A mine vehicle anomaly identification method and device

Abstract

The application provides a mine vehicle anomaly identification method and device, which can timely find the anomaly of the mine vehicle, so that the safety hidden danger can be timely handled. The method comprises the following steps: acquiring a first actual pose of a mine vehicle at a first time and a first pose adjustment instruction received by the mine vehicle at the first time; based on the first actual pose and the first pose adjustment instruction, calculating a first expected pose of the mine vehicle at a second time after the first time, wherein the first expected pose is a pose after the first actual pose is adjusted according to the first pose adjustment instruction by the mine vehicle; acquiring a second actual pose of the mine vehicle at the second time, wherein the second actual pose is a pose after the first actual pose is actually adjusted according to the first pose adjustment instruction by the mine vehicle; and when the difference between the first expected pose and the second actual pose is greater than an anomaly threshold, confirming that the mine vehicle is in an abnormal state.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a method and device for identifying abnormal vehicles in mining areas. Background Technology

[0002] Intelligent mining enables smart mining operations, improving production efficiency and reducing costs. Unmanned mining vehicles play a crucial role in this process and are an essential component of intelligent mining practices.

[0003] Unmanned mining vehicles operate in complex environments with harsh conditions, high workloads, and long operating times, making them prone to malfunctions. For example, rain, snow, strong winds, slippery and icy roads, and aging or malfunctioning vehicle components (such as broken brake shoes) can all cause mining vehicles to fail to execute control commands or to perform commands in a manner that is not as expected. These malfunctions can lead to dangerous situations such as vehicles deviating from their intended path, abnormal tilting, or abnormal pitching.

[0004] The lack of human drivers to monitor unmanned mining vehicles makes it impossible to detect abnormalities in a timely manner, thus leading to safety hazards in mining production. Summary of the Invention

[0005] This application provides a method and device for identifying abnormal vehicles in mining areas, which can promptly detect abnormalities in mining vehicles and thus address potential safety hazards in a timely manner.

[0006] Firstly, a method for identifying anomalies in mining vehicles is provided. This method includes: acquiring a first actual pose of the mining vehicle at a first moment and a first pose adjustment instruction received by the mining vehicle at the first moment; calculating a first expected pose of the mining vehicle at a second moment after the first moment based on the first actual pose and the first pose adjustment instruction, wherein the first expected pose is the predicted pose of the mining vehicle after adjusting the first actual pose according to the first pose adjustment instruction; acquiring a second actual pose of the mining vehicle at the second moment, wherein the second actual pose is the actual pose of the mining vehicle after adjusting the first pose according to the first pose adjustment instruction; and confirming that the mining vehicle is in an abnormal state when the difference between the first expected pose and the second actual pose is greater than an anomaly threshold.

[0007] For example, the first actual pose includes at least one of the position, speed, and attitude of the mining vehicle at the first moment; wherein, the attitude of the mining vehicle includes at least one of the heading information, roll information, pitch information, and cargo box lifting angle of the mining vehicle.

[0008] For example, the first position adjustment command includes at least one of the following: position adjustment command, speed adjustment command, and attitude adjustment command for mining vehicles.

[0009] If the difference between the expected pose and the actual pose is small (less than or equal to the anomaly threshold), it indicates that the mining vehicle accurately executed the pose adjustment command, and the execution effect of the pose adjustment command is good, reflecting that the mining vehicle is not in an abnormal state. If the difference between the expected pose and the actual pose is large (greater than the anomaly threshold), it indicates that the mining vehicle failed to accurately execute the pose adjustment command, and the execution effect of the pose adjustment command is poor, reflecting that the mining vehicle is in an abnormal state. In this way, it is possible to efficiently identify whether the mining vehicle is in an abnormal state.

[0010] In one possible implementation, the anomaly threshold includes a first threshold and a second threshold, wherein the second threshold is greater than the first threshold; when the difference between the first expected pose and the second actual pose is greater than the anomaly threshold, the mining vehicle is confirmed to be in an abnormal state, including: when the difference is greater than or equal to the first threshold and less than the second threshold, issuing an anomaly alarm; and / or, when the difference is greater than or equal to the second threshold, issuing a braking command to the mining vehicle to control the mining vehicle to brake.

[0011] In this implementation, the anomaly level of vehicles in the mining area can be identified, and different levels of anomalies can be handled differently. This allows for targeted handling of anomalies at different levels, ensuring both safety and efficiency.

[0012] In one possible implementation, the method further includes: obtaining the planned position of the mining vehicle in the work site; obtaining the actual position of the mining vehicle; and confirming that the mining vehicle is in an abnormal state when the difference between the planned position and the actual position is greater than a preset threshold.

[0013] The autonomous driving strategy controls the actual position of mining vehicles according to the planned location, with the goal of bringing the actual position of the vehicles close to the planned location. If the difference between the planned and actual positions exceeds a preset threshold, it indicates that the autonomous driving strategy is not effectively controlling the mining vehicles, reflecting an anomaly in the vehicle's components or the associated autonomous driving strategy. This implementation method also allows for the efficient detection of anomalies in mining vehicles.

[0014] In one possible implementation, the method further includes: obtaining a second pose adjustment instruction for the mining vehicle at a second time moment; calculating a second expected pose for the mining vehicle at a third time moment after the second time moment based on the second actual pose and the second pose adjustment instruction, wherein the second expected pose is the predicted pose of the mining vehicle after adjusting the second actual pose according to the second pose adjustment instruction; obtaining a third actual pose for the mining vehicle at the third time moment, wherein the third actual pose is the actual pose of the mining vehicle after adjusting the second pose according to the second pose adjustment instruction; confirming that the mining vehicle is in an abnormal state when the difference between the first expected pose and the second actual pose is greater than an abnormal threshold, including: confirming that the mining vehicle is in an abnormal state when the difference between the first expected pose and the second actual pose is greater than an abnormal threshold, and the difference between the second expected pose and the third actual pose is greater than an abnormal threshold.

[0015] In this implementation, the abnormal state of mining vehicles can be identified based on the expected pose and actual pose at two or more times, which can effectively avoid misjudgment.

[0016] In one possible implementation, the method further includes: acquiring the actual pose and pose adjustment instructions of the mining vehicle at multiple historical moments; acquiring the adjusted pose corresponding to each of the multiple moments, wherein the adjusted pose corresponding to each of the multiple moments is the pose of the mining vehicle after adjusting the actual pose at that moment according to the pose adjustment instructions at that moment; constructing a pose prediction model based on the actual pose, pose adjustment instructions, and adjusted pose corresponding to each of the multiple moments of the mining vehicle at multiple moments; and calculating the first expected pose of the mining vehicle at a second moment after the first moment based on the first actual pose and the first pose adjustment instructions, including: inputting the first actual pose and the first pose adjustment instructions into the pose prediction model, so that the pose prediction model outputs the first expected pose.

[0017] In this implementation, relevant data on vehicles in normal conditions in the mining area can be used to train a pose prediction model, and the desired pose can be calculated using this pose prediction model, which can improve the efficiency of anomaly identification.

[0018] Secondly, a mining vehicle anomaly identification device is provided. The device includes: a first acquisition module, used to acquire the first actual pose of the mining vehicle at a first moment and the first pose adjustment instruction received by the mining vehicle at the first moment; a calculation module, used to calculate the first expected pose of the mining vehicle at a second moment after the first moment based on the first actual pose and the first pose adjustment instruction, wherein the first expected pose is the predicted pose of the mining vehicle after adjusting the first actual pose according to the first pose adjustment instruction; a second acquisition module, used to acquire the second actual pose of the mining vehicle at the second moment, wherein the second actual pose is the actual pose of the mining vehicle after adjusting the first pose according to the first pose adjustment instruction; and a confirmation module, used to confirm that the mining vehicle is in an abnormal state when the difference between the first expected pose and the second actual pose is greater than an anomaly threshold.

[0019] Thirdly, a computing device cluster is provided, including at least one computing device, each computing device including a processor and a memory; the processor of the at least one computing device is used to execute instructions stored in the memory of the at least one computing device, so that the computing device cluster performs the method provided in the first aspect.

[0020] Fourthly, a computer-readable storage medium is provided, including computer program instructions that, when executed by a cluster of computing devices, execute the method provided in the first aspect.

[0021] Fifthly, a computer program product containing instructions is provided, which, when executed by a cluster of computer devices, causes the cluster of computer devices to perform the method provided in the first aspect.

[0022] The beneficial effects of the second to fifth aspects can be referred to the introduction of the beneficial effects of the first aspect above, and will not be repeated here. Attached Figure Description

[0023] Figure 1 This is a schematic diagram representing the vehicle's attitude information;

[0024] Figure 2 This is a schematic diagram of a system architecture provided in an embodiment of this application;

[0025] Figure 3 This is a schematic diagram showing the lifting angle of the cargo box of a mining vehicle;

[0026] Figure 4 This is a schematic diagram showing the relevant angles of vehicle tilt in the mining area;

[0027] Figure 5 This is a schematic diagram of the multiple degrees of freedom of vehicles in the mining area;

[0028] Figure 6This is a schematic diagram of a method for identifying abnormal vehicles in a mining area provided in an embodiment of this application;

[0029] Figure 7 This is a flowchart of a method for identifying abnormal vehicles in a mining area, provided in an embodiment of this application;

[0030] Figure 8 This is a schematic diagram of a pose difference calculation method provided in an embodiment of this application;

[0031] Figure 9 This is a schematic diagram of an exception handling method provided in an embodiment of this application;

[0032] Figure 10 This is a schematic diagram of an abnormal pitch scene provided in an embodiment of this application;

[0033] Figure 11 This is a schematic diagram of an abnormal driving situation provided in an embodiment of this application;

[0034] Figure 12 This is a schematic diagram of a planned driving route provided in an embodiment of this application;

[0035] Figure 13 This is a schematic diagram of an actual driving path provided in an embodiment of this application;

[0036] Figure 14 This is a schematic diagram of the structure of a mining area vehicle anomaly identification device provided in an embodiment of this application;

[0037] Figure 15 This is a schematic diagram of the structure of a computing device provided in an embodiment of this application;

[0038] Figure 16 This is a schematic diagram of the structure of a computing device cluster provided in an embodiment of this application;

[0039] Figure 17 This is a schematic diagram of another computing device cluster structure provided in an embodiment of this application. Detailed Implementation

[0040] The solutions provided in the embodiments of this application will now be described with reference to the accompanying drawings. In the embodiments of this application, "at least two" refers to two or more, and "multiple" refers to two or more. Terms such as "first," "second," etc., are only used to distinguish similar objects and are not necessarily used to describe a specific order or number of objects.

[0041] To facilitate understanding of the solutions provided in the embodiments of this application, the technical terms that may be involved in the embodiments of this application will be introduced first.

[0042] Mining vehicles, also known simply as mining cars, are vehicles that operate in mining areas such as mines and mining fields. Mining vehicles can perform tasks such as loading, transporting, and unloading. Loading refers to loading materials (such as ore and soil) collected in the mining area onto the vehicle; transporting refers to transporting the loaded materials; and unloading refers to unloading the loaded materials from the vehicle. In some embodiments, loading and unloading can be collectively referred to as operations, and transport can be referred to as patrolling.

[0043] Job: also known as work or task execution, such as performing loading, transportation and unloading tasks.

[0044] Work site: refers to the area where mining vehicles are located when performing tasks. For example, when mining vehicles are performing transportation tasks, the work site is a road.

[0045] Pose refers to the motion state of a vehicle in the mining area, including its position, speed, and attitude. The actual pose is the vehicle's true, real pose. The expected pose is the predicted or expected pose after the vehicle adjusts its actual pose according to pose adjustment commands. The actual pose is obtained through detection, while the expected pose is obtained through calculation.

[0046] Attitude: A concept in dynamics, attitude refers to the three-dimensional parameters of a vehicle caused by inertia or forces. Attitude can include yaw, roll, pitch, and the lifting angle of the vehicle's cargo box, among others.

[0047] Actuation: This refers to the process by which a vehicle's actuators (such as electric motors, hydraulic cylinders, etc.) receive signal commands and convert different forms of energy into mechanical motion, driving other vehicle components (such as wheels) to complete specific actions. Actuation is the opposite of braking; the core logic of actuation is converting energy (electric / hydraulic / pneumatic) into mechanical motion, such as wheel rotation, valve opening and closing, and robotic arm movement.

[0048] Braking, also known as braking, refers to the process of slowing down, stopping, or keeping a vehicle stationary through mechanical or electronic devices. The core logic of braking is to convert the vehicle's kinetic energy into heat energy through friction, thereby achieving the purpose of vehicle deceleration.

[0049] Yaw angle: This refers to the angle by which the front of a vehicle rotates relative to its perpendicular direction. The yaw angle can be referenced from... Figure 1 As shown.

[0050] Roll angle: This refers to the angle between a vehicle and the ground in both lateral directions. For more information, please refer to the following: Figure 1As shown. The roll angle reflects the vehicle's roll condition and is part of the vehicle's roll information.

[0051] Pitch angle: This refers to the angle between the vehicle's vertical upward direction and the ground. For more information on pitch angle, please refer to... Figure 1 As shown.

[0052] Unmanned mining vehicles lack driver monitoring, making it difficult to detect anomalies. Often, it is only when a safety accident (such as a rollover) occurs that people realize there is something wrong with the mining vehicles.

[0053] In view of this, embodiments of this application provide a method for identifying anomalies in mining vehicles, which can promptly detect anomalies in mining vehicles. Specifically, this method acquires the actual pose of the mining vehicle and the pose adjustment command received by the vehicle, and calculates the desired pose of the vehicle using the actual pose and the pose adjustment command. The mining vehicle adjusts its actual pose according to the pose adjustment command to obtain a new actual pose. The difference between the desired pose and the new actual pose of the mining vehicle can be compared, and the anomaly of the mining vehicle can be identified based on this difference.

[0054] This method compares the expected pose and actual pose of a mining vehicle to identify the effectiveness of its pose adjustment commands, or in other words, whether the vehicle has effectively executed the commands. If the difference between the expected and actual poses is small, it indicates that the vehicle has effectively executed the commands, meaning the relevant functional components are functioning normally, and therefore the vehicle is not malfunctioning. Conversely, if the difference is large, it indicates that the vehicle has not effectively executed the commands, meaning one or more functional components are malfunctioning, and therefore the vehicle itself is abnormal. This allows for timely and efficient identification of any abnormalities in mining vehicles.

[0055] Next, the method for identifying abnormal vehicles in mining areas provided in the embodiments of this application will be described.

[0056] Figure 2 A system for implementing this method is shown. The system includes an identification device and a mining vehicle as the object of identification. The identification device may include an anomaly management module, a real-time pose acquisition module, and a control module; the mining vehicle may include an actuator and a sensing module.

[0057] The actual pose acquisition module can acquire the actual pose of vehicles in the mining area. Specifically, the sensing module can collect the actual pose of the vehicles and send the collected pose to the actual pose acquisition module. For example... Figure 2As shown, the perception module can include the chassis of the mining vehicle and a positioning submodule. The chassis can collect and output information such as axle wheel speed, front wheel steering angle, and cargo box lifting angle of the mining vehicle. The positioning submodule can collect and output the position and attitude of the mining vehicle. Position can be represented by x-axis, y-axis, and z-axis information in three-dimensional coordinates. Attitude can include yaw angle, roll angle, and pitch angle.

[0058] In some embodiments, the positioning submodule may include radar, inertial measurement unit (IMU), etc.

[0059] The planning and control module is used to plan the trajectories of vehicles in the mining area, where the trajectory includes the vehicle's position and pose. For example... Figure 2 As shown, the control module can acquire the task information and actual position of the mining vehicle, and based on this information, issue position adjustment commands. Position adjustment commands can include drive command information (e.g., throttle opening information) or braking command information (e.g., braking deceleration request or braking opening request). Position adjustment commands can also include vehicle steering information (e.g., steering wheel angle information or front wheel angle information, front wheel curvature information). Position adjustment commands can also include cargo box lifting commands. For example, the task information indicates that the mining vehicle's task is unloading, where unloading requires the cargo box to be lifted at a 50° angle. Figure 3 As shown, the actual lifting angle of the mining vehicle is 40°, so the control module can issue a cargo box lifting command to instruct the cargo box of the mining vehicle to be raised by 10°.

[0060] The control module can send pose adjustment commands to the mining vehicles, enabling them to adjust their actual poses accordingly. The actuators on the mining vehicles can execute these commands to adjust the actual poses. If the mining vehicles are functioning normally, the execution of the pose adjustment commands will meet the expected results. Conversely, if the mining vehicles are malfunctioning, the execution of the pose adjustment commands will not meet the expected results.

[0061] like Figure 2As shown, the actuator may include a drive unit, brake, steering wheel, cargo box controller, etc. Taking the posture adjustment command as "raise the lifting angle of the cargo box of the mining vehicle by 10°" as an example, the cargo box controller can execute this posture adjustment command. If the cargo box controller is functioning correctly, it can raise the lifting angle of the mining vehicle's cargo box by 10° according to the posture adjustment command. However, if the cargo box controller is malfunctioning, it may be difficult to raise the lifting angle of the mining vehicle's cargo box by 10° according to the posture adjustment command; the actual effect may be that the lifting angle is greater than or less than 10°.

[0062] The anomaly management module is used to identify whether vehicles in the mining area are malfunctioning. For example... Figure 2 As shown, the anomaly management module can obtain the pose adjustment command issued by the mining vehicle at time T1 and the actual pose of the mining vehicle at time T1 from the pose acquisition module, and calculate the expected pose of the mining vehicle at time T2 based on the pose adjustment command and the actual pose.

[0063] Then, when the pose acquisition module obtains the actual pose of the mining vehicle at time T2, the anomaly management module can obtain the actual pose of the mining vehicle at time T2 from the pose acquisition module. The anomaly management module can identify whether the mining vehicle is in an abnormal state based on the expected pose of the mining vehicle at time T2 and the actual pose of the mining vehicle at time T2.

[0064] When the control module sends a position adjustment command to the mining area vehicle, it can simultaneously send the same position adjustment command to the anomaly management module.

[0065] Therefore, the anomaly management module and the mining vehicles can receive the same pose adjustment command simultaneously or almost simultaneously.

[0066] In some embodiments, such as Figure 2 As shown, the anomaly management module can have a pre-configured pose prediction model. In one example, the pose prediction model can be a neural network model trained through machine learning, such as a neural network model trained based on deep learning or reinforcement learning. In another example, the pose prediction model can be a mechanistic model constructed using vehicle dynamics.

[0067] The identification device can acquire the actual pose of mining vehicles at multiple historical moments, as well as pose adjustment commands at multiple moments. At these multiple moments, the mining vehicles are in a normal state, i.e., without any abnormalities. The actual pose at each of these multiple moments includes the actual pose of the mining vehicle at each of these multiple moments, and the pose adjustment commands at each of these multiple moments include the pose adjustment commands received by the mining vehicle at each of these multiple moments.

[0068] The identification device can acquire the adjusted pose corresponding to each of the multiple time points. The adjusted pose corresponding to a time point is the pose of the mining vehicle after adjusting its actual pose at that time according to the pose adjustment command received at that time. In other words, the adjusted pose corresponding to a certain time point is the pose of the mining vehicle after adjusting its actual pose according to the pose adjustment command received at that time.

[0069] The recognition device can construct a pose prediction model based on the actual pose at multiple time points, pose adjustment commands, and the adjusted pose corresponding to each of these multiple time points. Specifically, the adjusted pose corresponding to each of these multiple time points can be used as labeled data, and the actual pose and pose adjustment commands at these multiple time points can be used as training data. The pose prediction model is trained using machine learning (e.g., deep learning or reinforcement learning). The training process can be as follows: using the pose prediction model to calculate the expected pose corresponding to each time point based on the actual pose and pose adjustment commands, the parameters of the pose prediction model are adjusted in a direction that reduces the difference between the expected pose and the adjusted pose at each time point, so that the expected pose calculated by the pose prediction model gets closer and closer to the adjusted pose. When the pose prediction model converges or the number of iterations reaches a preset number, training can be stopped, and the pose prediction model is obtained.

[0070] Due to the requirements of tasks such as unloading, mining vehicles need to have the ability to lift cargo boxes. During the cargo box lifting phase, the center of gravity (i.e., center of mass) and load of the mining vehicle will change, thus affecting characteristics such as the vehicle's lateral stability. Figure 3 As shown, during the cargo box lifting and unloading process of mining vehicles, as the lifting angle of the cargo box increases, the center of gravity of the entire vehicle continuously shifts upward, leading to a gradual decrease in the lateral stability of the mining vehicle. In some embodiments, the pose prediction model can be a lateral stability model. For example... Figure 4 As shown, a roll stability model for mining vehicles can be constructed based on the estimation of the center of gravity position O, the observation of the roll angle φ, and the wheelbase B.

[0071] In some embodiments, due to the requirements of tasks such as collection, loading, transportation, and unloading, mining vehicles need to possess multi-degree-of-freedom characteristics such as forward and reverse movement, left and right turns, uphill and downhill movement, yaw, pitch, tilt, and cargo box lifting. In some embodiments, the pose prediction model can be a multi-degree-of-freedom dynamic model. For example... Figure 5 As shown, a multi-degree-of-freedom dynamic model of the mining vehicle can be constructed based on the estimated center of gravity position O, center of gravity sideslip angle β, and observed front wheel steering angle δ, yaw rate ω, and pitch angle θ of the mining vehicle, combined with the tire sideslip stiffness Cf / Cr and vehicle load information m.

[0072] In some embodiments, such as Figure 6 As shown, the perception module of the mining vehicle can input the actual pose into the pose prediction model, and the planning module can input pose adjustment commands into the pose prediction model. The pose prediction model can calculate the desired pose based on the actual pose and the pose adjustment commands. After the mining vehicle adjusts its actual pose according to the pose adjustment commands, the adjusted pose is obtained. The difference between the adjusted pose and the desired pose can be calculated. This difference is used to identify whether the mining vehicle is abnormal.

[0073] In some embodiments, the identification device may be deployed on mining vehicles. In some embodiments, the identification device may be deployed in the cloud, wherein the identification device can communicate with relevant components (e.g., sensing modules, actuators, etc.) in the mining vehicles via a network.

[0074] The above example illustrates the system provided in the embodiments of this application. Next, the process of the mining area vehicle anomaly identification method provided in the embodiments of this application will be described in conjunction with this system. This method can be executed by an identification device. Figure 7 As shown, the method includes the following steps.

[0075] First, in step 701, the identification device acquires the first actual pose of the mining vehicle at a first moment and the first pose adjustment command received by the mining vehicle at the first moment. The first actual pose can be the pose of the mining vehicle collected by the perception module at the first moment, and the first pose adjustment command can be the pose adjustment command sent by the planning module to the mining vehicle at the first moment.

[0076] In some embodiments, the first actual pose includes at least one of the position, speed, and attitude of the mining vehicle at the first moment, and / or the first position adjustment command includes at least one of the position adjustment command, speed adjustment command, and attitude adjustment command of the mining vehicle; wherein, the attitude of the mining vehicle includes at least one of the heading information, roll information, pitch information, and cargo box lifting angle of the mining vehicle.

[0077] The sensing module periodically collects the actual pose of vehicles in the mining area. Each time a collection cycle is completed, the sensing module collects the actual pose once. Specifically, the first actual pose is collected at the first moment, the second actual pose is collected at the second moment after the first moment, the third actual pose is collected at the third moment after the second moment, and so on. Each time the sensing module collects an actual pose, it sends it to the recognition device, enabling the recognition device to obtain the actual pose.

[0078] In some embodiments, the first time point can be represented by T1, the second time point by T2, and the third time point by T3. For example... Figure 8 As shown, the identification device can acquire the actual position T1-1 of the mining vehicle at the first moment. The identification device can acquire the actual position T2-1 of the mining vehicle at the second moment. The identification device can acquire the actual position T3-1 of the mining vehicle at the third moment.

[0079] The planning module can periodically send pose adjustment commands to the mining vehicles. After each planning cycle, the planning module generates and sends a pose adjustment command to the mining vehicles. The planning cycle and the acquisition cycle can be synchronized. Thus, the mining vehicles can receive the first pose adjustment command at the first moment, the second pose adjustment command at the second moment, and the third pose adjustment command at the third moment. Whenever the planning module sends a pose adjustment command to the mining vehicles, the recognition device can acquire that pose adjustment command.

[0080] Next, in step 702, the recognition device calculates the first expected pose of the mining vehicle at a second time after the first time based on the first actual pose and the first pose adjustment instruction, wherein the first expected pose is a predicted pose of the mining vehicle after adjusting the first actual pose according to the first pose adjustment instruction.

[0081] The second moment is the moment following the first moment, and the first expected pose is the pose that the mining vehicle is expected to reach at the second moment. In other words, if there are no abnormalities in the mining vehicle, the first expected pose is the pose that the mining vehicle should reach after adjusting the first actual pose according to the first pose adjustment command.

[0082] Similarly, the recognition device can calculate the second expected pose of the mining vehicle at a third time after the second time based on the second actual pose and the second pose adjustment command. The second expected pose is the predicted pose of the mining vehicle after adjusting the second actual pose according to the second pose adjustment command. The third time is the time after the second time, and the second expected pose is the pose the mining vehicle is expected to reach at the third time. In other words, if the mining vehicle is normal, the second expected pose is the pose the mining vehicle should reach after adjusting the second actual pose according to the second pose adjustment command.

[0083] The identification device can calculate the third expected pose of the mining vehicle at a fourth time point after the third time point, based on the third actual pose and the third pose adjustment command. The third expected pose is a predicted pose of the mining vehicle after adjusting the third actual pose according to the third pose adjustment command. The fourth time point is the time after the third time point, and the third expected pose is the pose the mining vehicle is expected to reach at the fourth time point. In other words, if the mining vehicle is normal, the third expected pose is the pose the mining vehicle should reach after adjusting the third actual pose according to the third pose adjustment command.

[0084] In some embodiments, such as Figure 8 As shown, the first desired pose can be represented by T1-2, the second desired pose by T2-2, and the third desired pose by T3-2. In one example, the recognition device can also calculate the desired pose T1-3 of the mining vehicle at the third time step based on the first actual pose and the first desired pose. The recognition device can also calculate the desired pose T2-3 of the mining vehicle at the fourth time step based on the second actual pose and the second desired pose. The recognition device can also calculate the desired pose T3-3 of the mining vehicle at the fifth time step based on the third actual pose and the third desired pose.

[0085] In some embodiments, the recognition device can input the actual pose and pose adjustment command into the pose prediction model, causing the pose prediction module to output the desired pose. For example, the recognition device can input the first actual pose and the first pose adjustment command into the pose prediction model, causing the pose prediction module to output the first desired pose.

[0086] And, in step 703, the identification device acquires the second actual pose of the mining vehicle at the second moment, wherein the second actual pose is the pose of the mining vehicle after adjusting the first pose according to the first pose adjustment command. Specifically, the second actual pose is the true pose of the mining vehicle at the second moment. After receiving the first pose adjustment command at the first moment, the mining vehicle executes the first pose adjustment command based on the first actual pose. That is, it adjusts the first actual pose according to the first pose adjustment command. The adjusted pose is the second actual pose.

[0087] Similarly, the identification device can acquire the third actual pose of the mining vehicle at the third moment, wherein the third actual pose is the pose of the mining vehicle after adjusting the second pose according to the second pose adjustment command. The third actual pose is the true pose of the mining vehicle at the third moment. After receiving the second pose adjustment command at the second moment, the mining vehicle executes the second pose adjustment command based on the second actual pose. That is, it adjusts the second actual pose according to the second pose adjustment command. The adjusted pose is the third actual pose.

[0088] like Figure 7 As shown, in step 704, when the difference between the first expected pose and the second actual pose is greater than the abnormal threshold, it is confirmed that the mining vehicle is in an abnormal state.

[0089] The abnormal threshold can be a preset value, which can be set based on experience or experimentation. For example, the abnormal threshold can include a position threshold and an attitude threshold. For instance, the position threshold can be 2 meters or 1 meter. The attitude threshold can include a heading angle threshold, a roll angle threshold, a pitch angle threshold, and a cargo box lifting angle threshold. For instance, the heading angle threshold, roll angle threshold, pitch angle threshold, and cargo box lifting angle threshold can be 2°, 1°, 3°, 5°, etc., respectively.

[0090] If the difference between the first expected pose and the second actual pose is less than or equal to the anomaly threshold, it indicates that the effect of the mining vehicle executing the first pose adjustment command has met expectations. This reflects an anomaly in the mining vehicle, thus confirming that the mining vehicle is not in an abnormal state.

[0091] If the difference between the first expected pose and the second actual pose is greater than the abnormal threshold, it indicates that the effect of the mining vehicle executing the first pose adjustment command is not as expected. This reflects that there is an abnormality in the mining vehicle. Thus, it can be confirmed that the mining vehicle is in an abnormal state.

[0092] In some embodiments, the identification device can identify whether a mining vehicle is in an abnormal state based on the differences between the expected pose and the actual pose at multiple times. For example, when the difference between the first expected pose and the second actual pose is greater than the abnormal threshold, and the difference between the second expected pose and the third actual pose is greater than the abnormal threshold, the mining vehicle is confirmed to be in an abnormal state.

[0093] See one example. Figure 8At time T1 (the first time), the actual pose of the mining vehicle is actual pose T1-1 (the first actual pose). The expected pose T1-2 (the first expected pose) of the mining vehicle at time T2 (the second time) can be calculated and recorded. At time T2, the actual pose of the mining vehicle is actual pose T2-1 (the second actual pose). The expected pose T2-2 (the second expected pose) of the mining vehicle at time T3 (the third time) can be calculated and recorded, as well as the difference between the first expected pose and the second actual pose. At time T3, the actual pose of the mining vehicle is actual pose T3-1 (the third actual pose). The expected pose T3-2 (the third expected pose) of the mining vehicle at time T4 (the fourth time) can be calculated and recorded, as well as the difference between the second expected pose and the third actual pose. This process continues, accumulating the differences between the expected pose and the actual pose. For ease of description, the difference between the desired pose and the actual pose can be called the pose difference.

[0094] The above method accumulates multiple pose differences, which can be used to identify whether mining vehicles are in an abnormal state. For example, a moving sliding window strategy can be used to filter these multiple pose differences, and then the processed pose differences can be used to identify whether mining vehicles are abnormal. The filtering can be Kalman filtering or mean filtering, etc.

[0095] In some embodiments, anomalies of mining vehicles can be classified into levels, where multiple different thresholds can be set to classify the anomalies into levels. Different levels of anomalies correspond to different handling methods. For example, the aforementioned anomaly thresholds may include a first threshold and a second threshold, wherein the second threshold is greater than the first threshold. Regardless of whether the pose difference (e.g., the difference between the first expected pose and the second actual pose) is greater than the first threshold or greater than the second threshold, it can be confirmed that the mining vehicle is in an abnormal state. Specifically, when the pose difference is greater than the first threshold but less than the second threshold, an anomaly alarm can be issued. When the pose difference is greater than the second threshold, a braking command can be issued to the mining vehicle to control the braking of the mining vehicle, causing the mining vehicle to slow down or stop.

[0096] For example, such as Figure 9 As shown, anomalies can be categorized into minor anomalies, general anomalies, and severe anomalies. If the anomaly of a mining vehicle is minor, an anomaly alarm will be issued. If the anomaly is general, the vehicle's speed can be reduced and an alarm will be issued. If the anomaly is severe, the vehicle can be stopped and an alarm will be issued. Stopping can be a slow stop or an emergency stop. For example, stopping can be done by pulling over to the side of the road or stopping in place.

[0097] Among these, anomaly alarms can be sent to the cloud monitoring platform, enabling maintenance personnel in the mining area to remotely manage vehicles in unmanned mining areas. When the above-mentioned anomalies are identified, the anomaly alarm needs to be reported to the cloud monitoring platform in a timely manner to facilitate remote handling by maintenance personnel. Different reporting and presentation strategies can be adopted for anomaly alarms of different levels. For example, the reported data and presentation methods are shown in Table 1.

[0098] Table 1

[0099] Abnormal level Reported data Presentation format Example Minor abnormality No data reported Display 10 seconds Slightly exceeded pitch angle General abnormalities 30-second historical data of mining vehicles Display 30 seconds Slight brake fade Serious abnormality 120-second historical data of mining vehicles Continuous display severe brake fade

[0100] The mining vehicle anomaly identification method provided in this application can improve the timeliness of anomaly warnings, proactively avoid safety risks caused by vehicle anomalies, and enhance the operational safety of mining vehicles. For example, when an anomaly is detected in a mining vehicle, safety degradation measures such as slowing down, pulling over, slowing down, or emergency stopping can be triggered to prevent dangerous scenarios such as vehicles deviating from their expected driving path, abnormal skidding, abnormal tilting, or abnormal pitching.

[0101] Next, the method for identifying abnormal vehicles in mining areas provided in this application will be introduced in conjunction with different embodiments.

[0102] In some embodiments, abnormal pitch can be identified. Figure 10 This paper illustrates a dangerous scenario where a mining vehicle's pitch angle becomes abnormal due to cargo blockage during unloading (e.g., dumping soil). When the mining vehicle is unloading soil at the dump site, the identification device receives real-time cargo box lifting commands and cargo box angle feedback information. Combined with the actual pose feedback from the sensing module, the desired pitch angle of the mining vehicle is calculated. As shown in Table 2, if the actual pitch angle of the mining vehicle deviates from the desired pitch angle of the mining truck within a certain time window, and the difference exceeds an abnormal threshold, the vehicle can be controlled to stop lifting the cargo box, and an abnormal alarm can be reported to the cloud monitoring platform. This allows on-site maintenance personnel to be notified promptly to handle the situation and avoid safety risks caused by continued lifting. The abnormal alarm may include information as shown in Table 3.

[0103] Table 2

[0104] Status / Instructions Lift Lift Lift Lift Emergency stop Emergency stop Expected pitch angle 3 degrees 4 degrees 5 degrees 5 degrees 5 degrees 5 degrees Vehicle pitch angle 3 degrees 5 degrees 6 degrees 6 degrees 19 degrees 21 degrees The size of the difference 0 degrees 1 degree 1 degree 1 degree 14 degrees 16 degrees

[0105] Table 3

[0106] Alarm subcategories Alarm Description Recovery Precautions Alarm from the control module Front of the vehicle tilted up - pitch angle: 21.432461° If the front of the car lifts up, remember not to restart it directly.

[0107] In some embodiments, abnormal driving paths, i.e., abnormal locations, can be identified. Figure 11This illustrates a scenario of abnormal driving path. The mining vehicle is expected to travel along the path indicated by the dashed arrow. When the vehicle reaches position 6, it deviates unexpectedly, and the difference between its actual and expected positions gradually increases (as shown in Table 4). When the vehicle reaches position 7, the difference exceeds the abnormal threshold. In this situation, the method described above can be used to first trigger a vehicle deceleration strategy, followed by an emergency stop strategy, ultimately leading to a safe and successful stop, avoiding a collision. When the vehicle triggers deceleration and emergency stop, an anomaly alarm is simultaneously reported to the cloud monitoring platform, promptly notifying on-site maintenance personnel for handling and ensuring safe on-site operations.

[0108] Table 4

[0109] instruction driving driving driving driving driving slow down Emergency stop Verification point 1 2 3 4 5 6 7 The size of the difference 0.2 meters 0.3 meters 0.2 meters 0.1 meters 0.2 meters 0.4 meters 1.2 meters

[0110] In some embodiments, the identification device can also obtain the planned location of the mining vehicle in the work area, and the actual location of the mining vehicle; when the difference between the planned location and the actual location is greater than a preset threshold, it can be confirmed that the mining vehicle is in an abnormal state. Taking transportation as an example, its operating area is a road. Figure 12 As shown, when vehicles are performing transportation tasks in the mining area, the planned driving path follows the center line of the lane. Figure 13 As shown, the actual driving path of vehicles in the mining area deviates from the lane center information, meaning the actual driving path is inconsistent with the planned driving path. In this situation, anomalies in mining vehicles can be identified, and appropriate measures can be taken to prevent safety accidents involving mining vehicles.

[0111] In summary, the mining vehicle anomaly identification method provided in this application can promptly detect anomalies in mining vehicles and take corresponding measures to ensure the operational safety of mining vehicles. Furthermore, the mining vehicle anomaly identification method provided in this application does not rely on anomaly or fault information provided by individual components of the mining vehicle, has low requirements for the vehicle's components, possesses good universality, and has a wide range of applications.

[0112] Based on the above description, this application also provides a mining area vehicle anomaly identification device 1400. For example... Figure 14 As shown, the device 1400 includes:

[0113] The first acquisition module is used to acquire the first actual pose of the mining vehicle at the first moment and the first pose adjustment command received by the mining vehicle at the first moment.

[0114] The calculation module is used to calculate the first expected pose of the mining vehicle at a second time after the first time based on the first actual pose and the first pose adjustment instruction, wherein the first expected pose is the predicted pose of the mining vehicle after adjusting the first actual pose according to the first pose adjustment instruction.

[0115] The second acquisition module is used to acquire the second actual pose of the mining vehicle at the second moment, wherein the second actual pose is the pose of the mining vehicle after the first pose is actually adjusted according to the first pose adjustment instruction.

[0116] The confirmation module is used to confirm that the mining vehicle is in an abnormal state when the difference between the first expected pose and the second actual pose is greater than an abnormal threshold.

[0117] The first acquisition module, calculation module, second acquisition module, and confirmation module can all be implemented in software or hardware. For example, the implementation of the first acquisition module will be described below. Similarly, the implementation of the calculation module, second acquisition module, and confirmation module can refer to the implementation of the first acquisition module.

[0118] As an example of a software functional unit, the first acquisition module may include code running on a computing instance. The computing instance may include at least one of a physical host (computing device), a virtual machine, and a container. Further, the aforementioned computing instance may be one or more. For example, the first acquisition module may include code running on multiple hosts / virtual machines / containers. It should be noted that the multiple hosts / virtual machines / containers used to run the code may be distributed in the same region or in different regions. Further, the multiple hosts / virtual machines / containers used to run the code may be distributed in the same availability zone (AZ) or in different AZs, each AZ including one or more geographically proximate data centers. Typically, a region may include multiple AZs.

[0119] Similarly, multiple hosts / virtual machines / containers used to run this code can be distributed within the same Virtual Private Cloud (VPC) or across multiple VPCs. Typically, a VPC is set up within a region. Communication between two VPCs within the same region, as well as between VPCs in different regions, requires a communication gateway to be set up within each VPC to enable interconnection between VPCs.

[0120] As an example of a hardware functional unit, the first acquisition module may include at least one computing device, such as a server. Alternatively, the first acquisition module may also be a device implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). The PLD may be implemented using a complex programmable logical device (CPLD), a field-programmable gate array (FPGA), generic array logic (GAL), or any combination thereof.

[0121] The multiple computing devices included in the first acquisition module can be distributed in the same region or in different regions. Similarly, the multiple computing devices included in the first acquisition module can be distributed in the same Availability Zone (AZ) or in different AZs. Likewise, the multiple computing devices included in the first acquisition module can be distributed in the same Virtual Private Cloud (VPC) or in multiple VPCs. These multiple computing devices can be any combination of computing devices such as servers, ASICs, PLDs, CPLDs, FPGAs, and GALs.

[0122] It should be noted that, in other embodiments, the first acquisition module can be used to perform... Figure 7 The computation module can be used to execute any step in the method shown. Figure 7 The second acquisition module can be used to execute any step in the method shown. Figure 7 Any step in the method shown can be confirmed by the module. Figure 7 Any step in the method shown. The steps implemented by the first acquisition module, calculation module, second acquisition module, and confirmation module can be specified as needed, and implemented by the first acquisition module, calculation module, second acquisition module, and confirmation module respectively. Figure 7 The different steps in the method shown enable the full functionality of device 1400.

[0123] This application also provides a computing device 1500. For example... Figure 15 As shown, the computing device 1500 includes a bus 1502, a processor 1504, a memory 1506, and a communication interface 1508. The processor 1504, the memory 1506, and the communication interface 1508 communicate with each other via the bus 1502. The computing device 1500 can be a server or a terminal device. It should be understood that this application does not limit the number of processors and memories in the computing device 1500.

[0124] Bus 1502 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be divided into address buses, data buses, control buses, etc. For ease of representation, Figure 15 The bus 1502 may be represented by a single line, but this does not mean that there is only one bus or one type of bus. The bus 1502 may include a path for transmitting information between various components of the computing device 1500 (e.g., memory 1506, processor 1504, communication interface 1508).

[0125] Processor 1504 may include any one or more processors such as a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0126] Memory 1506 may include volatile memory, such as random access memory (RAM). Memory 1506 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0127] The memory 1506 stores executable program code, and the processor 1504 executes the executable program code to implement the functions of the aforementioned first acquisition module, calculation module, second acquisition module, and confirmation module, thereby achieving... Figure 7 The method shown. That is, the memory 1506 stores the information for executing... Figure 7 The instructions for the method shown.

[0128] The communication interface 1508 uses transceiver modules, such as, but not limited to, network interface cards and transceivers, to enable communication between the computing device 1500 and other devices or communication networks.

[0129] This application also provides a computing device cluster. The computing device cluster includes at least one computing device. The computing device can be a server, such as a central server, an edge server, or a local server in a local data center. In some embodiments, the computing device can also be a terminal device such as a desktop computer, a laptop computer, or a smartphone.

[0130] like Figure 16 As shown, the computing device cluster includes at least one computing device 1500. The memory 1506 in one or more computing devices 1500 within the computing device cluster may store the same memory for executing... Figure 7 The instructions for the method shown.

[0131] In some possible implementations, the memory 1506 of one or more computing devices 1500 in the computing device cluster may also store memory for execution. Figure 7 The instructions of the method shown are partial. In other words, a combination of one or more computing devices 1500 can jointly execute instructions for performing... Figure 7 The instructions for the method shown.

[0132] It should be noted that the memory 1506 in different computing devices 1500 within the computing device cluster can store different instructions, each used to execute a portion of the functions of device 1400. That is, the instructions stored in the memory 1506 of different computing devices 1500 can implement the functions of one or more modules among the first acquisition module, the calculation module, the second acquisition module, and the confirmation module.

[0133] In some possible implementations, one or more computing devices in a computing device cluster can be connected via a network. This network can be a wide area network (WAN) or a local area network (LAN), etc. Figure 17 One possible implementation is shown. For example... Figure 17 As shown, the two computing devices 1500A and 1500B are connected via a network. Specifically, they are connected to the network through communication interfaces in each computing device. In this possible implementation, the memory 1506 in computing device 1500A stores instructions for executing the functions of the first acquisition module and the calculation module. Simultaneously, the memory 1506 in computing device 1500B stores instructions for executing the functions of the second acquisition module and the confirmation module.

[0134] It should be understood that Figure 17 The functions of computing device 1500A shown can also be performed by multiple computing devices 1500. Similarly, the functions of computing device 1500B can also be performed by multiple computing devices 1500.

[0135] This application also provides another computing device cluster. The connection relationships between the computing devices in this computing device cluster can be similarly referred to... Figure 16 and Figure 17 The connection method of the computing device cluster. The difference is that the memory 1506 in one or more computing devices 1500 within this computing device cluster can store the same data for execution. Figure 7 The instructions for the method shown.

[0136] In some possible implementations, the memory 1506 of one or more computing devices 1500 in the computing device cluster may also store memory for execution. Figure 7 The instructions of the method shown are partial. In other words, a combination of one or more computing devices 1500 can jointly execute instructions for performing... Figure 7 The instructions for the method shown.

[0137] This application also provides a computer program product containing instructions. The computer program product may be a software or program product containing instructions, capable of running on a computing device or stored on any usable medium. When the computer program product is run on at least one computing device, it causes the at least one computing device to perform... Figure 7 The method shown.

[0138] This application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that a computing device can store, or a host migration device such as a data center that includes one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive). The computer-readable storage medium includes instructions that instruct the computing device to execute... Figure 7 The method shown.

[0139] The above 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 protection scope of the technical solutions of the embodiments of this application.

Claims

1. A method for identifying abnormal vehicles in mining areas, characterized in that, The method includes: The first actual position and pose of the mining vehicle at the first moment and the first position adjustment command received by the mining vehicle at the first moment are obtained. Based on the first actual pose and the first pose adjustment instruction, the first expected pose of the mining vehicle at the second time after the first time is calculated, wherein the first expected pose is the predicted pose of the mining vehicle after adjusting the first actual pose according to the first pose adjustment instruction. The second actual pose of the mining vehicle at the second moment is obtained, wherein the second actual pose is the pose of the mining vehicle after the first pose is actually adjusted according to the first pose adjustment command. When the difference between the first expected pose and the second actual pose is greater than the abnormal threshold, the mining vehicle is confirmed to be in an abnormal state.

2. The method according to claim 1, characterized in that, The abnormal threshold includes a first threshold and a second threshold, wherein the second threshold is greater than the first threshold; When the difference between the first expected pose and the second actual pose is greater than an anomaly threshold, the mining vehicle is confirmed to be in an abnormal state, including: An anomaly alarm is issued when the difference is greater than or equal to the first threshold and less than the second threshold; And / or, When the difference is greater than or equal to the second threshold, a braking command is issued to the mining vehicle to control the mining vehicle to brake.

3. The method according to claim 1 or 2, characterized in that, The method further includes: Obtain the planned positions of the mining area vehicles at the work site; Obtain the actual location of the vehicles in the mining area; When the difference between the planned location and the actual location is greater than a preset threshold, the mining area vehicle is confirmed to be in an abnormal state.

4. The method according to any one of claims 1-3, characterized in that, The method further includes: Obtain the second pose adjustment command of the mining vehicle at the second moment; Based on the second actual pose and the second pose adjustment command, the second expected pose of the mining vehicle at the third time after the second time is calculated, wherein the second expected pose is the predicted pose of the mining vehicle after adjusting the second actual pose according to the second pose adjustment command. The third actual pose of the mining vehicle at the third time point is obtained, wherein the third actual pose is the pose of the mining vehicle after the second pose is actually adjusted according to the second pose adjustment command. The step of confirming that the mining vehicle is in an abnormal state when the difference between the first expected pose and the second actual pose is greater than an anomaly threshold includes: When the difference between the first expected pose and the second actual pose is greater than the abnormal threshold, and the difference between the second expected pose and the third actual pose is greater than the abnormal threshold, the mining vehicle is confirmed to be in an abnormal state.

5. The method according to any one of claims 1-4, characterized in that, The first actual pose includes at least one of the position, speed, and attitude of the mining vehicle at the first moment, and / or the first position adjustment command includes at least one of the position adjustment command, speed adjustment command, and attitude adjustment command of the mining vehicle. The attitude of the mining vehicle includes at least one of the following: heading information, roll information, pitch information, and cargo box lifting angle.

6. The method according to any one of claims 1-5, characterized in that, The method further includes: Obtain the actual pose and pose adjustment commands of the vehicles in the mining area at multiple historical moments; The adjusted pose corresponding to each of the plurality of times is obtained, wherein the adjusted pose corresponding to each of the plurality of times is the pose of the mining vehicle after adjusting the actual pose at that time according to the pose adjustment command at that time. Based on the actual pose of the mining vehicle at multiple times, the pose adjustment command, and the adjusted pose corresponding to each of the multiple times, a pose prediction model is constructed. The step of calculating the first desired pose of the mining vehicle at a second time after the first time, based on the first actual pose and the first pose adjustment command, includes: The first actual pose and the first pose adjustment command are input into the pose prediction model, so that the pose prediction model outputs the first desired pose.

7. A device for identifying abnormal vehicles in mining areas, characterized in that, The device includes: The first acquisition module is used to acquire the first actual pose of the mining vehicle at the first moment and the first pose adjustment command received by the mining vehicle at the first moment. The calculation module is used to calculate the first expected pose of the mining vehicle at a second time after the first time based on the first actual pose and the first pose adjustment instruction, wherein the first expected pose is the predicted pose of the mining vehicle after adjusting the first actual pose according to the first pose adjustment instruction. The second acquisition module is used to acquire the second actual pose of the mining vehicle at the second moment, wherein the second actual pose is the pose of the mining vehicle after the first pose is actually adjusted according to the first pose adjustment instruction. The confirmation module is used to confirm that the mining vehicle is in an abnormal state when the difference between the first expected pose and the second actual pose is greater than an abnormal threshold.

8. A computing device cluster, characterized in that, It includes at least one computing device, each computing device including a processor and memory; The processor of the at least one computing device is configured to execute instructions stored in the memory of the at least one computing device to cause the cluster of computing devices to perform the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It includes computer program instructions, which, when executed by a cluster of computing devices, perform the method as described in any one of claims 1 to 6.

10. A computer program product containing instructions, characterized in that, When the instructions are executed by a cluster of computer devices, the cluster of computer devices performs the method as described in any one of claims 1 to 6.

Images