Downhole vehicle driving detection method and device, electronic equipment, medium and product

Abstract

This disclosure provides a method, apparatus, electronic device, medium, and product for detecting vehicle movement in underground mines. The method includes: acquiring environmental point cloud data of the vehicle's environment while it is traveling on a track in an underground mine roadway; determining track point cloud data based on the environmental point cloud data; determining the vehicle's travel trend information for a future time period based on the track point cloud data; and predicting the vehicle's track trajectory for the future time period based on the travel trend information, thereby controlling the vehicle's movement according to the track trajectory. This technical solution achieves accurate identification and adaptive prediction of track trajectories in underground mine roadways, effectively improving the accuracy of trajectory planning and environmental adaptability, and meeting the technical requirements for vehicle driving safety and stable control in complex dynamic underground environments.

Description

Technical Field

[0001] This disclosure relates to the field of underground mining car technology, and in particular to an underground vehicle driving detection method, device, electronic equipment, medium and product. Background Technology

[0002] Underground rail transportation in mines is a crucial link in mineral resource extraction, and its operational efficiency and safety directly affect the overall production level of the mine. With the rapid development of intelligent mining technology, electric locomotive driving technology based on three-dimensional perception and automatic control is gradually becoming the mainstream development direction of underground transportation. Accurate trajectory prediction is a key prerequisite for achieving safe operation of underground vehicles.

[0003] In related technologies, current trajectory prediction technology for underground locomotives typically relies on pre-built 3D maps or track topology networks of underground roadways to determine the driving path through offline planning. This approach suffers from poor adaptability and insufficient accuracy, which can easily lead to trajectory planning deviations. Furthermore, it is difficult to meet the driving safety requirements of complex and dynamic underground roadways. Summary of the Invention

[0004] This invention provides a method, device, electronic equipment, medium, and product for detecting underground vehicle movement, enabling accurate identification and adaptive prediction of track trajectories in underground roadways, effectively improving the accuracy of trajectory planning and environmental adaptability, and meeting the needs for safe and stable vehicle control in complex dynamic underground environments.

[0005] According to one aspect of the present invention, a method for detecting the movement of underground vehicles is provided, the method comprising: While the vehicle is traveling on the track in the underground tunnel, environmental point cloud data of the environment in which the vehicle is located is acquired. Based on the environmental point cloud data, determine the orbit point cloud data of the track; Based on the orbital point cloud data, the driving trend information of the vehicle in the future time period is determined, and based on the driving trend information, the trajectory of the vehicle in the future time period is predicted, so as to control the vehicle's driving according to the trajectory; wherein, the driving trend information includes straight-line driving and curved driving.

[0006] According to another aspect of the present invention, an underground vehicle driving detection device is provided, the device comprising: The point cloud data acquisition module is used to acquire environmental point cloud data of the environment in which the vehicle is located while it is traveling on the track in the underground roadway. The track data determination module is used to determine the track point cloud data of the track based on the environmental point cloud data; The driving trend prediction module is used to determine the driving trend information of the vehicle in the future time period based on the track point cloud data, and to predict the track trajectory in the future time period based on the driving trend information, so as to determine the driving trajectory of the vehicle in the future time period based on the track trajectory; wherein, the driving trend information includes straight-line driving and curved driving.

[0007] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: One or more processors; Storage device for storing one or more programs. When one or more programs are executed by one or more processors, the one or more processors implement an underground vehicle driving detection method as described in any of the embodiments of this disclosure.

[0008] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement any of the downhole vehicle driving detection methods in the embodiments of the present disclosure.

[0009] According to another aspect of the present disclosure, a computer program product is provided, which, when executed by a processor, implements any of the downhole vehicle driving detection methods described in the embodiments of the present disclosure.

[0010] The technical solution of this disclosure collects environmental point cloud data of the surrounding environment while the vehicle is traveling on a track in an underground tunnel. This provides raw three-dimensional perception data for track recognition, obstacle detection, and trajectory prediction, ensuring the data source for subsequent processing is authentic and reliable. Furthermore, track point cloud data is extracted from the environmental point cloud data, eliminating interference from irrelevant point clouds such as those on the ground and tunnel walls, achieving accurate positioning and extraction of the track area. Further, based on the track point cloud data, the vehicle's driving trend information for the future time period is determined. The relationship between the track extension direction and the vehicle's driving direction is analyzed based on the track point cloud data to quickly determine the straight or curved driving trend, providing a basis for subsequent trajectory prediction. Furthermore, based on the driving trend information, the track trajectory for the future time period is predicted, and vehicle driving is controlled according to the track trajectory. Dynamic prediction of the future track trajectory for different driving trends provides accurate path references for autonomous or assisted driving, improving the safety and stability of underground driving. The technical solution of this disclosure solves the problems of poor adaptability and insufficient accuracy in related technologies, which easily lead to trajectory planning deviations and make it difficult to meet the driving safety requirements in complex and dynamic underground roadways. It realizes accurate identification and adaptive prediction of underground roadway trajectories, effectively improves the accuracy of trajectory planning and environmental adaptability, and can meet the vehicle driving safety and stability control requirements in complex and dynamic underground environments.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 A flowchart illustrating a method for detecting the movement of underground vehicles provided in an embodiment of this disclosure; Figure 2 A schematic flowchart of another method for detecting the movement of underground vehicles provided in an embodiment of this disclosure; Figure 3 This is a schematic diagram of the structure of an underground vehicle driving detection device provided in an embodiment of the present disclosure; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. 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 should fall within the scope of protection of the present invention.

[0015] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0017] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0018] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0019] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0020] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0021] Figure 1 This is a flowchart illustrating a method for detecting the movement of vehicles in an underground mine, as provided in this embodiment. This embodiment is applicable to situations where the vehicle's movement trend is detected and the mine's trajectory is predicted during operation in an underground mine roadway. This method can be executed by an underground vehicle detection device, which can be implemented in hardware and / or software and can be configured in electronic devices such as computers or servers. Figure 1 As shown, the method in this embodiment includes: S110. When the vehicle is traveling on the track in the underground tunnel, acquire environmental point cloud data of the environment in which the vehicle is located.

[0022] In this context, "vehicle" can be understood as an engineering vehicle that travels or operates within mine roadways. This engineering vehicle can be of any type, optionally including driverless or autonomous vehicles, such as autonomous electric locomotives. The underground roadway track refers to a fixed track line laid along the roadway's extension, specifically for underground ore-carrying vehicles, including straight and curved sections, used to define the vehicle's path, bear its weight, and guide its safe passage within the underground roadway. Environmental point cloud data can be understood as a set of three-dimensional spatial points covering the pre-travel area around the vehicle, collected during its movement within the underground roadway. This environmental point cloud data can be a digital representation of the underground roadway environment, including the three-dimensional coordinate information of all spatial objects within that environment. Specifically, it may include at least one of the following: underground track, roadway floor, roadway sidewalls, protrusions on the roadway roof, falling rocks, equipment, and personnel.

[0023] It should be noted that environmental point cloud data can be used to perform environmental perception and detection of the underground tunnel environment in which the vehicle is located during vehicle operation, thereby ensuring driving safety. Environmental point cloud data can be acquired in real time by a 3D imaging sensor installed on the vehicle. This 3D imaging sensor can be installed at least at one location on the front, side, and rear of the vehicle, depending on the driving detection requirements. In this embodiment, environmental point cloud data can also be used to predict the vehicle's driving trend information in the future. Therefore, the acquired environmental point cloud data can be used to characterize the 3D environmental information of the area the vehicle is about to enter. In this case, in order to acquire environmental point cloud data that meets the driving trend detection requirements, the 3D imaging sensor used to acquire the environmental point cloud data must be installed at least at the front of the vehicle. Thus, environmental point cloud data can be acquired by a 3D imaging sensor installed on the vehicle. This is because the front of the vehicle faces the same direction as the vehicle's driving direction, allowing for unobstructed and complete acquisition of the 3D environmental information of the area the vehicle is about to enter, enabling early detection of the track, curves, and obstacles ahead, providing sufficient reaction time for subsequent trajectory prediction and safety decisions, and adapting to the complex underground tunnel environment.

[0024] In one implementation, a 3D imaging sensor can be pre-installed on the front of the vehicle. Furthermore, as the vehicle travels along the track in the underground tunnel, the 3D imaging sensor installed on the vehicle collects 3D spatial point data of the vehicle's environment at a preset acquisition frequency, and uses the collected 3D spatial point data as environmental point cloud data of the vehicle's environment.

[0025] S120. Determine the orbit point cloud data based on the environmental point cloud data.

[0026] In this context, track point cloud data can be understood as a set of three-dimensional points identified from environmental point cloud data, representing the trajectory of underground vehicles. In this embodiment, track point cloud data may refer to the track surface point cloud of a double-track system within an underground tunnel.

[0027] In this embodiment, the environmental point cloud data typically includes ground point cloud data and non-ground point cloud data, and the tracks are usually set on the ground within the underground tunnel. Therefore, ground point cloud data can be identified from the environmental point cloud data first. Further, slightly protruding track point clouds can be identified from the ground point cloud data, ultimately obtaining the point cloud clusters corresponding to the left and right tracks respectively, and defining these point cloud clusters as the track point cloud data.

[0028] Optionally, the orbital point cloud data of the track can be determined based on the environmental point cloud data, including: determining the ground point cloud data based on the environmental point cloud data; and segmenting the ground point cloud data to obtain the orbital point cloud data of the track.

[0029] Ground point cloud data can be understood as a set of three-dimensional spatial points extracted from environmental point cloud data, corresponding to the surface of underground mine roadways. Ground point cloud data can be used to characterize the physical morphology of the road surface within underground roadways, reflecting its undulations, slope changes, and smoothness. It can be understood that since the track is laid on the surface of the underground roadway, closely adjacent to the ground with minimal elevation difference, the track point cloud data may be included in the ground point cloud data during the process of identifying ground point cloud data from the environmental point cloud data due to its proximity to the ground. Therefore, ground point cloud data includes not only the point cloud of the actual ground but also the point cloud corresponding to the track.

[0030] In this embodiment, the determination method for ground point cloud data may include at least one of the following: setting an elevation threshold, determining points in the environmental point cloud data with elevations below the threshold as ground points; projecting the environmental point cloud onto a two-dimensional plane and dividing it into grids, taking the minimum elevation point within each grid as a ground reference point, and determining whether it is ground based on the elevation difference between adjacent grids; using the RANSAC algorithm to perform planar fitting on the environmental point cloud, and classifying point clouds that conform to the ground plane model as ground point cloud data. One of these determination methods will be described in detail below.

[0031] Optionally, ground point cloud data is determined based on environmental point cloud data, including: downsampling the environmental point cloud data to obtain downsampled point cloud data; projecting the downsampled point cloud data onto a horizontal plane in a two-dimensional grid to obtain first projected point cloud data; the first projected point cloud data includes point cloud data with the minimum elevation value in each grid; and identifying ground point cloud data based on the elevation difference between adjacent grids in the first projected point cloud data and a first elevation difference threshold.

[0032] Downsampling can be understood as a processing method that reduces the number and density of point clouds without destroying the structure and distribution characteristics of environmental point cloud data, thereby reducing subsequent computation and improving algorithm efficiency. Downsampled point cloud data can be understood as point cloud data obtained after downsampling environmental point cloud data, which retains the overall spatial distribution characteristics of the environment but with a smaller data volume. The horizontal plane can be understood as the XOY plane parallel to the ground where the vehicle travels, serving as the reference plane for two-dimensional gridded projection. Two-dimensional gridded projection can be understood as the process of projecting downsampled point cloud data vertically onto the horizontal plane and dividing the projection area into several uniform grids according to a preset grid size. The first projected point cloud data can be understood as the set of points constructed by retaining only the point cloud with the smallest elevation value in each grid after two-dimensional gridded projection, used to reflect the ground reference height at the grid location. In other words, the first projected point cloud data can be a set composed of point cloud data with the smallest elevation value in each grid, and the point cloud data in each grid can be used to reflect the ground reference height at the corresponding grid location. A grid can be a two-dimensional unit with fixed side lengths, obtained by dividing a horizontal plane. It is used to discretize continuous point clouds, facilitating the evaluation of elevation changes region by region. Elevation values ​​can be understood as the height coordinates of the point cloud in the vertical direction (Z-axis), used to distinguish between the ground, tracks, and raised obstacles. Adjacent grids can be understood as grids directly adjacent to the current grid in the horizontal, vertical, or diagonal directions on the horizontal projection plane. Elevation difference can be understood as the height difference between the point cloud data with the minimum retained elevation values ​​within adjacent grids, used to determine whether the ground is continuous and smooth. The first elevation difference threshold can be understood as a pre-set upper limit for the height difference used to determine whether there is an abrupt change in the ground. The first elevation difference threshold can be set based on the smoothness characteristics of the underground roadway surface.

[0033] In one implementation, after acquiring environmental point cloud data, the environmental point cloud data can first be downsampled to obtain downsampled point cloud data. Further, the downsampled point cloud data is projected onto a horizontal plane, and this horizontal plane is divided into a two-dimensional grid of preset size. For all point cloud data within each grid, the point cloud data with the smallest elevation value is retained as the reference point within that grid, thereby forming the first projected point cloud data. Further, the elevation difference between the elevation values ​​of point cloud data in adjacent grids within the first projected point cloud data is determined, and points with elevation differences not exceeding a first elevation difference threshold are identified as ground points to obtain ground point cloud data.

[0034] In this embodiment, the determination method for orbit point cloud data may include at least one of the following: setting an elevation threshold and determining points in the ground point cloud data with elevations below the threshold as orbit points; projecting the ground point cloud onto a two-dimensional plane and dividing it into grids, taking the minimum elevation point within each grid as a ground reference point, and determining whether it is an orbit based on the elevation difference between adjacent grids; using the RANSAC algorithm to perform planar fitting on the ground point cloud and classifying point clouds that conform to the orbit model as orbit point cloud data. One of these determination methods will be described in detail below. Optionally, the ground point cloud data is segmented to obtain the orbit point cloud data of the track, including: projecting the ground point cloud data into a two-dimensional grid on a horizontal plane to obtain second projected point cloud data; the second projected point cloud data includes the point cloud data with the minimum elevation value in each grid; and identifying the orbit point cloud data of the track based on the elevation difference between adjacent grids and the second elevation difference threshold in the second projected point cloud data.

[0035] The second projected point cloud data can be understood as the set of points formed by retaining only the points with the smallest elevation values ​​within each grid after the ground point cloud data has been projected into a two-dimensional grid. This set reflects the reference height of that grid. The second elevation value threshold can be a pre-set threshold used to distinguish the elevation difference between the ground and the track. The second elevation difference threshold can be set according to the height of the track protruding from the ground. Generally, because further fine segmentation is needed based on the ground point cloud data, the second elevation difference threshold is usually smaller than the first elevation difference threshold.

[0036] In one implementation, ground point cloud data is projected onto a horizontal plane, and this horizontal plane is divided into a two-dimensional grid of preset size. For all point cloud data within each grid, the point cloud data with the smallest elevation value is retained as the reference point within that grid, thereby forming second projected point cloud data. Further, the elevation difference between the elevation values ​​of point cloud data in adjacent grids within the second projected point cloud data is determined, and points with elevation differences not exceeding a second elevation difference threshold are identified as orbital points to obtain orbital point cloud data.

[0037] S130. Based on the track point cloud data, determine the vehicle's driving trend information in the future time period, and predict the track trajectory in the future time period based on the driving trend information, so as to control the vehicle's driving according to the track trajectory.

[0038] The future time period can be understood as the short time range within which the vehicle will travel, starting from the current moment (i.e., the processing time of the environmental point cloud data), used to define the effective time period for trajectory prediction. Driving trend information can be understood as the overall direction type of the vehicle's journey along the track in the future time period, obtained based on the analysis of the track point cloud data, used to characterize the extension form of the track in the preceding road segment. Optionally, driving trend information can include two types: straight-line driving and curved driving. Driving trend information can serve as the basis for predicting the track trajectory. The track trajectory can be understood as the geometric extension path of the track itself in the future time period, serving as an objective constraint and benchmark path for vehicle travel. The track trajectory can be the spatial extension path of the track itself in the future road segment, predicted based on the directional characteristics of the track point cloud data. Simply put, the track trajectory can be a segment of track predicted based on the track point cloud data. The track trajectory can include straight-line trajectories and circular arc trajectories. Generally, when the vehicle traveling in the underground tunnel is an autonomous vehicle, its movement can be remotely controlled by technicians. During remote control of the vehicle's movement, the driving strategy can be determined using the environmental point cloud data collected by the vehicle. In this situation, if the trajectory of the track can be predicted for a future time period, technicians can control the vehicle's movement based on that trajectory.

[0039] It should be noted that the track trajectory is predicted in real time based on track point cloud data and driving trend information. It is not obtained directly by 3D imaging sensors, nor is it determined based on a pre-constructed 3D map of underground tunnels or track topology network.

[0040] In practical applications, for scenarios where vehicles travel in underground tunnels, the driving path is usually determined by pre-built 3D maps or track topology networks of the underground tunnels through offline planning. This method suffers from poor adaptability and insufficient accuracy, which can easily lead to trajectory planning deviations. Furthermore, it is difficult to meet the driving safety requirements of the complex and dynamic environment of underground tunnels.

[0041] To address the aforementioned issues, in this embodiment, while the vehicle is traveling in the underground tunnel, the driving trend information for the future time period is determined based on real-time collected track point cloud data. Furthermore, the track trajectory for the future time period is predicted based on this driving trend information. Consequently, vehicle movement can be controlled according to the track trajectory. This achieves autonomous track trajectory prediction based on real-time point cloud data, eliminating the need for pre-built maps and improving the vehicle's trajectory adaptability and positioning accuracy in the complex and dynamic underground environment. Simultaneously, it provides a real-time and reliable path reference for safe vehicle operation, effectively reducing trajectory deviation and improving the safety and stability of underground driving.

[0042] In this embodiment, the method for determining the driving trend information may include at least one of the following: judgment based on the angle between the main directions; judgment based on the linear fitting residual; judgment based on curvature calculation; and judgment based on the extrapolation direction of the track endpoints.

[0043] In this embodiment, the prediction method for the track trajectory may include at least one of the following: when the driving trend information is straight-line driving, extrapolate the straight line based on the main direction vector of the track point cloud data to obtain the straight-line extension trajectory of the track line in the future time period; when the driving trend information is curved driving, perform circular arc fitting on the track point cloud data, and extrapolate the center and radius of the fitted circle to obtain the circular arc trajectory of the track line; fit a polynomial curve according to the track point cloud data, and extrapolate a certain length forward along the curve direction to form the track trajectory of the future road segment; extract the end point and direction vector of the track point cloud data, and extend forward a preset distance along the vector to directly generate the future track trajectory.

[0044] In one implementation, given the track point cloud data, a first direction vector of the track and a second direction vector of the vehicle can be determined based on the track point cloud data. Further, the angle between the first and second direction vectors can be determined, and the vehicle's driving trend information for a future time period can be determined based on the angle and a preset angle threshold. Further, when the driving trend information indicates straight-line driving, a straight-line extrapolation is performed based on the main direction of the track point cloud data to obtain the straight-line extension trajectory of the track line in the future time period, i.e., the track line trajectory. Alternatively, when the driving trend information indicates curved driving, a circular arc fitting is performed on the track point cloud, and the arc trajectory of the track line is obtained by extrapolating the center and radius of the fitted circle, i.e., the track line trajectory. Further, the vehicle's driving can be controlled based on the predicted track line trajectory.

[0045] In this embodiment, when the vehicle is traveling in the underground tunnel, obstacle detection can also be performed on the environment in which the vehicle is located based on environmental point cloud data. Optionally, the underground vehicle driving detection method further includes: determining non-ground point cloud data based on environmental point cloud data; performing clustering processing on the non-ground point cloud data to obtain multiple clusters; determining the bounding box of each cluster, and determining obstacle information based on the attribute information of the bounding box; determining the vehicle's safety perception area based on driving trend information, and determining obstacle warning information based on obstacle information and safety perception area.

[0046] Non-ground point cloud data can be understood as the set of point cloud data remaining after excluding the point cloud data that constitutes the ground from the environmental point cloud data, used to represent various objects or obstacles above the ground. The elevation values ​​of non-ground point cloud data differ significantly from those of ground point cloud data; point cloud data with an elevation difference greater than a first elevation difference threshold between adjacent grids are marked as non-ground point clouds. Non-ground point cloud data can be environmental point cloud data other than ground point cloud data; the method for determining non-ground point cloud data will not be detailed here. Clustering processing can be understood as the process of grouping and dividing non-ground point cloud data using a clustering algorithm. Optionally, the clustering algorithm includes at least one of the following: density-based DBSCAN algorithm, Euclidean clustering algorithm, or region-growing clustering algorithm. A cluster can be understood as a set of points composed of spatially proximate non-ground point clouds, and each cluster can correspond to a potential obstacle. Specifically, based on the location distribution characteristics of non-ground point cloud data in three-dimensional space, discrete non-ground point clouds are automatically aggregated into several point cloud sets with inherent correlation, i.e., clusters. This makes point clouds within the same cluster closely adjacent in space and belong to the same entity object, while point clouds in different clusters are relatively scattered and belong to different entity objects.

[0047] In this context, a bounding box can be understood as the smallest three-dimensional cube structure that can completely enclose all point cloud data of a single cluster, used to characterize the spatial location and size of an obstacle. Attribute information can include at least one of the bounding box's size parameters, location information, orientation information, volume, and height. Obstacle information can be obstacle data extracted based on the bounding box's attribute information, including at least one of the obstacle's size parameters, location information, type, and distance. The safety perception zone can be understood as the spatial range in front of the vehicle that needs to be monitored in real time based on driving trend information, used to focus on high-risk areas. Obstacle warning information can be understood as a warning prompt generated when an obstacle is located within the safety perception zone; this warning prompt can be used to remind technicians or the autonomous driving system to take evasive action.

[0048] In one implementation, as the vehicle travels along the track in the underground tunnel, the environmental point cloud data undergoes ground segmentation and filtering to remove point cloud data belonging to the ground, thus obtaining non-ground point cloud data containing only protruding targets such as obstacles. Further, the non-ground point cloud data is clustered according to spatial distance, dividing adjacent point clouds into multiple independent clusters, each cluster corresponding to an independent target. Further, a minimum bounding box is generated for each cluster, and based on the bounding box's position, size, height, and other attributes, the location, size, and distance of the corresponding obstacle are identified and determined. Moreover, based on the vehicle's straight-line or curved-line driving trend information, the safety perception area ahead of the vehicle is dynamically determined, and it is judged whether obstacles are located within the safety perception area. If obstacles exist, corresponding obstacle warning information is generated to achieve real-time warnings of dangerous targets on the vehicle's driving path.

[0049] The technical solution of this disclosure collects environmental point cloud data of the surrounding environment while the vehicle is traveling on a track in an underground tunnel. This provides raw three-dimensional perception data for track recognition, obstacle detection, and trajectory prediction, ensuring the data source for subsequent processing is authentic and reliable. Furthermore, track point cloud data is extracted from the environmental point cloud data, eliminating interference from irrelevant point clouds such as those on the ground and tunnel walls, achieving accurate positioning and extraction of the track area. Further, based on the track point cloud data, the vehicle's driving trend information for the future time period is determined. The relationship between the track extension direction and the vehicle's driving direction is analyzed based on the track point cloud data to quickly determine the straight or curved driving trend, providing a basis for subsequent trajectory prediction. Furthermore, based on the driving trend information, the track trajectory for the future time period is predicted, and vehicle driving is controlled according to the track trajectory. Dynamic prediction of the future track trajectory for different driving trends provides accurate path references for autonomous or assisted driving, improving the safety and stability of underground driving. The technical solution of this disclosure solves the problems of poor adaptability and insufficient accuracy in related technologies, which easily lead to trajectory planning deviations and make it difficult to meet the driving safety requirements in complex and dynamic underground roadways. It realizes accurate identification and adaptive prediction of underground roadway trajectories, effectively improves the accuracy of trajectory planning and environmental adaptability, and can meet the vehicle driving safety and stability control requirements in complex and dynamic underground environments.

[0050] Figure 2 This is a schematic flowchart illustrating another method for detecting the movement of vehicles in an underground mine, provided by an embodiment of this disclosure. The technical solution of this embodiment can be combined with other embodiments; for the same or related parts, descriptions of other embodiments can be used, and will not be repeated here. Figure 2 As shown, the method in this embodiment may specifically include: S210. When the vehicle is traveling on the track in the underground tunnel, acquire the environmental point cloud data of the environment in which the vehicle is located.

[0051] S220. Determine the orbit point cloud data based on the environmental point cloud data.

[0052] S230. Determine the first direction vector of the orbit based on the orbit point cloud data.

[0053] The first direction vector can be understood as a direction vector calculated based on track point cloud data, used to represent the extension direction of the track itself, reflecting the overall orientation of the track at the current position. In other words, the first direction vector can be used to indicate the extension direction of the track. The extension direction of the track refers to the overall trend of the track extending forward in the current section, and is the basis for determining whether it is a straight section or a curve.

[0054] In this embodiment, the determination of the first direction vector may include at least one of the following: performing principal component analysis on the orbit point cloud data to obtain the first direction vector of the orbit; performing least squares line fitting on the orbit point cloud data to obtain the first direction vector of the orbit; extracting the first and last endpoints from the orbit point cloud data, and using the direction vector of the line connecting the first and last endpoints as the first direction vector. One of these determination methods will be described in detail below.

[0055] Optionally, the first direction vector of the orbit can be determined based on the orbit point cloud data, including: performing principal component analysis on the orbit point cloud data and determining the eigenvector corresponding to the largest eigenvalue as the first direction vector of the orbit.

[0056] Principal component analysis (PCA) is a mathematical analysis method used to analyze the main distribution direction of data. It extracts the main extension direction of the point cloud by performing feature decomposition on the orbital point cloud data. The largest eigenvalue is the eigenvalue with the highest numerical value calculated during PCA, representing the strongest energy distribution and greatest dispersion of the orbital point cloud data in that direction. The eigenvector corresponding to the largest eigenvalue is the vector corresponding to the direction in which the orbital point cloud data is most concentrated and extends most significantly, accurately reflecting the overall extension direction of the orbit.

[0057] In one implementation, principal component analysis (PCA) is used to perform PCA on the orbital point cloud data. Through mathematical transformations, multiple eigenvalues ​​and their corresponding eigenvectors corresponding to the orbital point cloud data are obtained. Furthermore, the eigenvector corresponding to the largest eigenvalue among the multiple eigenvalues ​​can be determined as the first direction vector representing the overall extension direction of the orbit.

[0058] S240. Obtain the second direction vector of the vehicle, and determine the angle between the first direction vector and the second direction vector as the first direction angle.

[0059] The second direction vector can refer to the direction vector representing the vehicle's current travel direction, usually aligned with the vehicle's heading, serving as a reference direction for comparison with the track's extension direction. Optionally, the second direction vector can be obtained in at least one of the following ways: determining the second direction vector based on the heading angle information input from the vehicle's inertial measurement unit or positioning module; determining the second direction vector based on the position coordinates of the vehicle's front and rear axle centers; fitting the motion trajectory based on multiple historical positioning points of the vehicle and determining the tangent direction of the motion trajectory as the second direction vector; or directly using the longitudinal axis vector of the vehicle's coordinate system as the reference, taking the vehicle's own coordinate system's forward direction as the reference. The first direction angle can be understood as the angle between the track's extension direction and the vehicle's travel direction, serving as a key basis for subsequently determining whether the travel trend is a straight road or a curve.

[0060] In one implementation, the longitudinal axis vector of the vehicle coordinate system can be determined as the second direction vector of the vehicle, based on the forward direction of the vehicle coordinate system. Further, the first and second direction vectors can be normalized to obtain normalized first and second direction vectors. Further, the cosine of the angle between the normalized first and second direction vectors is calculated, and then the first direction angle is obtained by solving the inverse cosine function.

[0061] For example, the included angle in the first direction can be determined by the following formula: in, Indicates the included angle in the first direction; Indicates the first direction vector; Indicates the second direction vector; This represents the first direction vector after normalization; This represents the normalized second direction vector.

[0062] S250. Based on the first directional angle, determine the vehicle's driving trend information for the future time period. Based on the driving trend information, predict the vehicle's trajectory for the future time period, and control the vehicle's driving according to the trajectory.

[0063] In this embodiment, given the first directional angle, it can be compared with a preset first angle threshold. Then, the vehicle's driving trend information for a future time period can be determined based on the comparison result.

[0064] Optionally, based on the first directional angle, the driving trend information of the vehicle in the future time period is determined, including: if the first directional angle is not greater than the first angle threshold, the driving trend information of the vehicle in the future time period is determined to be straight-line driving; if the first directional angle is greater than the first angle threshold, the driving trend information of the vehicle in the future time period is determined to be curved driving.

[0065] The first angle threshold can be a pre-set angle critical value through experimentation or calibration, used as a dividing standard to determine whether the track extends in a straight line or curves. Optionally, the first angle threshold can include 5°, 10°, and 15°, etc.

[0066] In one implementation, a first directional angle is compared with a first angle threshold. Further, if the first directional angle is not greater than the first angle threshold, the track extension direction is considered to be substantially consistent with the vehicle's travel direction, and the vehicle's travel trend information for the future time period is determined to be straight-line travel. If the first directional angle is greater than the first angle threshold, the track is considered to have a significant curve, and the vehicle's travel trend information for the future time period is determined to be curved travel.

[0067] It should be noted that the track alignment is complex and changes drastically in curved driving scenarios, making it more prone to trajectory deviations, inaccurate positioning, and higher safety risks compared to straight tracks. Therefore, this technical solution provides a detailed explanation of the track trajectory prediction method for curved driving scenarios, which can more accurately predict the turning path and improve the vehicle's driving stability and safety in complex and dynamic underground environments.

[0068] Optionally, based on driving trend information, the vehicle's trajectory in the future time period is predicted, including: if the vehicle's driving trend in the future time period is curved, determining the coordinates of the predicted starting point based on track point cloud data; determining the curve radius based on a preset angle change and a preset predicted arc length; determining the coordinates of the curve center based on the predicted starting point coordinates and the curve radius; for multiple predicted points, determining the second direction angle corresponding to the predicted point based on the first direction angle and the preset angle change, and determining the position coordinates of the predicted point based on the second direction angle and the curve center coordinates; and determining the vehicle's trajectory in the future time period based on the position coordinates of the multiple predicted points.

[0069] The predicted starting point coordinates can be the initial position coordinates determined from environmental point cloud data, used to begin extrapolating the curve trajectory. The preset predicted arc length can be understood as a pre-defined arc length, used to limit the predicted length of the vehicle's curve trajectory within a future time period, determining the range and distance of the trajectory prediction. Optionally, the preset predicted arc length can include 5 meters, 10 meters, or 15 meters, etc. The curve radius can be understood as the radius of the curve arc calculated based on the first direction angle and the preset predicted arc length, used to determine the degree of curvature of the curve. The curve center coordinates can be understood as the coordinates of the center position of the curve arc calculated based on the predicted starting point coordinates and the curve radius. Predicted points can be multiple discrete position points extrapolated to construct the curve trajectory, used to form a complete curve trajectory. Generally, the number of predicted points can be determined based on the preset predicted arc length and the preset division step size; specifically, the ratio between the preset predicted arc length and the preset division step size can be used to determine the number of predicted points. The preset angle change can be understood as a pre-defined angle increment between adjacent predicted points, used to gradually generate various points on the curve. The second directional angle can be understood as the angle value obtained by superimposing the first directional angle and the preset angle change at the corresponding prediction point, used to determine the direction of the prediction point. The position coordinates can be the specific spatial coordinates of each prediction point calculated by the coordinates of the curve center and the second directional angle.

[0070] In one implementation, if the vehicle's driving trend information in the future time period indicates that it is traveling along a curve, the position coordinates of each point in the track point cloud data are traversed, the distance between each point and the vehicle's current position is calculated, the target point with the largest distance is determined, and the position coordinates of this target point are determined as the predicted starting point coordinates. Further, a preset predicted arc length and a preset angle change are obtained, and the ratio between the preset predicted arc length and the preset angle change is determined; this ratio is then determined as the curve radius. Further, the turning direction of the track can be determined based on the track point cloud data, the sine value of the first direction angle is determined, and the sign of this sine value is determined according to the turning direction (e.g., positive for a left turn, negative for a right turn) to obtain a first numerical value. Furthermore, the product of the first value and the curve radius is determined to obtain the second value. This second value is then added to the x-coordinate of the predicted starting point coordinates to obtain the x-coordinate of the curve center. Additionally, the cosine of the first directional angle is determined, and its sign (positive for a left turn, negative for a right turn) is determined based on the turning direction to obtain the third value. Further, the product of the third value and the curve radius is determined to obtain the fourth value. This fourth value is then added to the y-coordinate of the predicted starting point coordinates to obtain the y-coordinate of the curve center. Further, for multiple predicted points, a fifth value is determined based on the total number of predicted points and the predicted point's sequence number. The product of this fifth value and a preset angle change is determined to obtain the sixth value. This sixth value is then added to the first directional angle to obtain the second directional angle corresponding to the predicted point. Finally, the position coordinates of the predicted point can be determined based on the second directional angle, the predicted starting point coordinates, and the curve center coordinates. Furthermore, after obtaining the position coordinates of multiple predicted points, the vehicle's trajectory within a future time period is obtained by fitting the position coordinates of multiple predicted points.

[0071] For example, the location coordinates of the predicted point can be determined by the following formula: ; ; ; ; ; in, Indicates the radius of the curve; Indicates the preset predicted arc length; Indicates the preset angle change; The x-coordinate represents the coordinates of the center of the curve. The x-coordinate represents the starting point coordinates of the prediction. Indicates the included angle in the first direction; The ordinate represents the coordinates of the center of the curve. The ordinate represents the predicted starting point coordinates; Indicates the first The included angle of the second direction corresponding to each prediction point; Indicates the first The sequence number of a prediction point among multiple prediction points; Indicates the total number of prediction points; Indicates the first The x-coordinate of the position coordinates of each predicted point; Indicates the first The ordinate of the position coordinates of each predicted point.

[0072] The technical solution of this disclosure determines a first direction vector of the track based on track point cloud data; further, it obtains a second direction vector of the vehicle and determines the angle between the first and second direction vectors as the first direction angle; further, it determines the vehicle's driving trend information in the future time period based on the first direction angle, thus achieving accurate and rapid judgment of the vehicle's driving trend, effectively distinguishing between straight and curved driving states, providing a reliable basis for subsequent track trajectory prediction, and improving the accuracy and safety of underground vehicle driving control.

[0073] Figure 3 This is a schematic diagram of the structure of an underground vehicle driving detection device provided in an embodiment of this disclosure. Figure 3 As shown, the underground vehicle driving detection device includes: a point cloud data acquisition module 310, a track data determination module 320, and a driving trend prediction module 330. The point cloud data acquisition module 310 acquires environmental point cloud data of the environment in which the vehicle is located while it is traveling on a track in an underground roadway. The track data determination module 320 determines the track point cloud data based on the environmental point cloud data. The driving trend prediction module 330 determines the driving trend information of the vehicle in a future time period based on the track point cloud data, and predicts the track trajectory of the vehicle in the future time period based on the driving trend information, so as to control the vehicle's driving according to the track trajectory. The driving trend information includes straight-line driving and curved-line driving.

[0074] The technical solution of this disclosure collects environmental point cloud data of the surrounding environment while the vehicle is traveling on a track in an underground tunnel. This provides raw three-dimensional perception data for track recognition, obstacle detection, and trajectory prediction, ensuring the data source for subsequent processing is authentic and reliable. Furthermore, track point cloud data is extracted from the environmental point cloud data, eliminating interference from irrelevant point clouds such as those on the ground and tunnel walls, achieving accurate positioning and extraction of the track area. Further, based on the track point cloud data, the vehicle's driving trend information for the future time period is determined. The relationship between the track extension direction and the vehicle's driving direction is analyzed based on the track point cloud data to quickly determine the straight or curved driving trend, providing a basis for subsequent trajectory prediction. Furthermore, based on the driving trend information, the track trajectory for the future time period is predicted, and vehicle driving is controlled according to the track trajectory. Dynamic prediction of the future track trajectory for different driving trends provides accurate path references for autonomous or assisted driving, improving the safety and stability of underground driving. The technical solution of this disclosure solves the problems of poor adaptability and insufficient accuracy in related technologies, which easily lead to trajectory planning deviations and make it difficult to meet the driving safety requirements in complex and dynamic underground roadways. It realizes accurate identification and adaptive prediction of underground roadway trajectories, effectively improves the accuracy of trajectory planning and environmental adaptability, and can meet the vehicle driving safety and stability control requirements in complex and dynamic underground environments.

[0075] In some embodiments of this disclosure, optionally, the driving trend prediction module 330 includes: a direction vector determination unit, a direction angle determination unit, and a driving trend information determination unit; wherein, the direction vector determination unit is used to determine a first direction vector of the track based on the track point cloud data; wherein, the first direction vector is used to indicate the extension direction of the track; the direction angle determination unit is used to obtain a second direction vector of the vehicle and determine the angle between the first direction vector and the second direction vector as the first direction angle; wherein, the second direction vector is used to indicate the driving direction of the vehicle; the driving trend information determination unit is used to determine the driving trend information of the vehicle in a future time period based on the first direction angle.

[0076] In some embodiments of this disclosure, optionally, the direction vector determination unit is specifically used to perform principal component analysis on the orbit point cloud data and determine the eigenvector corresponding to the largest eigenvalue as the first direction vector of the orbit.

[0077] In some embodiments of this disclosure, optionally, the driving trend information determining unit is specifically used to determine that the driving trend information of the vehicle in the future time period is straight-line driving when the first direction angle is less than a first angle threshold; and to determine that the driving trend information of the vehicle in the future time period is curved driving when the first direction angle is greater than a second angle threshold.

[0078] In some embodiments of this disclosure, optionally, the driving trend prediction module 330 includes: a prediction starting point coordinate determination unit, a curve radius determination unit, a circle center coordinate determination unit, a position coordinate determination unit, and a track trajectory determination unit; wherein, the prediction starting point coordinate determination unit is used to determine the prediction starting point coordinates based on the track point cloud data when the driving trend information of the vehicle in the future time period is curve driving; the curve radius determination unit is used to determine the curve radius based on a preset angle change and a preset prediction arc length; the circle center coordinate determination unit is used to determine the curve center coordinates based on the prediction starting point coordinates and the curve radius; the position coordinate determination unit is used to determine a second direction angle corresponding to the prediction point based on the first direction angle and the preset angle change for multiple prediction points, and to determine the position coordinates of the prediction point based on the second direction angle, the prediction starting point coordinates, and the curve center coordinates; the track trajectory determination unit is used to determine the track trajectory of the vehicle in the future time period based on the position coordinates of the multiple prediction points.

[0079] In some embodiments of this disclosure, optionally, the orbit data determination module 320 includes: a ground point cloud data determination unit and an orbit point cloud data determination unit; wherein, the ground point cloud data determination unit is used to determine ground point cloud data based on the environmental point cloud data; the orbit point cloud data determination unit is used to segment the ground point cloud data to obtain the orbit point cloud data of the orbit.

[0080] In some embodiments of this disclosure, the apparatus may optionally further include: a non-ground point cloud data determination module, a point cloud data clustering module, an obstacle information determination module, and an obstacle warning module; wherein, the non-ground point cloud data determination module is used to determine non-ground point cloud data based on the environmental point cloud data; the point cloud data clustering module is used to perform clustering processing on the non-ground point cloud data to obtain multiple clusters; the obstacle information determination module is used to determine the bounding box of each cluster and determine obstacle information based on the attribute information of the bounding box; the obstacle warning module is used to determine the vehicle's safety perception area based on the driving trend information and determine obstacle warning information based on the obstacle information and the safety perception area.

[0081] The underground vehicle driving detection device provided in this disclosure can execute the underground vehicle driving detection method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0082] It is worth noting that the various units and modules included in the above-mentioned underground vehicle driving detection device are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of this disclosure.

[0083] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0084] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0085] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0086] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as downhole vehicle driving detection methods.

[0087] In some embodiments, the downhole vehicle detection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via read-only memory (ROM) 12 and / or communication unit 19. When the computer program is loaded into random access memory (RAM) 13 and executed by processor 11, one or more steps of the downhole vehicle detection method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the downhole vehicle detection method by any other suitable means (e.g., by means of firmware).

[0088] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0089] Computer programs used to implement the downhole vehicle driving detection method of this disclosure can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0090] This disclosure provides a computer-readable storage medium storing computer instructions for causing a processor to execute a method for detecting the movement of an underground vehicle. The method includes: acquiring environmental point cloud data of the vehicle's environment while it is traveling on a track in an underground roadway; determining track point cloud data based on the environmental point cloud data; determining the vehicle's travel trend information for a future time period based on the track point cloud data; and predicting the vehicle's trajectory line within the future time period based on the travel trend information, so as to control the vehicle's movement according to the trajectory line line; wherein the travel trend information includes straight-line driving and curved-line driving.

[0091] In the context of this disclosure, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0092] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0093] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0094] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0095] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of embodiments of this disclosure.

[0096] This disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements an underground vehicle driving detection method according to any embodiment of this disclosure.

[0097] In implementing a computer program product, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0098] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this disclosure can be achieved, and this is not limited herein.

[0099] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for detecting the movement of underground vehicles, characterized in that, include: While the vehicle is traveling on the track in the underground tunnel, environmental point cloud data of the environment in which the vehicle is located is acquired. Based on the environmental point cloud data, determine the orbit point cloud data of the track; Based on the orbital point cloud data, the driving trend information of the vehicle in the future time period is determined, and based on the driving trend information, the trajectory of the vehicle in the future time period is predicted, so as to control the vehicle's driving according to the trajectory; wherein, the driving trend information includes straight-line driving and curved driving.

2. The method for detecting the movement of underground vehicles according to claim 1, characterized in that, The step of determining the vehicle's driving trend information over a future time period based on the orbital point cloud data includes: Based on the orbit point cloud data, a first direction vector of the orbit is determined; wherein, the first direction vector is used to indicate the extension direction of the orbit; Obtain the second direction vector of the vehicle, and determine the angle between the first direction vector and the second direction vector as the first direction angle; wherein, the second direction vector is used to indicate the driving direction of the vehicle; Based on the angle in the first direction, the driving trend information of the vehicle in the future time period is determined.

3. The method for detecting the movement of underground vehicles according to claim 2, characterized in that, The step of determining the first direction vector of the orbit based on the orbit point cloud data includes: Principal component analysis is performed on the orbital point cloud data, and the eigenvector corresponding to the largest eigenvalue is determined as the first direction vector of the orbit.

4. The method for detecting the movement of underground vehicles according to claim 2, characterized in that, Determining the vehicle's driving trend information over a future time period based on the first directional angle includes: If the included angle in the first direction is less than the first angle threshold, the driving trend information of the vehicle in the future time period is determined to be straight-line driving; If the included angle in the first direction is greater than the second angle threshold, the driving trend information of the vehicle in the future time period is determined to be driving on a curve.

5. The method for detecting the movement of underground vehicles according to claim 4, characterized in that, The step of predicting the vehicle's trajectory within the future time period based on the driving trend information includes: If the vehicle's driving trend information in the future time period indicates that it is driving on a curve, the predicted starting point coordinates are determined based on the orbital point cloud data. The radius of the curve is determined based on the preset angle change and the preset predicted arc length. Based on the predicted starting point coordinates and the turning radius, determine the center coordinates of the curve; For multiple prediction points, a second direction angle corresponding to the prediction point is determined based on the first direction angle and a preset angle change, and the position coordinates of the prediction point are determined based on the second direction angle, the prediction starting point coordinates, and the curve center coordinates. Based on the location coordinates of multiple predicted points, the trajectory of the vehicle within the future time period is determined.

6. The method for detecting the movement of underground vehicles according to claim 1, characterized in that, The step of determining the orbit point cloud data of the orbit based on the environmental point cloud data includes: Based on the environmental point cloud data, determine the ground point cloud data; The ground point cloud data is segmented to obtain the orbit point cloud data of the track.

7. The method for detecting the movement of underground vehicles according to claim 1, characterized in that, Also includes: Based on the environmental point cloud data, determine the non-ground point cloud data; The non-ground point cloud data is clustered to obtain multiple clusters; Determine the bounding box of each cluster, and determine obstacle information based on the attribute information of the bounding box; Based on the driving trend information, the vehicle's safety perception area is determined, and based on the obstacle information and the safety perception area, obstacle warning information is determined.

8. A vehicle driving detection device for underground mines, characterized in that, include: The point cloud data acquisition module is used to acquire environmental point cloud data of the environment in which the vehicle is located while it is traveling on the track in the underground roadway. The track data determination module is used to determine the track point cloud data of the track based on the environmental point cloud data; The driving trend prediction module is used to determine the driving trend information of the vehicle in the future time period based on the track point cloud data, and to predict the track trajectory in the future time period based on the driving trend information, so as to determine the driving trajectory of the vehicle in the future time period based on the track trajectory; wherein, the driving trend information includes straight-line driving and curved driving.

9. An electronic device, characterized in that, The electronic device includes: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the downhole vehicle driving detection method as described in any one of claims 1-7.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the downhole vehicle driving detection method according to any one of claims 1-7.

Images