A mining vehicle path planning method and device based on digital twin map

Abstract

The disclosed embodiment provides a method and device for vehicle path planning in a mining area based on a digital twin map, belonging to the technical field of vehicle path planning. The method includes: obtaining map data and physical scene data of the mining area; creating a dynamic twin map of the mining area based on the map data and the physical scene data; identifying and marking obstacle information based on the dynamic twin map, wherein the obstacles include natural obstacles and artificial obstacles; importing vehicle-related data into the dynamic twin map, and planning an obstacle avoidance path for the vehicle based on the marked obstacle information to obtain the optimal obstacle avoidance path. This solution can improve the operating efficiency of vehicles in mining areas and reduce collisions and obstacle detour time.

Description

Technical Field

[0001] The present invention relates to the field of path planning technology, and in particular to a method, device, computing equipment and storage medium for mining vehicle path planning based on a digital twin map. Background Art

[0002] With the improvement of automation and intelligence level in mining areas, the use of digital twin technology to accurately simulate mining areas has become a research hotspot. The application of digital twin technology in geological exploration is mainly reflected in geological model construction, geological disaster prediction, mineral resource exploration, etc. Although it is now possible to digitally represent the physical scene of the mining area, there are problems such as low calibration accuracy and poor real-time performance of path planning for the accurate classification and calibration of complex obstacles in the mining area and obstacle avoidance path planning based on obstacle calibration.

[0003] The Chinese patent document with publication number CN117824660A discloses a mine route planning method based on digital twins, which determines the planning point in each candidate point set according to the preset slope value, wherein the slope value between the planning point, any point in the preset starting point and the preset end point and the planning point in the candidate point set corresponding to the adjacent contour value is less than or equal to the preset slope value, so as to ensure that the path slope between points meets the requirements, and the preset starting point, planning point and preset end point are connected in sequence to obtain the mine route. This solution mainly focuses on slope and elevation control, and cannot achieve efficient automatic classification and accurate calibration of obstacles in the mining area. In addition, the three-dimensional morphology and dynamic changes of obstacles are not considered in path planning, resulting in deviations in the generated obstacle avoidance route in actual application. Summary of the invention

[0004] In view of the above problems, the present invention provides a vehicle path planning method for a mining area based on a digital twin map. By updating the dynamic twin map in real time, different types of obstacles in the mining area are calibrated and displayed in real time. When performing vehicle navigation, the obstacle avoidance path planning simulation is performed in combination with the vehicle positioning data to obtain the optimal obstacle avoidance route, thereby improving the safety of vehicle driving in the mining area.

[0005] According to a first aspect of the present invention, a method for vehicle path planning in a mining area based on a digital twin map is provided, comprising: acquiring map data and physical scene data of the mining area; creating a dynamic twin map of the mining area based on the map data and the physical scene data; identifying and marking obstacle information based on the dynamic twin map, the obstacles including natural obstacles and artificial obstacles; importing vehicle-related data into the dynamic twin map, and performing obstacle avoidance path planning for the vehicle based on the marked obstacle information to obtain the optimal obstacle avoidance path.

[0006] The above technical solution can more accurately identify and classify various obstacles in the mining area by creating a dynamic twin map of the mining area and dynamically calibrating obstacles. It can also perform path planning based on the dynamic twin map and formulate the optimal obstacle avoidance path based on real-time obstacle calibration information, thereby effectively improving the operating efficiency of vehicles in the mining area and reducing collisions and obstacle detour time.

[0007] Optionally, in the mining vehicle path planning method based on digital twin map provided by the present invention, map data of the mining area is obtained based on the geographic information system, and the map data includes latitude and longitude data, slope and aspect data, elevation data, geological data and building layout data; rainfall, temperature and wind speed data collected by the weather monitoring station are obtained; animal invasion, work surface progress and unconventional work vehicles are monitored by drones, and the work surface includes blasting, mining and unloading work surfaces; the position and posture data of the vehicle are collected based on the on-board acceleration sensor of the mining transport vehicle, and the road image is collected by the on-board camera.

[0008] The above technical solution improves the accuracy of the twin map by integrating geographic information system (GIS), satellite remote sensing, drone images and vehicle-mounted sensor data. This fusion of multi-source data helps to more accurately identify obstacles and plan paths.

[0009] Optionally, in the mining vehicle path planning method based on digital twin map provided by the present invention, a basic digital twin map of the mining area is constructed based on map data; when blasting, mining and unloading operations are carried out, the real-time data of the blasting area, mining area and unloading area are updated on the basic digital twin map; the location and identity of unconventional operation vehicles are marked in real time on the basic digital twin map.

[0010] The above technical solution can dynamically update the digital twin model through real-time monitoring data, so that the model can reflect the latest changes in the mining environment.

[0011] Optionally, in the mining vehicle path planning method based on digital twin map provided by the present invention, sunken or raised natural obstacles are identified in the mining area according to slope and aspect data, elevation data and geological data, construction areas are identified according to building layout data, and natural obstacles and construction areas are marked on the dynamic twin map; when waterlogging is detected on the road, the muddy area is updated, and whether a traffic obstruction is formed is evaluated in combination with the road slope data, and if a traffic obstruction is formed, the traffic obstruction is marked on the dynamic twin map; when a vehicle fault is identified according to the vehicle's position and posture data, the position of the faulty vehicle is marked on the dynamic twin map; when animal invasion is detected according to drone monitoring data, warning information is generated and marked on the basic digital twin map; when ore or earth is identified to be spilled on the road surface according to the road image, a temporary obstacle alarm is generated and the temporary obstacle is marked on the dynamic twin map; and when it is detected that the obstacle no longer exists, the obstacle mark generated on the dynamic twin map is deleted, or, when the terrain or road status changes, the terrain or road status information is modified on the dynamic twin map.

[0012] The above technical solution, by combining multiple real-time data sources, can accurately identify the specific location and shape of various obstacles.

[0013] Optionally, in the mining vehicle path planning method based on digital twin map provided by the present invention, the data collected by the vehicle-mounted sensors and cameras are input into a pre-trained temporary obstacle recognition model to identify the category and location area of ​​the temporary obstacles; and the position and moving speed of the movable temporary obstacles are tracked in real time.

[0014] The above technical solution, by real-time tracking of the position and moving speed of movable temporary obstacles, allows mining vehicles to dynamically adjust path planning to adapt to changes in obstacles, greatly reducing the risk of collision caused by the sudden appearance or movement of obstacles.

[0015] Optionally, in the mine vehicle path planning method based on the digital twin map provided by the present invention, if a vehicle is detected entering the mine area, the vehicle positioning data and vehicle type data are obtained, and the obtained vehicle positioning data and vehicle type data are imported into the dynamic twin map; the vehicle's historical driving trajectory is obtained, and the vehicle's direction of travel is predicted based on the vehicle's historical driving trajectory; the type and position of obstacles are identified and distinguished in the predicted direction of travel of the vehicle; obstacle avoidance paths are set according to the type and position of obstacles, and multiple obstacle avoidance paths are simulated in the dynamic twin map; each obstacle avoidance path is evaluated according to multiple dimensions including time efficiency, safety, and road conditions, and the path that performs best under the set goals is selected as the optimal obstacle avoidance path.

[0016] Optionally, in the mining vehicle path planning method based on digital twin map provided by the present invention, the optimal obstacle avoidance path is updated in real time to the navigation system of the mining vehicle to guide the vehicle driving; data during the vehicle driving process is collected and fed back to the trajectory prediction model to continuously optimize and adjust the model.

[0017] According to a second aspect of the present invention, a mining vehicle path planning device based on a digital twin map is provided, comprising: a data acquisition module, a model creation module, a marking module and a path planning module.

[0018] Among them, the data acquisition module is used to obtain the map data and physical scene data of the mining area; the model creation module is used to create a dynamic twin map of the mining area based on the map data and physical scene data; the marking module is used to identify and mark obstacle information based on the dynamic twin map, and the obstacles include natural obstacles and artificial obstacles; the path planning module is used to import vehicle-related data into the dynamic twin map, and plan the obstacle avoidance path for the vehicle based on the marked obstacle information to obtain the optimal obstacle avoidance path.

[0019] According to a third aspect of the present invention, a computing device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes a mining vehicle path planning method based on a digital twin map as in the first aspect.

[0020] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, comprising a computer program stored therein that can be loaded by a processor and execute the mining vehicle path planning method based on a digital twin map as in the first aspect.

[0021] According to the method and device for mine vehicle path planning based on digital twin map provided by the present invention, the mine environment can be simulated and analyzed more accurately by creating a dynamic twin map of the mine. By automatically classifying and calibrating the mine obstacles in the dynamic twin map, different types of obstacles and their characteristics can be accurately identified, reducing potential misidentification or mishandling, improving the efficiency and accuracy of obstacle calibration of the mine map, and the obstacle calibration can be updated in real time according to environmental changes, ensuring that the path planning can adapt to the dynamic mine environment. During driving, the vehicle can flexibly adjust and re-plan the path based on real-time data and dynamic twin map, improving the adaptability and flexibility of the system.

[0022] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0024] Figure 1 A block diagram of a computing device 100 according to an embodiment of the present invention is shown;

[0025] Figure 2 A schematic flow chart of a mining vehicle path planning method 200 based on a digital twin map according to an embodiment of the present invention is shown;

[0026] Figure 3 A structural schematic diagram of a mining vehicle path planning device 300 based on a digital twin map according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0027] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0028] Figure 1 FIG. 1 shows a block diagram of a computing device 100 according to an embodiment of the present invention. Figure 1 As shown, computing device 100 may include memory 106 and processor 104. Memory bus 108 may be used for communication between processor 104 and system memory 106.

[0029] Depending on the desired configuration, the processor 104 may be any type of processor, including but not limited to: a microprocessor (µP), a microcontroller (µC), a digital signal processor (DSP), or any combination thereof. The processor 104 may include one or more levels of cache, such as a level 1 cache 110 and a level 2 cache 112, a processor core 114, and registers 116. An example processor core 114 may include an arithmetic logic unit (ALU), a floating point unit (FPU), a digital signal processing core (DSP core), or any combination thereof. An example memory controller 118 may be used with the processor 104, or in some implementations, the memory controller 118 may be an internal part of the processor 104.

[0030] Depending on the desired configuration, the system memory 106 may be any type of memory, including but not limited to: volatile memory (such as RAM), non-volatile memory (such as ROM, flash memory, etc.), or any combination thereof. Physical memory in a computing device generally refers to volatile memory RAM, and data in a disk needs to be loaded into physical memory before it can be read by the processor 104. The system memory 106 may include an operating system 120, one or more applications 122, and program data 124.

[0031] In some embodiments, the application 122 may be arranged to execute instructions on an operating system by one or more processors 104 using program data 124. The operating system 120 may be, for example, Linux, Windows, etc., which includes program instructions for processing basic system services and performing hardware-dependent tasks. The application 122 includes program instructions for implementing various user-desired functions, and the application 122 may be, for example, a browser, instant messaging software, a software development tool (e.g., an integrated development environment IDE, a compiler, etc.), etc., but is not limited thereto. When the application 122 is installed in the computing device 300, a driver module may be added to the operating system 120.

[0032] When the computing device 100 starts running, the processor 104 reads and executes the program instructions of the operating system 120 from the memory 106. The application 122 runs on the operating system 120 and uses the interfaces provided by the operating system 120 and the underlying hardware to implement various functions desired by the user. When the user starts the application 122, the application 122 is loaded into the memory 106, and the processor 104 reads and executes the program instructions of the application 122 from the memory 106.

[0033] The computing device 100 also includes a storage device 132 including a removable storage 136 and a non-removable storage 138 , both of which are connected to the storage interface bus 134 .

[0034] The computing device 100 may also include an interface bus 140 that facilitates communication from various interface devices (e.g., output devices 142, peripheral interfaces 144, and communication devices 146) to the basic configuration 102 via the bus / interface controller 130. Example output devices 142 include a graphics processing unit 148 and an audio processing unit 150. They can be configured to facilitate communication with various external devices such as a display or speakers via one or more A / V ports 152. Example peripheral interfaces 144 may include a serial interface controller 154 and a parallel interface controller 156, which may be configured to facilitate communication with external devices such as input devices (e.g., keyboards, mice, pens, voice input devices, touch input devices) or other peripherals (e.g., printers, scanners, etc.) via one or more I / O ports 158. Example communication devices 146 may include a network controller 160, which may be arranged to facilitate communication with one or more other computing devices 162 via a network communication link via one or more communication ports 164.

[0035] A network communication link may be an example of a communication medium. Communication media may generally be embodied as computer-readable instructions, data structures, program modules in a modulated data signal such as a carrier wave or other transmission mechanism, and may include any information delivery medium. A "modulated data signal" may be a signal in which one or more of its data sets or its changes may be performed in a manner that encodes information in the signal. As non-limiting examples, communication media may include wired media such as a wired network or a dedicated network, and various wireless media such as sound, radio frequency (RF), microwave, infrared (IR) or other wireless media. The term computer-readable medium used herein may include both storage media and communication media. In a computing device 100 according to the present invention, an application 122 includes instructions for executing a mining vehicle path planning method 200 based on a digital twin map of the present invention.

[0036] Figure 2 FIG. 2 is a flow chart of a method 200 for planning a mining vehicle path based on a digital twin map according to an embodiment of the present invention. Figure 2 As shown, the map data and physical scene data of the mining area are obtained.

[0037] Specifically, map data of the mining area can be obtained based on the geographic information system (GIS platform), including slope and aspect data, elevation data, geological data, building layout, etc. These data are helpful in evaluating the stability of the slope and water flow path in the mining area. Obtain data such as rainfall, temperature, wind speed, etc. collected by weather monitoring stations, which affect the slippery or muddy conditions of the ground. Especially in extreme weather conditions, temperature changes may affect mechanical equipment, personnel safety, etc. Use drones to monitor animal intrusions, work surface progress, and unconventional work vehicles (such as command vehicles, refueling trucks, transport vehicles, etc.).

[0038] The vehicle position and posture data are collected based on the on-board acceleration sensor of the mining transport vehicle, and the road image is collected through the on-board camera. Specifically, a variety of sensors and cameras are installed on the mining transport vehicle, such as GPS sensors, laser radars, IMUs, etc., to collect the vehicle's position, speed, direction and other information in real time. The camera collects image data in the mining area, including roads, buildings, terrain, etc., and identifies road edges, building outlines, terrain changes and other data through image processing.

[0039] After pre-processing such as denoising and correction, the collected data is transmitted to the GIS platform via the wireless network to monitor the physical scene changes in the mining area in real time, update the mining area map data, and realize dynamic updating of the map.

[0040] Then, step S220 is executed to create a dynamic twin map of the mining area based on the map data and the physical scene data.

[0041] In one embodiment of the present invention, the map data and physical scene data of the mining area are imported into digital twin simulation software, such as Autodesk 3ds Max, Maya or geographic information system (GIS) modeling tools such as ArcGIS 3D, QGIS 3D, etc., for digital twin simulation, and a basic digital twin map of the mining area is constructed based on the acquired map data, wherein the basic digital twin map of the mining area includes features such as terrain undulations, landform distribution and building layout within the mining area, and can accurately reflect the structure and function of the physical entity.

[0042] Considering dynamic changes such as vehicle movement and personnel activities, the real-time monitoring data in actual operation is integrated with the basic digital twin map, and the basic digital twin map is dynamically updated. Combined with real-time data such as weather, drone monitoring, vehicle location, etc., dynamic events are updated in real time to ensure that they can accurately reflect the actual situation in the mining area.

[0043] For example, the ground moisture, climate conditions and potential risk areas (such as floods, landslides, etc.) of the mining area are dynamically updated based on real-time rainfall, temperature and wind speed data. The path of the transport vehicle and the location of the working surface are updated based on the real-time location and posture data of the mining area vehicles. At the same time, the drone data is integrated into the map to update the progress and safety status of the operation.

[0044] In one embodiment of the present invention, when blasting, mining and unloading operations are carried out, the real-time data of the blasting area, mining area and unloading area are updated on the basic digital twin map. The location and identity of unconventional operation vehicles are marked on the twin map in real time, where unconventional operation vehicles include command vehicles, refueling vehicles, personnel transport vehicles, etc.

[0045] Then, step S230 is executed to identify and mark obstacle information based on the dynamic twin map. The obstacles include natural obstacles and artificial obstacles.

[0046] Specifically, based on slope and aspect data, elevation data, and geological data, sunken or raised natural obstacles are identified in the mining area, and construction areas are identified based on the building layout, and natural obstacles and construction areas are marked on the dynamic twin map.

[0047] Add marking symbols, annotations or color codes to the identified obstacles in the dynamic twin map. When waterlogging is detected on the road, the muddy area is updated, and the road slope data is combined to evaluate whether a traffic obstruction is formed. If a traffic obstruction is formed, the traffic obstruction is marked on the dynamic twin map. When a vehicle failure is detected, the location of the faulty vehicle is marked on the dynamic twin map. When animal invasion is detected based on drone monitoring data, a warning message is generated and marked on the basic digital twin map. When ore or earth is spilled on the road surface based on the road image, a temporary obstacle alarm is generated and the temporary obstacle is marked on the dynamic twin map. Once a new obstacle is found, the corresponding obstacle mark is automatically generated on the dynamic twin map, and information such as the obstacle type, location, nature and impact range is recorded.

[0048] When it is detected that the obstacle no longer exists, the obstacle mark generated on the dynamic twin map will be deleted. For example, when animals leave, control of certain areas is lifted, vehicles are removed, or weather conditions improve, the obstacle mark is evaluated as "deletable". After confirming that the obstacle no longer exists, the obstacle mark can be automatically cleared through the feedback system and the map can be updated at the same time to keep the map clear and accurate.

[0049] When the terrain or road status changes, the status information of the terrain or road is modified on the dynamic twin map. For example, if some sections of the road are opened up to form new shortcuts after construction or other changes, this change information can be added to the map to ensure the optimization of transportation and action routes within the mining area.

[0050] In one embodiment of the present invention, the data collected by the vehicle-mounted sensors and cameras can also be input into a pre-trained temporary obstacle recognition model to identify the location area where temporary obstacles exist and the type of temporary obstacles; and track the location and moving speed of movable temporary obstacles in real time. For example, movable obstacles can be other vehicles, animals, pedestrians, etc. in the same period.

[0051] Finally, step S240 is executed to import the vehicle-related data into the dynamic twin map, and the obstacle avoidance path of the vehicle is planned based on the obstacle calibration to obtain the optimal obstacle avoidance path.

[0052] If a vehicle is detected entering the mining area, vehicle identification technology (such as license plate recognition, RFID tags, etc.) is used to obtain vehicle type information, such as vehicle size, weight, turning radius, power characteristics, etc., and the vehicle's own sensor data, such as GPS, lidar, etc., are integrated to obtain vehicle positioning data in real time. This information is imported into the dynamic twin map of the mining area to update the vehicle location and attribute information in the model.

[0053] The historical driving trajectory of the vehicle (including timestamp and location coordinates) is obtained from the database, and the direction of the vehicle is predicted based on the historical driving trajectory of the vehicle. That is, a trajectory prediction model is established using machine learning or deep learning algorithms (such as LSTM, RNN), the historical driving trajectory is input into the trajectory prediction model for training, a trained trajectory prediction model is obtained, and the current driving trajectory is input into the trained trajectory prediction model to predict the direction of the vehicle.

[0054] Identify and distinguish the type and location of obstacles in the predicted direction of the vehicle. Set obstacle avoidance paths based on the type and location of obstacles, and simulate multiple obstacle avoidance paths in the dynamic twin map.

[0055] Different obstacle avoidance strategies are used for different types of obstacles. Obstacle avoidance strategies can include detouring, deceleration, re-routing, etc. For example, you can choose to detour for fixed obstacles, decelerate and avoid movable obstacles, and re-route for natural obstacles with large areas to ensure that the vehicle can safely pass through the obstacle area.

[0056] Select an appropriate path planning algorithm, such as the A* algorithm, Dijkstra algorithm, or heuristic algorithm, simulate multiple possible obstacle avoidance paths, and optimize each path according to the set obstacle avoidance strategy and goal. Evaluate each obstacle avoidance path based on multiple dimensions such as time efficiency, safety, and road conditions, and select the path that performs best under the set goals (such as the shortest time and the best road conditions) as the optimal obstacle avoidance path.

[0057] The optimized obstacle avoidance path is updated to the navigation system of the mining vehicle in real time to guide the vehicle's driving. The data during the vehicle's driving process is collected and fed back to the trajectory prediction model for continuous optimization and adjustment of the model. The actual driving trajectory of the vehicle is monitored in real time to see if it is consistent with the preset optimal path, and the navigation instructions are adjusted according to the actual driving conditions.

[0058] Figure 3 FIG. 3 is a schematic diagram showing a structure of a mining vehicle path planning device 300 based on a digital twin map according to an embodiment of the present invention. Figure 3 As shown, the device 300 may include: a data acquisition module 310 , a model creation module 320 , a marking module 330 and a path planning module 340 .

[0059] Among them, the data acquisition module 310 can obtain the map data and physical scene data of the mining area. For example, the data acquisition module 310 can obtain the map data of the mining area based on the geographic information system (GIS platform), and the map data includes slope and aspect data, elevation data, and geological data; obtain the rainfall, temperature, and wind speed data collected by the weather monitoring station; monitor animal invasion, work surface progress, and unconventional work vehicles through drones; collect vehicle position and posture data based on the vehicle-mounted acceleration sensor of the mining area transport vehicle, and collect road images through the vehicle-mounted camera.

[0060] The model creation module 320 can create a dynamic twin map of the mining area based on the map data and the physical scene data. Specifically, the model creation module can update the real-time data of the blasting area, mining area, and unloading area on the twin map when the blasting, mining, and unloading operations are in progress; when animal intrusion is detected, a warning message is generated and marked on the twin map; the location and identity of unconventional operation vehicles such as command vehicles, refueling vehicles, and personnel transport vehicles are marked on the twin map in real time.

[0061] The marking module 330 can identify and mark obstacles based on the dynamic twin map, including natural obstacles and artificial obstacles. Specifically, the marking module 330 can identify sunken or raised natural obstacles in the mining area according to the slope and aspect data, elevation data, and geological data, identify the construction area according to the building layout, and mark the natural obstacles and construction areas on the dynamic twin map; when waterlogging is detected on the road, the muddy area is updated, and the road slope data is combined to evaluate whether a traffic obstruction is formed. If a traffic obstruction is formed, the traffic obstruction is marked on the dynamic twin map; when a vehicle fault is identified based on the vehicle's position and posture data, the position of the faulty vehicle is marked on the dynamic twin map; when ore or earth is identified on the road surface according to the road image, a temporary obstacle alarm is generated and the temporary obstacle is marked on the dynamic twin map. When it is detected that the obstacle no longer exists, the obstacle mark generated on the dynamic twin map is deleted. For example, when animals leave, control in certain areas is lifted, vehicles are removed, or weather conditions improve, obstacle markings are evaluated as "deletable". After confirming that the obstacles no longer exist, the obstacle markings can be automatically cleared through the feedback system, and the map can be updated at the same time to keep the map clear and accurate. When the terrain or road status changes, the status information of the terrain or road is modified on the dynamic twin map. For example, if some sections of the road are opened up to form new shortcuts after construction or other changes, this change information can be added to the map to ensure the optimization of transportation and action routes within the mining area.

[0062] The path planning module 340 can import vehicle-related data into the dynamic twin map, plan the obstacle avoidance path for the vehicle based on obstacle calibration, and obtain the optimal obstacle avoidance path. Specifically, if a vehicle is detected entering the mining area, the path planning module 340 can obtain the vehicle positioning data and vehicle type data, and import the obtained vehicle positioning data and vehicle type data into the dynamic twin map; obtain the historical driving trajectory of the vehicle, and predict the direction of the vehicle based on the historical driving trajectory of the vehicle; identify and distinguish the type and position of obstacles in the predicted direction of the vehicle; set the obstacle avoidance path according to the type and position of the obstacle, and simulate multiple obstacle avoidance paths in the dynamic twin map; evaluate each obstacle avoidance path according to multiple dimensions including time efficiency, safety, and road conditions, and select the path that performs best under the set goals as the optimal obstacle avoidance path.

[0063] According to the method and device for mine vehicle path planning based on digital twin map provided by the present invention, the mine environment can be simulated and analyzed more accurately by creating a dynamic twin map of the mine. By automatically classifying and calibrating the mine obstacles in the dynamic twin map, different types of obstacles and their characteristics can be accurately identified, reducing potential misidentification or mishandling, improving the efficiency and accuracy of obstacle calibration of the mine map, and the obstacle calibration can be updated in real time according to environmental changes, ensuring that the path planning can adapt to the dynamic mine environment. During driving, the vehicle can flexibly adjust and re-plan the path based on real-time data and dynamic twin map, improving the adaptability and flexibility of the system.

[0064] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0065] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the following intention: that the claimed invention requires more features than the features explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0066] Although the present invention has been described according to a limited number of embodiments, it will be apparent to those skilled in the art, with the benefit of the above description, that other embodiments may be envisioned within the scope of the invention thus described. In addition, it should be noted that the language used in this specification is selected primarily for readability and teaching purposes, rather than for explaining or defining the subject matter of the present invention. Therefore, many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the appended claims. The disclosure of the present invention is illustrative and not restrictive with respect to the scope of the present invention, and the scope of the present invention is defined by the appended claims.

Claims

1. A mining vehicle path planning method based on digital twin map, characterized in that: include: Obtain map data and physical scene data of the mining area; Creating a dynamic twin map of the mining area based on the map data and the physical scene data; Based on the dynamic twin map, obstacle information is identified and marked, and the obstacles include natural obstacles and artificial obstacles; vehicle-related data is imported into the dynamic twin map, and an obstacle avoidance path is planned for the vehicle based on the marked obstacle information to obtain an optimal obstacle avoidance path. Acquiring map data of the mining area based on a geographic information system, wherein the map data includes latitude and longitude data, slope and aspect data, elevation data, geological data, and building layout data; Obtain rainfall, temperature, and wind speed data collected by weather monitoring stations; Use drones to monitor animal intrusions, progress on work surfaces, and vehicles engaged in unconventional operations, including blasting, mining, and unloading; The vehicle position and posture data are collected based on the vehicle-mounted acceleration sensor of the mining area transport vehicle, and the road image is collected through the vehicle-mounted camera. Constructing a basic digital twin map of the mining area based on the map data; When blasting, mining and unloading operations are in progress, the real-time data of the blasting area, mining area and unloading area are updated on the basic digital twin map; The location and identity of the non-routine operation vehicle are marked in real time on the basic digital twin map. According to the slope and aspect data, elevation data and geological data, sunken or raised natural obstacles are identified in the mining area; according to the building layout data, construction areas are identified, and the natural obstacles and construction areas are marked on the dynamic twin map; When water accumulation on the road is detected, the muddy area is updated, and the road slope data is combined to evaluate whether a traffic obstruction is formed. If a traffic obstruction is formed, the traffic obstruction is marked on the dynamic twin map; When a vehicle fault is identified based on the vehicle's position and posture data, the position of the faulty vehicle is marked on the dynamic twin map; When animal intrusion is detected based on drone monitoring data, a warning message is generated and marked on the basic digital twin map; When ore or earth spilled on the road is identified based on road images, a temporary obstacle alarm is generated and the temporary obstacle is marked on the dynamic twin map; as well as When it is detected that the obstacle no longer exists, the obstacle mark generated on the dynamic twin map is deleted, or when the terrain or road status changes, the terrain or road status information is modified on the dynamic twin map.

2. The mining vehicle path planning method based on digital twin map according to claim 1 is characterized in that: The step of identifying and marking obstacle information based on the dynamic twin map, wherein the obstacles include natural obstacles and artificial obstacles, further includes: Input the data collected by the vehicle sensors and cameras into the pre-trained temporary obstacle recognition model to identify the category and location area of ​​the temporary obstacle; Track the position and speed of movable temporary obstacles in real time.

3. The mining area vehicle path planning method based on digital twin map according to claim 2 is characterized in that: The step of importing vehicle-related data into the dynamic twin map, planning an obstacle avoidance path for the vehicle based on the marked obstacle information, and obtaining an optimal obstacle avoidance path includes: If a vehicle is detected entering the mining area, the vehicle positioning data and vehicle type data are obtained, and the obtained vehicle positioning data and vehicle type data are imported into the dynamic twin map; Obtain the historical driving trajectory of the vehicle, and predict the direction of travel of the vehicle based on the historical driving trajectory of the vehicle; identify and distinguish the type and location of obstacles in the predicted direction of travel of the vehicle; Setting an obstacle avoidance path according to the type and position of the obstacle, and simulating multiple obstacle avoidance paths in the dynamic twin map; Each obstacle avoidance path is evaluated based on multiple dimensions including time efficiency, safety, and road conditions, and the path that performs best under the set goals is selected as the optimal obstacle avoidance path.

4. The mining area vehicle path planning method based on digital twin map according to claim 3 is characterized in that: The method further comprises: Update the optimal obstacle avoidance route to the navigation system of mining vehicles in real time to guide vehicle driving; Collect data during vehicle driving and feed it back to the trajectory prediction model for continuous optimization and adjustment of the model.

5. A mining vehicle path planning device based on a digital twin map, characterized in that: include: Data acquisition module, used to obtain map data and physical scene data of the mining area; A model creation module, used to create a dynamic twin map of the mining area based on the map data and physical scene data; A marking module, used to identify and mark obstacle information based on the dynamic twin map, wherein the obstacles include natural obstacles and artificial obstacles; A path planning module is used to import vehicle-related data into the dynamic twin map, plan the vehicle's obstacle avoidance path based on the marked obstacle information, and obtain the optimal obstacle avoidance path. Acquiring map data of the mining area based on a geographic information system, wherein the map data includes latitude and longitude data, slope and aspect data, elevation data, geological data, and building layout data; Obtain rainfall, temperature, and wind speed data collected by weather monitoring stations; Use drones to monitor animal intrusions, progress on work surfaces, and unconventional work vehicles, including blasting, mining, and unloading work surfaces; The vehicle position and posture data are collected based on the vehicle-mounted acceleration sensor of the mining area transport vehicle, and the road image is collected through the vehicle-mounted camera. Constructing a basic digital twin map of the mining area based on the map data; When blasting, mining and unloading operations are in progress, the real-time data of the blasting area, mining area and unloading area are updated on the basic digital twin map; The location and identity of the non-routine operation vehicle are marked in real time on the basic digital twin map. According to the slope and aspect data, elevation data and geological data, sunken or raised natural obstacles are identified in the mining area; according to the building layout data, construction areas are identified, and the natural obstacles and construction areas are marked on the dynamic twin map; When water accumulation on the road is detected, the muddy area is updated, and the road slope data is combined to evaluate whether a traffic obstruction is formed. If a traffic obstruction is formed, the traffic obstruction is marked on the dynamic twin map; When a vehicle fault is identified based on the vehicle's position and posture data, the position of the faulty vehicle is marked on the dynamic twin map; When animal intrusion is detected based on drone monitoring data, a warning message is generated and marked on the basic digital twin map; When ore or earth spilled on the road is identified based on road images, a temporary obstacle alarm is generated and the temporary obstacle is marked on the dynamic twin map; as well as When it is detected that the obstacle no longer exists, the obstacle mark generated on the dynamic twin map is deleted, or when the terrain or road status changes, the terrain or road status information is modified on the dynamic twin map.

6. A computing device, characterized in that include: at least one processor; A memory storing program instructions, wherein the program instructions are configured to be suitable for execution by the at least one processor, and the program instructions include instructions for executing the mining vehicle path planning method based on the digital twin map as described in any one of claims 1-4.

7. A readable storage medium storing program instructions, characterized in that: When the program instructions are read and executed by a computing device, the computing device executes the mining vehicle path planning method based on a digital twin map as described in any one of claims 1 to 4.

Images