the geological feature data to obtain environmental point cloud data; Performing coal-rock interface pattern recognition processing based on the environmental point cloud data and historical working face data to obtain interface recognition data; Performing posture collaborative registration processing on the corrected posture data and the interface recognition data to obtain compensated perception data; A dynamic reference plane construction process is performed based on the compensated perception data and the device posture information to obtain environmental model data.

4. The intelligent path planning method for a coal mining robot in a mine according to claim 1, characterized in that: Perform walking slip status monitoring and processing to obtain dynamic slip rate, including: Perform cumulative error reset processing on the original travel distance of the motor encoder to obtain reset distance data; Performing instantaneous speed deduction processing on the reset distance data and multipath effect suppression processing on the original displacement data of the external positioning system to obtain theoretical walking speed data and actual displacement data; The theoretical walking speed data and the actual displacement data are subjected to dynamic slip rate estimation processing to obtain a dynamic slip rate.

5. The intelligent path planning method for a coal mining robot in a mine according to claim 1, characterized in that: Perform initial path planning and slip compensation processing to obtain optimized path data, including: Performing initial path generation processing based on the environmental model data and a preset cutting template to obtain theoretical cutting path data; Based on the interface identification data and historical working face geological data, the geological characteristics of the working face are divided into zones to obtain geological zone map data; Performing a slip influence domain segmentation process based on the dynamic slip rate and the geological partition map data to obtain regionalized slip parameter data; performing trend prediction processing on the regionalized slip parameter data to obtain slip prediction data; Performing path point collaborative compensation processing on the theoretical cutting path data and the slip prediction data to obtain compensated path data; Dynamic posture constraint optimization processing is performed on the compensated path data and the corrected posture data to obtain optimized path data.

6. The intelligent path planning method for a coal mining robot in a mine according to claim 1, characterized in that: Performing security conflict detection and path adjustment processing based on the optimized path data to obtain path verification mark data and adjusted path data includes: Performing a safety distance conflict scanning process on the optimized path data to obtain conflict marking data; Performing local path replanning processing on the conflict mark data to obtain adjusted path data; Performing efficiency evaluation processing on the adjusted path data to obtain path score data; The path scoring data is subjected to an executable threshold verification process to obtain path verification mark data.

7. The intelligent path planning method for a coal mining robot in a mine according to claim 1, characterized in that: Based on the path verification flag data and the adjusted path data, path output and execution control processing are performed to obtain an actual path execution effect, including: Performing execution instruction conversion processing based on the path verification flag data and the adjusted path data to obtain control instruction data; Performing time sequence scheduling and allocation processing on the control instruction data to obtain time sequence instruction sequence data; Performing actuator compatibility adaptation processing on the timing instruction sequence data to obtain adaptation control data; The actual path execution effect is obtained by sending the adaptive control data to the robot drive unit for processing.

8. The intelligent path planning method for a coal mining robot in a mine according to claim 5, characterized in that: Performing dynamic posture constraint optimization processing on the compensated path data and the corrected posture data to obtain optimized path data, including: Perform dynamic posture constraint modeling and generate constraint rule data; An iterative optimization calculation is performed on the compensated path data based on the constraint rule data to obtain optimized path data.

9. The intelligent path planning method for a coal mining robot in a mine according to claim 4, characterized in that: Perform instantaneous speed deduction processing on the reset distance data, perform multipath effect suppression processing on the original displacement data of the external positioning system, and obtain theoretical walking speed data and actual displacement data, including: Performing instantaneous speed deduction processing on the reset distance data to obtain theoretical walking speed data; The original displacement data of the external positioning system is processed to suppress the multipath effect and obtain the actual displacement data.

10. An intelligent path planning system for a coal mining robot in a mine, characterized in that: It includes: Multi-source data preprocessing module: acquires the original camera image, contact sensor geological data and inertial measurement unit original posture data and preprocesses them to obtain 3D visual data, geological feature data and corrected posture data; Environmental perception correction and modeling module: acquires historical working face data and equipment posture information, combines the three-dimensional visual data, the geological feature data and the correction posture data, performs environmental perception collaborative correction processing, and obtains environmental model data; Walking slip monitoring module: obtains the original walking distance of the motor encoder and the original displacement data of the external positioning system, performs walking slip status monitoring and processing, and obtains the dynamic slip rate; Path planning and slip compensation module: obtains a preset cutting template, combines historical working face geological data in the historical working face data, the corrected posture data, the environmental model data and the dynamic slip rate, performs initial path planning and slip compensation processing, and obtains optimized path data; Safety conflict detection and path adjustment module: performs safety conflict detection and path adjustment processing based on the optimized path data to obtain path verification mark data and adjusted path data; Path output and execution control module: Based on the path verification mark data and the adjusted path data, the module performs path output and execution control processing to obtain the actual path execution effect.

Images