Driving control method and system of unmanned auxiliary transport vehicle in coal mine

Abstract

The application provides a driving control method and system of an unmanned auxiliary transport vehicle in a coal mine, and belongs to the field of unmanned vehicle control. The method comprises the following steps: obtaining a real-time gas concentration distribution of a roadway in a coal mine; determining a dynamic no-entry area of the roadway in the coal mine based on the real-time gas concentration distribution, and generating a real-time feasible area based on the dynamic no-entry area; generating a target transport route of a target vehicle according to the real-time feasible area; controlling the target vehicle to travel along the target transport route at a reference transport speed, and obtaining the flatness of a road in front of the target vehicle in real time through a vehicle-mounted laser radar of the target vehicle; and adjusting the travel speed of the target vehicle in real time according to the flatness of the road in front of the target vehicle, the reference transport speed, an upper limit constraint of the transport speed and a lower limit constraint of the transport speed. The unmanned transport vehicle is controlled according to the dynamic change of the gas concentration and the road condition, so that the transport safety and efficiency are improved.

Description

Technical Field

[0001] This invention relates to the field of unmanned vehicle control, and more particularly to a driving control method and system for unmanned assisted transportation vehicles in coal mines. Background Technology

[0002] In modern coal mine production, the automation and intelligence of underground transportation are increasing. Unmanned assisted transport vehicles, as important equipment for underground coal mine transportation, can effectively reduce manual labor and improve transportation efficiency.

[0003] However, in coal mine production, the distribution of methane concentration in underground roadways is extremely uneven and changes dynamically with factors such as mining progress, ventilation conditions, and geological structure. When transport vehicles travel in areas with high methane concentrations, the friction between the vehicle tires and the ground, the operation of the engine, and the heat and sparks generated during operation can easily trigger a high-concentration methane explosion. On the other hand, the road surface conditions in underground coal mine roadways are complex and variable, with adverse road conditions such as water accumulation, potholes, gravel, and changes in slope, which seriously affect the driving stability and safety of vehicles.

[0004] Existing unmanned underground transport vehicle control systems in coal mines typically employ preset fixed paths and constant speeds. These systems cannot dynamically adjust the travel path based on real-time changes in underground gas concentration, nor can they adjust the speed in real-time to adapt to complex road conditions. When vehicles travel along preset paths, they may enter dangerous areas with excessive gas concentrations, posing serious safety hazards. Furthermore, when encountering complex road conditions, the fixed speed cannot adapt to changes in road conditions, not only affecting transport efficiency but also potentially leading to vehicle damage or cargo spillage. Summary of the Invention

[0005] This invention addresses the technical problems in existing technologies, such as uneven methane concentration distribution and complex road conditions in underground coal mine roadways, which lead to safety hazards and low transportation efficiency in unmanned transport vehicles. It provides a driving control method and system for unmanned assisted transport vehicles in underground coal mines to solve these problems.

[0006] The technical solution of the present invention to solve the above-mentioned technical problems is as follows:

[0007] In a first aspect, the present invention provides a driving control method for an unmanned assisted transport vehicle in an underground coal mine, comprising: acquiring the real-time gas concentration distribution of an underground coal mine roadway; determining a dynamic restricted area of ​​the underground coal mine roadway based on the real-time gas concentration distribution; generating a real-time feasible area based on the dynamic restricted area; generating a target transport route for a target vehicle according to the real-time feasible area, wherein the target vehicle has a reference transport speed, a transport speed upper limit constraint, and a transport speed lower limit constraint; controlling the target vehicle to travel along the target transport route at the reference transport speed, and acquiring the road surface smoothness ahead in real time through the vehicle-mounted lidar of the target vehicle; and adjusting the driving speed of the target vehicle in real time according to the road surface smoothness ahead, the reference transport speed, the transport speed upper limit constraint, and the transport speed lower limit constraint.

[0008] Secondly, the present invention provides a driving control system for an unmanned assisted transport vehicle in an underground coal mine, comprising: a feasible area generation module, used to acquire the real-time gas concentration distribution of underground coal mine roadways, determine dynamic restricted areas of underground coal mine roadways based on the real-time gas concentration distribution, and generate real-time feasible areas based on the dynamic restricted areas; a route planning module, used to generate a target transport route for a target vehicle based on the real-time feasible areas, wherein the target vehicle has a reference transport speed, a transport speed upper limit constraint, and a transport speed lower limit constraint; a vehicle control module, used to control the target vehicle to travel along the target transport route at the reference transport speed, and to acquire the road surface smoothness ahead in real time through the vehicle-mounted lidar of the target vehicle; and a speed adjustment module, used to adjust the driving speed of the target vehicle in real time based on the road surface smoothness ahead, the reference transport speed, the transport speed upper limit constraint, and the transport speed lower limit constraint.

[0009] The beneficial effects of this invention are:

[0010] This system acquires real-time methane concentration distribution data from underground coal mine roadways, determines dynamic restricted zones based on this distribution, and generates real-time feasible zones. It can identify dangerous areas with excessive methane concentrations in underground roadways and designate them as dynamic restricted zones, thus providing a safe driving area for vehicles and preventing accidents caused by vehicles entering high-methane concentration areas. Based on the real-time feasible zones, a target transport route for the target vehicle is generated. The target vehicle has a baseline transport speed, an upper limit constraint, and a lower limit constraint. This allows for the planning of a driving path for the unmanned assisted transport vehicle within a safe feasible area, while pre-setting vehicle speed control parameters to provide basic constraints for subsequent speed adjustments. The target vehicle is controlled to travel along the target transport route at the baseline transport speed. The vehicle's onboard LiDAR acquires real-time information on the road surface smoothness ahead, ensuring the vehicle starts traveling along a safe path. Simultaneously, the LiDAR provides real-time road condition awareness, offering accurate data support for adjusting the driving speed based on road conditions. The target vehicle's speed is adjusted in real time based on the road surface smoothness, the baseline transport speed, the upper limit constraint of the transport speed, and the lower limit constraint of the transport speed. This allows the vehicle to dynamically adjust its speed within the preset speed constraint range according to the actual road conditions, ensuring both driving safety and improving transport efficiency.

[0011] The above technical solutions enable unmanned underground transport vehicles to be intelligently controlled based on dynamic changes in gas concentration and road conditions, thereby improving transport safety and efficiency. Attached Figure Description

[0012] Figure 1 A flowchart illustrating the driving control method for an unmanned assisted transport vehicle in an underground coal mine provided by the present invention;

[0013] Figure 2 This is a schematic diagram of the driving control system for an unmanned underground assisted transport vehicle provided by the present invention.

[0014] In the attached diagram, the components represented by each number are as follows:

[0015] The feasible area generation module 11, the route planning module 12, the vehicle control module 13, and the speed adjustment module 14 are all included. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] In the description of this invention, 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 indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0018] In the description of this invention, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed herein.

[0019] Example 1, as Figure 1 As shown, this embodiment of the invention provides a driving control method for unmanned assisted transportation vehicles in coal mines, including:

[0020] S1. Obtain the real-time gas concentration distribution of underground roadways in the coal mine, determine the dynamic restricted areas of underground roadways in the coal mine based on the real-time gas concentration distribution, and generate real-time feasible areas based on the dynamic restricted areas.

[0021] Specifically, firstly, multiple gas detection points are deployed within the underground roadways of the coal mine to collect real-time gas concentration data from each point. These detection points are distributed at predetermined intervals in key locations within the roadways, including but not limited to roadway bends, near ventilation openings, and areas prone to gas accumulation. Based on the gas concentration data fed back from each detection point, a spatial interpolation algorithm or a gas diffusion model is used to construct a real-time gas concentration distribution covering the entire underground coal mine roadway.

[0022] Then, the acquired real-time gas concentration distribution is compared with a preset gas concentration safety threshold. This safety threshold is determined according to coal mine safety regulations and is typically set at 0.5% or a more stringent value. When the gas concentration in any area of ​​the underground coal mine roadway exceeds this safety threshold, that area and its surrounding safety buffer zone are designated as a dynamic restricted area. This dynamic restricted area is dynamically adjusted according to real-time changes in gas concentration to ensure that transport vehicles avoid high-risk areas.

[0023] Subsequently, within the overall spatial area of ​​the underground coal mine roadways, the already determined dynamic restricted areas are excluded, and the remaining area constitutes the real-time feasible area. The real-time feasible area is the permitted passage range for unmanned transport vehicles. This area has dynamic update characteristics and can be adjusted accordingly based on real-time changes in gas concentration distribution, thereby providing a safe and reliable spatial basis for subsequent route planning.

[0024] Through the above process, real-time safety assessment of the complex underground environment of coal mines is achieved, providing dynamically updated safe passage areas for unmanned transport vehicles and effectively avoiding safety accidents caused by excessive gas concentration.

[0025] S2. Generate a target transportation route for the target vehicle based on the real-time feasible area. The target vehicle has a base transportation speed, an upper limit constraint on transportation speed, and a lower limit constraint on transportation speed.

[0026] Specifically, firstly, based on a defined real-time feasible area, a path planning algorithm is used to generate a target transportation route for the target vehicle, which is an unmanned underground assisted transportation vehicle. Specifically, the coordinates of the target vehicle's starting and ending positions are first obtained; this coordinate information can be obtained through a vehicle positioning system or preset task parameters. Then, within the constraints of the real-time feasible area, the optimal path from the starting position to the ending position is calculated using the A* algorithm, Dijkstra's algorithm, or other path search algorithms, serving as the target transportation route. This target transportation route comprehensively considers factors such as path length, traffic safety, and transportation efficiency to ensure that the generated target transportation route meets both safety requirements and good transportation economy.

[0027] Then, based on the vehicle parameters of the target vehicle and the current transportation task requirements, the baseline transportation speed for the target transportation route is determined. Vehicle parameters include, but are not limited to, technical specifications such as vehicle load capacity, power performance, braking performance, and vehicle dimensions. Transportation task requirements include cargo type, transportation timeliness requirements, and safety level requirements. By comprehensively analyzing the above parameters, a baseline transportation speed suitable for the current transportation conditions is derived, which serves as the standard operating speed for the vehicle under normal operating conditions.

[0028] To ensure the safe and stable operation of the target vehicle in the complex underground environment, upper and lower limits are set for its transport speed. Specifically, based on the technical specifications of the target vehicle and the safety regulations for underground coal mine roadways, a preset upper limit for transport speed is obtained as the upper limit constraint. This upper limit constraint ensures that the vehicle will not pose a safety hazard due to excessive speed under any circumstances. Simultaneously, a preset lower limit for transport speed is obtained as the lower limit constraint. This lower limit constraint ensures that the vehicle can maintain the minimum transport efficiency requirements, preventing the completion of the overall transport task from being affected by excessively slow speeds.

[0029] By generating target transportation routes for target vehicles, intelligent path planning under dynamic safety constraints was achieved, providing target vehicles with transportation routes that are both safe and efficient. At the same time, a speed control parameter system was established, laying the foundation for subsequent dynamic speed adjustments.

[0030] S3. Control the target vehicle to travel along the target transportation route at the benchmark transportation speed, and obtain the road surface smoothness in real time through the vehicle-mounted lidar of the target vehicle.

[0031] Specifically, firstly, based on the generated target transportation route and the determined baseline transportation speed, the target vehicle is controlled to begin performing the transportation task. Specifically, the vehicle control system sends control commands to the target vehicle's drive module, causing the target vehicle to travel along the target transportation route at the baseline transportation speed. The vehicle control system monitors the target vehicle's location and driving status in real time to ensure that the vehicle strictly follows the predetermined target transportation route and maintains stable operation at the baseline transportation speed. This baseline transportation speed serves as the vehicle's initial speed, providing a basic reference for subsequent dynamic speed adjustments based on road conditions.

[0032] During the vehicle's journey, an onboard LiDAR system provides real-time perception and assessment of the road conditions ahead. Specifically, the LiDAR emits a laser beam towards a pre-defined distance range in front of the vehicle and receives the reflected laser signals. By analyzing the time difference, reflection intensity, and spatial distribution characteristics of the laser signals, three-dimensional geometric information of the road surface is obtained. Based on this information, parameters such as elevation changes, slope changes, and surface undulations are calculated to determine the road surface smoothness. This smoothness reflects the real-time road quality of the area the vehicle is about to pass through, providing crucial information for dynamic speed adjustments.

[0033] Through the above process, stable operation control of the target vehicle on the predetermined route was achieved, and real-time perception of the road conditions ahead was established, laying the foundation for intelligent speed adjustment based on road conditions.

[0034] S4. Adjust the driving speed of the target vehicle in real time based on the road surface smoothness ahead, the reference transport speed, the upper limit constraint of the transport speed, and the lower limit constraint of the transport speed.

[0035] Specifically, firstly, based on the acquired road surface smoothness ahead and the determined baseline transport speed, a transport speed adjustment coefficient is calculated. Specifically, a baseline road surface smoothness is determined based on the target vehicle's baseline transport speed. This baseline road surface smoothness threshold is a reference value for road surface smoothness when the vehicle is traveling normally at the baseline transport speed. Then, the real-time acquired road surface smoothness ahead is compared and analyzed with the baseline road surface smoothness. When the road surface smoothness ahead is better than the baseline road surface smoothness threshold, a transport speed adjustment coefficient greater than 1 is generated; when the road surface smoothness ahead is worse than the baseline road surface smoothness threshold, a transport speed adjustment coefficient less than 1 is generated. Through this method, a transport speed adjustment coefficient that reflects the degree to which current road conditions affect the driving speed is obtained.

[0036] Then, the adjusted transport speed is calculated by multiplying the transport speed adjustment coefficient by the base transport speed. This adjusted transport speed comprehensively considers the vehicle's base transport speed and actual road conditions, optimizing driving efficiency while ensuring transport safety. Subsequently, the calculated adjusted transport speed is compared with the set upper and lower limits of the transport speed constraint. When the adjusted transport speed is between the upper and lower limits, it is directly used as the actual driving speed of the target vehicle. When the adjusted transport speed exceeds the upper limit, to avoid safety hazards caused by excessive speed, the upper limit value is used as the target vehicle's driving speed. When the adjusted transport speed is lower than the lower limit, to ensure basic transport efficiency requirements, the lower limit value is used as the target vehicle's driving speed.

[0037] Through the above process, intelligent dynamic adjustment of the target vehicle's speed is achieved. It can adaptively optimize the vehicle's speed within safety constraints based on real-time changes in the road surface smoothness, thereby improving transportation efficiency while ensuring transportation safety.

[0038] Furthermore, the real-time gas concentration distribution of underground coal mine roadways is obtained, dynamic restricted areas of the underground coal mine roadways are determined based on the gas concentration distribution, and real-time feasible areas are generated based on the dynamic restricted areas, including:

[0039] S11. Receive the effective gas concentration of multiple gas detection points, wherein each of the gas detection points is distributed in the underground roadway of the coal mine;

[0040] S12. Based on the effective gas concentration of multiple gas detection points, generate the real-time gas concentration distribution of underground roadways in coal mines;

[0041] S13. Obtain the safe threshold for gas concentration and obtain the roadway space area of ​​the underground roadway in the coal mine;

[0042] S14. Based on the real-time gas concentration distribution, the area in the roadway space where the gas concentration exceeds the gas concentration safety threshold is determined as a dynamic restricted area;

[0043] S15. The area in the alleyway space region excluding the dynamic restricted area is determined as the real-time feasible area.

[0044] In one feasible implementation, firstly, multiple gas detection points are deployed within underground coal mine roadways to receive real-time data on the effective gas concentration at each point. These gas detection points are distributed throughout the underground roadways according to a predetermined spatial layout, which includes, but is not limited to, uniform distribution at preset intervals within the roadways, and denser placement at key locations such as main roadways, branch passages, ventilation nodes, and hazardous areas prone to gas accumulation. Uniform distribution ensures comprehensive monitoring coverage of the entire roadway space, while denser placement at key locations improves monitoring accuracy in high-risk areas. Each gas detection point uses a gas concentration sensor to monitor the gas concentration at its location in real time, and the data is processed and verified to obtain the effective gas concentration for each detection point.

[0045] Subsequently, based on the effective gas concentrations received from multiple gas detection points, a real-time gas concentration distribution map covering the entire underground coal mine roadway is generated using spatial interpolation algorithms or gas diffusion mathematical models. Specifically, spatial analysis methods such as Kriging interpolation, inverse distance weighting, or triangular mesh interpolation are used to calculate estimated gas concentrations in the regions between each gas detection point, thereby constructing a continuous spatial distribution of gas concentration. This real-time gas concentration distribution can comprehensively reflect the spatial distribution characteristics and concentration variation trends of gas within the underground coal mine roadway.

[0046] Next, the safe threshold for methane concentration, preset according to the coal mine safety operation procedures, is obtained. This safe threshold is typically set at 0.5% or a more stringent value determined based on specific coal mine conditions. Simultaneously, the spatial area of ​​the underground coal mine roadways is acquired, including the roadway's geometric dimensions, spatial coordinate range, and the boundary definition of passable areas. This roadway spatial area provides a spatial reference for subsequent dynamic delineation of restricted areas and real-time generation of feasible areas.

[0047] Then, based on the generated real-time gas concentration distribution, areas within the roadway space where the gas concentration exceeds the safe gas concentration threshold are identified and designated as dynamically restricted zones. These dynamically restricted zones include not only areas where the gas concentration directly exceeds the limit but also safety buffer zones surrounding these areas to ensure that transport vehicles maintain a sufficient safe distance from high-risk areas. These dynamically restricted zones are dynamically updated as the gas concentration distribution changes in real time. Afterward, the remaining area within the roadway space, excluding the identified dynamically restricted zones, is designated as the real-time feasible area. This real-time feasible area represents the spatial range within which target vehicles can safely pass at the current moment. It possesses dynamic updating characteristics, capable of adjusting its boundaries in real time according to changes in the gas concentration distribution, providing a safe and reliable basis for subsequent route planning.

[0048] Through the above steps, precise monitoring and dynamic zoning of gas safety conditions in underground coal mine roadways are achieved, providing real-time updated safe passage zones for unmanned transport vehicles.

[0049] Furthermore, each of the aforementioned gas detection points has two gas concentration detectors; receiving the effective gas concentration from multiple gas detection points, including:

[0050] S111. Traverse the plurality of gas detection points, determine the first gas detection point, and obtain the first gas concentration and the second gas concentration detected by the two gas concentration detectors of the first gas detection point.

[0051] S112. Calculate the concentration difference between the first gas concentration and the second gas concentration, and determine whether the concentration difference is within a preset error range;

[0052] S113. When the concentration difference is within the preset error range, calculate the average value of the first gas concentration and the second gas concentration as the effective gas concentration of the first gas detection point;

[0053] S114. When the concentration difference exceeds the preset error range, extract the effective gas concentration of adjacent gas detection points around the first gas detection point, and combine the first gas concentration and the second gas concentration to obtain the effective gas concentration of the first gas detection point.

[0054] In a preferred embodiment, each gas detection point is equipped with two independent gas concentration detectors. These two detectors use the same sensor model and technical specifications, but are physically installed independently, each with its own independent signal acquisition circuit and data processing module. The two independent gas concentration detectors simultaneously monitor the gas concentration at the same spatial location in real time, thereby effectively identifying and correcting measurement errors caused by a single gas concentration detector due to factors such as sensor aging, environmental interference, or circuit failure, thus improving the accuracy and overall reliability of gas concentration detection.

[0055] First, following a pre-defined sequence of detection point numbers, multiple gas detection points deployed in the underground coal mine roadways are processed one by one using a loop-based approach. Specifically, within the current detection cycle, one detection point is selected as the first gas detection point for data processing. Simultaneously, the gas concentration values ​​independently detected by the two gas concentration detectors configured within this first gas detection point at the same timestamp are acquired. The detection result of the first detector is recorded as the first gas concentration, and the detection result of the second detector is recorded as the second gas concentration. This acquisition process is implemented through a data acquisition interface, ensuring the temporal synchronization and spatial consistency of the two concentration values.

[0056] Then, a consistency analysis is performed on the data from the two detectors at the first gas detection point. Specifically, the absolute difference between the first and second gas concentrations is calculated as the concentration difference, which directly reflects the degree of deviation between the measurement results of the two gas concentration detectors. The calculated concentration difference is then numerically compared with a preset error range. The preset error range is determined comprehensively based on the technical accuracy of the gas concentration detector, the measurement uncertainty of the coal mine environment, and safety requirements. It is typically set to 2-3 times the standard measurement accuracy of the gas concentration detector. For example, when the gas concentration detector accuracy is ±0.01%, the preset error range can be set to 0.02%-0.03%.

[0057] When the calculated concentration difference is less than or equal to the preset error range, the measurement results of the two gas concentration detectors are considered to have good consistency, indicating that the detection work is normal and the measurement data has high reliability. In this case, the arithmetic mean method is used to process the two detection results, that is, the first gas concentration and the second gas concentration are added together and then divided by 2, and the average value is taken as the effective gas concentration of the first gas detection point. This averaging method can effectively eliminate the influence of random measurement errors, improve the statistical accuracy of the detection results, and provide a more reliable data basis for subsequent safe zone delineation.

[0058] When the calculated concentration difference exceeds the preset error range, it is determined that there is a significant difference between the measurement results of the two gas concentration detectors. Possible reasons include a malfunction in one of the detectors, sensor interference from the local environment, detector calibration drift, or rapid changes in gas concentration at the detection point. In this case, an abnormal data verification and processing mechanism is activated. Specifically, firstly, the effective gas concentration values ​​of adjacent gas detection points within a preset range (e.g., within a 50-meter radius) around the first gas detection point are identified and extracted as spatial reference benchmarks. Then, based on the spatial continuity of gas in the underground roadway, a spatial interpolation algorithm or gas concentration gradient analysis method is used to calculate the theoretical gas concentration estimate at the location of the first gas detection point, i.e., the estimated gas concentration. Next, the deviations between the first and second gas concentrations and the estimated gas concentration are calculated respectively. By comparing and analyzing, it is determined which gas concentration detector's measurement result is closer to the estimated gas concentration, or whether both gas concentration detectors' measurement results have large deviations, thus obtaining the verification analysis results. Ultimately, based on the verification analysis results, the gas concentration detected by the gas concentration detector with the smaller deviation is selected as the effective gas concentration, or when the measurement results of both gas concentration detectors are abnormal, the estimated gas concentration is used as the effective gas concentration of the first gas detection point.

[0059] Through the aforementioned redundant detection and multi-level verification, comprehensive assurance of the quality of gas concentration detection data is achieved. This not only effectively identifies and corrects measurement errors of single-point detectors, but also improves the accuracy of abnormal data processing through spatial correlation analysis, thereby providing highly reliable gas concentration monitoring data support for the safe operation of unmanned transport vehicles in coal mines.

[0060] Furthermore, when the concentration difference exceeds the preset error range, the effective gas concentration of adjacent gas detection points of the first gas detection point is extracted, and the effective gas concentration of the first gas detection point is obtained by combining the first gas concentration and the second gas concentration, including:

[0061] S1141. Based on the effective gas concentration of the adjacent gas detection points, obtain the estimated gas concentration of the first gas detection point;

[0062] S1142. Calculate the first error value between the first gas concentration and the estimated gas concentration, and the second error value between the second gas concentration and the estimated gas concentration, respectively.

[0063] S1143. Determine whether the first error value and the second error value are within the preset verification error range;

[0064] S1144. When the first error value is within the preset verification error range and the second error value exceeds the preset verification error range, the first gas concentration is taken as the effective gas concentration of the first gas detection point.

[0065] S1145. When the second error value is within the preset verification error range and the first error value exceeds the preset verification error range, the second gas concentration is taken as the effective gas concentration of the first gas detection point.

[0066] S1146. When both the first error value and the second error value exceed the preset verification error range, the estimated gas concentration is taken as the effective gas concentration of the first gas detection point.

[0067] In a preferred embodiment, firstly, based on the effective gas concentrations of adjacent gas detection points around the first gas detection point, a spatial interpolation algorithm is used to calculate the estimated gas concentration of the first gas detection point. Specifically, firstly, adjacent gas detection points within a preset distance range (e.g., a radius of 30-100 meters) around the first gas detection point are identified, and the effective gas concentrations of these adjacent detection points are obtained. Then, based on the spatial distance relationship between each adjacent detection point and the first gas detection point, spatial analysis methods such as inverse distance weighted interpolation, Kriging interpolation, or triangular mesh interpolation are used to calculate a theoretical estimate of the gas concentration at the location of the first gas detection point, which serves as the estimated gas concentration of the first gas detection point. This estimated gas concentration, based on the continuous spatial distribution characteristics of gas in underground roadways, can provide a reliable reference benchmark for verifying abnormal data.

[0068] Then, the deviation between the measurement results (first gas concentration and second gas concentration) of the two gas concentration detectors at the first gas detection point and the estimated gas concentration is calculated. Specifically, the absolute difference between the first gas concentration and the estimated gas concentration is calculated as the first error value, reflecting the reliability of the first detector's measurement result. Simultaneously, the absolute difference between the second gas concentration and the estimated gas concentration is calculated as the second error value, reflecting the reliability of the second detector's measurement result. Through error value calculation, the accuracy of the measurement results of the two gas concentration detectors relative to the spatial estimation benchmark can be quantitatively assessed. Subsequently, the calculated first and second error values ​​are compared with preset verification error ranges. The preset verification error range is determined based on the accuracy characteristics of the spatial interpolation algorithm, the distribution density of adjacent detection points, and the spatial variability of gas concentration, and is typically set to 5%-15% of the estimated gas concentration or 0.05%-0.1% of the absolute error value. This judgment process provides a decision-making basis for subsequent selection of effective concentrations.

[0069] When the first error value is within the preset calibration error range and the second error value exceeds the preset calibration error range, it indicates that the measurement result of the first gas concentration detector has good consistency with the spatial estimate, while the measurement result of the second gas concentration detector has a large deviation. This may be due to a malfunction of the gas concentration detector, calibration drift, or interference from the local environment. In this case, the measurement data of the first detector is deemed to have higher reliability, and the first gas concentration is directly taken as the effective gas concentration of the first gas detection point. When the second error value is within the preset calibration error range and the first error value exceeds the preset calibration error range, it indicates that the measurement result of the second gas concentration detector has good consistency with the spatial estimate, while the measurement result of the first gas concentration detector has a large deviation. This situation indicates that the second gas concentration detector is working normally while the first gas concentration detector is malfunctioning. In this case, the measurement data of the second gas concentration detector is deemed to have higher reliability, and the second gas concentration is directly taken as the effective gas concentration of the first gas detection point.

[0070] When both the first and second error values ​​exceed the preset calibration error range, it indicates that the measurement results of the two gas concentration detectors deviate significantly from the spatial estimate. This may be due to special gas distribution conditions at the detection point location, simultaneous malfunction of both gas concentration detectors, or a sudden change in gas concentration at that location. In this case, the estimated gas concentration calculated based on data from adjacent gas detection points is used as the effective gas concentration for the first gas detection point to ensure spatial consistency and overall reliability of the data.

[0071] Through the above-mentioned multi-level verification and decision-making mechanism, intelligent processing of abnormal gas concentration data is realized, which can determine the most reliable effective gas concentration under various complex conditions, providing high-quality data support for the safe zone division of underground roadways in coal mines and the safe operation of unmanned transport vehicles.

[0072] Furthermore, a target transportation route for the target vehicle is generated based on the real-time feasible area. The target vehicle has a baseline transportation speed, an upper limit constraint on transportation speed, and a lower limit constraint on transportation speed, including:

[0073] S21. Obtain the starting position and ending position of the target vehicle;

[0074] S22. Within the real-time feasible area, generate a target transportation route based on the starting position and the ending position;

[0075] S23. Determine the base transportation speed of the target transportation route based on the vehicle parameters of the target vehicle and the transportation task requirements;

[0076] S24. Obtain the preset upper limit value of the target vehicle's transport speed as the upper limit constraint, and obtain the preset lower limit value of the target vehicle's transport speed as the lower limit constraint.

[0077] In one feasible implementation, firstly, the starting and ending coordinates of the target vehicle are obtained through an onboard positioning system or preset transportation task parameters. Specifically, the starting position is the current spatial location of the target vehicle or the loading starting point of the transportation task, and its precise coordinates in the coal mine roadway coordinate system are obtained through positioning technologies such as GPS positioning, inertial navigation systems, or underground positioning base stations. The ending position is the unloading location of the goods specified in the transportation task or the vehicle's predetermined arrival location; this location information can be preset or transmitted in real time through the transportation management system. The accurate acquisition of the starting and ending positions provides a spatial reference for subsequent route planning.

[0078] Then, within the defined real-time feasible area, based on the acquired start and end positions, a path planning algorithm is used to generate the optimal target transportation route. Specifically, using the real-time feasible area as the spatial constraint for vehicle passage, the A* algorithm, Dijkstra's algorithm, fast expanding random tree algorithm, or other applicable path search algorithms are used to calculate the optimal path from the start to the end position within the real-time feasible area, thus obtaining the target transportation route. This target transportation route, while satisfying gas safety constraints, comprehensively considers optimization objectives such as shortest path length, minimum travel time, and lowest energy consumption, ensuring that the generated route possesses both safety and reliability, as well as good transportation economy and efficiency.

[0079] Subsequently, based on the vehicle parameters of the target vehicle and the current transportation task requirements, a benchmark transportation speed corresponding to the target transportation route is determined through comprehensive analysis and calculation. Vehicle parameters include, but are not limited to, the target vehicle's maximum load capacity, engine power, braking system performance, turning radius, vehicle length, width, height, and other geometric dimensions, as well as tire specifications and other technical indicators. Transportation task requirements include the type of goods being transported (e.g., coal, equipment, materials), cargo weight, transportation timeliness requirements (e.g., emergency transport, routine transport), safety level requirements, and roadway environmental conditions. By establishing a matching model between vehicle performance and transportation conditions, a suitable benchmark transportation speed under the current transportation conditions is calculated. This speed serves as a reference value for the standard driving speed of the target vehicle under normal operating conditions.

[0080] Meanwhile, to ensure the safe and stable operation of the target vehicle in the complex environment of underground coal mine roadways, upper and lower limits are set for the vehicle's transport speed. Specifically, based on the target vehicle's technical specifications, manufacturer-recommended parameters, and safe operating procedures for underground coal mine roadways, a preset upper limit for the target vehicle's transport speed in the underground environment is obtained as the upper limit constraint. This upper limit constraint ensures that the target vehicle will not exceed the safe braking distance, cause rollover risks, or generate other safety hazards due to excessive speed under any operating condition. Simultaneously, a preset lower limit for the target vehicle's transport speed is obtained as the lower limit constraint. This lower limit constraint ensures that the vehicle can maintain basic traction and climbing ability, preventing problems such as the vehicle slipping on slopes due to excessively low speed, affecting transport efficiency, or causing traffic congestion.

[0081] Through the above steps, intelligent path planning and vehicle operation parameter setting based on dynamic safety zones were realized, providing the target vehicle with a transportation solution that combines safety, reliability and economy. At the same time, a speed control parameter system was established, laying the foundation for subsequent dynamic speed adjustment based on road conditions.

[0082] Furthermore, the road surface smoothness ahead is acquired in real time through the vehicle-mounted lidar of the target vehicle, including:

[0083] S31. Scan the road surface within a preset distance range in front of the target vehicle using the vehicle-mounted lidar to obtain road surface scanning data.

[0084] S32. Input the forward road surface scanning data into the road surface smoothness evaluator to obtain the forward road surface smoothness.

[0085] In one feasible implementation, firstly, an onboard LiDAR installed at the front of the target vehicle performs real-time laser scanning of the road surface area within a preset distance range in front of the target vehicle to acquire road surface scanning data. Specifically, the onboard LiDAR uses a multi-beam laser emitter to emit laser beams within a preset distance range in front of the target vehicle. This preset distance range is determined based on the vehicle's speed and braking distance requirements, typically set to 10-50 meters. The onboard LiDAR scans the road surface ahead at a preset scanning frequency (e.g., 10-20Hz) and angular resolution (e.g., 0.1°-0.5°), with the laser beam covering a fan-shaped area in front of the vehicle, and the scanning width matching the width of the vehicle's driving lane. When the laser beam illuminates the road surface, the onboard LiDAR's receiver detects the reflected laser signal and records information such as the laser signal's time of flight, reflection intensity, and reflection angle. Based on the principle of laser ranging, the distance data from the LiDAR to various points on the road surface is determined by calculating the round-trip time difference of the laser signal. By combining the installation location and emission angle of the lidar with the vehicle's motion state, the distance data is converted into coordinate information of various points on the road surface in a three-dimensional spatial coordinate system, thus obtaining the forward road surface scanning data. This forward road surface scanning data is stored in point cloud data format, containing information such as the three-dimensional coordinates (x, y, z), reflection intensity values, and timestamps of a large number of sampling points on the road surface, comprehensively describing the spatial geometric features of the forward road surface.

[0086] Then, the acquired road surface scan data is input into a pre-trained road surface smoothness evaluator for analysis and processing to obtain the road surface smoothness. Specifically, the road surface smoothness evaluator receives the road surface scan data in point cloud format as input, processes the data, and derives a quantitative value characterizing the road surface smoothness, i.e., the road surface smoothness. This road surface smoothness is represented in a dimensionless form; a larger smoothness indicates a smoother road surface, and a smaller smoothness indicates a rougher road surface. The output road surface smoothness value is updated in real time, providing an accurate road condition assessment basis for subsequent dynamic adjustment of vehicle speed.

[0087] Through the above steps, accurate perception and quantitative assessment of the road conditions ahead are achieved, providing reliable road information support for the intelligent speed control of unmanned transport vehicles, and ensuring that the vehicle can adjust its driving speed appropriately according to actual road conditions.

[0088] Furthermore, the construction steps of the road surface evenness evaluator include:

[0089] S321. Collect historical forward road surface scanning records, and construct a sample forward road surface scanning dataset based on the historical forward road surface records;

[0090] S322. Mark the road surface smoothness of each sample road surface scan data in the sample road surface scan dataset to obtain the sample road surface smoothness set.

[0091] S323. Based on the sample front road surface scan dataset and the sample front road surface smoothness set, train and generate the road surface smoothness evaluator.

[0092] In a preferred embodiment, firstly, a sample forward road surface scan dataset for training is constructed using historical forward road surface scan records. Specifically, in different underground coal mine roadways, a large number of laser scans are conducted using a vehicle-mounted LiDAR of the same model or similar specifications as the target vehicle. The collection range covers various typical road surface conditions, including but not limited to smooth concrete roads, slightly undulating gravel roads, damaged roads with potholes, slippery roads with water accumulation, sloping roads with varying gradients, and complex roads with obstacles. Each historical forward road surface scan record obtained from a scan contains complete point cloud data, recording the three-dimensional geometric information of the road surface, the reflection intensity distribution, and environmental parameters during the scan. The large number of historical forward road surface scan records are classified, organized, and quality-screened, removing records with poor scan quality, missing data, or obvious errors. Finally, a sample forward road surface scan dataset is constructed. This sample forward road surface scan dataset is organized according to a unified data format to ensure the structural consistency of each sample data.

[0093] Subsequently, professional road surface smoothness annotation was performed on the road surface scan data of each sample in the sample road surface scan dataset, establishing a correspondence between input data and output labels. Specifically, an annotation team composed of experienced road engineering experts, vehicle engineers, and coal mine safety technicians was invited to manually evaluate and annotate the road surface scan data of each sample in the sample road surface scan dataset. The annotators quantitatively evaluated the road surface smoothness of each sample's road surface scan data based on road surface smoothness evaluation specifications and coal mine underground road surface quality requirements, combined with the three-dimensional geometric features of the road surface obtained by laser scanning. During the annotation process, the expert team comprehensively considered multiple evaluation indicators such as the road surface elevation variation, slope continuity, surface roughness, and local defect density, assigning each sample a numerical label characterizing road surface smoothness. This numerical label adopted a standardized scoring system, such as a scoring range of 0-100, where a higher road surface smoothness value indicates a smoother road surface, and a lower value indicates a more uneven road surface. To ensure annotation quality and consistency, a multi-person cross-annotation and expert review mechanism was adopted to discuss and unify standards for samples with differing opinions. The final obtained sample road surface smoothness set contains smoothness labels that correspond one-to-one with the sample road surface scanning dataset, thus obtaining the sample road surface smoothness set, which provides accurate supervision signals for subsequent model training.

[0094] Subsequently, based on the constructed sample forward road surface scan dataset and the corresponding sample forward road surface evenness set, a road surface evenness estimator is trained using machine learning algorithms. Specifically, firstly, a neural network architecture suitable for point cloud data processing is designed. PointNet, PointNet++, or a point cloud processing model based on convolutional neural networks can be selected as the basic architecture, including a network input layer, a feature extraction part of the network, and a network output layer. The network input layer is designed to receive standardized point cloud data in a format including feature information such as the three-dimensional coordinates and reflection intensity of points, i.e., forward road surface scan data. The network feature extraction part automatically learns the spatial geometric and statistical features related to evenness in the road surface point cloud data through multi-layer convolution, pooling, and fully connected operations. The network output layer is designed to output a single numerical value, representing the predicted road surface evenness value. Then, the sample forward road surface scan dataset and the corresponding sample forward road surface evenness set are divided into training, validation, and test sets in a 7:2:1 ratio to ensure the scientific nature and generalization ability of the model training. Mean squared error or mean absolute error is used as the loss function to measure the difference between the predicted value and the true labeled value. Gradient descent training is performed using optimization algorithms such as Adam or SGD, and network parameters are continuously adjusted through backpropagation to minimize prediction error. Early stopping, learning rate decay, and regularization techniques are employed during training to prevent overfitting. After sufficient iterative training, model performance is validated on a test set to ensure the road surface evenness estimator has good prediction accuracy and stability on unseen data. The final trained road surface evenness estimator can receive real-time road surface scan data ahead and quickly and accurately output the corresponding road surface evenness assessment results.

[0095] Through the above construction process, the intelligent assessment capability of road surface smoothness based on big data and artificial intelligence technology has been realized, providing an accurate and reliable road condition perception tool for unmanned underground transport vehicles in coal mines, supporting subsequent dynamic speed control decisions.

[0096] Furthermore, the target vehicle's speed is adjusted in real time based on the road surface smoothness ahead, the baseline transport speed, the upper limit constraint of the transport speed, and the lower limit constraint of the transport speed, including:

[0097] S41. Based on the reference transport speed of the target vehicle, determine the reference road surface smoothness, and combine it with the road surface smoothness ahead to obtain the transport speed adjustment coefficient.

[0098] S42. Obtain the adjusted transport speed based on the transport speed adjustment coefficient and the reference transport speed;

[0099] S43. Determine whether the adjusted transport speed is between the upper limit constraint and the lower limit constraint of the transport speed;

[0100] S44. When the adjusted transport speed is between the upper limit constraint and the lower limit constraint of the transport speed, the adjusted transport speed shall be used as the driving speed of the target vehicle.

[0101] S45. When the adjusted transport speed exceeds the upper limit constraint of the transport speed, the upper limit constraint of the transport speed shall be used as the driving speed of the target vehicle.

[0102] S46. When the adjusted transport speed is lower than the lower limit constraint of the transport speed, the lower limit constraint of the transport speed shall be used as the driving speed of the target vehicle.

[0103] In a preferred embodiment, firstly, a reference road surface smoothness is determined based on the target vehicle's reference transport speed, and a transport speed adjustment coefficient is calculated by combining this with the real-time acquired road surface smoothness ahead. Specifically, firstly, based on the determined reference transport speed, the reference road surface smoothness corresponding to this reference transport speed is determined by consulting vehicle technical specifications or experience data tables. This reference road surface smoothness represents the road quality standard required for the target vehicle to safely travel at the reference transport speed under standard operating conditions, and is typically determined comprehensively based on factors such as the vehicle's suspension system performance, tire specifications, and load conditions. Then, the acquired road surface smoothness ahead is compared and analyzed with the reference road surface smoothness to calculate the transport speed adjustment coefficient. Specifically, the ratio of the road surface smoothness ahead to the reference road surface smoothness is calculated as the transport speed adjustment coefficient. When the road surface smoothness ahead is greater than the reference road surface smoothness, it indicates that the road surface quality ahead is better than the reference road surface smoothness, and the transport speed adjustment coefficient is greater than 1. When the road surface smoothness ahead is less than or equal to the reference road surface smoothness, it indicates that the road surface quality ahead is worse than or equal to the reference road surface smoothness, and the transport speed adjustment coefficient is less than or equal to 1.

[0104] Then, numerical calculations are performed based on the calculated transport speed adjustment coefficient and the determined baseline transport speed to obtain the adjusted transport speed, taking into account the influence of road conditions. Specifically, the baseline transport speed is multiplied by the transport speed adjustment coefficient. This adjusted transport speed comprehensively reflects the matching relationship between the vehicle's standard operating parameters and actual road conditions, optimizing driving efficiency while ensuring transport safety. When the road surface ahead is smooth, the adjusted transport speed will be higher than the baseline transport speed, which is beneficial for improving transport efficiency; when the road surface ahead is uneven, the adjusted transport speed will be lower than the baseline transport speed, which is beneficial for ensuring driving safety. Subsequently, the obtained adjusted transport speed is numerically compared with the set upper and lower limits of transport speed constraints to determine whether the adjusted transport speed is within the allowable speed range. The specific judgment logic is to check whether the adjusted transport speed exceeds the upper limit constraint or is lower than the lower limit constraint. This judgment process ensures that the final determined driving speed will not exceed the boundary conditions for the safe operation of the target vehicle, avoiding safety risks or efficiency problems due to excessively high or low speeds.

[0105] When the assessment result indicates that the adjusted transport speed falls between the upper and lower limits of the transport speed constraint, this adjusted transport speed is directly used as the actual driving speed of the target vehicle. At this point, the vehicle control system sends a speed control command to the drive module, causing the target vehicle to travel at the adjusted transport speed. This demonstrates that the speed adjustment result calculated based on road surface smoothness is reasonable and feasible, and can achieve adaptive response to changes in road conditions within safe constraints.

[0106] When the assessment indicates that the adjusted transport speed exceeds the upper limit constraint, to prevent insufficient braking distance, excessive turning radius, or other safety hazards due to excessive speed, the upper limit constraint value is set as the actual speed of the target vehicle. At this point, the vehicle control system sends a speed limit command to ensure the target vehicle's speed does not exceed the preset safety limit. This mechanism ensures that even under ideal road conditions, the target vehicle remains within a safe and controllable speed range.

[0107] When the assessment indicates that the adjusted transport speed is below the lower limit constraint, to avoid problems such as insufficient traction, reduced climbing ability, or severely impacted transport efficiency due to excessively low speed, the lower limit constraint value is used as the actual driving speed of the target vehicle. At this time, the vehicle control system sends a minimum speed maintenance command to ensure that the target vehicle can maintain basic transport capacity and traffic efficiency even under adverse road conditions. This mechanism guarantees the continuity and reliability of transport tasks, preventing transport interruptions due to poor road conditions.

[0108] Through the above dynamic speed adjustment, the intelligent matching between the target vehicle's speed and the road surface smoothness is achieved, maximizing transportation efficiency while ensuring transportation safety, and providing a complete adaptive speed control solution for unmanned underground transportation vehicles in coal mines.

[0109] Furthermore, embodiments of this application also include:

[0110] S51. The dynamic restricted area determined based on the real-time gas concentration distribution is taken as the first dynamic restricted area.

[0111] S52. Identify areas in coal mine underground roadways where the dust concentration during historical transportation processes exceeds a preset dust concentration threshold, and designate these areas as the second dynamic restricted area.

[0112] S53. Calculate the union of the first dynamic restricted area and the second dynamic restricted area to obtain the comprehensive dynamic restricted area;

[0113] S54. The area in the alleyway space region excluding the comprehensive dynamic restricted area is determined as the real-time feasible area.

[0114] In a preferred embodiment, a method for determining dynamic restricted areas that comprehensively considers multiple safety factors is further provided. By integrating two indicators, methane concentration and dust concentration, a more comprehensive control of safe areas is achieved.

[0115] First, the dynamically restricted areas defined based on real-time methane concentration distribution are redefined as the first dynamic restricted area. This first dynamic restricted area is specifically designed to manage methane safety risks and includes all areas where methane concentrations exceed the safe threshold, along with their surrounding safety buffer zones. The first dynamic restricted area is dynamically updated in real-time with changes in methane concentration distribution, ensuring that unmanned transport vehicles avoid high-risk areas with excessive methane concentrations and preventing accidents caused by methane safety issues.

[0116] Simultaneously, by analyzing historical dust monitoring data from underground coal mine roadways, areas with dust concentrations exceeding preset dust concentration thresholds are identified and designated as second dynamic restricted areas. Specifically, firstly, dust concentration data recorded by dust concentration monitoring equipment deployed in underground coal mine roadways during historical transportation activities is collected. This data covers dust distribution under different time periods, transportation intensities, and cargo types. Then, based on coal mine occupational health and safety standards and underground air quality requirements, preset dust concentration thresholds are set, typically referencing limits for inhalable particulate matter or total suspended particulate matter. Next, through data mining and statistical analysis, spatial areas in historical data where dust concentrations exceed preset thresholds are identified. These areas are usually located at cargo loading / unloading points, frequently used vehicle routes, poorly ventilated areas, or low-lying areas where dust easily accumulates. Finally, areas with dust concentrations exceeding preset thresholds are marked as second dynamic restricted areas. These areas are primarily used to prevent adverse effects on equipment operation, personnel health, or environmental safety caused by excessive dust concentrations.

[0117] Then, a union operation is used to calculate the union of the first and second dynamic restricted areas, resulting in a comprehensive dynamic restricted area that considers both gas safety and dust control. Specifically, the first and second dynamic restricted areas are overlaid in the same spatial coordinate system to identify the overlapping and independent parts of the two areas. The union operation result includes all spatial ranges belonging to either the first or second dynamic restricted area, ensuring that any area with a risk of exceeding gas or dust standards is included in the restricted area control scope. This comprehensive dynamic restricted area achieves unified management of multiple safety factors, providing a more comprehensive and stringent safety assurance mechanism.

[0118] Subsequently, within the overall spatial area of ​​the underground coal mine roadways, the determined comprehensive dynamic restricted areas were excluded, and the remaining areas were redefined as real-time feasible areas. These real-time feasible areas simultaneously meet both gas safety and dust control requirements, providing unmanned transport vehicles with a passage space that has undergone multi-dimensional safety verification. Compared to feasible areas that only consider gas factors, these real-time feasible areas offer a higher level of safety assurance and stronger environmental adaptability, effectively avoiding potential risks caused by insufficient consideration of a single safety factor. This area dynamically adjusts with changes in gas concentration distribution and dust conditions, providing a more reliable spatial basis for subsequent path planning and speed control.

[0119] By comprehensively considering the above-mentioned multi-dimensional safety factors, a comprehensive safety assessment and refined management of the complex underground environment of coal mines have been achieved, providing a more complete safety guarantee for unmanned transport vehicles and effectively improving the overall safety level and reliability of underground transportation operations.

[0120] Example 2, as Figure 2 As shown, based on the same inventive concept as the driving control method for the unmanned underground assisted transport vehicle provided in Embodiment 1, this embodiment of the invention also provides a driving control system for the unmanned underground assisted transport vehicle, including:

[0121] The feasible area generation module 11 is used to obtain the real-time gas concentration distribution of underground roadways in coal mines, determine the dynamic restricted areas of underground roadways in coal mines based on the real-time gas concentration distribution, and generate real-time feasible areas based on the dynamic restricted areas.

[0122] Route planning module 12 is used to generate a target transportation route for a target vehicle based on the real-time feasible area. The target vehicle has a base transportation speed, a transportation speed upper limit constraint, and a transportation speed lower limit constraint.

[0123] The vehicle control module 13 is used to control the target vehicle to travel along the target transportation route at the reference transportation speed, and to obtain the road surface smoothness in real time through the vehicle-mounted lidar of the target vehicle.

[0124] The speed adjustment module 14 is used to adjust the driving speed of the target vehicle in real time according to the road surface smoothness ahead, the reference transport speed, the upper limit constraint of the transport speed and the lower limit constraint of the transport speed.

[0125] Furthermore, the feasible region generation module 11 includes the following execution steps:

[0126] The effective gas concentration of multiple gas detection points is received, wherein each of the gas detection points is distributed in the underground roadway of the coal mine;

[0127] Based on the effective gas concentration at multiple gas detection points, the real-time gas concentration distribution in underground coal mine roadways is generated.

[0128] Obtain the safe threshold for gas concentration and the roadway space area of ​​the underground roadway in the coal mine;

[0129] Based on the real-time gas concentration distribution, areas in the roadway space where the gas concentration exceeds the gas concentration safety threshold are identified as dynamic restricted areas.

[0130] The area in the alleyway space region excluding the dynamically restricted area is determined as the real-time feasible area.

[0131] Furthermore, each of the gas detection points has two gas concentration detectors; the feasible area generation module 11 also includes the following execution steps:

[0132] Traverse the multiple gas detection points, determine the first gas detection point, and obtain the first gas concentration and the second gas concentration detected by the two gas concentration detectors at the first gas detection point;

[0133] Calculate the concentration difference between the first gas concentration and the second gas concentration, and determine whether the concentration difference is within a preset error range;

[0134] When the concentration difference is within the preset error range, the average value of the first gas concentration and the second gas concentration is calculated as the effective gas concentration of the first gas detection point;

[0135] When the concentration difference exceeds the preset error range, the effective gas concentration of adjacent gas detection points around the first gas detection point is extracted, and the effective gas concentration of the first gas detection point is obtained by combining the first gas concentration and the second gas concentration.

[0136] Furthermore, the feasible region generation module 11 also includes the following execution steps:

[0137] Based on the effective gas concentration of the adjacent gas detection points, the estimated gas concentration of the first gas detection point is obtained;

[0138] Calculate the first error value between the first gas concentration and the estimated gas concentration, and the second error value between the second gas concentration and the estimated gas concentration, respectively.

[0139] Determine whether the first error value and the second error value are within a preset verification error range;

[0140] When the first error value is within the preset verification error range and the second error value exceeds the preset verification error range, the first gas concentration is taken as the effective gas concentration of the first gas detection point.

[0141] When the second error value is within the preset verification error range and the first error value exceeds the preset verification error range, the second gas concentration is taken as the effective gas concentration of the first gas detection point.

[0142] When both the first error value and the second error value exceed the preset verification error range, the estimated gas concentration is taken as the effective gas concentration of the first gas detection point.

[0143] Furthermore, the route planning module 12 includes the following execution steps:

[0144] Obtain the starting and ending positions of the target vehicle;

[0145] Within the real-time feasible area, a target transportation route is generated based on the starting position and the ending position;

[0146] Based on the vehicle parameters of the target vehicle and the transportation task requirements, determine the base transportation speed of the target transportation route;

[0147] Obtain the preset upper limit value of the target vehicle's transport speed as the upper limit constraint, and obtain the preset lower limit value of the target vehicle's transport speed as the lower limit constraint.

[0148] Furthermore, the vehicle control module 13 includes the following execution steps:

[0149] The vehicle-mounted lidar scans the road surface within a preset distance range in front of the target vehicle to obtain road surface scanning data.

[0150] The road surface scanning data ahead is input into the road surface smoothness evaluator to obtain the road surface smoothness ahead.

[0151] Furthermore, the construction steps of the road surface evenness evaluator include:

[0152] Collect historical forward road surface scan records, and construct a sample forward road surface scan dataset based on the historical forward road surface records;

[0153] The road surface smoothness is labeled for each sample in the sample front road surface scan dataset to obtain the sample front road surface smoothness set;

[0154] The road surface smoothness estimator is trained and generated based on the sample front road surface scan dataset and the sample front road surface smoothness set.

[0155] Furthermore, the speed adjustment module 14 includes the following execution steps:

[0156] Based on the target vehicle's baseline transport speed, a baseline road surface smoothness is determined, and a transport speed adjustment coefficient is obtained by combining the road surface smoothness ahead.

[0157] The adjusted transport speed is obtained based on the transport speed adjustment coefficient and the baseline transport speed;

[0158] Determine whether the adjusted transport speed is between the upper limit constraint and the lower limit constraint of the transport speed;

[0159] When the adjusted transport speed is between the upper limit constraint and the lower limit constraint, the adjusted transport speed is taken as the driving speed of the target vehicle.

[0160] When the adjusted transport speed exceeds the upper limit constraint of the transport speed, the upper limit constraint of the transport speed shall be used as the driving speed of the target vehicle;

[0161] When the adjusted transport speed is lower than the lower limit constraint of the transport speed, the lower limit constraint of the transport speed shall be used as the driving speed of the target vehicle.

[0162] Furthermore, embodiments of this application also include a comprehensive restricted area determination module, which is used for:

[0163] The dynamic restricted area determined based on the real-time gas concentration distribution is designated as the first dynamic restricted area.

[0164] Areas in underground coal mine roadways where the dust concentration during historical transportation processes exceeds a preset dust concentration threshold are designated as the second dynamic restricted area.

[0165] Calculate the union of the first dynamic restricted area and the second dynamic restricted area to obtain the comprehensive dynamic restricted area;

[0166] The area in the alleyway space region excluding the integrated dynamic restricted area is determined as the real-time feasible area.

[0167] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0168] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0169] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0170] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0171] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0172] Although preferred embodiments of the invention have been described, those skilled in the art, once they have learned the basic inventive concept, can make other changes and modifications to these embodiments.

[0173] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of this invention and its equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for controlling the driving of unmanned assisted transport vehicles in underground coal mines, characterized in that, The method includes: The system receives the effective gas concentration from multiple gas detection points, each of which has two gas concentration detectors, including: Traverse the multiple gas detection points, determine the first gas detection point, and obtain the first gas concentration and the second gas concentration detected by the two gas concentration detectors at the first gas detection point; Calculate the concentration difference between the first gas concentration and the second gas concentration, and determine whether the concentration difference is within a preset error range; When the concentration difference is within the preset error range, the average value of the first gas concentration and the second gas concentration is calculated as the effective gas concentration of the first gas detection point; When the concentration difference exceeds the preset error range, the effective gas concentration of adjacent gas detection points around the first gas detection point is extracted. Combining the first gas concentration and the second gas concentration, the effective gas concentration of the first gas detection point is obtained, including: Based on the effective gas concentration of the adjacent gas detection points, the estimated gas concentration of the first gas detection point is obtained; Calculate the first error value between the first gas concentration and the estimated gas concentration, and the second error value between the second gas concentration and the estimated gas concentration, respectively. Determine whether the first error value and the second error value are within a preset verification error range; When the first error value is within the preset verification error range and the second error value exceeds the preset verification error range, the first gas concentration is taken as the effective gas concentration of the first gas detection point. When the second error value is within the preset verification error range and the first error value exceeds the preset verification error range, the second gas concentration is taken as the effective gas concentration of the first gas detection point. When both the first error value and the second error value exceed the preset verification error range, the estimated gas concentration is taken as the effective gas concentration of the first gas detection point. Based on the effective gas concentration of multiple gas detection points, the real-time gas concentration distribution of underground coal mine roadways is obtained. Based on the real-time gas concentration distribution, the dynamic restricted areas of underground coal mine roadways are determined, and the real-time feasible areas are generated based on the dynamic restricted areas. A target transportation route for the target vehicle is generated based on the real-time feasible area. The target vehicle has a baseline transportation speed, an upper limit constraint on transportation speed, and a lower limit constraint on transportation speed. The target vehicle is controlled to travel along the target transportation route at the benchmark transportation speed, and the road surface smoothness ahead is obtained in real time through the vehicle-mounted lidar of the target vehicle. The vehicle's speed is adjusted in real time based on the road surface smoothness, the baseline transport speed, the upper limit constraint of the transport speed, and the lower limit constraint of the transport speed, including: Based on the target vehicle's baseline transport speed, a baseline road surface smoothness is determined, and a transport speed adjustment coefficient is obtained by combining the road surface smoothness ahead. The adjusted transport speed is obtained based on the transport speed adjustment coefficient and the baseline transport speed; The target vehicle's speed is adjusted in real time based on the adjusted transport speed, the upper limit constraint of the transport speed, and the lower limit constraint of the transport speed.

2. The method according to claim 1, characterized in that, The method involves acquiring the real-time gas concentration distribution of underground coal mine roadways, determining dynamic restricted areas based on the gas concentration distribution, and generating real-time feasible areas based on the dynamic restricted areas, including: The effective gas concentration of multiple gas detection points is received, wherein each of the gas detection points is distributed in the underground roadway of the coal mine; Based on the effective gas concentration at multiple gas detection points, the real-time gas concentration distribution in underground coal mine roadways is generated. Obtain the safe threshold for gas concentration and the roadway space area of ​​the underground roadway in the coal mine; Based on the real-time gas concentration distribution, areas in the roadway space where the gas concentration exceeds the gas concentration safety threshold are identified as dynamic restricted areas. The area in the alleyway space region excluding the dynamically restricted area is determined as the real-time feasible area.

3. The method according to claim 1, characterized in that, A target transportation route for the target vehicle is generated based on the real-time feasible area. The target vehicle has a baseline transportation speed, an upper limit constraint on transportation speed, and a lower limit constraint on transportation speed, including: Obtain the starting and ending positions of the target vehicle; Within the real-time feasible area, a target transportation route is generated based on the starting position and the ending position; Based on the vehicle parameters of the target vehicle and the transportation task requirements, determine the base transportation speed of the target transportation route; Obtain the preset upper limit value of the target vehicle's transport speed as the upper limit constraint, and obtain the preset lower limit value of the target vehicle's transport speed as the lower limit constraint.

4. The method according to claim 1, characterized in that, The vehicle's onboard LiDAR is used to obtain real-time information on the road surface smoothness ahead, including: The vehicle-mounted lidar scans the road surface within a preset distance range in front of the target vehicle to obtain road surface scanning data. The road surface scanning data ahead is input into the road surface smoothness evaluator to obtain the road surface smoothness ahead.

5. The method according to claim 4, characterized in that, The construction steps of the road surface evenness evaluator include: Collect historical forward road surface scan records, and construct a sample forward road surface scan dataset based on the historical forward road surface records; The road surface smoothness is labeled for each sample in the sample front road surface scan dataset to obtain the sample front road surface smoothness set; The road surface smoothness estimator is trained and generated based on the sample front road surface scan dataset and the sample front road surface smoothness set.

6. The method according to claim 4, characterized in that, The vehicle's speed is adjusted in real time based on the road surface smoothness, the baseline transport speed, the upper limit constraint of the transport speed, and the lower limit constraint of the transport speed, including: Determine whether the adjusted transport speed is between the upper limit constraint and the lower limit constraint of the transport speed; When the adjusted transport speed is between the upper limit constraint and the lower limit constraint, the adjusted transport speed is taken as the driving speed of the target vehicle. When the adjusted transport speed exceeds the upper limit constraint of the transport speed, the upper limit constraint of the transport speed shall be used as the driving speed of the target vehicle; When the adjusted transport speed is lower than the lower limit constraint of the transport speed, the lower limit constraint of the transport speed shall be used as the driving speed of the target vehicle.

7. The method according to claim 2, characterized in that, The method further includes: The dynamic restricted area determined based on the real-time gas concentration distribution is designated as the first dynamic restricted area. Areas in underground coal mine roadways where the dust concentration during historical transportation processes exceeds a preset dust concentration threshold are designated as the second dynamic restricted area. Calculate the union of the first dynamic restricted area and the second dynamic restricted area to obtain the comprehensive dynamic restricted area; The area in the alleyway space region excluding the integrated dynamic restricted area is determined as the real-time feasible area.

8. A driving control system for unmanned assisted transport vehicles in coal mines, characterized in that, The system for implementing the method as described in any one of claims 1 to 7, the system comprising: The feasible area generation module is used to obtain the real-time gas concentration distribution of underground roadways in coal mines, determine the dynamic restricted areas of underground roadways in coal mines based on the real-time gas concentration distribution, and generate real-time feasible areas based on the dynamic restricted areas. The route planning module is used to generate a target transportation route for the target vehicle based on the real-time feasible area. The target vehicle has a base transportation speed, a transportation speed upper limit constraint, and a transportation speed lower limit constraint. The vehicle control module is used to control the target vehicle to travel along the target transportation route at the reference transportation speed, and to obtain the road surface smoothness in real time through the vehicle-mounted lidar of the target vehicle. The speed adjustment module is used to adjust the driving speed of the target vehicle in real time based on the road surface smoothness ahead, the reference transport speed, the upper limit constraint of the transport speed, and the lower limit constraint of the transport speed.

Images