Dual flywheel system, smart mine system, and method

Abstract

A dual flywheel system, a smart mine system, and a method. The dual flywheel system comprises a sensing system and a planning system. By means of using a bird's-eye view technology and a deep learning algorithm, the sensing system fuses acquired multi-dimensional environment data of a mine, and establishes a mine 3D environment model so as to output environment sensing data; on the basis of vehicle management information fed back by a fleet management platform, task scheduling data, and the environment sensing data, and by means of using the deep learning algorithm and a Monte Carlo tree search algorithm, the planning system predicts a planning path for each mine vehicle, so as to generate an optimal traveling path, the vehicle management information comprising vehicle attitude and health information, vehicle position state information, vehicle operation task priority information, and mine safety standard information. By means of the deep synergy of sensing and planning and the integration of fleet management information and safety standards, vehicles can operate more accurately on the basis of optimal paths, thereby improving the operation yield of mines and promoting the development of smart mines.

Description

A dual flywheel system, an intelligent mining system and method

[0001] This application claims priority to Chinese Patent Application No. 202411871916.4, filed on December 18, 2024, entitled "A Dual Flywheel System, Intelligent Mining System and Method", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of autonomous driving technology, and in particular to a dual flywheel system, an intelligent mining system and method. Background Technology

[0003] With the rapid development of autonomous driving technology and the increasing demand for automation in the mining industry, intelligent driving systems are gradually becoming a key technology in mines and other complex industrial environments.

[0004] Traditional intelligent driving systems typically rely on a single perception or planning model, or even some end-to-end models. Although end-to-end models have gained widespread attention in autonomous driving technology in recent years, reducing the data processing chain by generating driving control commands directly from sensor inputs, they have demonstrated a certain degree of flexibility and efficiency in public road scenarios. However, the application of existing end-to-end models still faces technical bottlenecks such as huge data requirements, inference "illusion" phenomena, and difficulty in real-time response to dynamic environments. These problems can directly affect the robustness and safety of end-to-end models. Furthermore, in the highly complex environment of mining, these end-to-end models cannot achieve deep adaptation to the physical environment, especially in slopes, gravel, and other complex terrains, where they cannot accurately plan paths, thus leading to reduced operational productivity in mining operations. Summary of the Invention

[0005] Based on this, it is necessary to address the aforementioned technical problems by providing a dual flywheel system, an intelligent mining system, and a method in this application. These methods can effectively solve the problems of insufficient robustness and security in end-to-end models, thereby achieving accurate path planning and improving the operational productivity of the mining farm.

[0006] A first aspect of this application provides an intelligent mining system, wherein the dual-flywheel system includes a sensing system and a planning system;

[0007] The perception system includes a multimodal sensor and a data processing module. The multimodal sensor is used to acquire multi-dimensional environmental data of the mine. The data processing module is used to fuse the multi-dimensional environmental data using bird's-eye view technology and deep learning algorithms to establish a 3D environmental model of the mine, so as to output environmental perception data and transmit the environmental perception data to the planning system.

[0008] The planning system includes a path planning module. The path planning module is used to predict the planned path for each mining truck based on vehicle management information, task scheduling data, and environmental perception data fed back by the fleet management platform, and to generate the optimal driving path by using deep learning algorithms and Monte Carlo tree search algorithms. The vehicle management information includes vehicle attitude and health information, vehicle position status information, vehicle operation task priority information, and mine safety standard information.

[0009] Furthermore, the multimodal sensor includes a lidar sensing module, a millimeter-wave radar sensing module, and a vision sensor module;

[0010] The lidar sensing module detects the surrounding environment by emitting a laser beam;

[0011] The millimeter-wave radar sensing module detects the surrounding environment by emitting millimeter-wave bands;

[0012] The visual sensor module uses optical elements and imaging technology to detect and acquire image information of the surrounding environment.

[0013] Furthermore, the planning system includes a task decision module and a safety monitoring module;

[0014] The task decision module is used to adjust the driving path and operation sequence of each mining truck in real time based on the vehicle attitude and health information, vehicle position status information and vehicle operation task priority information.

[0015] The safety monitoring module is used to monitor the driving path and potential risks in the operation tasks of each mining truck in real time based on the mine safety standard information.

[0016] A second aspect of this application provides an intelligent mining system, which includes a fleet management platform, a dual flywheel system, and a vehicle control system. The dual flywheel system includes a perception system and a planning system.

[0017] The fleet management platform includes a task scheduling module and a data sharing module. The task scheduling module is used to allocate the corresponding work tasks to each vehicle based on the acquired vehicle management information to obtain task scheduling data, and transmit the vehicle management information and the task scheduling data to the planning system in the dual flywheel system. The data sharing module is used to provide work scheduling instructions and transmit the work scheduling instructions to the vehicle control system. The vehicle management information includes vehicle attitude and health information, vehicle position status information, vehicle work task priority information, and mine safety standard information.

[0018] The perception system includes a multimodal sensor and a data processing module. The multimodal sensor is used to acquire multi-dimensional environmental data of the mine. The data processing module is used to fuse the multi-dimensional environmental data using bird's-eye view technology and deep learning algorithms to establish a 3D environmental model of the mine, so as to output environmental perception data and transmit the environmental perception data to the planning system.

[0019] The planning system includes a path planning module, which is used to predict the planned path for each mining truck based on the vehicle management information, the task scheduling data and the environmental perception data, using deep learning algorithms and Monte Carlo tree search algorithms, to generate the optimal driving path, and transmit the optimal driving path to the vehicle control system.

[0020] The vehicle control system is used to control the vehicle to travel along the optimal driving path based on the job scheduling instructions.

[0021] Furthermore, the multimodal sensor includes a lidar sensing module, a millimeter-wave radar sensing module, and a vision sensor module;

[0022] The lidar sensing module detects the surrounding environment by emitting a laser beam;

[0023] The millimeter-wave radar sensing module detects the surrounding environment by emitting millimeter-wave bands;

[0024] The visual sensor module uses optical elements and imaging technology to detect and acquire image information of the surrounding environment.

[0025] Furthermore, the planning system includes a task decision module and a safety monitoring module;

[0026] The task decision module is used to adjust the driving path and operation sequence of each mining truck in real time based on the vehicle attitude and health information, vehicle position status information and vehicle operation task priority information.

[0027] The safety monitoring module is used to monitor the driving path and potential risks in the operation tasks of each mining truck in real time based on the mine safety standard information.

[0028] Furthermore, the intelligent mining system also includes an environmental adaptation system, which includes an adaptation module and an adjustment module;

[0029] The adaptation module is used to adapt to the vehicle's driving needs in different physical environments.

[0030] The adjustment module is used to adjust the driving speed and driving mode of each mining truck in real time based on the environmental conditions of the mine.

[0031] Furthermore, the intelligent mining system also includes a manual closed-loop system, which includes a manual instruction module and a closed-loop feedback module.

[0032] The manual instruction module is used to input manual instructions through a manual interface and transmit the manual instructions to the vehicle control system.

[0033] The closed-loop feedback module is used to monitor and provide feedback on the execution status of the manual instructions in real time.

[0034] Furthermore, the vehicle control system includes an energy management module;

[0035] The energy management module is used to dynamically adjust the power output of each mining truck based on its battery status and route requirements.

[0036] A third aspect of this application provides a path planning and control method, which is applied to the intelligent mining system described in any of the second aspects above, the method comprising:

[0037] Based on the acquired vehicle management information, the corresponding work tasks of each vehicle are assigned to obtain task scheduling data. The vehicle management information includes vehicle attitude and health information, vehicle location status information, vehicle work task priority information, and mine safety standard information.

[0038] The task scheduling data and vehicle management information are sent to the dual flywheel system so that the dual flywheel system can predict the planned path for each mining truck based on the vehicle management information, the task scheduling data and environmental perception data, using deep learning algorithms and Monte Carlo tree search algorithms, generate the optimal driving path, and transmit the optimal driving path to the vehicle control system.

[0039] A job scheduling command is issued to the vehicle control system, so that the vehicle control system responds to the job scheduling command and controls the vehicle to travel along the optimal driving path:

[0040] In summary, this application provides a dual-flywheel system, an intelligent mining system, and a method. The dual-flywheel system includes a perception system and a planning system. The perception system uses bird's-eye view technology and deep learning algorithms to fuse multi-dimensional environmental data acquired from the mining area, establishing a 3D environmental model of the mining area to output environmental perception data. This environmental perception data is then transmitted to the planning system. The planning system, based on vehicle management information, task scheduling data, and environmental perception data fed back from the fleet management platform, uses deep learning algorithms and Monte Carlo tree search algorithms to predict the optimal driving path for each mining truck, generating the optimal travel path. The vehicle management information includes vehicle attitude and health information, vehicle position status information, vehicle task priority information, and mining safety standard information. Therefore, this application, by combining the collaborative architecture of the perception system and the planning system, and integrating fleet management information and safety standards, can accurately generate the optimal driving path, allowing vehicles to operate more precisely along the optimal path, reducing unnecessary waiting time and path conflicts. This not only improves the operational productivity of the mining area but also lays a solid technical foundation for the future development of intelligent mining areas. Furthermore, the dual flywheel system of this application has significant advantages in target optimization and modeling complexity. By introducing rule-based enhancement mechanisms (deep learning algorithms and Monte Carlo tree search algorithms) into the decision-making and planning stages, it effectively solves the problems of insufficient robustness and security in end-to-end models.

[0041] Details of one or more embodiments of this application are set forth in the following drawings and description, and other features and advantages of this application will become apparent from the specification, drawings and claims. Attached Figure Description

[0042] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those with ordinary technical skills in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 is a schematic diagram of the structure of an intelligent mining system provided in an embodiment of this application;

[0044] Figure 2 is another structural schematic diagram of an intelligent mining system provided in an embodiment of this application;

[0045] Figure 3 is a schematic diagram of a dual flywheel system provided in an embodiment of this application;

[0046] Figure 4 is a flowchart illustrating a path planning and control method according to an embodiment of this application; Detailed Implementation

[0047] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0048] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0049] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0050] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0051] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0052] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0053] It should be understood that the sequence number of each step in the following embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0054] To illustrate the technical solution of this application, specific embodiments are described below.

[0055] Figure 1 is a schematic diagram of the structure of an intelligent mining system according to an exemplary embodiment of the present application. As shown in Figure 1, the intelligent mining system includes a fleet management platform, a dual flywheel system and a vehicle control system, wherein the dual flywheel system includes a perception system and a planning system.

[0056] The fleet management platform includes a task scheduling module and a data sharing module. The task scheduling module is used to allocate the corresponding work tasks to each vehicle based on the acquired vehicle management information to obtain task scheduling data. The vehicle management information and task scheduling data are transmitted to the planning system in the dual flywheel system. The data sharing module is used to provide work scheduling instructions and transmit the work scheduling instructions to the vehicle control system. The vehicle management information includes vehicle attitude and health information, vehicle position status information, vehicle work task priority information, and mine safety standard information.

[0057] The perception system includes a multimodal sensor and a data processing module. The multimodal sensor is used to acquire multi-dimensional environmental data of the mine. The data processing module is used to fuse the multi-dimensional environmental data using bird's-eye view technology and deep learning algorithms to establish a 3D environmental model of the mine, so as to output environmental perception data and transmit the environmental perception data to the planning system.

[0058] The planning system includes a path planning module. The path planning module is used to predict the planned path for each mining truck based on vehicle management information, task scheduling data and environmental perception data, using deep learning algorithms and Monte Carlo tree search algorithms, generating the optimal driving path, and transmitting the optimal driving path to the vehicle control system.

[0059] The vehicle control system is used to control vehicles to travel along the optimal route based on job scheduling instructions.

[0060] In this embodiment, as shown in Figure 2, the intelligent mining system includes a fleet management platform, a dual-flywheel system, and a vehicle control system. The fleet management platform includes a task scheduling module and a data sharing module. The task scheduling module allocates the corresponding work tasks to each vehicle based on the acquired vehicle management information to obtain task scheduling data. It then transmits the vehicle management information and task scheduling data to the planning system in the dual-flywheel system to ensure optimal path planning for vehicle operation and charging. The data sharing module, through connection with all mining trucks, charging piles, and sensing modules, provides unified work scheduling instructions and transmits these instructions to the vehicle control system, thereby achieving global information sharing. The vehicle management information includes vehicle posture and health information, vehicle position status information, vehicle work task priority information, and mining safety standard information. Vehicle posture information refers to the overall state and appearance of the vehicle, including its contact with the ground, body tilt angle, and whether the vehicle is perpendicular, including normal driving posture, tilted posture, and abnormal posture. Vehicle health information refers to information related to vehicle operating status and component health, including engine health information, chassis health information, and body health information. Vehicle location status information refers to the real-time location, direction of travel, speed, and current status (e.g., empty or fully loaded) of vehicles within the mining area. This information is typically obtained through GPS and sensors, enabling the dispatch center to monitor vehicle operations in real time and ensure operational efficiency and safety. Vehicle task priority information refers to the order and priority of tasks performed by vehicles. For example, some tasks may be more urgent or important than others and therefore require priority processing. This helps optimize resource allocation within the mine, improve operational efficiency, and ensure that critical tasks are completed on time. Mine safety standard information refers to the various safety standards and regulations that must be followed during mine operations. This includes operating procedures, accident prevention measures, and emergency response procedures. These standards aim to ensure the safety of personnel, equipment, and the environment, ensuring that mine operations comply with relevant laws and regulations. By effectively integrating and managing these three types of information, and combining the system with vehicle management information and task scheduling data, the subsequent dual-flywheel system can predict through multi-agent interaction, ensuring that the travel paths and task priorities of each mining truck do not interfere with each other, achieving a collaborative operational effect. Collaborative management of mining vehicle fleets greatly reduces path conflicts and unnecessary waiting time, achieving optimal utilization of mining resources and thus improving overall operational efficiency and productivity.

[0061] In this embodiment, the dual flywheel system includes a perception system and a planning system. The perception system includes a multimodal sensor and a data processing module. The multimodal sensor is used to acquire multi-dimensional environmental data of the mine. The data processing module is used to filter, denoise, and correct the multi-dimensional environmental data in advance to improve the quality and accuracy of the data. Then, the multi-dimensional environmental data is fused through bird's-eye view technology and deep learning algorithms to form a more complete and reliable 3D environment model of the mine, which provides real-time detection and recognition of dynamic and static objects, thereby outputting environmental perception data. That is, feature extraction is performed on each modality of data, and a multimodal feature fusion structure is designed to effectively fuse the features of different modalities together to construct a 3D environment model of the mine. This model includes convolutional layers, fully connected layers, etc., for extracting environmental features, and an output layer for classification, which classifies the features after multimodal data fusion into environmental conditions. Bird's-eye view technology is a visualization technology that presents spatial information from a bird's-eye view perspective and is often used in fields such as autonomous driving, drones, and map services. Deep learning is a branch of machine learning that uses multi-layer neural networks for data learning and pattern recognition to automatically extract features. Through the above steps, vehicles can effectively identify slopes, obstacles, and other dynamic entities in complex mines, improving the accuracy of environmental perception. This reduces operational interruptions and safety hazards caused by environmental misjudgments, significantly enhancing the safety of mine operations. Furthermore, the environmental perception data is transmitted to the planning system via an information interaction interface to facilitate decision-making and route planning.

[0062] In this embodiment, the planning system includes a path planning module. This module, based on vehicle management information, task scheduling data, and environmental perception data, uses deep learning algorithms and Monte Carlo Tree Search (MCTS) to predict the planned path for each mining truck, generating the optimal driving path. It also rapidly responds to changes in task priority, vehicle status, and other entity behaviors, ensuring continuous operation of the unmanned vehicles. This not only reduces waiting time but also avoids resource waste, significantly improving vehicle response efficiency and path planning flexibility, and transmits the optimal driving path to the vehicle control system. Deep learning, a branch of machine learning, utilizes multi-layered neural networks for data learning and pattern recognition to automatically extract features. Monte Carlo Tree Search (MCTS) is a heuristic search algorithm used in decision-making processes for complex problems with vast and inexhaustible state spaces. This application, by introducing bird's-eye view technology and deep learning algorithms, can transform multimodal data into a top-down view, generating a more comprehensive and high-precision 3D environment model of the mine. By introducing deep learning algorithms and Monte Carlo tree search algorithms, this application utilizes simulated stochastic strategies to explore possible decision paths and employs statistical methods to evaluate the potential of each node, thereby progressively constructing and optimizing the search tree. This provides autonomous vehicles with multi-agent interaction prediction capabilities, enabling the simulation and prediction of multi-party interactive behaviors in complex traffic scenarios. This allows vehicles to be more proactive in responding to dynamic environments. Furthermore, considering the three-dimensional motion characteristics of mining trucks (such as uphill / downhill movement and load changes), the planning system in this application enhances its adaptability to multi-dimensional dynamics through modular training. It is evident that the dual-flywheel system in this application integrates a perception system and a planning system, enabling the system to work efficiently and collaboratively in dynamic and complex environments. This achieves a deep coupling of high-precision perception and flexible planning. Moreover, the introduction of rule-based enhancement mechanisms (deep learning algorithms and Monte Carlo tree search algorithms) in the decision-making and planning stages realizes an architectural innovation that combines feature extraction from end-to-end models with rule-based safety mechanisms, effectively addressing the issues of insufficient robustness and security in end-to-end models.

[0063] It should be noted that generating environmental perception data and the optimal driving path can also be achieved using other methods such as perception algorithms, Bayesian networks, or Markov decision processes. The specific method can be set according to the actual situation, and this application does not impose any restrictions on it.

[0064] In this embodiment, the vehicle control system receives work scheduling instructions from the fleet management platform, controls the vehicle to travel along the optimal driving path, and performs operations such as acceleration, steering, and braking.

[0065] In this embodiment, the perception system is combined with the planning system: high-precision environmental perception data generated by the perception system is transmitted to the planning system in real time through an information interaction interface. The planning system calculates path planning and decision-making strategies based on this information and sends instructions to the vehicle control system. Thus, through deep collaboration between perception and planning, and the integration of fleet management information and safety standards, the dual-flywheel system of this application effectively improves the automation level and operational efficiency of mining operations. Unmanned mining trucks can operate more accurately along the optimal path, reducing unnecessary waiting time and path conflicts, thereby maximizing mining productivity and promoting the development of smart mines. Furthermore, the planning system is combined with the fleet management platform: the fleet management system provides the planning system with information such as vehicle location, task priority, and safety standards to ensure that the planning system is on the correct path. In planning and multi-agent collaborative decision-making, scheduling data can be updated in real time. It is evident that the integration of the planning system and the fleet management system enables collaborative decision-making among multiple vehicles. After receiving scheduling instructions from the fleet management system and real-time status data from other vehicles, the planning system can optimize the running path and work sequence of each mining truck. This ensures that the driving paths of vehicles do not interfere with each other, significantly improving the overall operating efficiency of mining vehicles. Furthermore, the planning system can dynamically adjust the driving and work paths of vehicles based on their real-time location and mining traffic conditions, ensuring the efficient collaborative operation of the entire fleet. Finally, the fleet management platform is combined with the vehicle control system: scheduling instructions from the fleet management system are sent to the vehicle control system through the control instruction interface, achieving synchronization between mining trucks and mining operations, significantly improving mining production efficiency and operational safety.

[0066] For example, during operations at a mining site, vehicle A's perception system detects obstacles ahead in real time and calculates the shortest path to nearby vehicles. Upon receiving work scheduling instructions from the fleet management platform, the planning system considers task priority and vehicle battery status to select a safe and efficient path. When vehicle A approaches a charging station, the system automatically determines the timing of charging and task priority, optimizing operational efficiency and reducing vehicle downtime. Through these steps, the intelligence level of vehicle perception, planning, and collaborative operations is significantly improved, ensuring the operational efficiency, safety, and productivity of mining vehicles.

[0067] In one embodiment, the multimodal sensor includes a lidar sensing module, a millimeter-wave radar sensing module, and a vision sensor module;

[0068] The lidar sensing module detects the surrounding environment by emitting a laser beam;

[0069] The millimeter-wave radar sensing module detects the surrounding environment by emitting millimeter-wave bands;

[0070] The visual sensor module uses optical elements and imaging technology to detect and acquire image information of the surrounding environment.

[0071] In this embodiment, the multimodal sensor includes a lidar sensing module, a millimeter-wave radar sensing module, and a vision sensor module. The perception system utilizes these sensors to acquire real-time and accurate multi-dimensional environmental data around the vehicle, including road conditions, obstacles, traffic signs, and other vehicles. This multi-dimensional environmental data is then integrated into a 3D environment model of the mine, enabling real-time detection and identification of both dynamic and static objects. Specifically, the lidar sensing module detects the surrounding environment by emitting a laser beam; the millimeter-wave radar sensing module detects the surrounding environment by emitting millimeter-wave waves; and the vision sensor module uses optical elements and imaging technology to detect and acquire image information of the surrounding environment.

[0072] In one embodiment, the planning system includes a task decision module and a safety monitoring module;

[0073] The task decision module is used to adjust the driving path and operation sequence of each mining truck in real time based on the vehicle attitude and health information, vehicle position status information and vehicle operation task priority information.

[0074] The safety monitoring module is used to monitor the driving path and potential risks in the operation tasks of each mining truck in real time based on the mine safety standard information.

[0075] In this embodiment, the planning system includes a task decision module and a safety monitoring module. The task decision module adjusts the driving path and work sequence of each mining truck in real time based on vehicle attitude and health information, vehicle location status information, and vehicle task priority information fed back from the fleet management platform, thereby achieving multi-vehicle collaborative operation. The safety monitoring module monitors the driving path and potential risks in the work tasks of each mining truck in real time based on ISO-17757 mine safety standard information, and automatically adjusts the driving strategy in case of emergencies. By adhering to mine safety standards such as ISO-17757, the system monitors vehicle paths and task execution in real time, can promptly detect potential risks and proactively adjust them. This safety standard-based monitoring mechanism ensures compliant vehicle operation and reduces the accident rate in mine operations.

[0076] In one embodiment, the intelligent mining system further includes an environmental adaptation system, which includes an adaptation module and an adjustment module;

[0077] The adaptation module is used to adapt to the vehicle's driving needs in different physical environments.

[0078] The adjustment module is used to adjust the driving speed and driving mode of each mining truck in real time based on the environmental conditions of the mine.

[0079] In this embodiment, the intelligent mine system further includes an environmental adaptation system, which comprises an adaptation module and an adjustment module. The adaptation module collects real-time information such as mine terrain slope and gravel distribution via a sensor network. The adaptation module dynamically adapts to the driving needs of vehicles in different physical environments. When encountering steep slopes or special terrain, the adjustment module adjusts the driving speed and mode of each mine truck in real-time based on the mine's environmental conditions, ensuring operational stability and safety. This application's environmental adaptation system can monitor terrain changes in the mine in real-time, such as slope and gravel distribution, and adjust vehicle driving modes accordingly, thereby ensuring vehicle stability and safety in complex terrain. Through innovative adaptation to the physical environment, the system can maintain stable operation under different terrains, improving the mine truck's operational capabilities in varied terrain.

[0080] In one embodiment, the intelligent mining system further includes a manual closed-loop system, which includes a manual instruction module and a closed-loop feedback module;

[0081] The manual instruction module is used to input manual instructions through a manual interface and transmit the manual instructions to the vehicle control system.

[0082] The closed-loop feedback module is used to monitor and provide feedback on the execution status of the manual instructions in real time.

[0083] In this embodiment, the intelligent mining system also includes a manual closed-loop system. This system comprises a manual instruction module and a closed-loop feedback module. The manual instruction module allows operators to input manual instructions via a manual interface and transmit these instructions to the vehicle control system. This enables the system to respond quickly and provide adjustments to the control system, ensuring the mining vehicle's flexibility in special tasks or emergencies. The closed-loop feedback module monitors and provides real-time feedback on the execution status of the manual instructions, ensuring accurate and effective execution during vehicle operation. This allows operators to input manual instructions into the intelligent mining system during special tasks or emergencies. In emergency or non-standard scenarios, the system responds quickly and adjusts the vehicle path. If steep slopes or other complex terrain are detected, the system automatically adapts, ensuring accurate execution of instructions. This significantly improves the flexibility and reliability of mining operations, reduces the impact of emergencies, and further enhances safety and flexibility.

[0084] In one embodiment, the vehicle control system includes an energy management module;

[0085] The energy management module is used to dynamically adjust the power output of each mining truck based on its battery status and route requirements.

[0086] In this embodiment, the vehicle control system includes an energy management module. This module dynamically adjusts the vehicle's power output based on the battery status and route requirements of each mining truck, achieving efficient energy management. Therefore, this application optimizes power output and energy consumption by combining the vehicle's battery status and operational needs, reducing unnecessary braking, acceleration, and waiting time through efficient perception and planning. This significantly reduces the energy consumption of the mining trucks during operation, extends battery life, and helps mines achieve energy conservation, emission reduction, and sustainable development goals.

[0087] In this embodiment, the intelligent mine system includes a fleet management platform, a dual-flywheel system, and a vehicle control system. The task scheduling module in the fleet management platform allocates work tasks to each vehicle based on acquired vehicle management information to obtain task scheduling data. This vehicle management information and task scheduling data are then transmitted to the planning system in the dual-flywheel system. The vehicle management information includes vehicle attitude and health information, vehicle position status information, vehicle work task priority information, and mine safety standard information. The perception system in the dual-flywheel system uses bird's-eye view technology and deep learning algorithms to fuse the acquired multi-dimensional environmental data of the mine, establishing a 3D environment model of the mine to output environmental perception data, which is then transmitted to… The planning system, based on vehicle management information, task scheduling data, and environmental perception data, uses deep learning algorithms and Monte Carlo tree search algorithms to predict the optimal driving path for each mining truck, generating the optimal driving path. This optimal driving path is then transmitted to the vehicle control system, along with the operation scheduling instructions provided by the data sharing module in the fleet management platform. This allows the vehicle control system to control the vehicles to efficiently and safely complete their tasks in a dynamic environment by following the optimal driving path based on the operation scheduling instructions. Therefore, this application, by combining perception, planning, and collaborative management, overcomes the limitations of existing unmanned mining trucks in complex mining environments, thereby improving the safety, efficiency, and productivity of mining operations.

[0088] Figure 3 is a schematic diagram of a dual flywheel system according to an exemplary embodiment of this application. As shown in Figure 3, the dual flywheel system includes a sensing system and a planning system.

[0089] The perception system includes a multimodal sensor and a data processing module. The multimodal sensor is used to acquire multi-dimensional environmental data of the mine. The data processing module is used to fuse the multi-dimensional environmental data using bird's-eye view technology and deep learning algorithms to establish a 3D environmental model of the mine, so as to output environmental perception data and transmit the environmental perception data to the planning system.

[0090] The planning system includes a path planning module. The path planning module is used to predict the planned path for each mining truck based on the vehicle management information, task scheduling data and environmental perception data fed back by the fleet management platform, and to generate the optimal driving path. The vehicle management information includes vehicle attitude and health information, vehicle position status information, vehicle operation task priority information and mine safety standard information.

[0091] In this embodiment, the dual flywheel system includes a perception system and a planning system. The perception system includes a multimodal sensor and a data processing module. The multimodal sensor is used to acquire multi-dimensional environmental data of the mine. The data processing module is used to pre-filter, denoise, and correct the multi-dimensional environmental data to improve the quality and accuracy of the data. Then, the multi-dimensional environmental data is fused through bird's-eye view technology and deep learning algorithms to form a more complete and reliable 3D environment model of the mine, providing real-time detection and recognition of dynamic and static objects, thereby outputting environmental perception data. That is, feature extraction is performed on each modal data, and a multimodal feature fusion structure is designed to effectively fuse the features of different modalities together to construct a 3D environment model of the mine. This model includes convolutional layers, fully connected layers, etc., for extracting environmental features, and an output layer for classification, classifying the features after multimodal data fusion into environmental conditions. Bird's-eye view technology is a visualization technology that presents spatial information from a bird's-eye view perspective and is commonly used in fields such as autonomous driving, drones, and map services. Deep learning is a branch of machine learning that uses multi-layer neural networks for data learning and pattern recognition to automatically extract features. Through the above steps, vehicles can effectively identify slopes, obstacles, and other dynamic entities in complex mines, improving the accuracy of environmental perception. This reduces operational interruptions and safety hazards caused by environmental misjudgments, significantly enhancing the safety of mine operations. Furthermore, the environmental perception data is transmitted to the planning system via an information interaction interface to facilitate decision-making and route planning.

[0092] In this embodiment, the planning system includes a path planning module. This module, based on vehicle management information, task scheduling data, and environmental perception data, uses deep learning algorithms and Monte Carlo Tree Search (MCTS) to predict the planned path for each mining truck, generating the optimal driving path. It also rapidly responds to changes in task priority, vehicle status, and other entity behaviors, ensuring continuous operation of the unmanned vehicles. This not only reduces waiting time but also avoids resource waste, significantly improving vehicle response efficiency and path planning flexibility, and transmits the optimal driving path to the vehicle control system. Deep learning, a branch of machine learning, utilizes multi-layer neural networks for data learning and pattern recognition to automatically extract features. Monte Carlo Tree Search (MCTS) is a heuristic search algorithm used in decision-making processes for complex problems with vast and inexhaustible state spaces. By introducing bird's-eye view technology and deep learning algorithms, this application can transform multimodal data into a top-down view, generating a more comprehensive and high-precision 3D environment model of the mine. By introducing deep learning algorithms and Monte Carlo tree search algorithms, this application utilizes simulated stochastic strategies to explore possible decision paths and employs statistical methods to evaluate the potential of each node, thereby progressively constructing and optimizing the search tree. This provides autonomous vehicles with multi-agent interaction prediction capabilities, enabling the simulation and prediction of multi-party interactive behaviors in complex traffic scenarios. This allows vehicles to be more proactive in responding to dynamic environments. Furthermore, considering the three-dimensional motion characteristics of mining trucks (such as uphill / downhill movement and load changes), the planning system in this application enhances its adaptability to multi-dimensional dynamics through modular training. It is evident that the dual-flywheel system in this application integrates a perception system and a planning system, enabling the system to work efficiently and collaboratively in dynamic and complex environments. This achieves a deep coupling of high-precision perception and flexible planning. Moreover, the introduction of rule-based enhancement mechanisms (deep learning algorithms and Monte Carlo tree search algorithms) in the decision-making and planning stages realizes an architectural innovation that combines feature extraction from end-to-end models with rule-based safety mechanisms, effectively addressing the issues of insufficient robustness and security in end-to-end models.

[0093] It should be noted that generating environmental perception data and optimal driving paths can also be achieved by other methods such as perception algorithms, Bayesian networks, or Markov decision processes. The appropriate method can be selected for data and path generation based on the actual situation and needs. This application does not impose any limitations on this.

[0094] In this embodiment, a dual-flywheel system is formed by combining a perception system and a planning system. This system enhances the intelligence level of unmanned mining trucks, enabling mines to operate efficiently, safely, and environmentally, thus promoting the intelligentization and automation of mines. With the significant improvement in operational efficiency and safety, the overall competitiveness of the mine is strengthened, providing a solid technological foundation for the future development of intelligent mining.

[0095] In this embodiment, the dual-flywheel system includes a perception system and a planning system. The perception system uses bird's-eye view technology and deep learning algorithms to fuse multi-dimensional environmental data of the mine, establish a 3D environmental model of the mine, output environmental perception data, and transmit the environmental perception data to the planning system. The planning system uses deep learning algorithms and Monte Carlo tree search algorithms to predict the planned path for each mining truck based on vehicle management information, task scheduling data, and environmental perception data fed back from the fleet management platform, generating the optimal driving path. The vehicle management information includes vehicle attitude and health information, vehicle position status information, vehicle task priority information, and mine safety standard information. Therefore, this application, by combining the collaborative architecture of the perception system and the planning system, and integrating fleet management information and safety standards, can accurately generate the optimal driving path, allowing vehicles to operate more precisely along the optimal path, reducing unnecessary waiting time and path conflicts. This not only improves the operational productivity of the mine but also lays a solid technical foundation for the future development of intelligent mines. Furthermore, the dual flywheel system of this application has significant advantages in target optimization and modeling complexity. By introducing rule-based enhancement mechanisms (deep learning algorithms and Monte Carlo tree search algorithms) into the decision-making and planning stages, it effectively solves the problems of insufficient robustness and security in end-to-end models.

[0096] Figure 4 is a flowchart illustrating a path planning and control method according to an exemplary embodiment of this application. The path planning and control method can be applied to the intelligent mining system in Figure 1 or Figure 2. As shown in Figure 4, the path planning and control method is implemented through the following steps.

[0097] S401: Based on the acquired vehicle management information, assign the corresponding work tasks to each vehicle to obtain task scheduling data. The vehicle management information includes vehicle attitude and health information, vehicle location status information, vehicle work task priority information, and mine safety standard information.

[0098] S402: Send the task scheduling data and the vehicle management information to the dual flywheel system, so that the dual flywheel system can predict the planned path for each mining truck based on the vehicle management information, the task scheduling data and the environmental perception data, using deep learning algorithm and Monte Carlo tree search algorithm, generate the optimal driving path, and transmit the optimal driving path to the vehicle control system.

[0099] S403: Send a work scheduling instruction to the vehicle control system so that the vehicle control system responds to the work scheduling instruction and controls the vehicle to travel along the optimal driving path.

[0100] It should be noted that the implementation method of this embodiment is the same as that of the above-described intelligent mining system embodiment, and will not be repeated here.

[0101] In this embodiment, based on the acquired vehicle management information, work tasks are assigned to each vehicle to obtain task scheduling data. The vehicle management information includes vehicle attitude and health information, vehicle location status information, vehicle work task priority information, and mine safety standard information. This task scheduling data and vehicle management information are sent to the dual-flywheel system. The dual-flywheel system, based on the vehicle management information, task scheduling data, and environmental perception data, uses deep learning algorithms and Monte Carlo tree search algorithms to predict the planned path for each mining truck, generating the optimal driving path. This optimal driving path is then transmitted to the vehicle control system, which issues a work scheduling command. The vehicle control system responds to the work scheduling command and controls the vehicles to travel along the optimal driving path. Therefore, this application, by integrating fleet management information and safety standards, and utilizing the deep collaboration between perception and planning in the dual-flywheel system, can accurately generate the optimal driving path. This allows vehicles to operate more precisely along the optimal path, reducing unnecessary waiting time and path conflicts, thereby improving mine productivity and promoting the development of smart mines. Furthermore, the dual flywheel system of this application has significant advantages in target optimization and modeling complexity. By introducing rule-based enhancement mechanisms (deep learning algorithms and Monte Carlo tree search algorithms) into the decision-making and planning stages, it effectively solves the problems of insufficient robustness and security in end-to-end models.

[0102] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A dual flywheel system, wherein, The dual flywheel system includes a sensing system and a planning system; The perception system includes a multimodal sensor and a data processing module. The multimodal sensor is used to acquire multi-dimensional environmental data of the mine. The data processing module is used to fuse the multi-dimensional environmental data using bird's-eye view technology and deep learning algorithms to establish a 3D environmental model of the mine, so as to output environmental perception data and transmit the environmental perception data to the planning system. The planning system includes a path planning module. The path planning module is used to predict the planned path for each mining truck based on the vehicle management information, task scheduling data and environmental perception data fed back by the fleet management platform, and to generate the optimal driving path by using deep learning algorithms and Monte Carlo tree search algorithms. The vehicle management information includes vehicle attitude and health information, vehicle position status information, vehicle operation task priority information and mine safety standard information.

2. The dual flywheel system of claim 1, wherein, The multimodal sensor includes a lidar sensing module, a millimeter-wave radar sensing module, and a vision sensor module; The lidar sensing module detects the surrounding environment by emitting a laser beam; The millimeter-wave radar sensing module detects the surrounding environment by emitting millimeter-wave bands; The visual sensor module uses optical elements and imaging technology to detect and acquire image information of the surrounding environment.

3. The dual flywheel system of claim 1, wherein, The planning system includes a task decision module and a safety monitoring module; The task decision module is used to adjust the driving path and operation sequence of each mining truck in real time based on the vehicle attitude and health information, vehicle position status information and vehicle operation task priority information. The safety monitoring module is used to monitor the driving path and potential risks in the operation tasks of each mining truck in real time based on the mine safety standard information.

4. An intelligent mine system, wherein, The intelligent mining system includes a fleet management platform, a dual flywheel system, and a vehicle control system. The dual flywheel system includes a perception system and a planning system. The fleet management platform includes a task scheduling module and a data sharing module. The task scheduling module is used to allocate the corresponding work tasks to each vehicle based on the acquired vehicle management information to obtain task scheduling data, and transmit the vehicle management information and the task scheduling data to the planning system in the dual flywheel system. The data sharing module is used to provide work scheduling instructions and transmit the work scheduling instructions to the vehicle control system. The vehicle management information includes vehicle attitude and health information, vehicle position status information, vehicle work task priority information, and mine safety standard information. The perception system includes a multimodal sensor and a data processing module. The multimodal sensor is used to acquire multi-dimensional environmental data of the mine. The data processing module is used to fuse the multi-dimensional environmental data using bird's-eye view technology and deep learning algorithms to establish a 3D environmental model of the mine, so as to output environmental perception data and transmit the environmental perception data to the planning system. The planning system includes a path planning module, which is used to predict the planned path for each mining truck based on the vehicle management information, the task scheduling data and the environmental perception data, using deep learning algorithms and Monte Carlo tree search algorithms, to generate the optimal driving path, and transmit the optimal driving path to the vehicle control system. The vehicle control system is used to control the vehicle to travel along the optimal driving path based on the job scheduling instructions.

5. The intelligent mine system of claim 4, wherein, The multimodal sensor includes a lidar sensing module, a millimeter-wave radar sensing module, and a vision sensor module; The lidar sensing module detects the surrounding environment by emitting a laser beam; The millimeter-wave radar sensing module detects the surrounding environment by emitting millimeter-wave bands; The visual sensor module uses optical elements and imaging technology to detect and acquire image information of the surrounding environment.

6. The intelligent mine system of claim 4, wherein, The planning system includes a task decision module and a safety monitoring module; The task decision module is used to adjust the driving path and operation sequence of each mining truck in real time based on the vehicle attitude and health information, vehicle position status information and vehicle operation task priority information. The safety monitoring module is used to monitor the driving path and potential risks in the operation tasks of each mining truck in real time based on the mine safety standard information.

7. The intelligent mine system of claim 4, wherein, The intelligent mining system also includes an environmental adaptation system, which includes an adaptation module and an adjustment module. The adaptation module is used to adapt to the vehicle's driving needs in different physical environments. The adjustment module is used to adjust the driving speed and driving mode of each mining truck in real time based on the environmental conditions of the mine.

8. The intelligent mine system of claim 4, wherein, The intelligent mining system also includes a manual closed-loop system, which includes a manual instruction module and a closed-loop feedback module. The manual instruction module is used to input manual instructions through a manual interface and transmit the manual instructions to the vehicle control system. The closed-loop feedback module is used to monitor and provide feedback on the execution status of the manual instructions in real time.

9. The intelligent mine field system of claim 4, wherein, The vehicle control system includes an energy management module; The energy management module is used to dynamically adjust the power output of each mining truck based on its battery status and route requirements.

10. A path planning control method in which, Based on the intelligent mining system according to any one of claims 4 to 9, the method includes: Based on the acquired vehicle management information, the corresponding work tasks of each vehicle are assigned to obtain task scheduling data. The vehicle management information includes vehicle attitude and health information, vehicle location status information, vehicle work task priority information, and mine safety standard information. The task scheduling data and vehicle management information are sent to the dual flywheel system so that the dual flywheel system can predict the planned path for each mining truck based on the vehicle management information, the task scheduling data and environmental perception data, using deep learning algorithms and Monte Carlo tree search algorithms, generate the optimal driving path, and transmit the optimal driving path to the vehicle control system. A work scheduling command is sent to the vehicle control system so that the vehicle control system responds to the work scheduling command and controls the vehicle to travel along the optimal driving path.

Images